{"game_alias":null,"public_release_id":"gb2-20261026-cb69502a12d9","row_kind":"track","rows":[{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-5-5:12d35a0c8ebcfc9f","capped_draws":9,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677192},"codegen_evaluated_cells":8,"conditional_success_score":95.14696610308756,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":79,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5-5","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":84.36451415389676,"score":84.36451415389676},"GB2-02":{"attempts":1,"playable":96.04425995743617,"score":96.04425995743617},"GB2-03":{"attempts":1,"playable":97.11633628095088,"score":97.11633628095088},"GB2-04":{"attempts":1,"playable":94.80532092654904,"score":94.80532092654904},"GB2-05":{"attempts":1,"playable":98.2460503822685,"score":98.2460503822685},"GB2-06":{"attempts":1,"playable":99.48374593708698,"score":99.48374593708698},"GB2-07":{"attempts":1,"playable":97.81823072023141,"score":97.81823072023141},"GB2-08":{"attempts":1,"playable":93.2972704662808,"score":93.2972704662808}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:45Z","losses":163,"max_score":99.48374593708698,"measured_at":null,"min_score":84.36451415389676,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":1,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:10:36Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2383.6226925329806,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":95.14696610308756,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3846},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-astra:af89b97f9d676a8c","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.427439999999999},"codegen_evaluated_cells":8,"conditional_success_score":94.44100465618811,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":96,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-astra","reasoning_catalog_sha256":"01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":97.26310618029666,"score":97.26310618029666},"GB2-02":{"attempts":1,"playable":95.28254216483235,"score":95.28254216483235},"GB2-03":{"attempts":1,"playable":97.71729001652737,"score":97.71729001652737},"GB2-04":{"attempts":1,"playable":92.61249312688841,"score":92.61249312688841},"GB2-05":{"attempts":1,"playable":98.93325735214952,"score":98.93325735214952},"GB2-06":{"attempts":1,"playable":86.99208992144212,"score":86.99208992144212},"GB2-07":{"attempts":1,"playable":97.81823072023141,"score":97.81823072023141},"GB2-08":{"attempts":1,"playable":88.909027767137,"score":88.909027767137}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:58Z","losses":188,"max_score":98.93325735214952,"measured_at":null,"min_score":86.99208992144212,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":2,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:12:20Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2325.1607729134557,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-astra","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":94.44100465618811,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3804},{"admitted_plugins":11,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:mixed:claude-fable-5-1:d307977c9774b8cb","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369},"codegen_evaluated_cells":11,"conditional_success_score":94.36682200330814,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":125,"eligibility_flag":true,"entry_count":11,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"historical-provider-setting-intensive","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5-1","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":9,"first_pass_rate":0.8181818181818182,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_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":93.15989233649182,"score":93.15989233649182},"GB2-02":{"attempts":1,"playable":95.09196858035578,"score":95.09196858035578},"GB2-03":{"attempts":2,"playable":95.39910279160684,"score":95.39910279160684},"GB2-04":{"attempts":2,"playable":87.98030366893738,"score":87.98030366893738},"GB2-05":{"attempts":1,"playable":93.41214839874009,"score":93.41214839874009},"GB2-06":{"attempts":1,"playable":98.24081452142869,"score":98.24081452142869},"GB2-07":{"attempts":2,"playable":93.85788217399038,"score":93.85788217399038},"GB2-08":{"attempts":1,"playable":97.7924635549142,"score":97.7924635549142}},"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":"2026-10-26T02:02:54Z","losses":288,"max_score":98.24081452142869,"measured_at":null,"min_score":87.98030366893738,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":3,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:53Z","ranking_status":"ranked","rated_matches":5610,"rating_method":"bradley_terry_newton","raw_elo":2279.278983829725,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5-1","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.18181818181818182,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":94.36682200330814,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":null,"wins":5197},{"admitted_plugins":9,"attempted_matches":4626,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-5-5:7dce3bfc0734dff8","capped_draws":36,"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.006308},"codegen_evaluated_cells":9,"conditional_success_score":92.95307801297679,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":128,"eligibility_flag":true,"entry_count":9,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5-5","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":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":1,"playable":93.91877159812458,"score":93.91877159812458},"GB2-02":{"attempts":1,"playable":95.75873519610694,"score":95.75873519610694},"GB2-03":{"attempts":1,"playable":92.57125832418781,"score":92.57125832418781},"GB2-04":{"attempts":1,"playable":88.54928037127607,"score":88.54928037127607},"GB2-05":{"attempts":1,"playable":89.73340164958267,"score":89.73340164958267},"GB2-06":{"attempts":1,"playable":92.37059265200884,"score":92.37059265200884},"GB2-07":{"attempts":1,"playable":93.49401010142148,"score":93.49401010142148},"GB2-08":{"attempts":2,"playable":97.22857421110604,"score":97.22857421110604}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:49:54Z","losses":252,"max_score":97.22857421110604,"measured_at":null,"min_score":88.54928037127607,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":4,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:00Z","ranking_status":"ranked","rated_matches":4626,"rating_method":"bradley_terry_newton","raw_elo":2236.2042855289756,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.1111111111111111,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":92.95307801297679,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":4246},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-1-sol:4d9b9582c1d7737f","capped_draws":2,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.2665285,"median":0.263151,"min":0.174431,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.132228},"codegen_evaluated_cells":8,"conditional_success_score":92.68939233394522,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":105,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6.1-sol","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":76.04019891391917,"score":76.04019891391917},"GB2-02":{"attempts":1,"playable":94.71067501688863,"score":94.71067501688863},"GB2-03":{"attempts":1,"playable":98.23172588248056,"score":98.23172588248056},"GB2-04":{"attempts":1,"playable":95.07823560912824,"score":95.07823560912824},"GB2-05":{"attempts":1,"playable":97.89828459794494,"score":97.89828459794494},"GB2-06":{"attempts":1,"playable":89.8754449934844,"score":89.8754449934844},"GB2-07":{"attempts":1,"playable":95.8986580939694,"score":95.8986580939694},"GB2-08":{"attempts":1,"playable":93.78191556374637,"score":93.78191556374637}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:49:19Z","losses":259,"max_score":98.23172588248056,"measured_at":null,"min_score":76.04019891391917,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":5,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:20Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2262.646317596329,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-sol","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":92.68939233394522,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3724},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-sonnet-5-5:7f9dd6856af16a52","capped_draws":164,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.54817025,"median":0.548798,"min":0.28285,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":4.385361999999999},"codegen_evaluated_cells":8,"conditional_success_score":91.82247923237178,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":313,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5-5","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":80.28018091451669,"score":80.28018091451669},"GB2-02":{"attempts":1,"playable":95.94910286467913,"score":95.94910286467913},"GB2-03":{"attempts":1,"playable":95.05594147453033,"score":95.05594147453033},"GB2-04":{"attempts":1,"playable":83.48616604723223,"score":83.48616604723223},"GB2-05":{"attempts":1,"playable":97.3747731499052,"score":97.3747731499052},"GB2-06":{"attempts":1,"playable":89.78575025805709,"score":89.78575025805709},"GB2-07":{"attempts":1,"playable":93.6755483450511,"score":93.6755483450511},"GB2-08":{"attempts":1,"playable":98.97237080500244,"score":98.97237080500244}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:53Z","losses":190,"max_score":98.97237080500244,"measured_at":null,"min_score":80.28018091451669,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":6,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:16:25Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2240.5646192766685,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":91.82247923237178,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3585},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:unbiased-pareto-26-10:cede2d03a653c56c","capped_draws":1,"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":90.60945754866256,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":263,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"default","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"unbiased/pareto-26.10","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"omitted","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:21Z","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":1.0,"provider":"Unbiased","provider_key":"unbiased","rank":7,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:21Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2147.3973187820334,"reasoning_bracket":"baseline","reasoning_level":"Provider default (reasoning controls unavailable)","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"omitted","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Provider default (reasoning controls unavailable)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Provider default (reasoning controls unavailable)","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"omitted","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":90.60945754866256,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3555},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gemini-4-argon:162a9806a01485b9","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.5240959999999997},"codegen_evaluated_cells":8,"conditional_success_score":90.10521246266784,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":168,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-4-argon","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":95.3283412053958,"score":95.3283412053958},"GB2-02":{"attempts":1,"playable":94.90134536902329,"score":94.90134536902329},"GB2-03":{"attempts":1,"playable":92.31429760149187,"score":92.31429760149187},"GB2-04":{"attempts":1,"playable":71.36738900330297,"score":71.36738900330297},"GB2-05":{"attempts":1,"playable":96.32822867229156,"score":96.32822867229156},"GB2-06":{"attempts":1,"playable":97.59621949905328,"score":97.59621949905328},"GB2-07":{"attempts":1,"playable":84.26031114528222,"score":84.26031114528222},"GB2-08":{"attempts":1,"playable":88.74556720550174,"score":88.74556720550174}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:49Z","losses":341,"max_score":97.59621949905328,"measured_at":null,"min_score":71.36738900330297,"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":1.0,"provider":"Google","provider_key":"google","rank":8,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:49Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2153.9447699980187,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-4-argon","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"google","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":90.10521246266784,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3579},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:unbiased-pareto-26-10-preview:5ece4ec07c319ba8","capped_draws":17,"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":0.24543760000000003},"codegen_evaluated_cells":8,"conditional_success_score":89.68138346863117,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":142,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"default","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"unbiased/pareto-26.10-preview","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"omitted","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:59:16Z","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":1.0,"provider":"Unbiased","provider_key":"unbiased","rank":9,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T16:59:16Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2134.120020799106,"reasoning_bracket":"baseline","reasoning_level":"Provider default (reasoning controls unavailable)","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"omitted","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Provider default (reasoning controls unavailable)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Provider default (reasoning controls unavailable)","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"omitted","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":89.68138346863117,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3573},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-astra:9acce95ba71bd7c5","capped_draws":41,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"codegen_evaluated_cells":8,"conditional_success_score":89.64961921867949,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":268,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-astra","reasoning_catalog_sha256":"01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":76.89221681442544,"score":76.89221681442544},"GB2-02":{"attempts":1,"playable":80.9876563481334,"score":80.9876563481334},"GB2-03":{"attempts":1,"playable":94.79866348037507,"score":94.79866348037507},"GB2-04":{"attempts":1,"playable":91.41780283715886,"score":91.41780283715886},"GB2-05":{"attempts":1,"playable":93.07462175455832,"score":93.07462175455832},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":1,"playable":96.65952162760107,"score":96.65952162760107},"GB2-08":{"attempts":1,"playable":94.74947165976819,"score":94.74947165976819}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:40:05Z","losses":309,"max_score":96.65952162760107,"measured_at":null,"min_score":76.89221681442544,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":10,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T18:47:24Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2138.6856276040444,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":89.64961921867949,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3511},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-1-sol:8af525fd5abeb0ea","capped_draws":13,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.134667,"mean":0.084337375,"median":0.0768835,"min":0.057491,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.674699},"codegen_evaluated_cells":8,"conditional_success_score":87.46655549866425,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":211,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6.1-sol","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":75.37631164228648,"score":75.37631164228648},"GB2-02":{"attempts":1,"playable":79.70569279156288,"score":79.70569279156288},"GB2-03":{"attempts":1,"playable":96.60103548840144,"score":96.60103548840144},"GB2-04":{"attempts":1,"playable":87.15128537218678,"score":87.15128537218678},"GB2-05":{"attempts":1,"playable":94.7735320011636,"score":94.7735320011636},"GB2-06":{"attempts":1,"playable":91.92773394831342,"score":91.92773394831342},"GB2-07":{"attempts":1,"playable":95.71002403331707,"score":95.71002403331707},"GB2-08":{"attempts":1,"playable":78.48682871208231,"score":78.48682871208231}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:10Z","losses":440,"max_score":96.60103548840144,"measured_at":null,"min_score":75.37631164228648,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":11,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:13Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2091.1995556991747,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":87.46655549866425,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3437},{"admitted_plugins":8,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:mixed:claude-fable-5-1:fdf38228456af115","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609},"codegen_evaluated_cells":8,"conditional_success_score":86.60227933805807,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":325,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"historical-provider-setting-baseline","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5-1","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":88.26538965593794,"score":88.26538965593794},"GB2-02":{"attempts":1,"playable":83.43951956350753,"score":83.43951956350753},"GB2-03":{"attempts":1,"playable":93.2563755212143,"score":93.2563755212143},"GB2-04":{"attempts":1,"playable":74.19118166112764,"score":74.19118166112764},"GB2-05":{"attempts":1,"playable":91.73309054449655,"score":91.73309054449655},"GB2-06":{"attempts":1,"playable":83.91017408920956,"score":83.91017408920956},"GB2-07":{"attempts":1,"playable":88.2156328474168,"score":88.2156328474168},"GB2-08":{"attempts":1,"playable":89.80687082155418,"score":89.80687082155418}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:27Z","losses":418,"max_score":93.2563755212143,"measured_at":null,"min_score":74.19118166112764,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":12,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:00Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":2021.44095297462,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5-1","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":86.60227933805807,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":null,"wins":3344},{"admitted_plugins":13,"attempted_matches":6642,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-5:a953aed661ace78d","capped_draws":17,"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":2.09943,"mean":1.379653125,"median":1.3205149999999999,"min":0.8875599999999999,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":22.07445},"codegen_evaluated_cells":16,"conditional_success_score":86.13426288072226,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":377,"eligibility_flag":true,"entry_count":13,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":13,"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":2,"playable":70.03278917166492,"score":70.03278917166492},"GB2-02":{"attempts":2,"playable":83.41388903712786,"score":83.41388903712786},"GB2-03":{"attempts":2,"playable":94.75591830600256,"score":94.75591830600256},"GB2-04":{"attempts":2,"playable":80.43217375160833,"score":80.43217375160833},"GB2-05":{"attempts":2,"playable":93.32967242190527,"score":93.32967242190527},"GB2-07":{"attempts":1,"playable":95.89865809396942,"score":95.89865809396942},"GB2-08":{"attempts":2,"playable":85.07673938277742,"score":85.07673938277742}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:14Z","losses":835,"max_score":95.89865809396942,"measured_at":null,"min_score":70.03278917166492,"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":3,"plugin_success_rate":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":13,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:14:21Z","ranking_status":"ranked","rated_matches":6642,"rating_method":"bradley_terry_newton","raw_elo":2057.722453059526,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":86.13426288072226,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":5430},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k3-1-pro:d90c95261509278e","capped_draws":8,"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":0.520818,"mean":0.45841275000000004,"median":0.456374,"min":0.383384,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":3.6673019999999994},"codegen_evaluated_cells":8,"conditional_success_score":85.71901534767252,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":338,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3.1-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":93.24462885290633,"score":93.24462885290633},"GB2-02":{"attempts":1,"playable":79.70569279156288,"score":79.70569279156288},"GB2-03":{"attempts":1,"playable":87.31263492362999,"score":87.31263492362999},"GB2-04":{"attempts":1,"playable":83.76963489563613,"score":83.76963489563613},"GB2-05":{"attempts":1,"playable":90.39961322834613,"score":90.39961322834613},"GB2-06":{"attempts":1,"playable":85.3619372693454,"score":85.3619372693454},"GB2-07":{"attempts":1,"playable":74.60507048095543,"score":74.60507048095543},"GB2-08":{"attempts":1,"playable":91.35291033899789,"score":91.35291033899789}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":456,"max_score":93.24462885290633,"measured_at":null,"min_score":74.60507048095543,"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":1.0,"provider":"Moonshot","provider_key":"moonshotai","rank":14,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:56Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1984.4722203814754,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3.1-pro","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":85.71901534767252,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3294},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-astra:8883275fa81b106a","capped_draws":24,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349},"codegen_evaluated_cells":8,"conditional_success_score":85.12684582632687,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":515,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-astra","reasoning_catalog_sha256":"01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":93.15989233649182,"score":93.15989233649182},"GB2-02":{"attempts":1,"playable":72.62236899416067,"score":72.62236899416067},"GB2-03":{"attempts":1,"playable":75.50212573897703,"score":75.50212573897703},"GB2-04":{"attempts":1,"playable":83.39162029358637,"score":83.39162029358637},"GB2-05":{"attempts":1,"playable":94.26076154257755,"score":94.26076154257755},"GB2-06":{"attempts":1,"playable":84.99918664141589,"score":84.99918664141589},"GB2-07":{"attempts":1,"playable":94.5914071286307,"score":94.5914071286307},"GB2-08":{"attempts":1,"playable":82.48740393477489,"score":82.48740393477489}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:42Z","losses":389,"max_score":94.5914071286307,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":15,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:16:43Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2014.435959471345,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-astra","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"01944118fe4e38b452bca33ac0527ff8227e8c72d639eccebad38d0cb3b8633b","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":85.12684582632687,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3184},{"admitted_plugins":8,"attempted_matches":null,"canonical_public_row_identity":"publication-row.v1:mixed:claude-fable-5-1:2ceef8038de90922","capped_draws":null,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"codegen_evaluated_cells":8,"conditional_success_score":84.83104488902094,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":299,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"historical-provider-setting-balanced","output_mode":"unknown_legacy","prompt_identity":"unknown_legacy","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5-1","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":73.85519804895645,"score":73.85519804895645},"GB2-02":{"attempts":1,"playable":91.36643949382484,"score":91.36643949382484},"GB2-03":{"attempts":1,"playable":92.31429760149187,"score":92.31429760149187},"GB2-04":{"attempts":1,"playable":64.6256422345308,"score":64.6256422345308},"GB2-05":{"attempts":1,"playable":88.56478659126304,"score":88.56478659126304},"GB2-06":{"attempts":1,"playable":88.43679175363576,"score":88.43679175363576},"GB2-07":{"attempts":1,"playable":93.85761207733375,"score":93.85761207733375},"GB2-08":{"attempts":1,"playable":85.62759131113107,"score":85.62759131113107}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:40:39Z","losses":509,"max_score":93.85761207733375,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":16,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:12:36Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":2009.5091461226011,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":84.83104488902094,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":null,"wins":3279},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0","capped_draws":14,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"codegen_evaluated_cells":8,"conditional_success_score":81.09567801680645,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":300,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-sol","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":75.18644442389503,"score":75.18644442389503},"GB2-02":{"attempts":1,"playable":75.83154243743509,"score":75.83154243743509},"GB2-03":{"attempts":1,"playable":80.64898951980767,"score":80.64898951980767},"GB2-04":{"attempts":1,"playable":83.86406826181346,"score":83.86406826181346},"GB2-05":{"attempts":1,"playable":75.91303436651312,"score":75.91303436651312},"GB2-06":{"attempts":1,"playable":85.27126349579316,"score":85.27126349579316},"GB2-07":{"attempts":1,"playable":88.7341773057466,"score":88.7341773057466},"GB2-08":{"attempts":1,"playable":83.31590432344747,"score":83.31590432344747}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:24Z","losses":681,"max_score":88.7341773057466,"measured_at":null,"min_score":75.18644442389503,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":17,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:19:53Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1875.3378952389767,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":81.09567801680645,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3107},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:gemini-4-argon:9ab962c48e15448f","capped_draws":5,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.674042},"codegen_evaluated_cells":8,"conditional_success_score":81.02832681047835,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":328,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-4-argon","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":92.47836452792725,"score":92.47836452792725},"GB2-02":{"attempts":1,"playable":77.12756279010748,"score":77.12756279010748},"GB2-03":{"attempts":1,"playable":85.75153244741574,"score":85.75153244741574},"GB2-04":{"attempts":1,"playable":76.12724973365236,"score":76.12724973365236},"GB2-05":{"attempts":1,"playable":88.39734724294453,"score":88.39734724294453},"GB2-06":{"attempts":1,"playable":90.41289262543951,"score":90.41289262543951},"GB2-07":{"attempts":1,"playable":59.444836404257536,"score":59.444836404257536},"GB2-08":{"attempts":1,"playable":78.48682871208231,"score":78.48682871208231}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","losses":676,"max_score":92.47836452792725,"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":1.0,"provider":"Google","provider_key":"google","rank":18,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","ranking_status":"ranked","rated_matches":4089,"rating_method":"bradley_terry_newton","raw_elo":1894.3571321105933,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-4-argon","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"google","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":81.02832681047835,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3085},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k3-1-pro:42141b616cfa386d","capped_draws":125,"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":0.31477,"mean":0.2003284,"median":0.218258,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.6026272000000001},"codegen_evaluated_cells":8,"conditional_success_score":80.75399619268694,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":375,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3.1-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":43.485097050144255,"score":43.485097050144255},"GB2-02":{"attempts":1,"playable":82.55888543622167,"score":82.55888543622167},"GB2-03":{"attempts":1,"playable":88.78864195924888,"score":88.78864195924888},"GB2-04":{"attempts":1,"playable":78.91705948967778,"score":78.91705948967778},"GB2-05":{"attempts":1,"playable":84.65967981600397,"score":84.65967981600397},"GB2-06":{"attempts":1,"playable":92.1050424297417,"score":92.1050424297417},"GB2-07":{"attempts":1,"playable":79.9636809643598,"score":79.9636809643598},"GB2-08":{"attempts":1,"playable":95.55388239609753,"score":95.55388239609753}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","losses":642,"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":1.0,"provider":"Moonshot","provider_key":"moonshotai","rank":19,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1933.6921756793333,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3.1-pro","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":80.75399619268694,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3071},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-sol:410ceff1171c2cf1","capped_draws":29,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002},"codegen_evaluated_cells":8,"conditional_success_score":80.57319747530642,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":240,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-sol","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":10.356509846524498,"score":10.356509846524498},"GB2-02":{"attempts":1,"playable":83.63490681890951,"score":83.63490681890951},"GB2-03":{"attempts":1,"playable":94.37003524976566,"score":94.37003524976566},"GB2-04":{"attempts":1,"playable":88.27020369252344,"score":88.27020369252344},"GB2-05":{"attempts":1,"playable":93.750733178957,"score":93.750733178957},"GB2-06":{"attempts":1,"playable":90.23388548276091,"score":90.23388548276091},"GB2-07":{"attempts":1,"playable":94.40710040325735,"score":94.40710040325735},"GB2-08":{"attempts":1,"playable":89.56220512975295,"score":89.56220512975295}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:37Z","losses":698,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":20,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:41:39Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":2001.6109489647993,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-sol","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":80.57319747530642,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3150},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-wonder:33a6e9a71f16c38b","capped_draws":85,"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":0.680268,"mean":0.4875944,"median":0.46494,"min":0.362124,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":3.9007552},"codegen_evaluated_cells":8,"conditional_success_score":78.79080297221228,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":535,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-wonder","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":85.09852264593735,"score":85.09852264593735},"GB2-02":{"attempts":1,"playable":66.63991156296852,"score":66.63991156296852},"GB2-03":{"attempts":1,"playable":82.98897640682239,"score":82.98897640682239},"GB2-04":{"attempts":1,"playable":81.87510366079515,"score":81.87510366079515},"GB2-05":{"attempts":1,"playable":93.07462175455832,"score":93.07462175455832},"GB2-06":{"attempts":1,"playable":84.54555662982366,"score":84.54555662982366},"GB2-07":{"attempts":1,"playable":74.0840341297721,"score":74.0840341297721},"GB2-08":{"attempts":1,"playable":62.019696987020644,"score":62.019696987020644}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:32Z","losses":667,"max_score":93.07462175455832,"measured_at":null,"min_score":62.019696987020644,"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":1.0,"provider":"Meta","provider_key":"meta","rank":21,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:49:32Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1857.4676599527886,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":78.79080297221228,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2886},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gemini-4-argon:182c9aa8377552eb","capped_draws":7,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.774334},"codegen_evaluated_cells":8,"conditional_success_score":78.74051338079505,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":464,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-4-argon","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":91.09689584420343,"score":91.09689584420343},"GB2-02":{"attempts":1,"playable":65.3112643213262,"score":65.3112643213262},"GB2-03":{"attempts":1,"playable":80.0135112307614,"score":80.0135112307614},"GB2-04":{"attempts":1,"playable":68.91831714733743,"score":68.91831714733743},"GB2-05":{"attempts":1,"playable":90.39961322834613,"score":90.39961322834613},"GB2-06":{"attempts":1,"playable":92.72384329500343,"score":92.72384329500343},"GB2-07":{"attempts":1,"playable":77.8944751985715,"score":77.8944751985715},"GB2-08":{"attempts":1,"playable":63.566186780810916,"score":63.566186780810916}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":699,"max_score":92.72384329500343,"measured_at":null,"min_score":63.566186780810916,"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":1.0,"provider":"Google","provider_key":"google","rank":22,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:56Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1870.2425262083098,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"google","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"9e4afe58cb91b04b8519f2ea4a8640ab77c24ac662b81250ac0d536adb3bf1a9","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":78.74051338079505,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2925},{"admitted_plugins":9,"attempted_matches":4626,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-5-5:e7d2796533ceda7c","capped_draws":36,"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792},"codegen_evaluated_cells":9,"conditional_success_score":78.20306052994427,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":733,"eligibility_flag":true,"entry_count":9,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5-5","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":9,"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":91.00978394554295,"score":91.00978394554295},"GB2-02":{"attempts":1,"playable":80.19932091099078,"score":80.19932091099078},"GB2-03":{"attempts":1,"playable":52.762587763769716,"score":52.762587763769716},"GB2-04":{"attempts":1,"playable":70.19348371023403,"score":70.19348371023403},"GB2-05":{"attempts":1,"playable":91.90017957529739,"score":91.90017957529739},"GB2-06":{"attempts":1,"playable":77.45808483101766,"score":77.45808483101766},"GB2-07":{"attempts":1,"playable":91.8812219555953,"score":91.8812219555953},"GB2-08":{"attempts":2,"playable":70.21982154710635,"score":70.21982154710635}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:01Z","losses":760,"max_score":91.90017957529739,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":23,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:53:34Z","ranking_status":"ranked","rated_matches":4626,"rating_method":"bradley_terry_newton","raw_elo":1859.8407599129755,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":78.20306052994427,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3133},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-1-sol:8195851c77431240","capped_draws":71,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.057226,"mean":0.0485635,"median":0.049051,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.3885080000000001},"codegen_evaluated_cells":8,"conditional_success_score":77.7589824403664,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":574,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6.1-sol","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.52882128415899,"score":51.52882128415899},"GB2-02":{"attempts":1,"playable":65.00415088834143,"score":65.00415088834143},"GB2-03":{"attempts":1,"playable":86.00061197424166,"score":86.00061197424166},"GB2-04":{"attempts":1,"playable":73.80283201177676,"score":73.80283201177676},"GB2-05":{"attempts":1,"playable":91.3992768491011,"score":91.3992768491011},"GB2-06":{"attempts":1,"playable":80.00313072146281,"score":80.00313072146281},"GB2-07":{"attempts":1,"playable":94.5914071286307,"score":94.5914071286307},"GB2-08":{"attempts":1,"playable":79.74162866521762,"score":79.74162866521762}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:21Z","losses":671,"max_score":94.5914071286307,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":24,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:44Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1899.896340872643,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-sol","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":77.7589824403664,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2843},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-fable-5:9411c67711dccbe8","capped_draws":41,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.764550000000002},"codegen_evaluated_cells":8,"conditional_success_score":76.91860004426469,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":307,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":86.19355407039457,"score":86.19355407039457},"GB2-02":{"attempts":1,"playable":80.0019542790766,"score":80.0019542790766},"GB2-03":{"attempts":1,"playable":86.8763585040966,"score":86.8763585040966},"GB2-04":{"attempts":1,"playable":84.24151960692818,"score":84.24151960692818},"GB2-05":{"attempts":1,"playable":56.79079270779831,"score":56.79079270779831},"GB2-06":{"attempts":1,"playable":87.62475669772357,"score":87.62475669772357},"GB2-07":{"attempts":1,"playable":65.85198272520387,"score":65.85198272520387},"GB2-08":{"attempts":1,"playable":67.76788176289583,"score":67.76788176289583}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:49:59Z","losses":873,"max_score":87.62475669772357,"measured_at":null,"min_score":56.79079270779831,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":25,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:19:07Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1789.2716301963478,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":76.91860004426469,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2908},{"admitted_plugins":14,"attempted_matches":7172,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821","capped_draws":100,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.551725,"mean":0.44617968750000003,"median":0.45788,"min":0.33828,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":7.1388750000000005},"codegen_evaluated_cells":16,"conditional_success_score":76.4778641336363,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":994,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":14,"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":2,"playable":71.66073214835362,"score":71.66073214835362},"GB2-02":{"attempts":2,"playable":69.61904934172595,"score":69.61904934172595},"GB2-03":{"attempts":2,"playable":86.70136256363813,"score":86.70136256363813},"GB2-04":{"attempts":2,"playable":44.74996282207886,"score":44.74996282207886},"GB2-05":{"attempts":2,"playable":88.95917231625977,"score":88.95917231625977},"GB2-07":{"attempts":2,"playable":84.28516202622764,"score":84.28516202622764},"GB2-08":{"attempts":2,"playable":89.36960771717011,"score":89.36960771717011}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:43:57Z","losses":1255,"max_score":89.36960771717011,"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"],"performance_rejections":2,"plugin_success_rate":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":26,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:14:15Z","ranking_status":"ranked","rated_matches":7171,"rating_method":"bradley_terry_newton","raw_elo":1872.8587751964048,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":76.4778641336363,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":4922},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-sol:a64b94562f86a4f3","capped_draws":176,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165},"codegen_evaluated_cells":8,"conditional_success_score":76.36599413720651,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":626,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-sol","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":39.836679794128194,"score":39.836679794128194},"GB2-02":{"attempts":1,"playable":69.48910933445279,"score":69.48910933445279},"GB2-03":{"attempts":1,"playable":75.12913585488103,"score":75.12913585488103},"GB2-04":{"attempts":1,"playable":73.60851800637032,"score":73.60851800637032},"GB2-05":{"attempts":1,"playable":91.5661282050239,"score":91.5661282050239},"GB2-06":{"attempts":1,"playable":81.54823367582276,"score":81.54823367582276},"GB2-07":{"attempts":1,"playable":94.04021600292965,"score":94.04021600292965},"GB2-08":{"attempts":1,"playable":85.70993222404344,"score":85.70993222404344}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:12:41Z","losses":701,"max_score":94.04021600292965,"measured_at":null,"min_score":39.836679794128194,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":27,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:20:38Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1885.6664525459087,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":76.36599413720651,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2761},{"admitted_plugins":7,"attempted_matches":3572,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3:7ce2cd8cc2b9807c","capped_draws":1,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.549677025,"median":0.477676,"min":0.280382,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":4.3974162},"codegen_evaluated_cells":8,"conditional_success_score":84.04535422929325,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":380,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.62806649246055,"score":73.62806649246055},"GB2-03":{"attempts":1,"playable":84.67860328128754,"score":84.67860328128754},"GB2-04":{"attempts":1,"playable":77.09164191029542,"score":77.09164191029542},"GB2-05":{"attempts":1,"playable":90.23309662476808,"score":90.23309662476808},"GB2-06":{"attempts":1,"playable":91.12735803677934,"score":91.12735803677934},"GB2-07":{"attempts":1,"playable":78.58485722865328,"score":78.58485722865328},"GB2-08":{"attempts":1,"playable":92.97385603080852,"score":92.97385603080852}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:48:51Z","losses":412,"max_score":92.97385603080852,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"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":0.875,"provider":"Zhipu","provider_key":"z-ai","rank":28,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:48:51Z","ranking_status":"ranked","rated_matches":3572,"rating_method":"bradley_terry_newton","raw_elo":1978.6129169672693,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":73.5396849506316,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2780},{"admitted_plugins":7,"attempted_matches":3588,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-7:17d94eaf6cfc2e9a","capped_draws":41,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.576454,"mean":0.39871924999999997,"median":0.380795,"min":0.216934,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":3.1897539999999998},"codegen_evaluated_cells":8,"conditional_success_score":83.83038175693655,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":214,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.7","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":79.99922856456925,"score":79.99922856456925},"GB2-02":{"attempts":1,"playable":81.18445694776506,"score":81.18445694776506},"GB2-03":{"attempts":1,"playable":72.68817598879767,"score":72.68817598879767},"GB2-04":{"attempts":1,"playable":92.33722489519916,"score":92.33722489519916},"GB2-05":{"attempts":1,"playable":93.07462175455832,"score":93.07462175455832},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":76.33850998213276,"score":76.33850998213276},"GB2-08":{"attempts":1,"playable":91.19045416553367,"score":91.19045416553367}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:41Z","losses":512,"max_score":93.07462175455832,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Grok 4.7","model_slug":"x-ai-grok-4-7","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"xAI","provider_key":"x-ai","rank":29,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:18:46Z","ranking_status":"ranked","rated_matches":3586,"rating_method":"bradley_terry_newton","raw_elo":1946.3909795458437,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":73.35158403731948,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2860},{"admitted_plugins":7,"attempted_matches":3590,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-7:25c857b56d2ed467","capped_draws":13,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":1.2177,"mean":0.779445,"median":0.759332,"min":0.571358,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":6.2355599999999995},"codegen_evaluated_cells":8,"conditional_success_score":83.64160864674342,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":160,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.7","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":59.41863663239461,"score":59.41863663239461},"GB2-02":{"attempts":1,"playable":89.06248216137189,"score":89.06248216137189},"GB2-03":{"attempts":1,"playable":88.00858030972678,"score":88.00858030972678},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":93.41214839874009,"score":93.41214839874009},"GB2-06":{"attempts":1,"playable":90.23388548276091,"score":90.23388548276091},"GB2-07":{"attempts":1,"playable":78.41232521796309,"score":78.41232521796309},"GB2-08":{"attempts":1,"playable":86.94320232424666,"score":86.94320232424666}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:48Z","losses":548,"max_score":93.41214839874009,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Grok 4.7","model_slug":"x-ai-grok-4-7","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"xAI","provider_key":"x-ai","rank":30,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:21:15Z","ranking_status":"ranked","rated_matches":3590,"rating_method":"bradley_terry_newton","raw_elo":1989.6771823677773,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":73.1864075659005,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2882},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:55714c02a9471341","capped_draws":80,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.056915889375,"median":0.0447982575,"min":0.02822715,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.45532711500000006},"codegen_evaluated_cells":8,"conditional_success_score":73.15756430631654,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":386,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.6-pro","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":54.06745685878506,"score":54.06745685878506},"GB2-02":{"attempts":1,"playable":80.79074236697731,"score":80.79074236697731},"GB2-03":{"attempts":1,"playable":85.91279600396095,"score":85.91279600396095},"GB2-04":{"attempts":1,"playable":45.371362908471355,"score":45.371362908471355},"GB2-05":{"attempts":1,"playable":85.00449802467791,"score":85.00449802467791},"GB2-06":{"attempts":1,"playable":57.0670286353555,"score":57.0670286353555},"GB2-07":{"attempts":1,"playable":89.77514727559289,"score":89.77514727559289},"GB2-08":{"attempts":1,"playable":87.27148237671136,"score":87.27148237671136}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:58:25Z","losses":961,"max_score":89.77514727559289,"measured_at":null,"min_score":45.371362908471355,"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":1.0,"provider":"Xiaomi","provider_key":"xiaomi","rank":31,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:58:25Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1804.1950606979067,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":73.15756430631654,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2741},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3:2dbca3140c06e14c","capped_draws":125,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.25555516},"codegen_evaluated_cells":8,"conditional_success_score":72.04274607752602,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":591,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.62656602805672,"score":51.62656602805672},"GB2-02":{"attempts":1,"playable":54.25293952450121,"score":54.25293952450121},"GB2-03":{"attempts":1,"playable":78.18527157184437,"score":78.18527157184437},"GB2-04":{"attempts":1,"playable":83.56150075093387,"score":83.56150075093387},"GB2-05":{"attempts":1,"playable":67.18977853745805,"score":67.18977853745805},"GB2-06":{"attempts":1,"playable":92.45899504353238,"score":92.45899504353238},"GB2-07":{"attempts":1,"playable":76.68460518642742,"score":76.68460518642742},"GB2-08":{"attempts":1,"playable":72.38231197745408,"score":72.38231197745408}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:17Z","losses":920,"max_score":92.45899504353238,"measured_at":null,"min_score":51.62656602805672,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GLM-5.3","model_slug":"z-ai-glm-5-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":32,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:20:30Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1751.0725302356598,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":72.04274607752602,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":2576},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-1-flash-1017:0e21134c7b1a52ee","capped_draws":119,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394},"codegen_evaluated_cells":8,"conditional_success_score":71.86740093318276,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":567,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash-1017","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.88198430461675,"score":68.88198430461675},"GB2-02":{"attempts":1,"playable":80.9876563481334,"score":80.9876563481334},"GB2-03":{"attempts":1,"playable":46.81990753998457,"score":46.81990753998457},"GB2-04":{"attempts":1,"playable":70.19348371023403,"score":70.19348371023403},"GB2-05":{"attempts":1,"playable":73.8910899940238,"score":73.8910899940238},"GB2-06":{"attempts":1,"playable":77.9827938772014,"score":77.9827938772014},"GB2-07":{"attempts":1,"playable":72.86638736782065,"score":72.86638736782065},"GB2-08":{"attempts":1,"playable":83.31590432344747,"score":83.31590432344747}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:59Z","losses":942,"max_score":83.31590432344747,"measured_at":null,"min_score":46.81990753998457,"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":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":33,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:49:59Z","ranking_status":"ranked","rated_matches":4086,"rating_method":"bradley_terry_newton","raw_elo":1736.5542141296753,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":71.86740093318276,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2577},{"admitted_plugins":14,"attempted_matches":7144,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc","capped_draws":382,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999},"codegen_evaluated_cells":16,"conditional_success_score":71.79397454177959,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1319,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-5","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":14,"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":2,"playable":76.70040734479815,"score":76.70040734479815},"GB2-02":{"attempts":2,"playable":71.53961375862548,"score":71.53961375862548},"GB2-03":{"attempts":2,"playable":51.687255463366554,"score":51.687255463366554},"GB2-04":{"attempts":2,"playable":49.134564968486444,"score":49.134564968486444},"GB2-05":{"attempts":2,"playable":89.14961944232594,"score":89.14961944232594},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":1,"playable":75.99222192441798,"score":75.99222192441798},"GB2-08":{"attempts":2,"playable":71.53111420480064,"score":71.53111420480064}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:53Z","losses":1582,"max_score":89.14961944232594,"measured_at":null,"min_score":49.134564968486444,"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":2,"plugin_success_rate":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":34,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:07:26Z","ranking_status":"ranked","rated_matches":7144,"rating_method":"bradley_terry_newton","raw_elo":1753.2310631611613,"reasoning_bracket":"baseline","reasoning_level":"Thinking disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Thinking disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Thinking disabled","reasoning_catalog_sha256":"54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":71.79397454177959,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":4243},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-6:bca3abc3bf41095f","capped_draws":132,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"codegen_evaluated_cells":8,"conditional_success_score":71.44109447735818,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":787,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.6","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":62.519569499522106,"score":62.519569499522106},"GB2-02":{"attempts":1,"playable":54.56565896441634,"score":54.56565896441634},"GB2-03":{"attempts":1,"playable":67.43501293246544,"score":67.43501293246544},"GB2-04":{"attempts":1,"playable":65.36937787646515,"score":65.36937787646515},"GB2-05":{"attempts":1,"playable":82.74387796459857,"score":82.74387796459857},"GB2-06":{"attempts":1,"playable":79.7304481203572,"score":79.7304481203572},"GB2-07":{"attempts":1,"playable":76.51158145988063,"score":76.51158145988063},"GB2-08":{"attempts":1,"playable":82.65322900116001,"score":82.65322900116001}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:57Z","losses":841,"max_score":82.74387796459857,"measured_at":null,"min_score":54.56565896441634,"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":1.0,"provider":"xAI","provider_key":"x-ai","rank":35,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:18Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1750.617875294576,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":71.44109447735818,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2460},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-1-3:5fca675bd4449b6f","capped_draws":55,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.24868390625000003,"median":0.2596235,"min":0.12429875,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.9894712500000002},"codegen_evaluated_cells":8,"conditional_success_score":70.94238807829937,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":529,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.3","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":76.79763775927,"score":76.79763775927},"GB2-02":{"attempts":1,"playable":62.84925449361422,"score":62.84925449361422},"GB2-03":{"attempts":1,"playable":83.16763929406432,"score":83.16763929406432},"GB2-04":{"attempts":1,"playable":51.35760364448936,"score":51.35760364448936},"GB2-05":{"attempts":1,"playable":79.36395137706818,"score":79.36395137706818},"GB2-06":{"attempts":1,"playable":84.72703232529484,"score":84.72703232529484},"GB2-07":{"attempts":1,"playable":58.18745218546933,"score":58.18745218546933},"GB2-08":{"attempts":1,"playable":71.08853354712474,"score":71.08853354712474}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:08Z","losses":1005,"max_score":84.72703232529484,"measured_at":null,"min_score":51.35760364448936,"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":1.0,"provider":"Meta","provider_key":"meta","rank":36,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:08Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1730.2343149882975,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.3","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":70.94238807829937,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2554},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-max-0902:c8aeec787bf0e7fd","capped_draws":253,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.398628,"median":0.380653,"min":0.332482,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.1890240000000003},"codegen_evaluated_cells":8,"conditional_success_score":70.20934940685238,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":816,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max-0902","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":76.60841138976626,"score":76.60841138976626},"GB2-02":{"attempts":1,"playable":49.546072293601604,"score":49.546072293601604},"GB2-03":{"attempts":1,"playable":71.3622706955068,"score":71.3622706955068},"GB2-04":{"attempts":1,"playable":84.71269669876197,"score":84.71269669876197},"GB2-05":{"attempts":1,"playable":92.40236120027856,"score":92.40236120027856},"GB2-06":{"attempts":1,"playable":64.40973208370043,"score":64.40973208370043},"GB2-07":{"attempts":1,"playable":76.33850998213276,"score":76.33850998213276},"GB2-08":{"attempts":1,"playable":46.294740911070704,"score":46.294740911070704}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:13Z","losses":887,"max_score":92.40236120027856,"measured_at":null,"min_score":46.294740911070704,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":37,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:13Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1733.4782802821328,"reasoning_bracket":"intensive","reasoning_level":"Xhigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Xhigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Xhigh","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":70.20934940685238,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2385},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:b85a8fb56d024434","capped_draws":224,"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":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389},"codegen_evaluated_cells":8,"conditional_success_score":69.02452864844383,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":757,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":63.486591391141424,"score":63.486591391141424},"GB2-02":{"attempts":1,"playable":57.4774541619302,"score":57.4774541619302},"GB2-03":{"attempts":1,"playable":59.99259918658731,"score":59.99259918658731},"GB2-04":{"attempts":1,"playable":75.16041171335864,"score":75.16041171335864},"GB2-05":{"attempts":1,"playable":82.56812866647837,"score":82.56812866647837},"GB2-06":{"attempts":1,"playable":82.27520760420894,"score":82.27520760420894},"GB2-07":{"attempts":1,"playable":75.81900444019345,"score":75.81900444019345},"GB2-08":{"attempts":1,"playable":55.41683202365234,"score":55.41683202365234}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:56:59Z","losses":971,"max_score":82.56812866647837,"measured_at":null,"min_score":55.41683202365234,"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":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":38,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:55:10Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1699.3117837046973,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":69.02452864844383,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2360},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:b4ca94f8b60a9e88","capped_draws":153,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.4542268568195333},"codegen_evaluated_cells":8,"conditional_success_score":68.68946946146029,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":840,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-2.4t-a95b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":58.641928528358974,"score":58.641928528358974},"GB2-02":{"attempts":1,"playable":53.62708451092556,"score":53.62708451092556},"GB2-03":{"attempts":1,"playable":82.09279624646348,"score":82.09279624646348},"GB2-04":{"attempts":1,"playable":46.490509638186836,"score":46.490509638186836},"GB2-05":{"attempts":1,"playable":69.0618156800023,"score":69.0618156800023},"GB2-06":{"attempts":1,"playable":80.00313072146281,"score":80.00313072146281},"GB2-07":{"attempts":1,"playable":69.5471049404985,"score":69.5471049404985},"GB2-08":{"attempts":1,"playable":90.05138542578382,"score":90.05138542578382}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:20Z","losses":923,"max_score":90.05138542578382,"measured_at":null,"min_score":46.490509638186836,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":39,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:14:34Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1727.0740641965092,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-2.4t-a95b","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":68.68946946146029,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2325},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3-flashx:43f4326da261c154","capped_draws":211,"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":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296144},"codegen_evaluated_cells":8,"conditional_success_score":68.6039314720645,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":619,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flashx","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":42.00746268161959,"score":42.00746268161959},"GB2-02":{"attempts":1,"playable":68.98161685961959,"score":68.98161685961959},"GB2-03":{"attempts":1,"playable":84.85546915992354,"score":84.85546915992354},"GB2-04":{"attempts":1,"playable":78.0535351595473,"score":78.0535351595473},"GB2-05":{"attempts":1,"playable":78.64256950562759,"score":78.64256950562759},"GB2-06":{"attempts":1,"playable":81.8208639592235,"score":81.8208639592235},"GB2-07":{"attempts":1,"playable":72.86638736782065,"score":72.86638736782065},"GB2-08":{"attempts":1,"playable":41.60354708313428,"score":41.60354708313428}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:25Z","losses":1060,"max_score":84.85546915992354,"measured_at":null,"min_score":41.60354708313428,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":40,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:58:16Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1691.9631043272884,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":68.6039314720645,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2409},{"admitted_plugins":25,"attempted_matches":12774,"canonical_public_row_identity":"publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367","capped_draws":176,"codegen_cost_usd":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":31,"run_count":28,"total":0.0},"codegen_evaluated_cells":25,"conditional_success_score":68.34010983325358,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1292,"eligibility_flag":true,"entry_count":25,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/ox-alpha","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":22,"first_pass_rate":0.88,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":58.588730554692084,"score":58.588730554692084},"GB2-02":{"attempts":2,"playable":74.06155524082445,"score":74.06155524082445},"GB2-03":{"attempts":5,"playable":71.23432297404122,"score":71.23432297404122},"GB2-04":{"attempts":3,"playable":71.51274169554084,"score":71.51274169554084},"GB2-05":{"attempts":3,"playable":62.63991432545314,"score":62.63991432545314},"GB2-06":{"attempts":3,"playable":68.62895630210221,"score":68.62895630210221},"GB2-07":{"attempts":3,"playable":66.69265511451336,"score":66.69265511451336},"GB2-08":{"attempts":3,"playable":73.36200245886134,"score":73.36200245886134}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":5,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:26Z","losses":3684,"max_score":74.06155524082445,"measured_at":null,"min_score":58.588730554692084,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Ox Alpha","model_slug":"stealth-ox-alpha","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Other","provider_key":"other","rank":41,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:16:36Z","ranking_status":"ranked","rated_matches":12771,"rating_method":"bradley_terry_newton","raw_elo":1676.7849106946098,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/ox-alpha","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.12,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":68.34010983325358,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":174,"wins":7795},{"admitted_plugins":8,"attempted_matches":4089,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91","capped_draws":142,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.8325049999999998},"codegen_evaluated_cells":8,"conditional_success_score":67.9956324960286,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":544,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-sol","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.78596380719114,"score":68.78596380719114},"GB2-02":{"attempts":1,"playable":67.96492649750486,"score":67.96492649750486},"GB2-03":{"attempts":1,"playable":62.16771778328458,"score":62.16771778328458},"GB2-04":{"attempts":1,"playable":78.34160803379433,"score":78.34160803379433},"GB2-05":{"attempts":1,"playable":76.8267887285266,"score":76.8267887285266},"GB2-06":{"attempts":1,"playable":41.85962447765607,"score":41.85962447765607},"GB2-07":{"attempts":1,"playable":71.2967744860653,"score":71.2967744860653},"GB2-08":{"attempts":1,"playable":76.7216561542059,"score":76.7216561542059}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:03:22Z","losses":1126,"max_score":78.34160803379433,"measured_at":null,"min_score":41.85962447765607,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":42,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:41Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1656.1001526782866,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":67.9956324960286,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":2418},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-sol:a790476a054b6a1d","capped_draws":25,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.345568},"codegen_evaluated_cells":8,"conditional_success_score":67.02394154797457,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":706,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-sol","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":61.84206851689213,"score":61.84206851689213},"GB2-02":{"attempts":1,"playable":52.89622916309222,"score":52.89622916309222},"GB2-03":{"attempts":1,"playable":82.27241448296013,"score":82.27241448296013},"GB2-04":{"attempts":1,"playable":43.945090981756195,"score":43.945090981756195},"GB2-05":{"attempts":1,"playable":77.91826645726006,"score":77.91826645726006},"GB2-06":{"attempts":1,"playable":73.54868883883643,"score":73.54868883883643},"GB2-07":{"attempts":1,"playable":57.64736615822385,"score":57.64736615822385},"GB2-08":{"attempts":1,"playable":86.1214077847756,"score":86.1214077847756}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:24Z","losses":1067,"max_score":86.1214077847756,"measured_at":null,"min_score":43.945090981756195,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":43,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:42Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1698.4870985515004,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-sol","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":67.02394154797457,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2315},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-1-3:111be2eb4c7d6522","capped_draws":12,"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":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740125000000006},"codegen_evaluated_cells":8,"conditional_success_score":66.77284273884489,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":625,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.3","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":75.09148073051385,"score":75.09148073051385},"GB2-02":{"attempts":1,"playable":57.78866741068549,"score":57.78866741068549},"GB2-03":{"attempts":1,"playable":63.44521844397948,"score":63.44521844397948},"GB2-04":{"attempts":1,"playable":64.2800529662376,"score":64.2800529662376},"GB2-05":{"attempts":1,"playable":59.45194791054944,"score":59.45194791054944},"GB2-06":{"attempts":1,"playable":81.8208639592235,"score":81.8208639592235},"GB2-07":{"attempts":1,"playable":54.57289357501711,"score":54.57289357501711},"GB2-08":{"attempts":1,"playable":77.7316169145525,"score":77.7316169145525}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:31Z","losses":1135,"max_score":81.8208639592235,"measured_at":null,"min_score":54.57289357501711,"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":1.0,"provider":"Meta","provider_key":"meta","rank":44,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T15:13:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1662.1030340265377,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":66.77284273884489,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2328},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-1-flash-1017:42cde21755d87ecd","capped_draws":12,"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":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.33613289399999996},"codegen_evaluated_cells":8,"conditional_success_score":66.72194055046423,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":640,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash-1017","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":84.27255262799545,"score":84.27255262799545},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":51.133542812877764,"score":51.133542812877764},"GB2-04":{"attempts":1,"playable":69.11472471991067,"score":69.11472471991067},"GB2-05":{"attempts":1,"playable":61.72584535971883,"score":61.72584535971883},"GB2-06":{"attempts":1,"playable":83.84426380372147,"score":83.84426380372147},"GB2-07":{"attempts":1,"playable":73.56251496756252,"score":73.56251496756252},"GB2-08":{"attempts":1,"playable":66.2606052041496,"score":66.2606052041496}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:09Z","losses":1118,"max_score":84.27255262799545,"measured_at":null,"min_score":43.861474907777556,"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":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":45,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:09Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1671.2851328124068,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":66.72194055046423,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":2329},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-6:d94ddefd8b9f53eb","capped_draws":373,"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":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758},"codegen_evaluated_cells":8,"conditional_success_score":66.35912688101574,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":832,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.6","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":50.55091318051426,"score":50.55091318051426},"GB2-02":{"attempts":1,"playable":83.28680710805719,"score":83.28680710805719},"GB2-03":{"attempts":1,"playable":51.74536624339686,"score":51.74536624339686},"GB2-04":{"attempts":1,"playable":60.20104195579413,"score":60.20104195579413},"GB2-05":{"attempts":1,"playable":85.00449802467791,"score":85.00449802467791},"GB2-06":{"attempts":1,"playable":66.33931517535959,"score":66.33931517535959},"GB2-07":{"attempts":1,"playable":76.16539028897841,"score":76.16539028897841},"GB2-08":{"attempts":1,"playable":57.579683071347496,"score":57.579683071347496}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:56:42Z","losses":1049,"max_score":85.00449802467791,"measured_at":null,"min_score":50.55091318051426,"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":1.0,"provider":"xAI","provider_key":"x-ai","rank":46,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:19:03Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1666.0508078352595,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.6","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":66.35912688101574,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2206},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gemini-3-1-pro-preview:0ecce8df0f776c80","capped_draws":29,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.3240465,"median":0.32247400000000004,"min":0.095864,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.592372},"codegen_evaluated_cells":8,"conditional_success_score":66.23066407825534,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":551,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-3.1-pro-preview","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":74.42618707235431,"score":74.42618707235431},"GB2-02":{"attempts":1,"playable":43.33329461578827,"score":43.33329461578827},"GB2-03":{"attempts":1,"playable":66.46750411509237,"score":66.46750411509237},"GB2-04":{"attempts":1,"playable":80.44699792971859,"score":80.44699792971859},"GB2-05":{"attempts":1,"playable":85.1765009642433,"score":85.1765009642433},"GB2-06":{"attempts":1,"playable":19.515189123449016,"score":19.515189123449016},"GB2-07":{"attempts":1,"playable":74.6050704809554,"score":74.6050704809554},"GB2-08":{"attempts":1,"playable":85.87456832444144,"score":85.87456832444144}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:48Z","losses":1162,"max_score":85.87456832444144,"measured_at":null,"min_score":19.515189123449016,"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":1.0,"provider":"Google","provider_key":"google","rank":47,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:16:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1667.2002417522003,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"google","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":66.23066407825534,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2375},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-8-flash:e50b23a03b02a00c","capped_draws":141,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865},"codegen_evaluated_cells":8,"conditional_success_score":66.20021724635149,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":460,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.8-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":55.432052071829915,"score":55.432052071829915},"GB2-02":{"attempts":1,"playable":69.69194480968862,"score":69.69194480968862},"GB2-03":{"attempts":1,"playable":71.64705790034347,"score":71.64705790034347},"GB2-04":{"attempts":1,"playable":47.20198870902211,"score":47.20198870902211},"GB2-05":{"attempts":1,"playable":67.18977853745804,"score":67.18977853745804},"GB2-06":{"attempts":1,"playable":88.61699922741556,"score":88.61699922741556},"GB2-07":{"attempts":1,"playable":69.5471049404985,"score":69.5471049404985},"GB2-08":{"attempts":1,"playable":60.274811774555594,"score":60.274811774555594}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:48:47Z","losses":1241,"max_score":88.61699922741556,"measured_at":null,"min_score":47.20198870902211,"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":1.0,"provider":"Google","provider_key":"google","rank":48,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:13:44Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1662.3731181240641,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.8-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":66.20021724635149,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2387},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:elorian-glimpse:d613dad94964ec86","capped_draws":37,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248},"codegen_evaluated_cells":8,"conditional_success_score":65.83738011304924,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":928,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"elorian/glimpse","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":83.07306782963423,"score":83.07306782963423},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":36.44436895903613,"score":36.44436895903613},"GB2-04":{"attempts":1,"playable":55.79328232032243,"score":55.79328232032243},"GB2-05":{"attempts":1,"playable":58.69249200332186,"score":58.69249200332186},"GB2-06":{"attempts":1,"playable":84.63629825457303,"score":84.63629825457303},"GB2-07":{"attempts":1,"playable":75.12563458860022,"score":75.12563458860022},"GB2-08":{"attempts":1,"playable":89.07242204112839,"score":89.07242204112839}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":986,"max_score":89.07242204112839,"measured_at":null,"min_score":36.44436895903613,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Glimpse","model_slug":"elorian-glimpse","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Other","provider_key":"other","rank":49,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:07:56Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1702.4587313762174,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":65.83738011304924,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2174},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-fable-5:1f4ca1763387a608","capped_draws":44,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"codegen_evaluated_cells":8,"conditional_success_score":65.81695308116886,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":734,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":76.4190951971478,"score":76.4190951971478},"GB2-02":{"attempts":1,"playable":57.996058159075126,"score":57.996058159075126},"GB2-03":{"attempts":1,"playable":20.85286434586851,"score":20.85286434586851},"GB2-04":{"attempts":1,"playable":53.57872837341826,"score":53.57872837341826},"GB2-05":{"attempts":1,"playable":69.24862460139967,"score":69.24862460139967},"GB2-06":{"attempts":1,"playable":81.72998896896267,"score":81.72998896896267},"GB2-07":{"attempts":1,"playable":73.7364089726703,"score":73.7364089726703},"GB2-08":{"attempts":1,"playable":92.97385603080852,"score":92.97385603080852}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:07Z","losses":1078,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":50,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:07:55Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1708.2070907615816,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":65.81695308116886,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2276},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:fireworks-ember-1:7393828552cef5d9","capped_draws":13,"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":0.508434,"mean":0.298893375,"median":0.3053985,"min":0.149517,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":2.391147},"codegen_evaluated_cells":8,"conditional_success_score":65.0853117856486,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":717,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"fireworks/ember-1","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":77.08130575673387,"score":77.08130575673387},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":81.1918431229029,"score":81.1918431229029},"GB2-04":{"attempts":1,"playable":41.08644928581932,"score":41.08644928581932},"GB2-05":{"attempts":1,"playable":63.237816289157955,"score":63.237816289157955},"GB2-06":{"attempts":1,"playable":51.75602740212671,"score":51.75602740212671},"GB2-07":{"attempts":1,"playable":75.81900444019345,"score":75.81900444019345},"GB2-08":{"attempts":1,"playable":87.59950869232675,"score":87.59950869232675}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:03:01Z","losses":1134,"max_score":87.59950869232675,"measured_at":null,"min_score":41.08644928581932,"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":1.0,"provider":"Fireworks AI","provider_key":"fireworks","rank":51,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:59Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1665.345120845054,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":65.0853117856486,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2237},{"admitted_plugins":16,"attempted_matches":8178,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd","capped_draws":398,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":57},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.531673125,"mean":0.4248703476562501,"median":0.446083425,"min":0.28979720625,"recorded_attempt_count":57,"run_count":20,"total":8.014536974999999},"codegen_evaluated_cells":16,"conditional_success_score":64.58218353568154,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1492,"eligibility_flag":true,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.6-flash","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":12,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":55.81610926740474,"score":55.81610926740474},"GB2-02":{"attempts":2,"playable":54.980534929468845,"score":54.980534929468845},"GB2-03":{"attempts":2,"playable":69.05690088333495,"score":69.05690088333495},"GB2-04":{"attempts":2,"playable":63.06826791424943,"score":63.06826791424943},"GB2-05":{"attempts":2,"playable":83.85508646801725,"score":83.85508646801725},"GB2-06":{"attempts":2,"playable":82.60903300478043,"score":82.60903300478043},"GB2-07":{"attempts":2,"playable":51.38166979730925,"score":51.38166979730925},"GB2-08":{"attempts":2,"playable":55.88986602088737,"score":55.88986602088737}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-02","GB2-03","GB2-07"],"infra_failures_excluded":5,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:45Z","losses":2326,"max_score":83.85508646801725,"measured_at":null,"min_score":51.38166979730925,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.6 Flash","model_slug":"google-gemini-3-6-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Google","provider_key":"google","rank":52,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:14:02Z","ranking_status":"ranked","rated_matches":8177,"rating_method":"bradley_terry_newton","raw_elo":1663.3301062017065,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":4,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":64.58218353568154,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":4359},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:tencent-hy4-preview:2077a0aa15ce66b2","capped_draws":517,"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":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525},"codegen_evaluated_cells":8,"conditional_success_score":64.4909676291399,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":973,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy4-preview","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":55.042337638007275,"score":55.042337638007275},"GB2-02":{"attempts":1,"playable":78.71632855665378,"score":78.71632855665378},"GB2-03":{"attempts":1,"playable":72.4992470077333,"score":72.4992470077333},"GB2-04":{"attempts":1,"playable":56.39605880742696,"score":56.39605880742696},"GB2-05":{"attempts":1,"playable":70.36785336156095,"score":70.36785336156095},"GB2-06":{"attempts":1,"playable":81.00293289509779,"score":81.00293289509779},"GB2-07":{"attempts":1,"playable":67.79115840389798,"score":67.79115840389798},"GB2-08":{"attempts":1,"playable":34.11182436274114,"score":34.11182436274114}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:16:02Z","losses":1062,"max_score":81.00293289509779,"measured_at":null,"min_score":34.11182436274114,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Hy4 Preview","model_slug":"tencent-hy4-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Tencent","provider_key":"tencent","rank":53,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T18:52:03Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1627.4140867006215,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":64.4909676291399,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2053},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash:188028ef432c73f8","capped_draws":107,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.164549388465127},"codegen_evaluated_cells":8,"conditional_success_score":64.0865576806636,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":675,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":90.48531473976723,"score":90.48531473976723},"GB2-02":{"attempts":1,"playable":62.84925449361422,"score":62.84925449361422},"GB2-03":{"attempts":1,"playable":70.98199665336188,"score":70.98199665336188},"GB2-04":{"attempts":1,"playable":39.96129123978842,"score":39.96129123978842},"GB2-05":{"attempts":1,"playable":52.01913687544882,"score":52.01913687544882},"GB2-06":{"attempts":1,"playable":75.5491946702753,"score":75.5491946702753},"GB2-07":{"attempts":1,"playable":52.022714507735756,"score":52.022714507735756},"GB2-08":{"attempts":1,"playable":68.82355826531712,"score":68.82355826531712}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:33Z","losses":1223,"max_score":90.48531473976723,"measured_at":null,"min_score":39.96129123978842,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.5 Flash","model_slug":"google-gemini-3-5-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Google","provider_key":"google","rank":54,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:03Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1632.9785354281767,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":64.0865576806636,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2190},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184","capped_draws":69,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":1.38945,"mean":0.93123625,"median":0.95991,"min":0.36561,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":7.449890000000001},"codegen_evaluated_cells":8,"conditional_success_score":72.88629537163214,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":485,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-8","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.78596380719114,"score":68.78596380719114},"GB2-02":{"attempts":1,"playable":79.21136097509942,"score":79.21136097509942},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":70.48724931008368,"score":70.48724931008368},"GB2-05":{"attempts":1,"playable":49.337466438153236,"score":49.337466438153236},"GB2-06":{"attempts":1,"playable":82.4569280608738,"score":82.4569280608738},"GB2-07":{"attempts":1,"playable":76.85758163467997,"score":76.85758163467997},"GB2-08":{"attempts":1,"playable":83.06751737534383,"score":83.06751737534383}},"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":"2026-10-26T02:09:01Z","losses":793,"max_score":83.06751737534383,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Claude Opus 4.8","model_slug":"claude-opus-4-8","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Anthropic","provider_key":"anthropic","rank":55,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:07:50Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1752.9989992354278,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.77550845017813,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2316},{"admitted_plugins":7,"attempted_matches":3609,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4:483e8409583d40a0","capped_draws":73,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"codegen_evaluated_cells":8,"conditional_success_score":72.61089170836732,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":504,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":95.24631432919804,"score":95.24631432919804},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.22701691364703,"score":44.22701691364703},"GB2-04":{"attempts":1,"playable":56.69724994545443,"score":56.69724994545443},"GB2-05":{"attempts":1,"playable":85.86183696737152,"score":85.86183696737152},"GB2-06":{"attempts":1,"playable":81.63911217049767,"score":81.63911217049767},"GB2-07":{"attempts":1,"playable":77.7217719313222,"score":77.7217719313222},"GB2-08":{"attempts":1,"playable":66.88293970108037,"score":66.88293970108037}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:13Z","losses":795,"max_score":95.24631432919804,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"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":0.875,"provider":"OpenAI","provider_key":"openai","rank":56,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:18:59Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1801.2639925738645,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.534530244821404,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2309},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-wonder:eca0332e70baf930","capped_draws":35,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4270272,"mean":0.2502732,"median":0.206604,"min":0.16216,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":2.0021856},"codegen_evaluated_cells":8,"conditional_success_score":63.482439435561815,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":669,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-wonder","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":53.286943540124355,"score":53.286943540124355},"GB2-02":{"attempts":1,"playable":56.23109924276132,"score":56.23109924276132},"GB2-03":{"attempts":1,"playable":36.86911022917292,"score":36.86911022917292},"GB2-04":{"attempts":1,"playable":39.55185774658149,"score":39.55185774658149},"GB2-05":{"attempts":1,"playable":85.34823456158135,"score":85.34823456158135},"GB2-06":{"attempts":1,"playable":77.0945052028131,"score":77.0945052028131},"GB2-07":{"attempts":1,"playable":87.52572113245827,"score":87.52572113245827},"GB2-08":{"attempts":1,"playable":71.95204382900168,"score":71.95204382900168}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:48:48Z","losses":1217,"max_score":87.52572113245827,"measured_at":null,"min_score":36.86911022917292,"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":1.0,"provider":"Meta","provider_key":"meta","rank":57,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T17:48:48Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1687.1461731146273,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.482439435561815,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2202},{"admitted_plugins":8,"attempted_matches":4089,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c","capped_draws":132,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07455065,"median":0.0607138,"min":0.0448404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.5964052000000001},"codegen_evaluated_cells":8,"conditional_success_score":63.4772921247202,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":672,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.5","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":83.6275738997741,"score":83.6275738997741},"GB2-02":{"attempts":1,"playable":59.238956333712366,"score":59.238956333712366},"GB2-03":{"attempts":1,"playable":45.37018462718579,"score":45.37018462718579},"GB2-04":{"attempts":1,"playable":44.25089660655846,"score":44.25089660655846},"GB2-05":{"attempts":1,"playable":73.70656014798726,"score":73.70656014798726},"GB2-06":{"attempts":1,"playable":54.51921324294854,"score":54.51921324294854},"GB2-07":{"attempts":1,"playable":56.56499142897715,"score":56.56499142897715},"GB2-08":{"attempts":1,"playable":90.53996071061802,"score":90.53996071061802}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","losses":1232,"max_score":90.53996071061802,"measured_at":null,"min_score":44.25089660655846,"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":1.0,"provider":"xAI","provider_key":"x-ai","rank":58,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:05:13Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1649.3316133883272,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.4772921247202,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":2184},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3-flash:6bc93e3f26e0f0e5","capped_draws":141,"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":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"codegen_evaluated_cells":8,"conditional_success_score":63.334509179752644,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":706,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":71.08671603660993,"score":71.08671603660993},"GB2-02":{"attempts":1,"playable":46.39253976872338,"score":46.39253976872338},"GB2-03":{"attempts":1,"playable":80.46765982501938,"score":80.46765982501938},"GB2-04":{"attempts":1,"playable":73.99705337511335,"score":73.99705337511335},"GB2-05":{"attempts":1,"playable":48.570174105681495,"score":48.570174105681495},"GB2-06":{"attempts":1,"playable":81.45735359322124,"score":81.45735359322124},"GB2-07":{"attempts":1,"playable":75.64573739534956,"score":75.64573739534956},"GB2-08":{"attempts":1,"playable":29.05883933830283,"score":29.05883933830283}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:55Z","losses":1231,"max_score":81.45735359322124,"measured_at":null,"min_score":29.05883933830283,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":59,"rank_movement":-3,"rank_movement_baseline_at":"2026-10-24T19:18:50Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1618.7026720901936,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.334509179752644,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2151},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-flash:98dfb2fac355b676","capped_draws":308,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"codegen_evaluated_cells":8,"conditional_success_score":63.08758585684125,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1021,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":51.62656602805672,"score":51.62656602805672},"GB2-02":{"attempts":1,"playable":58.61781945897073,"score":58.61781945897073},"GB2-03":{"attempts":1,"playable":66.46750411509237,"score":66.46750411509237},"GB2-04":{"attempts":1,"playable":48.115921740853715,"score":48.115921740853715},"GB2-05":{"attempts":1,"playable":71.66985312607504,"score":71.66985312607504},"GB2-06":{"attempts":1,"playable":80.91204535467794,"score":80.91204535467794},"GB2-07":{"attempts":1,"playable":75.29905289404675,"score":75.29905289404675},"GB2-08":{"attempts":1,"playable":51.99192413695668,"score":51.99192413695668}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:30Z","losses":1086,"max_score":80.91204535467794,"measured_at":null,"min_score":48.115921740853715,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":60,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:07:43Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1624.1288544341674,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.08758585684125,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1981},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc","capped_draws":54,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0878628,"mean":0.0635932,"median":0.06199639999999999,"min":0.0498884,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.5087456},"codegen_evaluated_cells":8,"conditional_success_score":61.882626639667734,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":845,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.5","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":83.90425679819714,"score":83.90425679819714},"GB2-02":{"attempts":1,"playable":52.478268451558996,"score":52.478268451558996},"GB2-03":{"attempts":1,"playable":56.29807121307564,"score":56.29807121307564},"GB2-04":{"attempts":1,"playable":42.9250607025321,"score":42.9250607025321},"GB2-05":{"attempts":1,"playable":67.37729200558647,"score":67.37729200558647},"GB2-06":{"attempts":1,"playable":44.94891798146081,"score":44.94891798146081},"GB2-07":{"attempts":1,"playable":58.54710537662376,"score":58.54710537662376},"GB2-08":{"attempts":1,"playable":88.58204058830702,"score":88.58204058830702}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:18:16Z","losses":1214,"max_score":88.58204058830702,"measured_at":null,"min_score":42.9250607025321,"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":1.0,"provider":"xAI","provider_key":"x-ai","rank":61,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:19:44Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1617.4399814830454,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":61.882626639667734,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2029},{"admitted_plugins":7,"attempted_matches":3608,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0","capped_draws":182,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475},"codegen_evaluated_cells":8,"conditional_success_score":70.34791389387141,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":626,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":80.9346384024902,"score":80.9346384024902},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":51.133542812877764,"score":51.133542812877764},"GB2-04":{"attempts":1,"playable":36.88696967756637,"score":36.88696967756637},"GB2-05":{"attempts":1,"playable":77.19125124108702,"score":77.19125124108702},"GB2-06":{"attempts":1,"playable":81.54823367582276,"score":81.54823367582276},"GB2-07":{"attempts":1,"playable":87.00914453270325,"score":87.00914453270325},"GB2-08":{"attempts":1,"playable":77.7316169145525,"score":77.7316169145525}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:02Z","losses":811,"max_score":87.00914453270325,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"GPT-5.5","model_slug":"gpt-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"OpenAI","provider_key":"openai","rank":62,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:13:16Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1765.9661860715112,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":61.55442465713748,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2171},{"admitted_plugins":8,"attempted_matches":4089,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-8-flash:6b8b02f1f727feff","capped_draws":197,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"codegen_evaluated_cells":8,"conditional_success_score":61.2087923226988,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":968,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.8-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":71.18240320394425,"score":71.18240320394425},"GB2-02":{"attempts":1,"playable":40.05218343975386,"score":40.05218343975386},"GB2-03":{"attempts":1,"playable":84.5901003533996,"score":84.5901003533996},"GB2-04":{"attempts":1,"playable":60.89947429906761,"score":60.89947429906761},"GB2-05":{"attempts":1,"playable":55.07572688871119,"score":55.07572688871119},"GB2-06":{"attempts":1,"playable":79.09418456303702,"score":79.09418456303702},"GB2-07":{"attempts":1,"playable":57.467174986402846,"score":57.467174986402846},"GB2-08":{"attempts":1,"playable":41.30909084727405,"score":41.30909084727405}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:04Z","losses":1193,"max_score":84.5901003533996,"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":1.0,"provider":"Google","provider_key":"google","rank":63,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:37:59Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1594.6820684438221,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":61.2087923226988,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1927},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-fable-5:346aadd5d76b812b","capped_draws":101,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885},"codegen_evaluated_cells":8,"conditional_success_score":60.19752144645451,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":917,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-fable-5","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":71.46937457256453,"score":71.46937457256453},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":35.06079366276128,"score":35.06079366276128},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":68.68797508514861,"score":68.68797508514861},"GB2-06":{"attempts":1,"playable":77.00360964515674,"score":77.00360964515674},"GB2-07":{"attempts":1,"playable":61.94804537058572,"score":61.94804537058572},"GB2-08":{"attempts":1,"playable":85.13322706875395,"score":85.13322706875395}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:01Z","losses":1233,"max_score":85.13322706875395,"measured_at":null,"min_score":35.06079366276128,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":64,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:14:58Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1623.8599722750964,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":60.19752144645451,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1938},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:3fe477f1e3ed7e39","capped_draws":224,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062},"codegen_evaluated_cells":8,"conditional_success_score":60.1913228654651,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":524,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.6-flash","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":53.677267651639525,"score":53.677267651639525},"GB2-02":{"attempts":1,"playable":66.84399961192453,"score":66.84399961192453},"GB2-03":{"attempts":1,"playable":62.758061666473175,"score":62.758061666473175},"GB2-04":{"attempts":1,"playable":58.70174355075301,"score":58.70174355075301},"GB2-05":{"attempts":1,"playable":60.021061787878295,"score":60.021061787878295},"GB2-06":{"attempts":1,"playable":66.24759668126995,"score":66.24759668126995},"GB2-07":{"attempts":1,"playable":83.23019220896973,"score":83.23019220896973},"GB2-08":{"attempts":1,"playable":30.050659764812487,"score":30.050659764812487}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:02Z","losses":1459,"max_score":83.23019220896973,"measured_at":null,"min_score":30.050659764812487,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"MiMo-V2.6-Flash","model_slug":"xiaomi-mimo-v2-6-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Xiaomi","provider_key":"xiaomi","rank":65,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:14:37Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1574.2232993380796,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":60.1913228654651,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2105},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-1-2:c2e0113edd4e5952","capped_draws":15,"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":0.2224195,"mean":0.1433925625,"median":0.13115787499999998,"min":0.104555,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":1.1471405},"codegen_evaluated_cells":8,"conditional_success_score":59.674538064803045,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":689,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.2","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":80.5608541872989,"score":80.5608541872989},"GB2-02":{"attempts":1,"playable":48.39115651225852,"score":48.39115651225852},"GB2-03":{"attempts":1,"playable":61.08221142804463,"score":61.08221142804463},"GB2-04":{"attempts":1,"playable":49.535698213129706,"score":49.535698213129706},"GB2-05":{"attempts":1,"playable":61.53661978064131,"score":61.53661978064131},"GB2-06":{"attempts":1,"playable":27.07629811042509,"score":27.07629811042509},"GB2-07":{"attempts":1,"playable":74.77864378963382,"score":74.77864378963382},"GB2-08":{"attempts":1,"playable":74.43482249699235,"score":74.43482249699235}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:37Z","losses":1383,"max_score":80.5608541872989,"measured_at":null,"min_score":27.07629811042509,"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":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Meta","provider_key":"meta","rank":66,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:49:37Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1561.6870211874445,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":59.674538064803045,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2016},{"admitted_plugins":7,"attempted_matches":3586,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b","capped_draws":67,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.060198249999999995,"mean":0.047021,"median":0.04824225,"min":0.0324825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.37616799999999995},"codegen_evaluated_cells":8,"conditional_success_score":59.33488623832671,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":780,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.2","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"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":85.82938002593471,"score":85.82938002593471},"GB2-02":{"attempts":1,"playable":46.81368819709062,"score":46.81368819709062},"GB2-03":{"attempts":1,"playable":52.25436624935729,"score":52.25436624935729},"GB2-04":{"attempts":1,"playable":45.880231916103,"score":45.880231916103},"GB2-05":{"attempts":1,"playable":49.912626901458104,"score":49.912626901458104},"GB2-07":{"attempts":1,"playable":64.25915621579892,"score":64.25915621579892},"GB2-08":{"attempts":1,"playable":70.3947541625443,"score":70.3947541625443}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:01Z","losses":1138,"max_score":85.82938002593471,"measured_at":null,"min_score":45.880231916103,"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":1.0,"provider":"Meta","provider_key":"meta","rank":67,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:07:40Z","ranking_status":"ranked","rated_matches":3586,"rating_method":"bradley_terry_newton","raw_elo":1570.8770824952346,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":59.33488623832671,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1668},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3-flash:1540ade2fda6b881","capped_draws":51,"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":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.119209325},"codegen_evaluated_cells":8,"conditional_success_score":59.095129153799014,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":455,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":65.99600951760388,"score":65.99600951760388},"GB2-02":{"attempts":1,"playable":66.43573754691377,"score":66.43573754691377},"GB2-03":{"attempts":1,"playable":78.36892503795902,"score":78.36892503795902},"GB2-04":{"attempts":1,"playable":78.82121553724855,"score":78.82121553724855},"GB2-05":{"attempts":1,"playable":74.2598107921713,"score":74.2598107921713},"GB2-06":{"attempts":1,"playable":17.24808744063479,"score":17.24808744063479},"GB2-07":{"attempts":1,"playable":69.72234893364258,"score":69.72234893364258},"GB2-08":{"attempts":1,"playable":21.90889842421831,"score":21.90889842421831}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:15:49Z","losses":1533,"max_score":78.82121553724855,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":68,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:41Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1525.9287763180582,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":59.095129153799014,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2100},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-luna:06fb6314cedafbae","capped_draws":33,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199},"codegen_evaluated_cells":8,"conditional_success_score":57.91646553492024,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":574,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-luna","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":29.81318081377865,"score":29.81318081377865},"GB2-02":{"attempts":1,"playable":63.15763310706362,"score":63.15763310706362},"GB2-03":{"attempts":1,"playable":50.213724619244374,"score":50.213724619244374},"GB2-04":{"attempts":1,"playable":65.07251021291862,"score":65.07251021291862},"GB2-05":{"attempts":1,"playable":53.930599354883036,"score":53.930599354883036},"GB2-06":{"attempts":1,"playable":85.72453199600761,"score":85.72453199600761},"GB2-07":{"attempts":1,"playable":39.204261853711586,"score":39.204261853711586},"GB2-08":{"attempts":1,"playable":76.2152823217545,"score":76.2152823217545}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:45Z","losses":1528,"max_score":85.72453199600761,"measured_at":null,"min_score":29.81318081377865,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":69,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:24:26Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1568.834667389216,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-luna","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.91646553492024,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1986},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:mistralai-mistral-large-4-0:4820a17c6350d8c5","capped_draws":290,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.33846634,"mean":0.191117675,"median":0.19018014,"min":0.07351397,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.5289414},"codegen_evaluated_cells":8,"conditional_success_score":57.85279997474128,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":989,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"mistralai/mistral-large-4-0","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":34.98596030617719,"score":34.98596030617719},"GB2-02":{"attempts":1,"playable":65.41359404194165,"score":65.41359404194165},"GB2-03":{"attempts":1,"playable":43.60195874561567,"score":43.60195874561567},"GB2-04":{"attempts":1,"playable":65.56719653014635,"score":65.56719653014635},"GB2-05":{"attempts":1,"playable":49.52921654279083,"score":49.52921654279083},"GB2-06":{"attempts":1,"playable":79.63955354616625,"score":79.63955354616625},"GB2-07":{"attempts":1,"playable":79.44691027123345,"score":79.44691027123345},"GB2-08":{"attempts":1,"playable":44.63800981385882,"score":44.63800981385882}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:04:51Z","losses":1318,"max_score":79.63955354616625,"measured_at":null,"min_score":34.98596030617719,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Mistral Large 4","model_slug":"mistralai-mistral-large-4-0","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Mistral","provider_key":"mistral","rank":70,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T17:04:51Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1559.3047906082827,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.85279997474128,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1781},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-haiku-5-5:f36e1e66260e3efb","capped_draws":394,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0174997,"mean":0.0119476,"median":0.012623549999999999,"min":0.0054094,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.0955808},"codegen_evaluated_cells":8,"conditional_success_score":57.64469547081516,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":944,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-haiku-5-5","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":45.55051096100455,"score":45.55051096100455},"GB2-02":{"attempts":1,"playable":62.952066864120745,"score":62.952066864120745},"GB2-03":{"attempts":1,"playable":67.82097932487197,"score":67.82097932487197},"GB2-04":{"attempts":1,"playable":67.73816657363633,"score":67.73816657363633},"GB2-05":{"attempts":1,"playable":57.55198442693155,"score":57.55198442693155},"GB2-06":{"attempts":1,"playable":68.90168340024606,"score":68.90168340024606},"GB2-07":{"attempts":1,"playable":56.92611116770436,"score":56.92611116770436},"GB2-08":{"attempts":1,"playable":33.71606104800567,"score":33.71606104800567}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:36:50Z","losses":1368,"max_score":68.90168340024606,"measured_at":null,"min_score":33.71606104800567,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":71,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:36:50Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1529.765389054973,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.64469547081516,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1776},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash:79befaaad7974375","capped_draws":92,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478311},"codegen_evaluated_cells":8,"conditional_success_score":57.363642946497215,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":828,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":73.3788760709071,"score":73.3788760709071},"GB2-02":{"attempts":1,"playable":44.600427873465655,"score":44.600427873465655},"GB2-03":{"attempts":1,"playable":70.17124171661679,"score":70.17124171661679},"GB2-04":{"attempts":1,"playable":54.28409063356446,"score":54.28409063356446},"GB2-05":{"attempts":1,"playable":67.18977853745804,"score":67.18977853745804},"GB2-06":{"attempts":1,"playable":74.45815982704819,"score":74.45815982704819},"GB2-07":{"attempts":1,"playable":54.209603332930065,"score":54.209603332930065},"GB2-08":{"attempts":1,"playable":20.616965579987426,"score":20.616965579987426}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:28Z","losses":1425,"max_score":74.45815982704819,"measured_at":null,"min_score":20.616965579987426,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.5 Flash","model_slug":"google-gemini-3-5-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Google","provider_key":"google","rank":72,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:08Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1542.846460502181,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.363642946497215,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1834},{"admitted_plugins":8,"attempted_matches":4089,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55","capped_draws":38,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925},"codegen_evaluated_cells":8,"conditional_success_score":57.06538147558733,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":834,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-sol","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":79.34262727198148,"score":79.34262727198148},"GB2-02":{"attempts":1,"playable":45.76043854681514,"score":45.76043854681514},"GB2-03":{"attempts":1,"playable":53.67541484767906,"score":53.67541484767906},"GB2-04":{"attempts":1,"playable":41.39310769434979,"score":41.39310769434979},"GB2-05":{"attempts":1,"playable":53.54859225427029,"score":53.54859225427029},"GB2-06":{"attempts":1,"playable":61.26768165598104,"score":61.26768165598104},"GB2-07":{"attempts":1,"playable":47.61160891393276,"score":47.61160891393276},"GB2-08":{"attempts":1,"playable":73.92358061968909,"score":73.92358061968909}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T18:03:22Z","losses":1432,"max_score":79.34262727198148,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":73,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:47:26Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1544.8734142159426,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":57.06538147558733,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1822},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-wonder:3d73d47d8aac3d79","capped_draws":240,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.187324,"mean":0.12070595,"median":0.10780200000000001,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.9656475999999999},"codegen_evaluated_cells":8,"conditional_success_score":56.80785802653988,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1046,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-wonder","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.97799180980552,"score":68.97799180980552},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"playable":17.08812627475027,"score":17.08812627475027},"GB2-04":{"attempts":1,"playable":53.881108654651364,"score":53.881108654651364},"GB2-05":{"attempts":1,"playable":85.1765009642433,"score":85.1765009642433},"GB2-06":{"attempts":1,"playable":69.00075586704354,"score":69.00075586704354},"GB2-07":{"attempts":1,"playable":54.02783130374852,"score":54.02783130374852},"GB2-08":{"attempts":1,"playable":63.294303743711986,"score":63.294303743711986}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:37Z","losses":1316,"max_score":85.1765009642433,"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":1.0,"provider":"Meta","provider_key":"meta","rank":74,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:49:37Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1570.0506325427223,"reasoning_bracket":"baseline","reasoning_level":"Minimal","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Minimal","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":56.80785802653988,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1725},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220","capped_draws":61,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795},"codegen_evaluated_cells":8,"conditional_success_score":56.542942439794004,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":836,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":63.77650188114862,"score":63.77650188114862},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":60.29017029445606,"score":60.29017029445606},"GB2-04":{"attempts":1,"playable":53.17536482756301,"score":53.17536482756301},"GB2-05":{"attempts":1,"playable":54.69416900833654,"score":54.69416900833654},"GB2-06":{"attempts":1,"playable":28.7088915902937,"score":28.7088915902937},"GB2-07":{"attempts":1,"playable":68.14286552155062,"score":68.14286552155062},"GB2-08":{"attempts":1,"playable":81.4911023882058,"score":81.4911023882058}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:01Z","losses":1438,"max_score":81.4911023882058,"measured_at":null,"min_score":28.7088915902937,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":75,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:31:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1530.9496281581598,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":56.542942439794004,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1814},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-open:afccdf89d01c95e6","capped_draws":93,"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":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.22147360000000002},"codegen_evaluated_cells":8,"conditional_success_score":56.28068539310311,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":814,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-open","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":64.74219896051368,"score":64.74219896051368},"GB2-02":{"attempts":1,"playable":45.56434921703077,"score":45.56434921703077},"GB2-03":{"attempts":1,"playable":57.100683119070354,"score":57.100683119070354},"GB2-04":{"attempts":1,"playable":46.69384599832737,"score":46.69384599832737},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":61.45320043406526,"score":61.45320043406526},"GB2-07":{"attempts":1,"playable":32.73183651180149,"score":32.73183651180149},"GB2-08":{"attempts":1,"playable":83.64687213519258,"score":83.64687213519258}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:55Z","losses":1471,"max_score":83.64687213519258,"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":1.0,"provider":"Meta","provider_key":"meta","rank":76,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:49:55Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1543.6263516122613,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-open","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":56.28068539310311,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1802},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d0b5b92265541548","capped_draws":127,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828},"codegen_evaluated_cells":8,"conditional_success_score":55.91744014634476,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":776,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro-0813","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":43.58353633785871,"score":43.58353633785871},"GB2-02":{"attempts":1,"playable":45.022421426676964,"score":45.022421426676964},"GB2-03":{"attempts":1,"playable":64.13066103380365,"score":64.13066103380365},"GB2-04":{"attempts":1,"playable":43.33319700499054,"score":43.33319700499054},"GB2-05":{"attempts":1,"playable":74.81201350070057,"score":74.81201350070057},"GB2-06":{"attempts":1,"playable":66.33931517535959,"score":66.33931517535959},"GB2-07":{"attempts":1,"playable":79.27457840265981,"score":79.27457840265981},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:48:58Z","losses":1498,"max_score":79.27457840265981,"measured_at":null,"min_score":30.843798288708303,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4 Pro 0813","model_slug":"deepseek-deepseek-v4-pro-0813","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":77,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:23:41Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1546.3720169457665,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.91744014634476,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1814},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96","capped_draws":311,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.24666659999999999},"codegen_evaluated_cells":8,"conditional_success_score":55.862096065373166,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1186,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-luna","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":81.401125129377,"score":81.401125129377},"GB2-02":{"attempts":1,"playable":45.338788424049355,"score":45.338788424049355},"GB2-03":{"attempts":1,"playable":41.72041770372514,"score":41.72041770372514},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":51.25358631759123,"score":51.25358631759123},"GB2-06":{"attempts":1,"playable":83.72858164014411,"score":83.72858164014411},"GB2-07":{"attempts":1,"playable":72.69221573249251,"score":72.69221573249251},"GB2-08":{"attempts":1,"playable":32.13196509707394,"score":32.13196509707394}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:49Z","losses":1290,"max_score":83.72858164014411,"measured_at":null,"min_score":32.13196509707394,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":78,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:04Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1553.2483602211792,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.862096065373166,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1612},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:reflection-beam-1-0-501b-a23b:27d5e34f0b0db7e0","capped_draws":146,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.227669},"codegen_evaluated_cells":8,"conditional_success_score":55.60815060684604,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":725,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"reflection/beam-1.0-501b-a23b","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":24.91348009565777,"score":24.91348009565777},"GB2-02":{"attempts":1,"playable":50.17533136484096,"score":50.17533136484096},"GB2-03":{"attempts":1,"playable":78.73568284375807,"score":78.73568284375807},"GB2-04":{"attempts":1,"playable":61.09887828448084,"score":61.09887828448084},"GB2-05":{"attempts":1,"playable":53.16644009511591,"score":53.16644009511591},"GB2-06":{"attempts":1,"playable":74.73094620480506,"score":74.73094620480506},"GB2-07":{"attempts":1,"playable":39.204261853711586,"score":39.204261853711586},"GB2-08":{"attempts":1,"playable":62.84018411239812,"score":62.84018411239812}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":1554,"max_score":78.73568284375807,"measured_at":null,"min_score":24.91348009565777,"model_code_failure_rate":0.0,"model_code_failures":0,"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":1.0,"provider":"Other","provider_key":"other","rank":79,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:07:56Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1523.946824579442,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"reflection/beam-1.0-501b-a23b","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.60815060684604,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1809},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:d1c3d52890a12a42","capped_draws":452,"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":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934},"codegen_evaluated_cells":8,"conditional_success_score":55.58022173760598,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1194,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.11346235814054,"score":68.11346235814054},"GB2-02":{"attempts":1,"playable":58.20338066890267,"score":58.20338066890267},"GB2-03":{"attempts":1,"playable":55.09029052603635,"score":55.09029052603635},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":53.930599354883036,"score":53.930599354883036},"GB2-06":{"attempts":1,"playable":76.73092068582082,"score":76.73092068582082},"GB2-07":{"attempts":1,"playable":69.5471049404985,"score":69.5471049404985},"GB2-08":{"attempts":1,"playable":24.29347129725537,"score":24.29347129725537}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:24Z","losses":1311,"max_score":76.73092068582082,"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":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":80,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:20:59Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1528.8092039843432,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.58022173760598,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1583},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-8-flash:83795e08736dcbd6","capped_draws":231,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196},"codegen_evaluated_cells":8,"conditional_success_score":55.521591530257865,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":980,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.8-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":56.60037369856589,"score":56.60037369856589},"GB2-02":{"attempts":1,"playable":40.58211986231627,"score":40.58211986231627},"GB2-03":{"attempts":1,"playable":51.541548933129086,"score":51.541548933129086},"GB2-04":{"attempts":1,"playable":45.880231916103,"score":45.880231916103},"GB2-05":{"attempts":1,"playable":55.64777346044759,"score":55.64777346044759},"GB2-06":{"attempts":1,"playable":73.73060888844665,"score":73.73060888844665},"GB2-07":{"attempts":1,"playable":42.96299010506729,"score":42.96299010506729},"GB2-08":{"attempts":1,"playable":77.22708537798715,"score":77.22708537798715}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:30:56Z","losses":1417,"max_score":77.22708537798715,"measured_at":null,"min_score":40.58211986231627,"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":1.0,"provider":"Google","provider_key":"google","rank":81,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:23:57Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1542.2169532272978,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.8-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.521591530257865,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1691},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c","capped_draws":123,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"codegen_evaluated_cells":8,"conditional_success_score":55.33043041538656,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":988,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":97.50040588860446,"score":97.50040588860446},"GB2-02":{"attempts":1,"playable":46.81368819709062,"score":46.81368819709062},"GB2-03":{"attempts":1,"playable":44.33108968183731,"score":44.33108968183731},"GB2-04":{"attempts":1,"playable":33.187510514814925,"score":33.187510514814925},"GB2-05":{"attempts":1,"playable":71.4841167856698,"score":71.4841167856698},"GB2-06":{"attempts":1,"playable":77.18540045807114,"score":77.18540045807114},"GB2-07":{"attempts":1,"playable":33.881725359608645,"score":33.881725359608645},"GB2-08":{"attempts":1,"playable":38.25950643739559,"score":38.25950643739559}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:17Z","losses":1415,"max_score":97.50040588860446,"measured_at":null,"min_score":33.187510514814925,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.4","model_slug":"gpt-5-4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":82,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:25Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1574.5125319835183,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":55.33043041538656,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1685},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-open:29312afcfc1923c1","capped_draws":136,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985},"codegen_evaluated_cells":8,"conditional_success_score":54.98399866703712,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":971,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-open","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.72430239386958,"score":51.72430239386958},"GB2-02":{"attempts":1,"playable":44.38935843142217,"score":44.38935843142217},"GB2-03":{"attempts":1,"playable":33.672393099704045,"score":33.672393099704045},"GB2-04":{"attempts":1,"playable":47.30358303033733,"score":47.30358303033733},"GB2-05":{"attempts":1,"playable":57.55198442693155,"score":57.55198442693155},"GB2-06":{"attempts":1,"playable":77.6293099265343,"score":77.6293099265343},"GB2-07":{"attempts":1,"playable":57.467174986402846,"score":57.467174986402846},"GB2-08":{"attempts":1,"playable":70.13388304109516,"score":70.13388304109516}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:21Z","losses":1438,"max_score":77.6293099265343,"measured_at":null,"min_score":33.672393099704045,"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":1.0,"provider":"Meta","provider_key":"meta","rank":83,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:21Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1539.1810980901928,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":54.98399866703712,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1678},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-terra:bd3aacb7be18fc49","capped_draws":225,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998},"codegen_evaluated_cells":8,"conditional_success_score":54.76266822043014,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":986,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-terra","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":72.1384361760712,"score":72.1384361760712},"GB2-02":{"attempts":1,"playable":59.65269552895921,"score":59.65269552895921},"GB2-03":{"attempts":1,"playable":36.76296797467189,"score":36.76296797467189},"GB2-04":{"attempts":1,"playable":42.31255022830733,"score":42.31255022830733},"GB2-05":{"attempts":1,"playable":55.64777346044759,"score":55.64777346044759},"GB2-06":{"attempts":1,"playable":80.7302675590266,"score":80.7302675590266},"GB2-07":{"attempts":1,"playable":44.27016262800866,"score":44.27016262800866},"GB2-08":{"attempts":1,"playable":46.586492207948666,"score":46.586492207948666}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:41Z","losses":1454,"max_score":80.7302675590266,"measured_at":null,"min_score":36.76296797467189,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.6 Terra","model_slug":"gpt-5-6-terra","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":84,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:05:48Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1520.7949293586712,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":54.76266822043014,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1648},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:fireworks-ember-1:221b6c2f5a9ba6bb","capped_draws":350,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.20107799999999998,"mean":0.142499625,"median":0.14239200000000002,"min":0.071757,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":1.1399970000000001},"codegen_evaluated_cells":8,"conditional_success_score":54.68341219816406,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1061,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"fireworks/ember-1","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.235536792230654,"score":51.235536792230654},"GB2-02":{"attempts":1,"playable":44.91694128410355,"score":44.91694128410355},"GB2-03":{"attempts":1,"playable":62.46304509166916,"score":62.46304509166916},"GB2-04":{"attempts":1,"playable":53.276225943954394,"score":53.276225943954394},"GB2-05":{"attempts":1,"playable":47.61042676894488,"score":47.61042676894488},"GB2-06":{"attempts":1,"playable":57.91147700886635,"score":57.91147700886635},"GB2-07":{"attempts":1,"playable":64.25915621579892,"score":64.25915621579892},"GB2-08":{"attempts":1,"playable":55.7944884797446,"score":55.7944884797446}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:52:58Z","losses":1424,"max_score":64.25915621579892,"measured_at":null,"min_score":44.91694128410355,"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":1.0,"provider":"Fireworks AI","provider_key":"fireworks","rank":85,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T18:47:06Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1500.8881061366726,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":54.68341219816406,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1603},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-pro:c37d073d6b142a09","capped_draws":53,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.37262013029400004},"codegen_evaluated_cells":8,"conditional_success_score":53.667004053189046,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":811,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":4,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":62.326046402047176,"score":62.326046402047176},"GB2-02":{"attempts":1,"playable":39.30981926802688,"score":39.30981926802688},"GB2-03":{"attempts":1,"playable":29.58652296151986,"score":29.58652296151986},"GB2-04":{"attempts":1,"playable":44.35281068247941,"score":44.35281068247941},"GB2-05":{"attempts":1,"playable":49.14568681479483,"score":49.14568681479483},"GB2-06":{"attempts":1,"playable":48.670508702846305,"score":48.670508702846305},"GB2-07":{"attempts":1,"playable":71.47140899698569,"score":71.47140899698569},"GB2-08":{"attempts":1,"playable":84.47322859681222,"score":84.47322859681222}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:23Z","losses":1557,"max_score":84.47322859681222,"measured_at":null,"min_score":29.58652296151986,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4 Pro","model_slug":"deepseek-deepseek-v4-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":86,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:46Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1527.8478857278592,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":4,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":53.667004053189046,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1720},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363","capped_draws":425,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.58673,"mean":0.44285687500000004,"median":0.4176025,"min":0.34269,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":3.5428550000000003},"codegen_evaluated_cells":8,"conditional_success_score":53.14804758528771,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1171,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":64.93521214747375,"score":64.93521214747375},"GB2-02":{"attempts":1,"playable":55.711088338828816,"score":55.711088338828816},"GB2-03":{"attempts":1,"playable":39.61869369407654,"score":39.61869369407654},"GB2-04":{"attempts":1,"playable":39.44947595905667,"score":39.44947595905667},"GB2-05":{"attempts":1,"playable":77.0090970640164,"score":77.0090970640164},"GB2-06":{"attempts":1,"playable":29.358038652970798,"score":29.358038652970798},"GB2-07":{"attempts":1,"playable":61.05578240397785,"score":61.05578240397785},"GB2-08":{"attempts":1,"playable":58.04699242190091,"score":58.04699242190091}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:51:49Z","losses":1420,"max_score":77.0090970640164,"measured_at":null,"min_score":29.358038652970798,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.5","model_slug":"gpt-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":87,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:12:32Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1487.47279071709,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":53.14804758528771,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1497},{"admitted_plugins":14,"attempted_matches":7158,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a","capped_draws":337,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3888165,"mean":0.26060548125,"median":0.24728879999999998,"min":0.17802225,"recorded_attempt_count":44,"run_count":16,"total":4.1696877},"codegen_evaluated_cells":16,"conditional_success_score":59.2565550590453,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1392,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.6-flash","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":14,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":72.36687780212262,"score":72.36687780212262},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":37.504788276235715,"score":18.752394138117857},"GB2-03":{"attempts":2,"playable":49.340297921174475,"score":49.340297921174475},"GB2-04":{"attempts":2,"playable":41.33829786076156,"score":41.33829786076156},"GB2-05":{"attempts":2,"playable":69.95613195624621,"score":69.95613195624621},"GB2-06":{"attempts":2,"playable":83.77303910526301,"score":83.77303910526301},"GB2-07":{"attempts":2,"playable":48.51144728367936,"score":48.51144728367936},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":71.26156026687946,"score":35.63078013343973}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:49Z","losses":2301,"max_score":83.77303910526301,"measured_at":null,"min_score":18.752394138117857,"model_code_failure_rate":0.125,"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":0.875,"provider":"Google","provider_key":"google","rank":88,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:16:43Z","ranking_status":"ranked","rated_matches":7158,"rating_method":"bradley_terry_newton","raw_elo":1635.2872521578754,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":52.45865827510061,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3465},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3-flashx:d5d0648c410f1ae2","capped_draws":144,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"codegen_evaluated_cells":8,"conditional_success_score":52.348000012946464,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":851,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flashx","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":77.55361591884589,"score":77.55361591884589},"GB2-02":{"attempts":1,"playable":52.478268451558996,"score":52.478268451558996},"GB2-03":{"attempts":1,"playable":57.401127531830454,"score":57.401127531830454},"GB2-04":{"attempts":1,"playable":55.99426584982658,"score":55.99426584982658},"GB2-05":{"attempts":1,"playable":40.68351463237852,"score":40.68351463237852},"GB2-06":{"attempts":1,"playable":55.84310189813421,"score":55.84310189813421},"GB2-07":{"attempts":1,"playable":59.80337275739795,"score":59.80337275739795},"GB2-08":{"attempts":1,"playable":19.026733063599135,"score":19.026733063599135}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:20Z","losses":1628,"max_score":77.55361591884589,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":89,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T18:59:05Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1464.63424304211,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":52.348000012946464,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1609},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e","capped_draws":207,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586},"codegen_evaluated_cells":10,"conditional_success_score":55.16981094046571,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":824,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":32.60183738521237,"score":32.60183738521237},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":51.85088546914854,"score":25.92544273457427},"GB2-03":{"attempts":1,"playable":57.30101192815999,"score":57.30101192815999},"GB2-04":{"attempts":1,"playable":66.75252041544007,"score":66.75252041544007},"GB2-05":{"attempts":1,"playable":47.41839642713655,"score":47.41839642713655},"GB2-06":{"attempts":1,"playable":52.13892655650203,"score":52.13892655650203},"GB2-07":{"attempts":1,"playable":78.06713479000248,"score":78.06713479000248},"GB2-08":{"attempts":1,"playable":55.22777455212362,"score":55.22777455212362}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:02Z","losses":1518,"max_score":78.06713479000248,"measured_at":null,"min_score":25.92544273457427,"model_code_failure_rate":0.1111111111111111,"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":0.8888888888888888,"provider":"Alibaba","provider_key":"qwen","rank":90,"rank_movement":9,"rank_movement_baseline_at":"2026-10-24T19:03:46Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1507.4992903344441,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.92913059864392,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1746},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-sonnet-5-5:6b457c283468fc9c","capped_draws":58,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.083848,"mean":0.06079725,"median":0.058081,"min":0.039074,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.486378},"codegen_evaluated_cells":8,"conditional_success_score":51.92727517846182,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":931,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5-5","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":46.827209408703894,"score":46.827209408703894},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":32.06442448205719,"score":32.06442448205719},"GB2-04":{"attempts":1,"playable":40.881961647250705,"score":40.881961647250705},"GB2-05":{"attempts":1,"playable":19.50173450694367,"score":19.50173450694367},"GB2-06":{"attempts":1,"playable":77.0945052028131,"score":77.0945052028131},"GB2-07":{"attempts":1,"playable":71.99495941342104,"score":71.99495941342104},"GB2-08":{"attempts":1,"playable":84.14286747057714,"score":84.14286747057714}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:49Z","losses":1565,"max_score":84.14286747057714,"measured_at":null,"min_score":19.50173450694367,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":91,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:04:54Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1519.7936398098177,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.92727517846182,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1592},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3-flashx:746a19cef7ee23ef","capped_draws":336,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627},"codegen_evaluated_cells":8,"conditional_success_score":51.86318956901767,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1133,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flashx","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":65.89962850329437,"score":65.89962850329437},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-03":{"attempts":1,"playable":47.74876632823254,"score":47.74876632823254},"GB2-04":{"attempts":1,"playable":51.96399450515018,"score":51.96399450515018},"GB2-05":{"attempts":1,"playable":49.72093680458015,"score":49.72093680458015},"GB2-06":{"attempts":1,"playable":63.94914667204261,"score":63.94914667204261},"GB2-07":{"attempts":1,"playable":65.49851489264262,"score":65.49851489264262},"GB2-08":{"attempts":1,"playable":28.165864415051487,"score":28.165864415051487}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:23Z","losses":1497,"max_score":65.89962850329437,"measured_at":null,"min_score":28.165864415051487,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":92,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:12:16Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1476.9797470977715,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.86318956901767,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1458},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6","capped_draws":170,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.244315,"mean":0.178065,"median":0.19681749999999998,"min":0.10277,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":1.42452},"codegen_evaluated_cells":8,"conditional_success_score":51.837783858490795,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1008,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-5","reasoning_catalog_sha256":"3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":57.86464980653705,"score":57.86464980653705},"GB2-02":{"attempts":1,"playable":43.967075478045246,"score":43.967075478045246},"GB2-03":{"attempts":1,"playable":47.02653132835043,"score":47.02653132835043},"GB2-04":{"attempts":1,"playable":43.843134736241275,"score":43.843134736241275},"GB2-05":{"attempts":1,"playable":46.84214988189366,"score":46.84214988189366},"GB2-06":{"attempts":1,"playable":51.85180751822701,"score":51.85180751822701},"GB2-07":{"attempts":1,"playable":46.50096345229458,"score":46.50096345229458},"GB2-08":{"attempts":1,"playable":76.80595866633712,"score":76.80595866633712}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:26Z","losses":1560,"max_score":76.80595866633712,"measured_at":null,"min_score":43.843134736241275,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":93,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:14:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1483.964623262025,"reasoning_bracket":"balanced","reasoning_level":"Medium effort + 16,000 thinking tokens","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium effort + 16,000 thinking tokens","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium effort + 16,000 thinking tokens","reasoning_catalog_sha256":"3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.837783858490795,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1520},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-1-flash-1017:7a6614195303225f","capped_draws":73,"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":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.046843572},"codegen_evaluated_cells":8,"conditional_success_score":51.708762136040676,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":968,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash-1017","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":73.28355889590416,"score":73.28355889590416},"GB2-02":{"attempts":1,"playable":43.967075478045246,"score":43.967075478045246},"GB2-03":{"attempts":1,"playable":39.9346947850152,"score":39.9346947850152},"GB2-04":{"attempts":1,"playable":42.72093112604436,"score":42.72093112604436},"GB2-05":{"attempts":1,"playable":52.59294502518301,"score":52.59294502518301},"GB2-06":{"attempts":1,"playable":46.0402270700513,"score":46.0402270700513},"GB2-07":{"attempts":1,"playable":33.30720043746538,"score":33.30720043746538},"GB2-08":{"attempts":1,"playable":81.82346427061673,"score":81.82346427061673}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:48:51Z","losses":1579,"max_score":81.82346427061673,"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":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":94,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T17:48:51Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1486.8828625247704,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.708762136040676,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1540},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-2:4571486d5f3c5826","capped_draws":434,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23894740000000003,"mean":0.121926546075,"median":0.109979,"min":0.0289264146,"recorded_attempt_count":10,"run_count":8,"total":0.9754123686},"codegen_evaluated_cells":8,"conditional_success_score":51.6276087892073,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1223,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.2","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":46.04171899042915,"score":46.04171899042915},"GB2-02":{"attempts":1,"playable":53.94008099588955,"score":53.94008099588955},"GB2-03":{"attempts":1,"playable":27.636931072548244,"score":27.636931072548244},"GB2-04":{"attempts":1,"playable":56.39605880742696,"score":56.39605880742696},"GB2-05":{"attempts":1,"playable":52.59294502518301,"score":52.59294502518301},"GB2-06":{"attempts":1,"playable":85.81515405853162,"score":85.81515405853162},"GB2-07":{"attempts":1,"playable":66.2051728960299,"score":66.2051728960299},"GB2-08":{"attempts":1,"playable":24.392808467619947,"score":24.392808467619947}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:29Z","losses":1450,"max_score":85.81515405853162,"measured_at":null,"min_score":24.392808467619947,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":95,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:05:44Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1499.087498086456,"reasoning_bracket":"balanced","reasoning_level":"High (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High (historical request variant 1)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-1","reasoning_bucket_label":"High (historical request variant 1)","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced-variant-1"},"reasoning_setting":"historical-provider-setting-balanced-variant-1","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.6276087892073,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1415},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988","capped_draws":267,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.1077678,"mean":0.076003275,"median":0.070269,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.6080262},"codegen_evaluated_cells":8,"conditional_success_score":51.61785428673993,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":973,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.72430239386958,"score":51.72430239386958},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":49.49659136353635,"score":49.49659136353635},"GB2-04":{"attempts":1,"playable":45.880231916103,"score":45.880231916103},"GB2-05":{"attempts":1,"playable":55.266448071150265,"score":55.266448071150265},"GB2-06":{"attempts":1,"playable":47.7950627448825,"score":47.7950627448825},"GB2-07":{"attempts":1,"playable":27.903670654718134,"score":27.903670654718134},"GB2-08":{"attempts":1,"playable":92.81205314286193,"score":92.81205314286193}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:49Z","losses":1574,"max_score":92.81205314286193,"measured_at":null,"min_score":27.903670654718134,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Kimi K3","model_slug":"moonshotai-kimi-k3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Moonshot","provider_key":"moonshotai","rank":96,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:12:12Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1509.4657025639451,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.61785428673993,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1541},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3:9e30a36ab00bd740","capped_draws":304,"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":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688},"codegen_evaluated_cells":8,"conditional_success_score":51.42810872156023,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1131,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.40175329217033,"score":68.40175329217033},"GB2-02":{"attempts":1,"playable":44.2838056546712,"score":44.2838056546712},"GB2-03":{"attempts":1,"playable":42.6623790200342,"score":42.6623790200342},"GB2-04":{"attempts":1,"playable":48.62325324165005,"score":48.62325324165005},"GB2-05":{"attempts":1,"playable":59.641698621129635,"score":59.641698621129635},"GB2-06":{"attempts":1,"playable":49.7358004353113,"score":49.7358004353113},"GB2-07":{"attempts":1,"playable":71.99495941342104,"score":71.99495941342104},"GB2-08":{"attempts":1,"playable":26.081220094094103,"score":26.081220094094103}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:39Z","losses":1512,"max_score":71.99495941342104,"measured_at":null,"min_score":26.081220094094103,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GLM-5.3","model_slug":"z-ai-glm-5-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":97,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:04:54Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1470.0685047887252,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.42810872156023,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1445},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:f9ec308f9bb8850b","capped_draws":197,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726},"codegen_evaluated_cells":8,"conditional_success_score":51.202341872576675,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":988,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-2.4t-a95b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":36.473239590319295,"score":36.473239590319295},"GB2-02":{"attempts":1,"playable":49.33620937974867,"score":49.33620937974867},"GB2-03":{"attempts":1,"playable":50.213724619244374,"score":50.213724619244374},"GB2-04":{"attempts":1,"playable":46.18542092099077,"score":46.18542092099077},"GB2-05":{"attempts":1,"playable":35.476935369558205,"score":35.476935369558205},"GB2-06":{"attempts":1,"playable":63.21119746214339,"score":63.21119746214339},"GB2-07":{"attempts":1,"playable":44.08368895950843,"score":44.08368895950843},"GB2-08":{"attempts":1,"playable":84.6383186791003,"score":84.6383186791003}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:01Z","losses":1591,"max_score":84.6383186791003,"measured_at":null,"min_score":35.476935369558205,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":98,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:05:18Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1493.0164764231952,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-2.4t-a95b","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.202341872576675,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1509},{"admitted_plugins":7,"attempted_matches":3608,"canonical_public_row_identity":"publication-row.v1:mixed:tencent-hy4-preview:014a9ceb67d5b786","capped_draws":41,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"codegen_evaluated_cells":8,"conditional_success_score":58.358477962384605,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":573,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy4-preview","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":52.79884906579119,"score":52.79884906579119},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":41.09112538431462,"score":41.09112538431462},"GB2-04":{"attempts":1,"playable":35.34683349909481,"score":35.34683349909481},"GB2-05":{"attempts":1,"playable":52.40171003122839,"score":52.40171003122839},"GB2-06":{"attempts":1,"playable":60.43168330617621,"score":60.43168330617621},"GB2-07":{"attempts":1,"playable":77.20339463461717,"score":77.20339463461717},"GB2-08":{"attempts":1,"playable":89.23574981546986,"score":89.23574981546986}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:59Z","losses":1275,"max_score":89.23574981546986,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Hy4 Preview","model_slug":"tencent-hy4-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Tencent","provider_key":"tencent","rank":99,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:06:54Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1604.5967554289957,"reasoning_bracket":"balanced","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.06366821708653,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1760},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-6-pro:091b7e3f3afd6616","capped_draws":225,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.05751309},"codegen_evaluated_cells":8,"conditional_success_score":51.00996634667253,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1016,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.6-pro","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":39.5403292159651,"score":39.5403292159651},"GB2-02":{"attempts":1,"playable":40.15819245415532,"score":40.15819245415532},"GB2-03":{"attempts":1,"playable":44.95490332572907,"score":44.95490332572907},"GB2-04":{"attempts":1,"playable":55.69276892990924,"score":55.69276892990924},"GB2-05":{"attempts":1,"playable":45.688988962286096,"score":45.688988962286096},"GB2-06":{"attempts":1,"playable":56.22023369086085,"score":56.22023369086085},"GB2-07":{"attempts":1,"playable":43.33691025969965,"score":43.33691025969965},"GB2-08":{"attempts":1,"playable":82.48740393477489,"score":82.48740393477489}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:24Z","losses":1585,"max_score":82.48740393477489,"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":1.0,"provider":"Xiaomi","provider_key":"xiaomi","rank":100,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:26Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1485.6269478285049,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":51.00996634667253,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1487},{"admitted_plugins":8,"attempted_matches":4090,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-terra:ac05ef4b9a51340d","capped_draws":139,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987500000001},"codegen_evaluated_cells":8,"conditional_success_score":50.97355583210514,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1035,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-terra","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":77.27030124028664,"score":77.27030124028664},"GB2-02":{"attempts":1,"playable":46.181889573237264,"score":46.181889573237264},"GB2-03":{"attempts":1,"playable":34.41556090723444,"score":34.41556090723444},"GB2-04":{"attempts":1,"playable":43.843134736241275,"score":43.843134736241275},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":41.85962447765607,"score":41.85962447765607},"GB2-07":{"attempts":1,"playable":60.87709979353989,"score":60.87709979353989},"GB2-08":{"attempts":1,"playable":45.02833915982205,"score":45.02833915982205}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:45Z","losses":1582,"max_score":77.27030124028664,"measured_at":null,"min_score":34.41556090723444,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.6 Terra","model_slug":"gpt-5-6-terra","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":101,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:32Z","ranking_status":"ranked","rated_matches":4089,"rating_method":"bradley_terry_newton","raw_elo":1459.9964053892215,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.97355583210514,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1472},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd","capped_draws":261,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73533,"mean":0.5886581249999999,"median":0.58241,"min":0.410635,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8},"run_count":8,"token_priced_attempt_count":8,"total":4.709265},"codegen_evaluated_cells":8,"conditional_success_score":50.82406525596982,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1010,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-5","reasoning_catalog_sha256":"3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":72.13843617607122,"score":72.13843617607122},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":50.4183440046138,"score":50.4183440046138},"GB2-04":{"attempts":1,"playable":41.69967780442835,"score":41.69967780442835},"GB2-05":{"attempts":1,"playable":51.25358631759123,"score":51.25358631759123},"GB2-06":{"attempts":1,"playable":56.4086180600745,"score":56.4086180600745},"GB2-07":{"attempts":1,"playable":50.1908466096623,"score":50.1908466096623},"GB2-08":{"attempts":1,"playable":40.62153816753958,"score":40.62153816753958}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:24Z","losses":1609,"max_score":72.13843617607122,"measured_at":null,"min_score":40.62153816753958,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":102,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:21:13Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1458.8489370231266,"reasoning_bracket":"intensive","reasoning_level":"High effort + 32,000 thinking tokens","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"High effort + 32,000 thinking tokens","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High effort + 32,000 thinking tokens","reasoning_catalog_sha256":"3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.82406525596982,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1469},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-max-0902:1a5946a1ae31cc68","capped_draws":389,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.9697739999999999},"codegen_evaluated_cells":8,"conditional_success_score":50.741522502796954,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1146,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max-0902","reasoning_catalog_sha256":"2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":42.20459427392016,"score":42.20459427392016},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":55.795390298790515,"score":55.795390298790515},"GB2-04":{"attempts":1,"playable":37.810117835138485,"score":37.810117835138485},"GB2-05":{"attempts":1,"playable":59.83140336003518,"score":59.83140336003518},"GB2-06":{"attempts":1,"playable":81.27558907899275,"score":81.27558907899275},"GB2-07":{"attempts":1,"playable":39.3930442666294,"score":39.3930442666294},"GB2-08":{"attempts":1,"playable":47.55756690207156,"score":47.55756690207156}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:53Z","losses":1538,"max_score":81.27558907899275,"measured_at":null,"min_score":37.810117835138485,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":103,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:04:31Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1484.3593907584855,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"2ba3f8fb7fd583ee9cd19289f7a7daee50f52ab1c236d9ed7c6da6bec21e6484","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.741522502796954,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1404},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c","capped_draws":255,"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":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"codegen_evaluated_cells":8,"conditional_success_score":50.66565082784072,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1066,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":42.401690774062445,"score":42.401690774062445},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":56.69963599400225,"score":56.69963599400225},"GB2-04":{"attempts":1,"playable":37.912645619152194,"score":37.912645619152194},"GB2-05":{"attempts":1,"playable":68.12667167289695,"score":68.12667167289695},"GB2-06":{"attempts":1,"playable":49.7358004353113,"score":49.7358004353113},"GB2-07":{"attempts":1,"playable":39.77034106847703,"score":39.77034106847703},"GB2-08":{"attempts":1,"playable":67.76788176289583,"score":67.76788176289583}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:46:12Z","losses":1584,"max_score":68.12667167289695,"measured_at":null,"min_score":37.912645619152194,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Qwen3.8 Max","model_slug":"qwen-qwen3-8-max","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Alibaba","provider_key":"qwen","rank":104,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:14:53Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1468.290465248636,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.66565082784072,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1438},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:nvidia-nemotron-3-5-super-vl:9a0402e94be8b8b5","capped_draws":89,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0934742},"codegen_evaluated_cells":8,"conditional_success_score":50.174554112269085,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":968,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3.5-super-vl","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":66.18873786369763,"score":66.18873786369763},"GB2-02":{"attempts":1,"playable":44.81144895648299,"score":44.81144895648299},"GB2-03":{"attempts":1,"playable":36.23182617727008,"score":36.23182617727008},"GB2-04":{"attempts":1,"playable":41.08644928581932,"score":41.08644928581932},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":46.81810703397261,"score":46.81810703397261},"GB2-07":{"attempts":1,"playable":57.10654768753967,"score":57.10654768753967},"GB2-08":{"attempts":1,"playable":50.840819124546954,"score":50.840819124546954}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:25Z","losses":1650,"max_score":66.18873786369763,"measured_at":null,"min_score":36.23182617727008,"model_code_failure_rate":0.0,"model_code_failures":0,"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":1.0,"provider":"NVIDIA","provider_key":"nvidia","rank":105,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:25Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1453.2904006078456,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":50.174554112269085,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1470},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584","capped_draws":230,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.4398702,"mean":0.29041619999999996,"median":0.301782,"min":0.095232,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":2.3233295999999997},"codegen_evaluated_cells":8,"conditional_success_score":49.57130649717783,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1003,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":69.07398625142943,"score":69.07398625142943},"GB2-02":{"attempts":1,"playable":41.4294472413882,"score":41.4294472413882},"GB2-03":{"attempts":1,"playable":66.17653557525448,"score":66.17653557525448},"GB2-04":{"attempts":1,"playable":47.60829699628472,"score":47.60829699628472},"GB2-05":{"attempts":1,"playable":51.63642816425957,"score":51.63642816425957},"GB2-06":{"attempts":1,"playable":56.0317286642899,"score":56.0317286642899},"GB2-07":{"attempts":1,"playable":25.17264569142056,"score":25.17264569142056},"GB2-08":{"attempts":1,"playable":39.44138339309575,"score":39.44138339309575}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:52:43Z","losses":1670,"max_score":69.07398625142943,"measured_at":null,"min_score":25.17264569142056,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Kimi K3","model_slug":"moonshotai-kimi-k3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Moonshot","provider_key":"moonshotai","rank":106,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:24:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1434.255445413412,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":49.57130649717783,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1415},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5:16f7def69ce10ccd","capped_draws":309,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45464499999999997,"mean":0.28201406249999994,"median":0.2695775,"min":0.17401125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":2.2561124999999995},"codegen_evaluated_cells":8,"conditional_success_score":49.452229432393345,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1156,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":39.73790526536497,"score":39.73790526536497},"GB2-02":{"attempts":1,"playable":42.27605906017271,"score":42.27605906017271},"GB2-03":{"attempts":1,"playable":37.611301069122675,"score":37.611301069122675},"GB2-04":{"attempts":1,"playable":40.06362607016069,"score":40.06362607016069},"GB2-05":{"attempts":1,"playable":75.91303436651312,"score":75.91303436651312},"GB2-06":{"attempts":1,"playable":69.90573731056207,"score":69.90573731056207},"GB2-07":{"attempts":1,"playable":52.93541386858993,"score":52.93541386858993},"GB2-08":{"attempts":1,"playable":37.17475844866062,"score":37.17475844866062}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:44:02Z","losses":1578,"max_score":75.91303436651312,"measured_at":null,"min_score":37.17475844866062,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5","model_slug":"gpt-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":107,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:18:14Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1475.802913919254,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":49.452229432393345,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1354},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d","capped_draws":246,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036},"codegen_evaluated_cells":8,"conditional_success_score":49.40248896541706,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1044,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.5","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":52.44469857894575,"score":52.44469857894575},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":15.752084763952883,"score":15.752084763952883},"GB2-04":{"attempts":1,"playable":42.82300100995158,"score":42.82300100995158},"GB2-05":{"attempts":1,"playable":42.80266050358737,"score":42.80266050358737},"GB2-06":{"attempts":1,"playable":43.36084532221298,"score":43.36084532221298},"GB2-07":{"attempts":1,"playable":69.37179816696903,"score":69.37179816696903},"GB2-08":{"attempts":1,"playable":84.80334846993928,"score":84.80334846993928}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:12:49Z","losses":1610,"max_score":84.80334846993928,"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":1.0,"provider":"xAI","provider_key":"x-ai","rank":108,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:46Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1475.998197829034,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":49.40248896541706,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1433},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-pro:42034002bcfc5f74","capped_draws":163,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.9135725942489998},"codegen_evaluated_cells":8,"conditional_success_score":48.708988669738766,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":999,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":27.516500344886474,"score":27.516500344886474},"GB2-02":{"attempts":1,"playable":45.76043854681514,"score":45.76043854681514},"GB2-03":{"attempts":1,"playable":46.71655058071938,"score":46.71655058071938},"GB2-04":{"attempts":1,"playable":46.490509638186836,"score":46.490509638186836},"GB2-05":{"attempts":1,"playable":45.112094261816324,"score":45.112094261816324},"GB2-06":{"attempts":1,"playable":78.70569511408215,"score":78.70569511408215},"GB2-07":{"attempts":1,"playable":74.77864378963382,"score":74.77864378963382},"GB2-08":{"attempts":1,"playable":24.59147708177002,"score":24.59147708177002}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T23:06:03Z","losses":1681,"max_score":78.70569511408215,"measured_at":null,"min_score":24.59147708177002,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4 Pro","model_slug":"deepseek-deepseek-v4-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":109,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:32:05Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1466.1427686528639,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.708988669738766,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1407},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80","capped_draws":325,"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":0.173358,"mean":0.1197105,"median":0.119348,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.9576840000000001},"codegen_evaluated_cells":8,"conditional_success_score":48.59019041732298,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1152,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":26.816405095011675,"score":26.816405095011675},"GB2-02":{"attempts":1,"playable":40.47615436428729,"score":40.47615436428729},"GB2-03":{"attempts":1,"playable":39.091444932727754,"score":39.091444932727754},"GB2-04":{"attempts":1,"playable":41.49530757762349,"score":41.49530757762349},"GB2-05":{"attempts":1,"playable":90.56613075261299,"score":90.56613075261299},"GB2-06":{"attempts":1,"playable":22.7698174814249,"score":22.7698174814249},"GB2-07":{"attempts":1,"playable":71.99495941342104,"score":71.99495941342104},"GB2-08":{"attempts":1,"playable":55.51130372147471,"score":55.51130372147471}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:00Z","losses":1592,"max_score":90.56613075261299,"measured_at":null,"min_score":22.7698174814249,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Qwen3.8 Max","model_slug":"qwen-qwen3-8-max","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Alibaba","provider_key":"qwen","rank":110,"rank_movement":3,"rank_movement_baseline_at":"2026-10-24T19:17:03Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1482.8984524117875,"reasoning_bracket":"baseline","reasoning_level":"Minimal","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Minimal","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.59019041732298,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1344},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-7:7805d7703d63f406","capped_draws":173,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.6637360000000001},"codegen_evaluated_cells":8,"conditional_success_score":55.362666471232274,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":657,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.7","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":27.516500344886474,"score":27.516500344886474},"GB2-02":{"attempts":1,"playable":52.89622916309222,"score":52.89622916309222},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.2311783551885,"score":43.2311783551885},"GB2-05":{"attempts":1,"playable":42.610087464525805,"score":42.610087464525805},"GB2-06":{"attempts":1,"playable":82.82033367565535,"score":82.82033367565535},"GB2-07":{"attempts":1,"playable":55.47964545859105,"score":55.47964545859105},"GB2-08":{"attempts":1,"playable":82.98469083668653,"score":82.98469083668653}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:26Z","losses":1337,"max_score":82.98469083668653,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Grok 4.7","model_slug":"x-ai-grok-4-7","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"xAI","provider_key":"x-ai","rank":111,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:28Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1569.873856212642,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.44233316232824,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1600},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db","capped_draws":365,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"codegen_evaluated_cells":8,"conditional_success_score":48.29706343241805,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1206,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-8","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":41.41585669789332,"score":41.41585669789332},"GB2-02":{"attempts":1,"playable":42.1702722263371,"score":42.1702722263371},"GB2-03":{"attempts":1,"playable":31.204237061055146,"score":31.204237061055146},"GB2-04":{"attempts":1,"playable":42.516760894618045,"score":42.516760894618045},"GB2-05":{"attempts":1,"playable":48.18635741237079,"score":48.18635741237079},"GB2-06":{"attempts":1,"playable":79.71694138066104,"score":79.71694138066104},"GB2-07":{"attempts":1,"playable":68.14286552155062,"score":68.14286552155062},"GB2-08":{"attempts":1,"playable":33.02321626485831,"score":33.02321626485831}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:18Z","losses":1592,"max_score":79.71694138066104,"measured_at":null,"min_score":31.204237061055146,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Claude Opus 4.8","model_slug":"claude-opus-4-8","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":112,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:49Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1465.3759449354445,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.29706343241805,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1289},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3","capped_draws":214,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"codegen_evaluated_cells":8,"conditional_success_score":48.27784746950317,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1041,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4-mini","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":69.74557538933259,"score":69.74557538933259},"GB2-02":{"attempts":1,"playable":41.53531315649431,"score":41.53531315649431},"GB2-03":{"attempts":1,"playable":45.78498915227661,"score":45.78498915227661},"GB2-04":{"attempts":1,"playable":44.25089660655846,"score":44.25089660655846},"GB2-05":{"attempts":1,"playable":47.994407605115654,"score":47.994407605115654},"GB2-06":{"attempts":1,"playable":47.69757081673043,"score":47.69757081673043},"GB2-07":{"attempts":1,"playable":45.9444532821712,"score":45.9444532821712},"GB2-08":{"attempts":1,"playable":43.26957374734612,"score":43.26957374734612}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:56:44Z","losses":1699,"max_score":69.74557538933259,"measured_at":null,"min_score":41.53531315649431,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":113,"rank_movement":-3,"rank_movement_baseline_at":"2026-10-24T19:19:07Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1425.4352328937748,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.27784746950317,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1348},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-3-flash:22cd36959459fbdd","capped_draws":340,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847899999999997},"codegen_evaluated_cells":8,"conditional_success_score":48.185978763244805,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1008,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.3-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":37.2655929750953,"score":37.2655929750953},"GB2-02":{"attempts":1,"playable":44.91694128410355,"score":44.91694128410355},"GB2-03":{"attempts":1,"playable":56.39851082933254,"score":56.39851082933254},"GB2-04":{"attempts":1,"playable":64.57736155284643,"score":64.57736155284643},"GB2-05":{"attempts":1,"playable":37.59863568665383,"score":37.59863568665383},"GB2-06":{"attempts":1,"playable":43.85144732560902,"score":43.85144732560902},"GB2-07":{"attempts":1,"playable":71.8205011140149,"score":71.8205011140149},"GB2-08":{"attempts":1,"playable":29.05883933830283,"score":29.05883933830283}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:37:36Z","losses":1714,"max_score":71.8205011140149,"measured_at":null,"min_score":29.05883933830283,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":114,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:28Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1421.1877336778982,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":48.185978763244805,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1365},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9","capped_draws":326,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.144235,"mean":0.12174125,"median":0.121475,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.97393},"codegen_evaluated_cells":8,"conditional_success_score":47.88772284374605,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1146,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"omitted","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":44.56745366819474,"score":44.56745366819474},"GB2-02":{"attempts":1,"playable":44.38935843142217,"score":44.38935843142217},"GB2-03":{"attempts":1,"playable":42.34865602776778,"score":42.34865602776778},"GB2-04":{"attempts":1,"playable":48.62325324165005,"score":48.62325324165005},"GB2-05":{"attempts":1,"playable":47.03425763251552,"score":47.03425763251552},"GB2-06":{"attempts":1,"playable":45.63960534898207,"score":45.63960534898207},"GB2-07":{"attempts":1,"playable":32.34779179198245,"score":32.34779179198245},"GB2-08":{"attempts":1,"playable":78.1514066074536,"score":78.1514066074536}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:32:28Z","losses":1654,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":115,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:19:03Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1437.551203918167,"reasoning_bracket":"baseline","reasoning_level":"Thinking field omitted","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"omitted","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Thinking field omitted","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Thinking field omitted","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"omitted","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":47.88772284374605,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1288},{"admitted_plugins":26,"attempted_matches":13224,"canonical_public_row_identity":"publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f","capped_draws":599,"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":39,"run_count":30,"total":0.0},"codegen_evaluated_cells":30,"conditional_success_score":51.508250593963965,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":2819,"eligibility_flag":true,"entry_count":26,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/ox-alpha","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":21,"first_pass_rate":0.7241379310344828,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_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":62.32038654873581,"score":41.54692436582388},"GB2-02":{"attempts":3,"playable":50.16934662495466,"score":50.16934662495466},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":57.69067869722377,"score":44.870527875618485},"GB2-04":{"attempts":3,"playable":57.29271491847438,"score":57.29271491847438},"GB2-05":{"attempts":3,"playable":49.32461277255595,"score":49.32461277255595},"GB2-06":{"attempts":2,"playable":28.098379301525302,"score":28.098379301525302},"GB2-07":{"attempts":3,"playable":45.60526028368986,"score":45.60526028368986},"GB2-08":{"attempts":3,"playable":61.56462560455196,"score":61.56462560455196}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:42Z","losses":5143,"max_score":61.56462560455196,"measured_at":null,"min_score":28.098379301525302,"model_code_failure_rate":0.10344827586206896,"model_code_failures":3,"model_display_name":"Ox Alpha","model_slug":"stealth-ox-alpha","performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"plugin_success_rate":0.896551724137931,"provider":"Other","provider_key":"other","rank":116,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:13Z","ranking_status":"ranked","rated_matches":13220,"rating_method":"bradley_terry_newton","raw_elo":1461.5195386181445,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/ox-alpha","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":5,"repaired_rate":0.1724137931034483,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":47.30904896839931,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":2,"wins":5258},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:d3192451477fbf98","capped_draws":386,"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":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.98845232184},"codegen_evaluated_cells":8,"conditional_success_score":46.91108795092154,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":970,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro-0813","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.52882128415899,"score":51.52882128415899},"GB2-02":{"attempts":1,"playable":40.89995054217238,"score":40.89995054217238},"GB2-03":{"attempts":1,"playable":43.08026465020685,"score":43.08026465020685},"GB2-04":{"attempts":1,"playable":33.80482228941814,"score":33.80482228941814},"GB2-05":{"attempts":1,"playable":44.53500355323505,"score":44.53500355323505},"GB2-06":{"attempts":1,"playable":39.02304595041499,"score":39.02304595041499},"GB2-07":{"attempts":1,"playable":74.0840341297721,"score":74.0840341297721},"GB2-08":{"attempts":1,"playable":48.33276120799385,"score":48.33276120799385}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:33:14Z","losses":1774,"max_score":74.0840341297721,"measured_at":null,"min_score":33.80482228941814,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4 Pro 0813","model_slug":"deepseek-deepseek-v4-pro-0813","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":117,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T14:43:56Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1421.9381393423016,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":46.91108795092154,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1344},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9","capped_draws":179,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001},"codegen_evaluated_cells":8,"conditional_success_score":46.83621400235444,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":999,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":80.65434866807438,"score":80.65434866807438},"GB2-02":{"attempts":1,"playable":39.41590335477645,"score":39.41590335477645},"GB2-03":{"attempts":1,"playable":32.49383966343138,"score":32.49383966343138},"GB2-04":{"attempts":1,"playable":39.44947595905667,"score":39.44947595905667},"GB2-05":{"attempts":1,"playable":61.9150209611777,"score":61.9150209611777},"GB2-06":{"attempts":1,"playable":63.02650853175248,"score":63.02650853175248},"GB2-07":{"attempts":1,"playable":28.874188292553626,"score":28.874188292553626},"GB2-08":{"attempts":1,"playable":28.86042658801284,"score":28.86042658801284}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:38Z","losses":1768,"max_score":80.65434866807438,"measured_at":null,"min_score":28.86042658801284,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5.4","model_slug":"gpt-5-4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":118,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:37:08Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1427.6211498909458,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":46.83621400235444,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1321},{"admitted_plugins":6,"attempted_matches":3114,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-27b:739c4d774075dc83","capped_draws":73,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999},"codegen_evaluated_cells":8,"conditional_success_score":60.60704272237828,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":239,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-27b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03"],"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":74.71142886560035,"score":74.71142886560035},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":71.07420340446123,"score":71.07420340446123},"GB2-05":{"attempts":1,"playable":59.262151563671,"score":59.262151563671},"GB2-06":{"attempts":1,"playable":29.033746354786555,"score":29.033746354786555},"GB2-07":{"attempts":1,"playable":78.23975127005579,"score":78.23975127005579},"GB2-08":{"attempts":1,"playable":51.320974875694716,"score":51.320974875694716}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T01:36:54Z","losses":1174,"max_score":78.23975127005579,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Qwen3.8 27B","model_slug":"qwen-qwen3-8-27b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Alibaba","provider_key":"qwen","rank":119,"rank_movement":3,"rank_movement_baseline_at":"2026-10-24T19:19:07Z","ranking_status":"ranked","rated_matches":3114,"rating_method":"bradley_terry_newton","raw_elo":1550.5043208036213,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":45.45528204178371,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1701},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-4-6:aedb1b245d3cd53f","capped_draws":276,"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":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483},"codegen_evaluated_cells":8,"conditional_success_score":45.352263760241286,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1370,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-4.6","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":66.76664981444975,"score":66.76664981444975},"GB2-02":{"attempts":1,"playable":44.07266414671792,"score":44.07266414671792},"GB2-03":{"attempts":1,"playable":44.74708420911853,"score":44.74708420911853},"GB2-04":{"attempts":1,"playable":42.9250607025321,"score":42.9250607025321},"GB2-05":{"attempts":1,"playable":51.25358631759123,"score":51.25358631759123},"GB2-06":{"attempts":1,"playable":13.704028343787897,"score":13.704028343787897},"GB2-07":{"attempts":1,"playable":57.64736615822385,"score":57.64736615822385},"GB2-08":{"attempts":1,"playable":41.70167038950902,"score":41.70167038950902}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:38Z","losses":1636,"max_score":66.76664981444975,"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":1.0,"provider":"xAI","provider_key":"x-ai","rank":120,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:20:39Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1375.8279834892253,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.6","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":45.352263760241286,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1082},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-luna:5a6b5b178d35010c","capped_draws":510,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.007622525,"mean":0.0031813812500000004,"median":0.0022472374999999998,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":0.02545105},"codegen_evaluated_cells":8,"conditional_success_score":45.13147374009205,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1313,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-luna","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":48.29854369491118,"score":48.29854369491118},"GB2-02":{"attempts":1,"playable":44.17824088266641,"score":44.17824088266641},"GB2-03":{"attempts":1,"playable":46.09577902379266,"score":46.09577902379266},"GB2-04":{"attempts":1,"playable":44.454714144494474,"score":44.454714144494474},"GB2-05":{"attempts":1,"playable":36.0556041211425,"score":36.0556041211425},"GB2-06":{"attempts":1,"playable":72.18374494883687,"score":72.18374494883687},"GB2-07":{"attempts":1,"playable":33.49880171248045,"score":33.49880171248045},"GB2-08":{"attempts":1,"playable":36.28636139241186,"score":36.28636139241186}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:58:40Z","losses":1691,"max_score":72.18374494883687,"measured_at":null,"min_score":33.49880171248045,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":121,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T16:58:40Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1404.5123553306462,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-luna","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":45.13147374009205,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1084},{"admitted_plugins":7,"attempted_matches":3586,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k3:88ac46ad773e56f5","capped_draws":192,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.46446825,"median":0.4896297,"min":0.2393742,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":3.715746},"codegen_evaluated_cells":8,"conditional_success_score":51.56279070927451,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":806,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":6.581556640181834,"score":6.581556640181834},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":77.81741844741386,"score":77.81741844741386},"GB2-04":{"attempts":1,"playable":52.77178646458028,"score":52.77178646458028},"GB2-05":{"attempts":1,"playable":62.29322062554687,"score":62.29322062554687},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.6755483450511,"score":93.6755483450511},"GB2-08":{"attempts":1,"playable":24.889465146219823,"score":24.889465146219823}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:58:46Z","losses":1387,"max_score":93.6755483450511,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Kimi K3","model_slug":"moonshotai-kimi-k3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Moonshot","provider_key":"moonshotai","rank":122,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T16:58:46Z","ranking_status":"ranked","rated_matches":3586,"rating_method":"bradley_terry_newton","raw_elo":1514.6344365132948,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":45.117441870615195,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1393},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-max-0902:5961da4fe746e1db","capped_draws":284,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.30508599999999997,"mean":0.10921525,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":10,"run_count":8,"total":0.873722},"codegen_evaluated_cells":8,"conditional_success_score":45.01534092627758,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1039,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-max-0902","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":26.31601551085625,"score":26.31601551085625},"GB2-02":{"attempts":1,"playable":48.916320467449594,"score":48.916320467449594},"GB2-03":{"attempts":1,"playable":57.000469978231585,"score":57.000469978231585},"GB2-04":{"attempts":1,"playable":45.88023191610302,"score":45.88023191610302},"GB2-05":{"attempts":1,"playable":43.76526237793952,"score":43.76526237793952},"GB2-06":{"attempts":1,"playable":59.500477636639005,"score":59.500477636639005},"GB2-07":{"attempts":1,"playable":36.55188391526639,"score":36.55188391526639},"GB2-08":{"attempts":1,"playable":42.192065607735294,"score":42.192065607735294}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:58Z","losses":1839,"max_score":59.500477636639005,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":123,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:02:19Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1392.4443338118094,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":45.01534092627758,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1210},{"admitted_plugins":16,"attempted_matches":8176,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b","capped_draws":454,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.35917138039999996},"codegen_evaluated_cells":16,"conditional_success_score":44.78800437872484,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":2119,"eligibility_flag":true,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.2","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":9,"first_pass_rate":0.5625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":27.607989554128842,"score":27.607989554128842},"GB2-02":{"attempts":2,"playable":40.263533261686156,"score":40.263533261686156},"GB2-03":{"attempts":2,"playable":42.52806568087197,"score":42.52806568087197},"GB2-04":{"attempts":2,"playable":43.230992907330446,"score":43.230992907330446},"GB2-05":{"attempts":2,"playable":43.41380976455447,"score":43.41380976455447},"GB2-06":{"attempts":2,"playable":54.37859003141238,"score":54.37859003141238},"GB2-07":{"attempts":2,"playable":50.050619914967726,"score":50.050619914967726},"GB2-08":{"attempts":2,"playable":56.83043391484678,"score":56.83043391484678}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:18Z","losses":3634,"max_score":56.83043391484678,"measured_at":null,"min_score":27.607989554128842,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":124,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:18:47Z","ranking_status":"ranked","rated_matches":8176,"rating_method":"bradley_terry_newton","raw_elo":1410.9102459399892,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled (historical request variant 1)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-1","reasoning_bucket_label":"Reasoning disabled (historical request variant 1)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline-variant-1"},"reasoning_setting":"historical-provider-setting-baseline-variant-1","repaired_admitted":7,"repaired_rate":0.4375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.78800437872484,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2423},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-2:20c65e2b7513d4b4","capped_draws":499,"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":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303000003},"codegen_evaluated_cells":8,"conditional_success_score":44.45230475823284,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1128,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.2","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":54.06745685878506,"score":54.06745685878506},"GB2-02":{"attempts":1,"playable":62.12902691074697,"score":62.12902691074697},"GB2-03":{"attempts":1,"playable":37.293391875996114,"score":37.293391875996114},"GB2-04":{"attempts":1,"playable":58.60166410752101,"score":58.60166410752101},"GB2-05":{"attempts":1,"playable":58.8824232837549,"score":58.8824232837549},"GB2-06":{"attempts":1,"playable":42.36140665519106,"score":42.36140665519106},"GB2-07":{"attempts":1,"playable":10.34922351327472,"score":10.34922351327472},"GB2-08":{"attempts":1,"playable":31.93384486059297,"score":31.93384486059297}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:00Z","losses":1818,"max_score":62.12902691074697,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":125,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:05:44Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1353.0840337181553,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.45230475823284,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1142},{"admitted_plugins":15,"attempted_matches":7682,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899","capped_draws":612,"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.30059250000000004,"mean":0.256004375,"median":0.25514000000000003,"min":0.2090225,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":17},"run_count":16,"token_priced_attempt_count":17,"total":4.096070000000001},"codegen_evaluated_cells":16,"conditional_success_score":47.49754845060036,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":2111,"eligibility_flag":true,"entry_count":15,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"legacy_shared_thinking_budget","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"budget","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":14,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":32.2925007643594,"score":32.2925007643594},"GB2-02":{"attempts":2,"playable":43.75571446967459,"score":43.75571446967459},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":51.541548933129086,"score":25.770774466564543},"GB2-04":{"attempts":2,"playable":39.65393048330402,"score":39.65393048330402},"GB2-05":{"attempts":2,"playable":43.57277847647596,"score":43.57277847647596},"GB2-06":{"attempts":2,"playable":46.505658891339166,"score":46.505658891339166},"GB2-07":{"attempts":2,"playable":56.451883039828196,"score":56.451883039828196},"GB2-08":{"attempts":2,"playable":66.20637254669249,"score":66.20637254669249}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:14Z","losses":3171,"max_score":66.20637254669249,"measured_at":null,"min_score":25.770774466564543,"model_code_failure_rate":0.0625,"model_code_failures":1,"model_display_name":"Claude Opus 4.5","model_slug":"claude-opus-4-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.9375,"provider":"Anthropic","provider_key":"anthropic","rank":126,"rank_movement":4,"rank_movement_baseline_at":"2026-10-24T19:24:14Z","ranking_status":"ranked","rated_matches":7682,"rating_method":"bradley_terry_newton","raw_elo":1430.864618779566,"reasoning_bracket":null,"reasoning_level":"Historical thinking-budget setting","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"mixed","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"budget","requested_effort":"historical-thinking-budget-setting","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Historical thinking-budget setting","reasoning_bracket":"mixed","reasoning_bucket":"historical-thinking-budget-setting","reasoning_bucket_label":"Historical thinking-budget setting","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"budget","requested_reasoning_effort":"historical-thinking-budget-setting"},"reasoning_setting":"historical-thinking-budget-setting","repaired_admitted":1,"repaired_rate":0.0625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.276201642279794,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2400},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:tencent-hy4-preview:b8e7119f660161ad","capped_draws":262,"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":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125},"codegen_evaluated_cells":8,"conditional_success_score":44.23087546055762,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1094,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy4-preview","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":46.53271418856003,"score":46.53271418856003},"GB2-02":{"attempts":1,"playable":43.227623284677975,"score":43.227623284677975},"GB2-03":{"attempts":1,"playable":63.54324414092344,"score":63.54324414092344},"GB2-04":{"attempts":1,"playable":41.597497623253474,"score":41.597497623253474},"GB2-05":{"attempts":1,"playable":50.48751301185782,"score":50.48751301185782},"GB2-06":{"attempts":1,"playable":39.329186363594,"score":39.329186363594},"GB2-07":{"attempts":1,"playable":37.69077726852129,"score":37.69077726852129},"GB2-08":{"attempts":1,"playable":31.43844780307297,"score":31.43844780307297}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:39Z","losses":1842,"max_score":63.54324414092344,"measured_at":null,"min_score":31.43844780307297,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Hy4 Preview","model_slug":"tencent-hy4-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Tencent","provider_key":"tencent","rank":127,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:07:54Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1375.1086792714714,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.23087546055762,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1152},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-flash:14b865d3f352c468","capped_draws":224,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01663094,"mean":0.00499588742,"median":0.0034890575,"min":0.00258188,"recorded_attempt_count":12,"run_count":8,"total":0.03996709936},"codegen_evaluated_cells":8,"conditional_success_score":44.04879907481547,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1083,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":33.19839222532428,"score":33.19839222532428},"GB2-02":{"attempts":1,"playable":40.89995054217238,"score":40.89995054217238},"GB2-03":{"attempts":1,"playable":46.71655058071938,"score":46.71655058071938},"GB2-04":{"attempts":1,"playable":40.16595143167495,"score":40.16595143167495},"GB2-05":{"attempts":1,"playable":50.6790792678975,"score":50.6790792678975},"GB2-06":{"attempts":1,"playable":48.476269808324766,"score":48.476269808324766},"GB2-07":{"attempts":1,"playable":36.93187650272706,"score":36.93187650272706},"GB2-08":{"attempts":1,"playable":55.322322239683466,"score":55.322322239683466}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:48Z","losses":1851,"max_score":55.322322239683466,"measured_at":null,"min_score":33.19839222532428,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4 Flash","model_slug":"deepseek-deepseek-v4-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":128,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:06:59Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1385.9028457826525,"reasoning_bracket":"balanced","reasoning_level":"High (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High (historical request variant 1)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-1","reasoning_bucket_label":"High (historical request variant 1)","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced-variant-1"},"reasoning_setting":"historical-provider-setting-balanced-variant-1","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.04879907481547,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1154},{"admitted_plugins":8,"attempted_matches":4091,"canonical_public_row_identity":"publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d","capped_draws":363,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5249900000000001},"codegen_evaluated_cells":8,"conditional_success_score":44.0220882198153,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1159,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":46.04171899042915,"score":46.04171899042915},"GB2-02":{"attempts":1,"playable":43.65023818652617,"score":43.65023818652617},"GB2-03":{"attempts":1,"playable":42.24402295900123,"score":42.24402295900123},"GB2-04":{"attempts":1,"playable":45.16773876484072,"score":45.16773876484072},"GB2-05":{"attempts":1,"playable":42.99521653630814,"score":42.99521653630814},"GB2-06":{"attempts":1,"playable":39.63478336827751,"score":39.63478336827751},"GB2-07":{"attempts":1,"playable":50.74131656363051,"score":50.74131656363051},"GB2-08":{"attempts":1,"playable":41.70167038950902,"score":41.70167038950902}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:56:59Z","losses":1813,"max_score":50.74131656363051,"measured_at":null,"min_score":39.63478336827751,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":129,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:20:14Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1377.1073240357443,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.0220882198153,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1116},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa","capped_draws":230,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14831665,"mean":0.06589574925,"median":0.044104765,"min":0.0155414,"recorded_attempt_count":16,"run_count":8,"total":0.527165994},"codegen_evaluated_cells":8,"conditional_success_score":43.9582169603899,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1053,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.2","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":32.203937526457665,"score":32.203937526457665},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":33.458366110929646,"score":33.458366110929646},"GB2-04":{"attempts":1,"playable":40.16595143167495,"score":40.16595143167495},"GB2-05":{"attempts":1,"playable":55.266448071150265,"score":55.266448071150265},"GB2-06":{"attempts":1,"playable":71.63743419358703,"score":71.63743419358703},"GB2-07":{"attempts":1,"playable":51.47406250609785,"score":51.47406250609785},"GB2-08":{"attempts":1,"playable":23.598060935444277,"score":23.598060935444277}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T15:33:32Z","losses":1856,"max_score":71.63743419358703,"measured_at":null,"min_score":23.598060935444277,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":130,"rank_movement":-4,"rank_movement_baseline_at":"2026-10-24T19:03:28Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1406.351472686366,"reasoning_bracket":"balanced","reasoning_level":"Medium (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium (historical request variant 2)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-2","reasoning_bucket_label":"Medium (historical request variant 2)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced-variant-2"},"reasoning_setting":"historical-provider-setting-balanced-variant-2","repaired_admitted":8,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.9582169603899,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1179},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-6-luna:3dfecd4fa4d78509","capped_draws":417,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688899999999998},"codegen_evaluated_cells":8,"conditional_success_score":43.94225192948782,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1201,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-6-luna","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":39.04623118521132,"score":39.04623118521132},"GB2-02":{"attempts":1,"playable":44.91694128410355,"score":44.91694128410355},"GB2-03":{"attempts":1,"playable":51.541548933129086,"score":51.541548933129086},"GB2-04":{"attempts":1,"playable":50.44715644017009,"score":50.44715644017009},"GB2-05":{"attempts":1,"playable":50.870613777803655,"score":50.870613777803655},"GB2-06":{"attempts":1,"playable":34.887629105231156,"score":34.887629105231156},"GB2-07":{"attempts":1,"playable":53.84597448275231,"score":53.84597448275231},"GB2-08":{"attempts":1,"playable":25.981920227501416,"score":25.981920227501416}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:58Z","losses":1795,"max_score":53.84597448275231,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":131,"rank_movement":-3,"rank_movement_baseline_at":"2026-10-24T19:21:15Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1372.0739629462405,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.94225192948782,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1092},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-2-4t-a95b:78fb6a9e00356b09","capped_draws":402,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"codegen_evaluated_cells":8,"conditional_success_score":43.827347139161155,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1225,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-2.4t-a95b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":53.189341463485576,"score":53.189341463485576},"GB2-02":{"attempts":1,"playable":43.65023818652617,"score":43.65023818652617},"GB2-03":{"attempts":1,"playable":43.39336960174158,"score":43.39336960174158},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":50.48751301185782,"score":50.48751301185782},"GB2-06":{"attempts":1,"playable":46.426033908503975,"score":46.426033908503975},"GB2-07":{"attempts":1,"playable":32.155628167045116,"score":32.155628167045116},"GB2-08":{"attempts":1,"playable":42.58410870481845,"score":42.58410870481845}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:55Z","losses":1791,"max_score":53.189341463485576,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":132,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:03:20Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1376.9795526064663,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.827347139161155,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1072},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec","capped_draws":289,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337},"codegen_evaluated_cells":8,"conditional_success_score":43.7766304523458,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1066,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":49.474246735581524,"score":49.474246735581524},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"playable":56.29807121307564,"score":56.29807121307564},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":1,"playable":23.342125558174647,"score":23.342125558174647},"GB2-06":{"attempts":1,"playable":48.379085648735845,"score":48.379085648735845},"GB2-07":{"attempts":1,"playable":35.40972666449984,"score":35.40972666449984},"GB2-08":{"attempts":1,"playable":50.55237418486409,"score":50.55237418486409}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:41Z","losses":1878,"max_score":56.29807121307564,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":133,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:14:37Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1364.674783414754,"reasoning_bracket":"baseline","reasoning_level":"Thinking disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Thinking disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Thinking disabled","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.7766304523458,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1144},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a","capped_draws":325,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.011164349999999998,"mean":0.00631805625,"median":0.005847,"min":0.00434295,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.05054445},"codegen_evaluated_cells":8,"conditional_success_score":43.030258555037776,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1222,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-luna","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":46.53271418856003,"score":46.53271418856003},"GB2-02":{"attempts":1,"playable":43.43895423021337,"score":43.43895423021337},"GB2-03":{"attempts":1,"playable":44.33108968183731,"score":44.33108968183731},"GB2-04":{"attempts":1,"playable":47.7098452152136,"score":47.7098452152136},"GB2-05":{"attempts":1,"playable":44.53500355323505,"score":44.53500355323505},"GB2-06":{"attempts":1,"playable":54.80342947849586,"score":54.80342947849586},"GB2-07":{"attempts":1,"playable":28.680284444924364,"score":28.680284444924364},"GB2-08":{"attempts":1,"playable":34.210747647822636,"score":34.210747647822636}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:22Z","losses":1827,"max_score":54.80342947849586,"measured_at":null,"min_score":28.680284444924364,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":134,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:07:02Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1368.4349250375863,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.030258555037776,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1039},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:bytedance-seed-seed-2-0-code:c69120230888411c","capped_draws":334,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996},"codegen_evaluated_cells":8,"conditional_success_score":43.02828227925883,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1126,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"bytedance-seed/seed-2.0-code","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":41.31722481191092,"score":41.31722481191092},"GB2-02":{"attempts":1,"playable":41.00587206875293,"score":41.00587206875293},"GB2-03":{"attempts":1,"playable":41.61560876606564,"score":41.61560876606564},"GB2-04":{"attempts":1,"playable":38.527623776115156,"score":38.527623776115156},"GB2-05":{"attempts":1,"playable":49.912626901458104,"score":49.912626901458104},"GB2-06":{"attempts":1,"playable":20.304515731648973,"score":20.304515731648973},"GB2-07":{"attempts":1,"playable":45.0151740935915,"score":45.0151740935915},"GB2-08":{"attempts":1,"playable":66.52761208452745,"score":66.52761208452745}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:36Z","losses":1855,"max_score":66.52761208452745,"measured_at":null,"min_score":20.304515731648973,"model_code_failure_rate":0.0,"model_code_failures":0,"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":1.0,"provider":"ByteDance","provider_key":"bytedance-seed","rank":135,"rank_movement":5,"rank_movement_baseline_at":"2026-10-24T19:24:34Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1367.5962582649681,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":43.02828227925883,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1107},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea","capped_draws":115,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.190125,"mean":0.15785312499999998,"median":0.15388000000000002,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.262825},"codegen_evaluated_cells":8,"conditional_success_score":48.893053561878425,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":804,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-opus-4-8","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"omitted","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":56.40573941869387,"score":56.40573941869387},"GB2-02":{"attempts":1,"playable":39.41590335477645,"score":39.41590335477645},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.2104298005408,"score":42.2104298005408},"GB2-05":{"attempts":1,"playable":22.573598674551278,"score":22.573598674551278},"GB2-06":{"attempts":1,"playable":48.864576287789,"score":48.864576287789},"GB2-07":{"attempts":1,"playable":52.205426166317395,"score":52.205426166317395},"GB2-08":{"attempts":1,"playable":80.57570123048013,"score":80.57570123048013}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:18Z","losses":1506,"max_score":80.57570123048013,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Claude Opus 4.8","model_slug":"claude-opus-4-8","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Anthropic","provider_key":"anthropic","rank":136,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:12:32Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1453.4029116871022,"reasoning_bracket":"baseline","reasoning_level":"Thinking field omitted","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"omitted","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Thinking field omitted","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Thinking field omitted","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"omitted","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.78142186664362,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1284},{"admitted_plugins":7,"attempted_matches":3608,"canonical_public_row_identity":"publication-row.v1:mixed:minimax-minimax-m3-1-flash:e33f5737bf48ec2c","capped_draws":92,"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":48.767646435695134,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":500,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3.1-flash:free","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":68.11346235814054,"score":68.11346235814054},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.849547148522728,"score":31.849547148522728},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":50.48751301185782,"score":50.48751301185782},"GB2-06":{"attempts":1,"playable":51.660210126745696,"score":51.660210126745696},"GB2-07":{"attempts":1,"playable":71.47140899698569,"score":71.47140899698569},"GB2-08":{"attempts":1,"playable":29.05883933830283,"score":29.05883933830283}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:17Z","losses":1679,"max_score":71.47140899698569,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Minimax M3.1 Flash","model_slug":"minimax-minimax-m3-1-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"MiniMax","provider_key":"minimax","rank":137,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:17Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1442.0986488710012,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"unknown_legacy","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.67169063123324,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1429},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-4-1:731bd482a4919a05","capped_draws":266,"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":42.397549164017946,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1090,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-4.1","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"omitted","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"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":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:26Z","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":1.0,"provider":"OpenAI","provider_key":"openai","rank":138,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:15Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1347.7574508236921,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"omitted","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"omitted","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.397549164017946,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1083},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:o3:a01262f48556a975","capped_draws":346,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.08754999999999999,"mean":0.04313775,"median":0.033532,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.3451019999999999},"codegen_evaluated_cells":8,"conditional_success_score":42.349686127627386,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1107,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"o3","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":37.859469048836694,"score":37.859469048836694},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"playable":41.92994773322229,"score":41.92994773322229},"GB2-04":{"attempts":1,"playable":44.65848911173256,"score":44.65848911173256},"GB2-05":{"attempts":1,"playable":51.44502373076455,"score":51.44502373076455},"GB2-06":{"attempts":1,"playable":47.89251013058481,"score":47.89251013058481},"GB2-07":{"attempts":1,"playable":39.204261853711586,"score":39.204261853711586},"GB2-08":{"attempts":1,"playable":33.32018896021172,"score":33.32018896021172}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:28:40Z","losses":1909,"max_score":51.44502373076455,"measured_at":null,"min_score":33.32018896021172,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"o3","model_slug":"o3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":139,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:28:40Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1364.8773173805134,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.349686127627386,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1072},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gemini-3-1-pro-preview:296f8f275ba5a6e4","capped_draws":297,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.10957599999999999,"mean":0.08025825,"median":0.080065,"min":0.052756,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.642066},"codegen_evaluated_cells":8,"conditional_success_score":42.25377008914947,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1065,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-3.1-pro-preview","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":35.085178473954535,"score":35.085178473954535},"GB2-02":{"attempts":1,"playable":44.81144895648299,"score":44.81144895648299},"GB2-03":{"attempts":1,"playable":67.04845201670798,"score":67.04845201670798},"GB2-04":{"attempts":1,"playable":46.18542092099077,"score":46.18542092099077},"GB2-05":{"attempts":1,"playable":17.58313650452452,"score":17.58313650452452},"GB2-06":{"attempts":1,"playable":29.466010577145134,"score":29.466010577145134},"GB2-07":{"attempts":1,"playable":71.47140899698569,"score":71.47140899698569},"GB2-08":{"attempts":1,"playable":26.379104266404084,"score":26.379104266404084}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:43Z","losses":1924,"max_score":71.47140899698569,"measured_at":null,"min_score":17.58313650452452,"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":1.0,"provider":"Google","provider_key":"google","rank":140,"rank_movement":-6,"rank_movement_baseline_at":"2026-10-24T19:24:33Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1342.227526530076,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"google","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":42.25377008914947,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1099},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea","capped_draws":171,"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":0.03564825,"mean":0.0239263125,"median":0.02294625,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.1914105},"codegen_evaluated_cells":8,"conditional_success_score":41.98877756601745,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":940,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.2","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":37.2655929750953,"score":37.2655929750953},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-03":{"attempts":1,"playable":46.30282272199312,"score":46.30282272199312},"GB2-04":{"attempts":1,"playable":47.81138183054571,"score":47.81138183054571},"GB2-05":{"attempts":1,"playable":51.63642816425957,"score":51.63642816425957},"GB2-06":{"attempts":1,"playable":19.740941347498214,"score":19.740941347498214},"GB2-07":{"attempts":1,"playable":34.646462034947504,"score":34.646462034947504},"GB2-08":{"attempts":1,"playable":56.54792702265282,"score":56.54792702265282}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:31Z","losses":1999,"max_score":56.54792702265282,"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":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Meta","provider_key":"meta","rank":141,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:27Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1343.9608701636523,"reasoning_bracket":"baseline","reasoning_level":"Minimal","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Minimal","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":41.98877756601745,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1149},{"admitted_plugins":6,"attempted_matches":3088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5:707323710fb901e4","capped_draws":180,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.15380375000000002,"mean":0.09741312500000002,"median":0.090410625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12},"run_count":8,"token_priced_attempt_count":12,"total":0.779305},"codegen_evaluated_cells":8,"conditional_success_score":41.51936122201238,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":598,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5","reasoning_catalog_sha256":"36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":4,"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":1,"playable":70.60805904529305,"score":70.60805904529305},"GB2-02":{"attempts":1,"playable":38.67309283043393,"score":38.67309283043393},"GB2-03":{"attempts":1,"playable":15.863564596042682,"score":15.863564596042682},"GB2-05":{"attempts":1,"playable":47.80243060986596,"score":47.80243060986596},"GB2-07":{"attempts":1,"playable":41.463765182392905,"score":41.463765182392905},"GB2-08":{"attempts":1,"playable":34.70525506804573,"score":34.70525506804573}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","losses":1566,"max_score":70.60805904529305,"measured_at":null,"min_score":15.863564596042682,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-5","model_slug":"gpt-5","performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":142,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:00:30Z","ranking_status":"ranked","rated_matches":3088,"rating_method":"bradley_terry_newton","raw_elo":1354.2023278006745,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.3333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":41.51936122201238,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":924},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-1-3:22ddc49b675eb171","capped_draws":347,"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":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975000000002},"codegen_evaluated_cells":8,"conditional_success_score":41.453142805813016,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1088,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-1.3","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":26.816405095011675,"score":26.816405095011675},"GB2-02":{"attempts":1,"playable":47.33983603398062,"score":47.33983603398062},"GB2-03":{"attempts":1,"playable":55.09029052603637,"score":55.09029052603637},"GB2-04":{"attempts":1,"playable":43.12914940293223,"score":43.12914940293223},"GB2-05":{"attempts":1,"playable":41.0689414396043,"score":41.0689414396043},"GB2-06":{"attempts":1,"playable":41.45718741890594,"score":41.45718741890594},"GB2-07":{"attempts":1,"playable":38.069687009036706,"score":38.069687009036706},"GB2-08":{"attempts":1,"playable":38.653645520996264,"score":38.653645520996264}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:20Z","losses":1960,"max_score":55.09029052603637,"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":1.0,"provider":"Meta","provider_key":"meta","rank":143,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:37Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1344.9227912315919,"reasoning_bracket":"baseline","reasoning_level":"Minimal","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.3","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Minimal","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":41.453142805813016,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1040},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-sonnet-5-5:d7321f408b9bf12e","capped_draws":114,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.048946,"mean":0.040937249999999994,"median":0.039029,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.327498},"codegen_evaluated_cells":8,"conditional_success_score":41.268127943425036,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":865,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-sonnet-5-5","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.52882128415899,"score":51.52882128415899},"GB2-02":{"attempts":1,"playable":46.39253976872338,"score":46.39253976872338},"GB2-03":{"attempts":1,"playable":48.77796183035881,"score":48.77796183035881},"GB2-04":{"attempts":1,"playable":45.06591040934613,"score":45.06591040934613},"GB2-05":{"attempts":1,"playable":14.322008174638762,"score":14.322008174638762},"GB2-06":{"attempts":1,"playable":17.929981650115,"score":17.929981650115},"GB2-07":{"attempts":1,"playable":46.13004472242078,"score":46.13004472242078},"GB2-08":{"attempts":1,"playable":59.997755707638426,"score":59.997755707638426}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:58Z","losses":2067,"max_score":59.997755707638426,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":144,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:55:01Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1315.6789764700386,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":41.268127943425036,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1156},{"admitted_plugins":28,"attempted_matches":14196,"canonical_public_row_identity":"publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2","capped_draws":903,"codegen_cost_usd":{"admitted_cell_count":28,"cell_count":8,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":42,"run_count":30,"total":0.0},"codegen_evaluated_cells":30,"conditional_success_score":43.11119427501237,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":4140,"eligibility_flag":true,"entry_count":28,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/ox-alpha","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":3,"playable":42.53242652243116,"score":42.53242652243116},"GB2-02":{"attempts":3,"playable":43.05071298496239,"score":43.05071298496239},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":45.24418017041154,"score":40.217049040365815},"GB2-04":{"attempts":3,"playable":49.55647106555795,"score":49.55647106555795},"GB2-05":{"attempts":3,"playable":51.6895192937611,"score":51.6895192937611},"GB2-06":{"attempts":3,"playable":42.80953412657357,"score":42.80953412657357},"GB2-07":{"attempts":3,"playable":39.759286886859144,"score":39.759286886859144},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":30.247423149542144,"score":20.16494876636143}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:13Z","losses":6270,"max_score":51.6895192937611,"measured_at":null,"min_score":20.16494876636143,"model_code_failure_rate":0.06666666666666667,"model_code_failures":2,"model_display_name":"Ox Alpha","model_slug":"stealth-ox-alpha","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.9333333333333333,"provider":"Other","provider_key":"other","rank":145,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:16:43Z","ranking_status":"ranked","rated_matches":14196,"rating_method":"bradley_terry_newton","raw_elo":1375.4129743938047,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/ox-alpha","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":9,"repaired_rate":0.3,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":41.22249358585908,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":3786},{"admitted_plugins":7,"attempted_matches":3586,"canonical_public_row_identity":"publication-row.v1:mixed:reflection-beam-1-0-501b-a23b:0b6c062e87a35ee5","capped_draws":246,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.06745949999999999},"codegen_evaluated_cells":8,"conditional_success_score":46.68875725038328,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":993,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"reflection/beam-1.0-501b-a23b","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":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,"playable":42.992770354304724,"score":42.992770354304724},"GB2-02":{"attempts":1,"playable":45.549638241944415,"score":45.549638241944415},"GB2-03":{"attempts":1,"playable":43.810429759022526,"score":43.810429759022526},"GB2-04":{"attempts":1,"playable":39.75659327595914,"score":39.75659327595914},"GB2-05":{"attempts":1,"playable":61.9150209611777,"score":61.9150209611777},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":10.143619159114431,"score":10.143619159114431},"GB2-08":{"attempts":1,"playable":82.65322900116001,"score":82.65322900116001}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:57Z","losses":1481,"max_score":82.65322900116001,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"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":0.875,"provider":"Other","provider_key":"other","rank":146,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","ranking_status":"ranked","rated_matches":3586,"rating_method":"bradley_terry_newton","raw_elo":1427.5727738714174,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"reflection/beam-1.0-501b-a23b","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":4,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.85266259408537,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1112},{"admitted_plugins":7,"attempted_matches":3550,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-27b:9d730dc03d31d16f","capped_draws":163,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.06623293499999999,"mean":0.04480870625,"median":0.0402421875,"min":0.0205156,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.35846965},"codegen_evaluated_cells":8,"conditional_success_score":46.660937976152,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":1006,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-27b","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-08"],"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":53.091730974515094,"score":53.091730974515094},"GB2-02":{"attempts":1,"playable":42.1702722263371,"score":42.1702722263371},"GB2-03":{"attempts":1,"playable":48.983436825560815,"score":48.983436825560815},"GB2-04":{"attempts":1,"playable":40.16595143167495,"score":40.16595143167495},"GB2-05":{"attempts":1,"playable":59.262151563671,"score":59.262151563671},"GB2-06":{"attempts":1,"playable":61.916597957680565,"score":61.916597957680565},"GB2-07":{"attempts":1,"playable":21.036424853624478,"score":21.036424853624478},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:36:59Z","losses":1478,"max_score":61.916597957680565,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Qwen3.8 27B","model_slug":"qwen-qwen3-8-27b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Alibaba","provider_key":"qwen","rank":147,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:36:59Z","ranking_status":"ranked","rated_matches":3550,"rating_method":"bradley_terry_newton","raw_elo":1421.947059346994,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.828320729133,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1066},{"admitted_plugins":7,"attempted_matches":3592,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-6-flash:9b3aa3914934b08c","capped_draws":367,"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":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.0234374},"codegen_evaluated_cells":8,"conditional_success_score":46.33904218188586,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":870,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.6-flash","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"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":68.40175329217033,"score":68.40175329217033},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"playable":40.14521690712411,"score":40.14521690712411},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":52.784145231806455,"score":52.784145231806455},"GB2-06":{"attempts":1,"playable":51.180560534215644,"score":51.180560534215644},"GB2-07":{"attempts":1,"playable":40.71202227658455,"score":40.71202227658455},"GB2-08":{"attempts":1,"playable":28.661998579345,"score":28.661998579345}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:26Z","losses":1587,"max_score":68.40175329217033,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"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":0.875,"provider":"Xiaomi","provider_key":"xiaomi","rank":148,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:55:18Z","ranking_status":"ranked","rated_matches":3590,"rating_method":"bradley_terry_newton","raw_elo":1400.9681411240329,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"0543bc94f06164fcbb1f128910de38d38a5c66d2cf128bf83dabc69dffc41d08","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.546661909150124,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1133},{"admitted_plugins":16,"attempted_matches":8177,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28","capped_draws":624,"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000001},"codegen_evaluated_cells":16,"conditional_success_score":40.424303134884006,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":2265,"eligibility_flag":true,"entry_count":16,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.6-flash","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":12,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":31.505426538892607,"score":31.505426538892607},"GB2-02":{"attempts":2,"playable":40.31715165103505,"score":40.31715165103505},"GB2-03":{"attempts":2,"playable":56.50948393882645,"score":56.50948393882645},"GB2-04":{"attempts":2,"playable":42.36058412191249,"score":42.36058412191249},"GB2-05":{"attempts":2,"playable":47.6081903875952,"score":47.6081903875952},"GB2-06":{"attempts":2,"playable":23.867679983290934,"score":23.867679983290934},"GB2-07":{"attempts":2,"playable":47.51121036538618,"score":47.51121036538618},"GB2-08":{"attempts":2,"playable":33.714698092133126,"score":33.714698092133126}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:27Z","losses":3932,"max_score":56.50948393882645,"measured_at":null,"min_score":23.867679983290934,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.6 Flash","model_slug":"google-gemini-3-6-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Google","provider_key":"google","rank":149,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:20:46Z","ranking_status":"ranked","rated_matches":8176,"rating_method":"bradley_terry_newton","raw_elo":1330.1938102028666,"reasoning_bracket":"baseline","reasoning_level":"Minimal","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Minimal","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":4,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.424303134884006,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1979},{"admitted_plugins":7,"attempted_matches":3558,"canonical_public_row_identity":"publication-row.v1:mixed:bytedance-seed-seed-2-0-code:2447db730c8d12fe","capped_draws":82,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.428104},"codegen_evaluated_cells":8,"conditional_success_score":45.869562641390225,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":831,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"bytedance-seed/seed-2.0-code","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.25,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":50.942176921604464,"score":50.942176921604464},"GB2-02":{"attempts":1,"playable":39.52197680046837,"score":39.52197680046837},"GB2-03":{"attempts":1,"playable":40.46078193506135,"score":40.46078193506135},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":48.37827969173142,"score":48.37827969173142},"GB2-06":{"attempts":1,"playable":14.163085520441673,"score":14.163085520441673},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":86.94320232424666,"score":86.94320232424666}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:05Z","losses":1565,"max_score":86.94320232424666,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"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":0.875,"provider":"ByteDance","provider_key":"bytedance-seed","rank":150,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:20Z","ranking_status":"ranked","rated_matches":3558,"rating_method":"bradley_terry_newton","raw_elo":1422.481008634438,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":5,"repaired_rate":0.625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.135867311216444,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1162},{"admitted_plugins":7,"attempted_matches":3550,"canonical_public_row_identity":"publication-row.v1:mixed:minimax-minimax-m3-1-flash:d17db1acc4e18412","capped_draws":27,"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":45.71851251224634,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":790,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3.1-flash:free","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-08"],"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":14.931506354971024,"score":14.931506354971024},"GB2-02":{"attempts":1,"playable":41.111782530814864,"score":41.111782530814864},"GB2-03":{"attempts":1,"playable":49.13808216264724,"score":49.13808216264724},"GB2-04":{"attempts":1,"playable":39.65423019410055,"score":39.65423019410055},"GB2-05":{"attempts":1,"playable":72.78229423571837,"score":72.78229423571837},"GB2-06":{"attempts":1,"playable":32.163984579948654,"score":32.163984579948654},"GB2-07":{"attempts":1,"playable":70.24770752752374,"score":70.24770752752374},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:42:43Z","losses":1598,"max_score":72.78229423571837,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Minimax M3.1 Flash","model_slug":"minimax-minimax-m3-1-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"MiniMax","provider_key":"minimax","rank":151,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:42:43Z","ranking_status":"ranked","rated_matches":3548,"rating_method":"bradley_terry_newton","raw_elo":1418.091526661026,"reasoning_bracket":"intensive","reasoning_level":"Xhigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"unknown_legacy","provider_setting_label":"Xhigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Xhigh","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.00369844821555,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":36,"wins":1160},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59","capped_draws":316,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.12185499999999999,"mean":0.09110296875000001,"median":0.09280125,"min":0.0343775,"recorded_attempt_count":15,"run_count":8,"total":0.7288237499999999},"codegen_evaluated_cells":8,"conditional_success_score":45.606093053062914,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":982,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.7-max","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":18.47367135694114,"score":18.47367135694114},"GB2-02":{"attempts":1,"playable":44.38935843142217,"score":44.38935843142217},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.63919085975499,"score":43.63919085975499},"GB2-05":{"attempts":1,"playable":39.52695378355019,"score":39.52695378355019},"GB2-06":{"attempts":1,"playable":61.45320043406526,"score":61.45320043406526},"GB2-07":{"attempts":1,"playable":76.16539028897841,"score":76.16539028897841},"GB2-08":{"attempts":1,"playable":35.59488621672822,"score":35.59488621672822}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:03Z","losses":1533,"max_score":76.16539028897841,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Qwen3.7 Max","model_slug":"qwen-qwen3-7-max","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Alibaba","provider_key":"qwen","rank":152,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:13:33Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1420.556162512417,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":6,"repaired_rate":0.75,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":39.90533142143005,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1079},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:claude-haiku-5-5:fa59920773e01b68","capped_draws":397,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0063593,"mean":0.0031203999999999997,"median":0.00236545,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.0249632},"codegen_evaluated_cells":8,"conditional_success_score":39.308289079965675,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1264,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-haiku-5-5","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":35.382775953240746,"score":35.382775953240746},"GB2-02":{"attempts":1,"playable":42.38183447863047,"score":42.38183447863047},"GB2-03":{"attempts":1,"playable":43.08026465020685,"score":43.08026465020685},"GB2-04":{"attempts":1,"playable":41.69967780442835,"score":41.69967780442835},"GB2-05":{"attempts":1,"playable":16.24037589149305,"score":16.24037589149305},"GB2-06":{"attempts":1,"playable":49.34900558721307,"score":49.34900558721307},"GB2-07":{"attempts":1,"playable":52.022714507735756,"score":52.022714507735756},"GB2-08":{"attempts":1,"playable":34.30966376677716,"score":34.30966376677716}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:59:16Z","losses":1954,"max_score":52.022714507735756,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":153,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:59:16Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1319.4851058149343,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":39.308289079965675,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":870},{"admitted_plugins":15,"attempted_matches":7682,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e","capped_draws":581,"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.27157109999999995},"codegen_evaluated_cells":16,"conditional_success_score":42.61689769685302,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1972,"eligibility_flag":true,"entry_count":15,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash-lite","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":36.91061110024815,"score":36.91061110024815},"GB2-02":{"attempts":2,"playable":40.62709272086003,"score":40.62709272086003},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":55.191114920093845,"score":27.595557460046923},"GB2-04":{"attempts":2,"playable":47.048023455639125,"score":47.048023455639125},"GB2-05":{"attempts":2,"playable":11.921475429839985,"score":11.921475429839985},"GB2-06":{"attempts":2,"playable":56.43791909852378,"score":56.43791909852378},"GB2-07":{"attempts":2,"playable":62.104276468822164,"score":62.104276468822164},"GB2-08":{"attempts":2,"playable":30.694668380797154,"score":30.694668380797154}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:49Z","losses":3669,"max_score":62.104276468822164,"measured_at":null,"min_score":11.921475429839985,"model_code_failure_rate":0.0625,"model_code_failures":1,"model_display_name":"Gemini 3.5 Flash Lite","model_slug":"google-gemini-3-5-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.9375,"provider":"Google","provider_key":"google","rank":154,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:14:37Z","ranking_status":"ranked","rated_matches":7681,"rating_method":"bradley_terry_newton","raw_elo":1344.1898077714673,"reasoning_bracket":"baseline","reasoning_level":"Minimal","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Minimal","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":6,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":39.16745301434716,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2040},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:inception-mercury-3:4e13a814bbf52466","capped_draws":220,"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":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.022427299999999997},"codegen_evaluated_cells":8,"conditional_success_score":38.92444813745101,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":990,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-3","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":34.886732613705796,"score":34.886732613705796},"GB2-02":{"attempts":1,"playable":42.69909194377107,"score":42.69909194377107},"GB2-03":{"attempts":1,"playable":33.672393099704045,"score":33.672393099704045},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":25.26458038695291,"score":25.26458038695291},"GB2-06":{"attempts":1,"playable":66.88153779134291,"score":66.88153779134291},"GB2-07":{"attempts":1,"playable":33.49880171248045,"score":33.49880171248045},"GB2-08":{"attempts":1,"playable":33.81501225547331,"score":33.81501225547331}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:09Z","losses":2102,"max_score":66.88153779134291,"measured_at":null,"min_score":25.26458038695291,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Mercury 3","model_slug":"inception-mercury-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Inception","provider_key":"inception","rank":155,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:09Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1334.2408504627792,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-3","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":38.92444813745101,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":995},{"admitted_plugins":7,"attempted_matches":3609,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2","capped_draws":182,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"codegen_evaluated_cells":8,"conditional_success_score":44.146569962818695,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":652,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":21.095558671137997,"score":21.095558671137997},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.742066078343424,"score":31.742066078343424},"GB2-04":{"attempts":1,"playable":42.82300100995158,"score":42.82300100995158},"GB2-05":{"attempts":1,"playable":61.53661978064131,"score":61.53661978064131},"GB2-06":{"attempts":1,"playable":49.155359737347496,"score":49.155359737347496},"GB2-07":{"attempts":1,"playable":62.838415616371904,"score":62.838415616371904},"GB2-08":{"attempts":1,"playable":39.83496884593718,"score":39.83496884593718}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:31:41Z","losses":1772,"max_score":62.838415616371904,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"GPT-5","model_slug":"gpt-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"OpenAI","provider_key":"openai","rank":156,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T18:51:12Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1390.7614537089862,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":38.628248717466356,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1184},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemma-4-31b-it:a8935428499c4622","capped_draws":426,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0061656,"mean":0.00384247375,"median":0.003310595,"min":0.00192299,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.03073979},"codegen_evaluated_cells":8,"conditional_success_score":38.09245916181765,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1250,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemma-4-31b-it","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":22.403539400699408,"score":22.403539400699408},"GB2-02":{"attempts":1,"playable":43.43895423021337,"score":43.43895423021337},"GB2-03":{"attempts":1,"playable":43.91462092939784,"score":43.91462092939784},"GB2-04":{"attempts":1,"playable":43.33319700499054,"score":43.33319700499054},"GB2-05":{"attempts":1,"playable":72.04104952761561,"score":72.04104952761561},"GB2-06":{"attempts":1,"playable":27.839887011061393,"score":27.839887011061393},"GB2-07":{"attempts":1,"playable":18.250286878375718,"score":18.250286878375718},"GB2-08":{"attempts":1,"playable":33.518138312187396,"score":33.518138312187396}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:59:02Z","losses":2003,"max_score":72.04104952761561,"measured_at":null,"min_score":18.250286878375718,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemma 4 31B","model_slug":"google-gemma-4-31b-it","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Google","provider_key":"google","rank":157,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T16:59:02Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1306.9371169005528,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":38.09245916181765,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":835},{"admitted_plugins":7,"attempted_matches":3572,"canonical_public_row_identity":"publication-row.v1:mixed:reflection-beam-1-0-501b-a23b:8b214f4de64fd0f1","capped_draws":11,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"codegen_evaluated_cells":8,"conditional_success_score":43.09289557839141,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":779,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"reflection/beam-1.0-501b-a23b","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01"],"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,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":33.88605126157579,"score":33.88605126157579},"GB2-03":{"attempts":1,"playable":39.302431406504105,"score":39.302431406504105},"GB2-04":{"attempts":1,"playable":40.06362607016069,"score":40.06362607016069},"GB2-05":{"attempts":1,"playable":41.0689414396043,"score":41.0689414396043},"GB2-06":{"attempts":1,"playable":55.66838045383894,"score":55.66838045383894},"GB2-07":{"attempts":1,"playable":31.386026642500507,"score":31.386026642500507},"GB2-08":{"attempts":1,"playable":60.274811774555594,"score":60.274811774555594}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:03Z","losses":1732,"max_score":60.274811774555594,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"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":0.875,"provider":"Other","provider_key":"other","rank":158,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T17:50:03Z","ranking_status":"ranked","rated_matches":3571,"rating_method":"bradley_terry_newton","raw_elo":1378.3663056565133,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":37.70628363109249,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1060},{"admitted_plugins":7,"attempted_matches":3586,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db","capped_draws":563,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.156555,"mean":0.1422525,"median":0.14850249999999998,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":1.13802},"codegen_evaluated_cells":8,"conditional_success_score":42.8771413058059,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1358,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":51.235536792230675,"score":51.235536792230675},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":38.774748036360926,"score":38.774748036360926},"GB2-04":{"attempts":1,"playable":41.597497623253474,"score":41.597497623253474},"GB2-05":{"attempts":1,"playable":52.210440548196146,"score":52.210440548196146},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.069687009036706,"score":38.069687009036706},"GB2-08":{"attempts":1,"playable":36.18760512476575,"score":36.18760512476575}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:14Z","losses":1451,"max_score":52.210440548196146,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"GPT-5.5","model_slug":"gpt-5-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"OpenAI","provider_key":"openai","rank":159,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:59Z","ranking_status":"ranked","rated_matches":3586,"rating_method":"bradley_terry_newton","raw_elo":1375.9451812660875,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":37.517498642580165,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":777},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:fireworks-ember-1:5a9bb90daa43eef7","capped_draws":332,"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":0.143745,"mean":0.07283400000000001,"median":0.063006,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.582672},"codegen_evaluated_cells":8,"conditional_success_score":37.39745515028769,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1211,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"fireworks/ember-1","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":50.746561800860114,"score":50.746561800860114},"GB2-02":{"attempts":1,"playable":45.338788424049355,"score":45.338788424049355},"GB2-03":{"attempts":1,"playable":36.44436895903613,"score":36.44436895903613},"GB2-04":{"attempts":1,"playable":40.98421031880623,"score":40.98421031880623},"GB2-05":{"attempts":1,"playable":21.805315335411894,"score":21.805315335411894},"GB2-06":{"attempts":1,"playable":47.40482584358757,"score":47.40482584358757},"GB2-07":{"attempts":1,"playable":36.93187650272706,"score":36.93187650272706},"GB2-08":{"attempts":1,"playable":19.523694017823157,"score":19.523694017823157}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:27Z","losses":2060,"max_score":50.746561800860114,"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":1.0,"provider":"Fireworks AI","provider_key":"fireworks","rank":160,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:04Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1297.3353766328116,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":37.39745515028769,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":817},{"admitted_plugins":6,"attempted_matches":3114,"canonical_public_row_identity":"publication-row.v1:mixed:stealth-space-bunny-alpha:f6f23b9a4cbbb25d","capped_draws":246,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":49.127473247932954,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":542,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/space-bunny-alpha","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":63.77650188114862,"score":63.77650188114862},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":45.688988962286096,"score":45.688988962286096},"GB2-06":{"attempts":1,"playable":38.81864854033569,"score":38.81864854033569},"GB2-07":{"attempts":1,"playable":74.43144469769753,"score":74.43144469769753},"GB2-08":{"attempts":1,"playable":33.41916692759776,"score":33.41916692759776}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:56:42Z","losses":1379,"max_score":74.43144469769753,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Space Bunny Alpha","model_slug":"stealth-space-bunny-alpha","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Other","provider_key":"other","rank":161,"rank_movement":4,"rank_movement_baseline_at":"2026-10-24T19:18:19Z","ranking_status":"ranked","rated_matches":3114,"rating_method":"bradley_terry_newton","raw_elo":1436.7785803208674,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":5,"repaired_rate":0.625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":36.845604935949716,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1193},{"admitted_plugins":7,"attempted_matches":3558,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-flash:e0a2978fff9e81b1","capped_draws":376,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.058475471099999995},"codegen_evaluated_cells":8,"conditional_success_score":41.801212728556365,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1165,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-05"],"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":15.64110811112249,"score":15.64110811112249},"GB2-02":{"attempts":1,"playable":42.910539295927805,"score":42.910539295927805},"GB2-03":{"attempts":1,"playable":34.7408210165092,"score":34.7408210165092},"GB2-04":{"attempts":1,"playable":42.41466060211229,"score":42.41466060211229},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":82.0934769045649,"score":82.0934769045649},"GB2-07":{"attempts":1,"playable":39.01539001530872,"score":39.01539001530872},"GB2-08":{"attempts":1,"playable":35.792493154349145,"score":35.792493154349145}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:48Z","losses":1572,"max_score":82.0934769045649,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"DeepSeek V4 Flash","model_slug":"deepseek-deepseek-v4-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"DeepSeek","provider_key":"deepseek","rank":162,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:24:33Z","ranking_status":"ranked","rated_matches":3558,"rating_method":"bradley_terry_newton","raw_elo":1392.2454110242766,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":36.57606113748682,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":821},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-1-flash:130c334db8df04f4","capped_draws":438,"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":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997},"codegen_evaluated_cells":8,"conditional_success_score":36.533416411225765,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1224,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4.1-flash","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":45.84526135492576,"score":45.84526135492576},"GB2-02":{"attempts":1,"playable":41.852843528898845,"score":41.852843528898845},"GB2-03":{"attempts":1,"playable":48.557733587614784,"score":48.557733587614784},"GB2-04":{"attempts":1,"playable":38.73254406931057,"score":38.73254406931057},"GB2-05":{"attempts":1,"playable":30.270501001803357,"score":30.270501001803357},"GB2-06":{"attempts":1,"playable":28.81723881742438,"score":28.81723881742438},"GB2-07":{"attempts":1,"playable":25.564044191476587,"score":25.564044191476587},"GB2-08":{"attempts":1,"playable":32.62716473835184,"score":32.62716473835184}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:42Z","losses":2087,"max_score":48.557733587614784,"measured_at":null,"min_score":25.564044191476587,"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":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":163,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:12:08Z","ranking_status":"ranked","rated_matches":4087,"rating_method":"bradley_terry_newton","raw_elo":1280.8092602258098,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"010eda555321e9d99662cb0238bc76680a45197bc56d713357584bd1193331ab","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":36.533416411225765,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":776},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73","capped_draws":422,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761485},"codegen_evaluated_cells":10,"conditional_success_score":38.798889684625735,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1214,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling-small","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"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":1,"playable":33.19839222532428,"score":33.19839222532428},"GB2-02":{"attempts":1,"playable":42.06447400679762,"score":42.06447400679762},"GB2-03":{"attempts":1,"playable":45.57764655257097,"score":45.57764655257097},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.31255022830733,"score":21.156275114153665},"GB2-05":{"attempts":1,"playable":41.839633609815536,"score":41.839633609815536},"GB2-06":{"attempts":1,"playable":54.51921324294854,"score":54.51921324294854},"GB2-07":{"attempts":1,"playable":18.4501050975686,"score":18.4501050975686},"GB2-08":{"attempts":1,"playable":32.429102513673,"score":32.429102513673}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:18Z","losses":2002,"max_score":54.51921324294854,"measured_at":null,"min_score":18.4501050975686,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"model_display_name":"Inkling Small","model_slug":"thinkingmachines-inkling-small","performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"plugin_success_rate":0.8888888888888888,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":164,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:24:26Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1319.8026720818011,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling-small","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.2222222222222222,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":36.154355295356524,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":872},{"admitted_plugins":7,"attempted_matches":3559,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-terra:4506b3e0a8fb5629","capped_draws":365,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425},"codegen_evaluated_cells":8,"conditional_success_score":41.075299313785756,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1225,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-terra","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-05"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":54.55500320868485,"score":54.55500320868485},"GB2-02":{"attempts":1,"playable":44.2838056546712,"score":44.2838056546712},"GB2-03":{"attempts":1,"playable":33.244225498930376,"score":33.244225498930376},"GB2-04":{"attempts":1,"playable":44.454714144494474,"score":44.454714144494474},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":37.48406368914366,"score":37.48406368914366},"GB2-07":{"attempts":1,"playable":29.648815267901497,"score":29.648815267901497},"GB2-08":{"attempts":1,"playable":43.8564677326743,"score":43.8564677326743}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:54:15Z","losses":1581,"max_score":54.55500320868485,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"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":0.875,"provider":"OpenAI","provider_key":"openai","rank":165,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:24:14Z","ranking_status":"ranked","rated_matches":3558,"rating_method":"bradley_terry_newton","raw_elo":1341.472689839417,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.940886899562535,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":752},{"admitted_plugins":7,"attempted_matches":3586,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-glimmer-30b:085624a1bd2a3883","capped_draws":401,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572},"codegen_evaluated_cells":8,"conditional_success_score":41.00982525986189,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1191,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-glimmer-30b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"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":31.71092374401135,"score":31.71092374401135},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"playable":37.399390391057594,"score":37.399390391057594},"GB2-04":{"attempts":1,"playable":49.231658345772594,"score":49.231658345772594},"GB2-05":{"attempts":1,"playable":45.88124187411278,"score":45.88124187411278},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":47.79640907135037,"score":47.79640907135037},"GB2-08":{"attempts":1,"playable":32.032907798363944,"score":32.032907798363944}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:01Z","losses":1599,"max_score":49.231658345772594,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Muse Glimmer 30B","model_slug":"meta-muse-glimmer-30b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Meta","provider_key":"meta","rank":166,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:19Z","ranking_status":"ranked","rated_matches":3585,"rating_method":"bradley_terry_newton","raw_elo":1356.1617117841313,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.883597102379156,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":795},{"admitted_plugins":7,"attempted_matches":3550,"canonical_public_row_identity":"publication-row.v1:mixed:stealth-space-bunny-alpha:4fea768782ed57d5","capped_draws":100,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":40.91334008523291,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":912,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/space-bunny-alpha","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-08"],"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":49.37631766797478,"score":49.37631766797478},"GB2-02":{"attempts":1,"playable":42.69909194377107,"score":42.69909194377107},"GB2-03":{"attempts":1,"playable":45.78498915227661,"score":45.78498915227661},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":1,"playable":13.170633701862291,"score":13.170633701862291},"GB2-06":{"attempts":1,"playable":58.192454763139864,"score":58.192454763139864},"GB2-07":{"attempts":1,"playable":35.98121484580971,"score":35.98121484580971},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:47Z","losses":1735,"max_score":58.192454763139864,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Space Bunny Alpha","model_slug":"stealth-space-bunny-alpha","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Other","provider_key":"other","rank":167,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:24:34Z","ranking_status":"ranked","rated_matches":3550,"rating_method":"bradley_terry_newton","raw_elo":1338.4757325902574,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.7991725745788,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":903},{"admitted_plugins":7,"attempted_matches":3586,"canonical_public_row_identity":"publication-row.v1:mixed:mistralai-mistral-large-4-0:2a4917b7c19d5bb6","capped_draws":423,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03127107,"mean":0.02115604125,"median":0.02234344,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.16924833},"codegen_evaluated_cells":8,"conditional_success_score":40.725974917221876,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1213,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"mistralai/mistral-large-4-0","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"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":59.32157960937489,"score":59.32157960937489},"GB2-02":{"attempts":1,"playable":43.12194026739476,"score":43.12194026739476},"GB2-03":{"attempts":1,"playable":30.450091838780786,"score":30.450091838780786},"GB2-04":{"attempts":1,"playable":38.63008847853202,"score":38.63008847853202},"GB2-05":{"attempts":1,"playable":63.80393649824361,"score":63.80393649824361},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.52583159206098,"score":9.52583159206098},"GB2-08":{"attempts":1,"playable":40.228356136166084,"score":40.228356136166084}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:33Z","losses":1594,"max_score":63.80393649824361,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"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":0.875,"provider":"Mistral","provider_key":"mistral","rank":168,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T17:49:33Z","ranking_status":"ranked","rated_matches":3586,"rating_method":"bradley_terry_newton","raw_elo":1333.884227604204,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.63522805256914,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":779},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash:e1e7937be001cd2a","capped_draws":353,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.13084687320145388,"mean":0.0871504498983802,"median":0.08084431374719805,"min":0.0619993303028941,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.6972035991870416},"codegen_evaluated_cells":8,"conditional_success_score":35.54503356604796,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1096,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"minimal","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":5,"first_pass_rate":0.625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":38.74966369112913,"score":38.74966369112913},"GB2-02":{"attempts":1,"playable":39.62803957736176,"score":39.62803957736176},"GB2-03":{"attempts":1,"playable":23.052829935002148,"score":23.052829935002148},"GB2-04":{"attempts":1,"playable":39.8589469664451,"score":39.8589469664451},"GB2-05":{"attempts":1,"playable":14.513869835026567,"score":14.513869835026567},"GB2-06":{"attempts":1,"playable":60.24564115789285,"score":60.24564115789285},"GB2-07":{"attempts":1,"playable":35.98121484580971,"score":35.98121484580971},"GB2-08":{"attempts":1,"playable":32.33006251971647,"score":32.33006251971647}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:21Z","losses":2184,"max_score":60.24564115789285,"measured_at":null,"min_score":14.513869835026567,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Gemini 3.5 Flash","model_slug":"google-gemini-3-5-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Google","provider_key":"google","rank":169,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:15:48Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1285.0815572029774,"reasoning_bracket":"baseline","reasoning_level":"Minimal (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Minimal (historical request variant 2)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-2","reasoning_bucket_label":"Minimal (historical request variant 2)","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline-variant-2"},"reasoning_setting":"historical-provider-setting-baseline-variant-2","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.54503356604796,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":808},{"admitted_plugins":7,"attempted_matches":3592,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3","capped_draws":407,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03912625,"mean":0.022799843750000003,"median":0.021642500000000002,"min":0.015285,"recorded_attempt_count":9,"run_count":8,"total":0.18239875000000003},"codegen_evaluated_cells":8,"conditional_success_score":40.332250580415675,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":896,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.7-max","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":65.99600951760388,"score":65.99600951760388},"GB2-02":{"attempts":1,"playable":45.86582005046848,"score":45.86582005046848},"GB2-03":{"attempts":1,"playable":29.690595943558773,"score":29.690595943558773},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":36.63426256655947,"score":36.63426256655947},"GB2-06":{"attempts":1,"playable":16.1084841297855,"score":16.1084841297855},"GB2-07":{"attempts":1,"playable":61.05578240397785,"score":61.05578240397785},"GB2-08":{"attempts":1,"playable":26.974799450955743,"score":26.974799450955743}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:54Z","losses":1769,"max_score":65.99600951760388,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Qwen3.7 Max","model_slug":"qwen-qwen3-7-max","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Alibaba","provider_key":"qwen","rank":170,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:08Z","ranking_status":"ranked","rated_matches":3591,"rating_method":"bradley_terry_newton","raw_elo":1314.6055853410394,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.290719257863714,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":926},{"admitted_plugins":7,"attempted_matches":3572,"canonical_public_row_identity":"publication-row.v1:mixed:openai-gpt-oss-120b:7e4ecfa424847773","capped_draws":147,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.05953976200000001},"codegen_evaluated_cells":8,"conditional_success_score":40.09693380847334,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":946,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"openai/gpt-oss-120b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01"],"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,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.861474907777556,"score":43.861474907777556},"GB2-03":{"attempts":1,"playable":46.40629965489456,"score":46.40629965489456},"GB2-04":{"attempts":1,"playable":42.516760894618045,"score":42.516760894618045},"GB2-05":{"attempts":1,"playable":58.31249676882345,"score":58.31249676882345},"GB2-06":{"attempts":1,"playable":22.88129159889048,"score":22.88129159889048},"GB2-07":{"attempts":1,"playable":34.07304809595744,"score":34.07304809595744},"GB2-08":{"attempts":1,"playable":32.62716473835184,"score":32.62716473835184}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:03:00Z","losses":1756,"max_score":58.31249676882345,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"GPT-OSS 120B","model_slug":"openai-gpt-oss-120b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"OpenAI","provider_key":"openai","rank":171,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:12:27Z","ranking_status":"ranked","rated_matches":3572,"rating_method":"bradley_terry_newton","raw_elo":1319.1539846910105,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.08481708241417,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":870},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69","capped_draws":333,"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":34.91176220956577,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1191,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"x-ai/grok-build-0.1","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"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":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:39Z","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":1.0,"provider":"xAI","provider_key":"x-ai","rank":172,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:20:25Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1267.3575528276635,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":8,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.91176220956577,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":734},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:z-ai-glm-5-2:184634950256ca6a","capped_draws":258,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"codegen_evaluated_cells":8,"conditional_success_score":34.30905696069874,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1076,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"z-ai/glm-5.2","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":30.311735105867715,"score":30.311735105867715},"GB2-02":{"attempts":1,"playable":42.27605906017271,"score":42.27605906017271},"GB2-03":{"attempts":1,"playable":35.380509346539824,"score":35.380509346539824},"GB2-04":{"attempts":1,"playable":42.9250607025321,"score":42.9250607025321},"GB2-05":{"attempts":1,"playable":19.693637278801596,"score":19.693637278801596},"GB2-06":{"attempts":1,"playable":30.97096724237314,"score":30.97096724237314},"GB2-07":{"attempts":1,"playable":42.96299010506729,"score":42.96299010506729},"GB2-08":{"attempts":1,"playable":29.951496844235564,"score":29.951496844235564}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:54Z","losses":2248,"max_score":42.96299010506729,"measured_at":null,"min_score":19.693637278801596,"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":1.0,"provider":"Zhipu","provider_key":"z-ai","rank":173,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1259.105478638993,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled (historical request variant 2)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-2","reasoning_bucket_label":"Reasoning disabled (historical request variant 2)","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline-variant-2"},"reasoning_setting":"historical-provider-setting-baseline-variant-2","repaired_admitted":4,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.30905696069874,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":764},{"admitted_plugins":6,"attempted_matches":3114,"canonical_public_row_identity":"publication-row.v1:mixed:o3:f70fd8105d3dfec2","capped_draws":194,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.072978,"mean":0.048872,"median":0.046325000000000005,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.390976},"codegen_evaluated_cells":8,"conditional_success_score":45.737333502794975,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":555,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"o3","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":37.46358856237706,"score":37.46358856237706},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":1,"playable":44.72738826431963,"score":44.72738826431963},"GB2-06":{"attempts":1,"playable":45.24522447749243,"score":45.24522447749243},"GB2-07":{"attempts":1,"playable":58.72681136385298,"score":58.72681136385298},"GB2-08":{"attempts":1,"playable":47.07230982693174,"score":47.07230982693174}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:17Z","losses":1487,"max_score":58.72681136385298,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"o3","model_slug":"o3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"OpenAI","provider_key":"openai","rank":174,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:19:03Z","ranking_status":"ranked","rated_matches":3114,"rating_method":"bradley_terry_newton","raw_elo":1398.1492262981594,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.30300012709623,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1072},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-flash:e1a2822fb5bba20e","capped_draws":290,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.02748863},"codegen_evaluated_cells":8,"conditional_success_score":33.75792043850485,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1130,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":34.588992262839916,"score":34.588992262839916},"GB2-02":{"attempts":1,"playable":43.227623284677975,"score":43.227623284677975},"GB2-03":{"attempts":1,"playable":45.37018462718579,"score":45.37018462718579},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":1,"playable":17.199481343556844,"score":17.199481343556844},"GB2-06":{"attempts":1,"playable":55.465478779936475,"score":55.465478779936475},"GB2-07":{"attempts":1,"playable":10.143619159114431,"score":10.143619159114431},"GB2-08":{"attempts":1,"playable":23.697410406441467,"score":23.697410406441467}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:34Z","losses":2250,"max_score":55.465478779936475,"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":1.0,"provider":"Alibaba","provider_key":"qwen","rank":175,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:24:30Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1240.6646902919304,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":33.75792043850485,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":708},{"admitted_plugins":14,"attempted_matches":7176,"canonical_public_row_identity":"publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011","capped_draws":649,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":60},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.261503015,"mean":0.224623670625,"median":0.22750746833333335,"min":0.17735088333333335,"recorded_attempt_count":60,"run_count":22,"total":4.90638056},"codegen_evaluated_cells":16,"conditional_success_score":39.18673544516585,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1895,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"max","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04","GB2-06"],"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":40.0905826031761,"score":40.0905826031761},"GB2-02":{"attempts":2,"playable":41.90575398002311,"score":41.90575398002311},"GB2-03":{"attempts":2,"playable":47.90330464403783,"score":47.90330464403783},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.04703672763066,"score":22.02351836381533},"GB2-05":{"attempts":2,"playable":16.240371999207255,"score":16.240371999207255},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":53.75985489041197,"score":26.879927445205986},"GB2-07":{"attempts":2,"playable":28.777137037920316,"score":28.777137037920316},"GB2-08":{"attempts":2,"playable":40.76984167891956,"score":40.76984167891956}},"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":3704,"max_score":47.90330464403783,"measured_at":null,"min_score":16.240371999207255,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"Inkling","model_slug":"thinkingmachines-inkling","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":176,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:04:18Z","ranking_status":"ranked","rated_matches":7176,"rating_method":"bradley_terry_newton","raw_elo":1293.1937277282507,"reasoning_bracket":"intensive","reasoning_level":"Max","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Max","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Max","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":5,"repaired_rate":0.3125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":33.07380471903819,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1577},{"admitted_plugins":6,"attempted_matches":3096,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f","capped_draws":293,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500896},"codegen_evaluated_cells":8,"conditional_success_score":43.97381135158849,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":705,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.7-plus","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":1,"first_pass_rate":0.125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":50.942176921604464,"score":50.942176921604464},"GB2-02":{"attempts":1,"playable":43.016245594364584,"score":43.016245594364584},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":43.95772723420936,"score":43.95772723420936},"GB2-06":{"attempts":1,"playable":71.09088716682969,"score":71.09088716682969},"GB2-07":{"attempts":1,"playable":24.38856478275738,"score":24.38856478275738},"GB2-08":{"attempts":1,"playable":30.447266409765394,"score":30.447266409765394}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:50:03Z","losses":1458,"max_score":71.09088716682969,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Qwen3.7 Plus","model_slug":"qwen-qwen3-7-plus","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Alibaba","provider_key":"qwen","rank":177,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:17:41Z","ranking_status":"ranked","rated_matches":3096,"rating_method":"bradley_terry_newton","raw_elo":1386.5123403347473,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":5,"repaired_rate":0.625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":32.980358513691364,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":933},{"admitted_plugins":14,"attempted_matches":6642,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab","capped_draws":358,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0719635,"mean":0.060768406250000004,"median":0.0604727,"min":0.05086675,"recorded_attempt_count":50,"run_count":16,"total":0.9722945000000002},"codegen_evaluated_cells":16,"conditional_success_score":37.91930266989309,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1459,"eligibility_flag":true,"entry_count":13,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash-lite","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":13,"first_pass_rate":0.8125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":35.18438712947898,"score":17.59219356473949},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":45.12788935224403,"score":22.563944676122016},"GB2-03":{"attempts":2,"playable":47.550334569425274,"score":47.550334569425274},"GB2-04":{"attempts":2,"playable":39.755391022817186,"score":39.755391022817186},"GB2-05":{"attempts":2,"playable":18.06278094308005,"score":18.06278094308005},"GB2-06":{"attempts":2,"playable":41.404123575210555,"score":41.404123575210555},"GB2-07":{"attempts":2,"playable":44.73197677868093,"score":44.73197677868093},"GB2-08":{"attempts":2,"playable":31.53753798820775,"score":31.53753798820775}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:57Z","losses":3553,"max_score":47.550334569425274,"measured_at":null,"min_score":17.59219356473949,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"Gemini 3.5 Flash Lite","model_slug":"google-gemini-3-5-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Google","provider_key":"google","rank":178,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:15:51Z","ranking_status":"ranked","rated_matches":6642,"rating_method":"bradley_terry_newton","raw_elo":1296.2464371406134,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.0625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":32.89978538978541,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1630},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd","capped_draws":193,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.007539277999999999,"mean":0.0032457859375,"median":0.0019568429999999998,"min":0.001266762,"recorded_attempt_count":14,"run_count":9,"total":0.031586439},"codegen_evaluated_cells":9,"conditional_success_score":41.51457921517773,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":902,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy3-preview","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":65.22465150047583,"score":65.22465150047583},"GB2-02":{"attempts":1,"playable":39.09761928198411,"score":39.09761928198411},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":60.21067356103889,"score":30.105336780519444},"GB2-06":{"attempts":1,"playable":14.277776758291424,"score":14.277776758291424},"GB2-07":{"attempts":1,"playable":25.564044191476587,"score":25.564044191476587},"GB2-08":{"attempts":1,"playable":42.48612119350707,"score":42.48612119350707}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:51:53Z","losses":1723,"max_score":65.22465150047583,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"model_display_name":"Hy3 Preview","model_slug":"tencent-hy3-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.7777777777777778,"provider":"Tencent","provider_key":"tencent","rank":179,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:59Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1327.9542690159064,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":2,"repaired_rate":0.2222222222222222,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":32.56208971571559,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":969},{"admitted_plugins":12,"attempted_matches":6210,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62","capped_draws":255,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.034210525000000006,"mean":0.024715571875,"median":0.0256067375,"min":0.01676735,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":16,"token_priced_attempt_count":25,"total":0.39544915},"codegen_evaluated_cells":16,"conditional_success_score":43.649881843132114,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":894,"eligibility_flag":true,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4-nano","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":16.249501432738306,"score":16.249501432738306},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.26419063187367,"score":20.132095315936834},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":51.559785454938435,"score":25.779892727469218},"GB2-05":{"attempts":2,"playable":50.73086039977494,"score":50.73086039977494},"GB2-06":{"attempts":2,"playable":60.18176763434397,"score":60.18176763434397},"GB2-07":{"attempts":2,"playable":35.13922005709468,"score":35.13922005709468},"GB2-08":{"attempts":2,"playable":51.423847291160804,"score":51.423847291160804}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:52Z","losses":3201,"max_score":60.18176763434397,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":4,"model_display_name":"GPT-5.4 Nano","model_slug":"gpt-5-4-nano","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"OpenAI","provider_key":"openai","rank":180,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:25Z","ranking_status":"ranked","rated_matches":6210,"rating_method":"bradley_terry_newton","raw_elo":1375.391796495188,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":7,"repaired_rate":0.4375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":32.454648107314846,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2115},{"admitted_plugins":19,"attempted_matches":9904,"canonical_public_row_identity":"publication-row.v1:mixed:o3:1084c60ee563e860","capped_draws":401,"codegen_cost_usd":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"codegen_evaluated_cells":32,"conditional_success_score":46.45247006544458,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":540,"eligibility_flag":true,"entry_count":19,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"o3","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6785714285714286,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_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":60.81631957647386,"score":45.612239682355394},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":36.23182617727008,"score":9.05795654431752},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":49.02142322077218,"score":49.02142322077218},"GB2-06":{"attempts":4,"playable":41.49880946747784,"score":41.49880946747784},"GB2-07":{"attempts":4,"playable":43.3188075842468,"score":43.3188075842468},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":47.827634366426736,"score":35.87072577482005}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:04Z","losses":5212,"max_score":49.02142322077218,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.32142857142857145,"model_code_failures":9,"model_display_name":"o3","model_slug":"o3","performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4,"plugin_success_rate":0.6785714285714286,"provider":"OpenAI","provider_key":"openai","rank":181,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:21:13Z","ranking_status":"ranked","rated_matches":9904,"rating_method":"bradley_terry_newton","raw_elo":1397.9158920515883,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":32.05428032485568,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":4152},{"admitted_plugins":12,"attempted_matches":6198,"canonical_public_row_identity":"publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424","capped_draws":528,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00407402,"mean":0.0029986699999999997,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":33,"run_count":14,"total":0.04176386},"codegen_evaluated_cells":14,"conditional_success_score":39.42540266506848,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":1212,"eligibility_flag":true,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"poolside/laguna-s-2.1","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":50.316181015211114,"score":50.316181015211114},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":41.00587206875293,"score":20.502936034376464},"GB2-03":{"attempts":2,"playable":39.443330694108724,"score":39.443330694108724},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.406128220973585,"score":48.406128220973585},"GB2-06":{"attempts":1,"playable":21.09153307102837,"score":21.09153307102837},"GB2-07":{"attempts":2,"playable":45.21795121798449,"score":45.21795121798449},"GB2-08":{"attempts":2,"playable":30.496822367420158,"score":30.496822367420158}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:39Z","losses":3205,"max_score":50.316181015211114,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"model_display_name":"Laguna S 2.1","model_slug":"poolside-laguna-s-2-1","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.8571428571428571,"provider":"Poolside","provider_key":"poolside","rank":182,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:07:26Z","ranking_status":"ranked","rated_matches":6198,"rating_method":"bradley_terry_newton","raw_elo":1331.82796164424,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":5,"repaired_rate":0.35714285714285715,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.934360327637865,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1781},{"admitted_plugins":7,"attempted_matches":3552,"canonical_public_row_identity":"publication-row.v1:mixed:minimax-minimax-m3-1-flash:71b78d475d831a6f","capped_draws":47,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"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":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":36.04378203536947,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":923,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3.1-flash:free","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-08"],"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":30.909664676470744,"score":30.909664676470744},"GB2-02":{"attempts":1,"playable":41.74701132948479,"score":41.74701132948479},"GB2-03":{"attempts":1,"playable":23.49151007875027,"score":23.49151007875027},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"playable":23.534296912770603,"score":23.534296912770603},"GB2-06":{"attempts":1,"playable":69.7232732790763,"score":69.7232732790763},"GB2-07":{"attempts":1,"playable":22.22328267485598,"score":22.22328267485598},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:04:51Z","losses":1889,"max_score":69.7232732790763,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Minimax M3.1 Flash","model_slug":"minimax-minimax-m3-1-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"MiniMax","provider_key":"minimax","rank":183,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T17:04:51Z","ranking_status":"ranked","rated_matches":3550,"rating_method":"bradley_terry_newton","raw_elo":1310.7021020620598,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"unknown_legacy","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.538309280948283,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":738},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-glimmer-30b:20d2aea9e268d0ef","capped_draws":309,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"codegen_evaluated_cells":8,"conditional_success_score":31.36286013831701,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1179,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-glimmer-30b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":22.001291370452723,"score":22.001291370452723},"GB2-02":{"attempts":1,"playable":43.43895423021337,"score":43.43895423021337},"GB2-03":{"attempts":1,"playable":39.9346947850152,"score":39.9346947850152},"GB2-04":{"attempts":1,"playable":45.26955627433336,"score":45.26955627433336},"GB2-05":{"attempts":1,"playable":15.473079984383576,"score":15.473079984383576},"GB2-06":{"attempts":1,"playable":17.1342988476045,"score":17.1342988476045},"GB2-07":{"attempts":1,"playable":37.501187377236114,"score":37.501187377236114},"GB2-08":{"attempts":1,"playable":30.149818237297243,"score":30.149818237297243}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:14Z","losses":2312,"max_score":45.26955627433336,"measured_at":null,"min_score":15.473079984383576,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Muse Glimmer 30B","model_slug":"meta-muse-glimmer-30b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Meta","provider_key":"meta","rank":184,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:05:44Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1209.4264498839957,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.36286013831701,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":597},{"admitted_plugins":11,"attempted_matches":5600,"canonical_public_row_identity":"publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3","capped_draws":420,"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917795999999999},"codegen_evaluated_cells":13,"conditional_success_score":34.2582051133006,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1773,"eligibility_flag":true,"entry_count":11,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"poolside/laguna-s-2.1","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"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":2,"failed_attempts":1,"playable":40.92260870065246,"score":20.46130435032623},"GB2-02":{"attempts":2,"playable":43.01622234350885,"score":43.01622234350885},"GB2-03":{"attempts":2,"playable":38.761728989351525,"score":38.761728989351525},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":2,"playable":28.07691920678637,"score":28.07691920678637},"GB2-06":{"attempts":1,"playable":19.402244997158455,"score":19.402244997158455},"GB2-08":{"attempts":2,"playable":29.25713791136063,"score":29.25713791136063}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-04","GB2-06","GB2-07"],"infra_failures_excluded":3,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:55:34Z","losses":2918,"max_score":43.01622234350885,"measured_at":null,"min_score":19.402244997158455,"model_code_failure_rate":0.08333333333333333,"model_code_failures":1,"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":0.9166666666666666,"provider":"Poolside","provider_key":"poolside","rank":185,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:47:01Z","ranking_status":"ranked","rated_matches":5600,"rating_method":"bradley_terry_newton","raw_elo":1254.5077564318135,"reasoning_bracket":"balanced","reasoning_level":"Enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Enabled","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":4,"repaired_rate":0.3333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.335161634682557,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":909},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:openai-gpt-oss-120b:59563b7e90e4a253","capped_draws":372,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085672999999999},"codegen_evaluated_cells":8,"conditional_success_score":31.234603233380938,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1180,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"openai/gpt-oss-120b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":35.97771540616969,"score":35.97771540616969},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"playable":35.91279705643585,"score":35.91279705643585},"GB2-04":{"attempts":1,"playable":38.93742781528057,"score":38.93742781528057},"GB2-05":{"attempts":1,"playable":15.66490775172327,"score":15.66490775172327},"GB2-06":{"attempts":1,"playable":26.638636751420268,"score":26.638636751420268},"GB2-07":{"attempts":1,"playable":21.23452636920462,"score":21.23452636920462},"GB2-08":{"attempts":1,"playable":33.02321626485831,"score":33.02321626485831}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:00Z","losses":2322,"max_score":42.487598451954895,"measured_at":null,"min_score":15.66490775172327,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"GPT-OSS 120B","model_slug":"openai-gpt-oss-120b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"OpenAI","provider_key":"openai","rank":186,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:06:59Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1212.37551152838,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.234603233380938,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":586},{"admitted_plugins":7,"attempted_matches":3590,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-flash:04d7da5a4f2e2af2","capped_draws":288,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.01067159692},"codegen_evaluated_cells":8,"conditional_success_score":35.58868205524872,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":813,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-flash","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":20.692708856110247,"score":20.692708856110247},"GB2-02":{"attempts":1,"playable":41.852843528898845,"score":41.852843528898845},"GB2-03":{"attempts":1,"playable":35.06079366276128,"score":35.06079366276128},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.919751962210135,"score":44.919751962210135},"GB2-06":{"attempts":1,"playable":56.50276533438551,"score":56.50276533438551},"GB2-07":{"attempts":1,"playable":19.248112753666703,"score":19.248112753666703},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:04:59Z","losses":1998,"max_score":56.50276533438551,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"DeepSeek V4 Flash","model_slug":"deepseek-deepseek-v4-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"DeepSeek","provider_key":"deepseek","rank":187,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:19:03Z","ranking_status":"ranked","rated_matches":3590,"rating_method":"bradley_terry_newton","raw_elo":1281.7767509733683,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":31.14009679834263,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":779},{"admitted_plugins":6,"attempted_matches":3020,"canonical_public_row_identity":"publication-row.v1:mixed:stepfun-step-3-7-flash:e4b72c1ffe9d9779","capped_draws":131,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.02271207,"mean":0.0141778,"median":0.011690184999999999,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1134224},"codegen_evaluated_cells":8,"conditional_success_score":40.77294833480597,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":976,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-3.7-flash","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-05","GB2-08"],"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,"playable":32.99957979145639,"score":32.99957979145639},"GB2-02":{"attempts":1,"playable":43.54460209735465,"score":43.54460209735465},"GB2-03":{"attempts":1,"playable":37.399390391057594,"score":37.399390391057594},"GB2-04":{"attempts":1,"playable":40.16595143167495,"score":40.16595143167495},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.252203517308516,"score":49.252203517308516},"GB2-07":{"attempts":1,"playable":41.275962779983715,"score":41.275962779983715},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:16:12Z","losses":1381,"max_score":49.252203517308516,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Step 3.7 Flash","model_slug":"stepfun-step-3-7-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"StepFun","provider_key":"stepfun","rank":188,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:16:12Z","ranking_status":"ranked","rated_matches":3020,"rating_method":"bradley_terry_newton","raw_elo":1364.7569197789953,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.579711251104477,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":663},{"admitted_plugins":6,"attempted_matches":3088,"canonical_public_row_identity":"publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51","capped_draws":105,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.09803328,"mean":0.0253809975,"median":0.00943521,"min":0.00639384,"recorded_attempt_count":13,"run_count":8,"total":0.20304798},"codegen_evaluated_cells":8,"conditional_success_score":40.50312266124666,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":563,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":58.7390484129797,"score":58.7390484129797},"GB2-02":{"attempts":1,"playable":39.73409165764812,"score":39.73409165764812},"GB2-03":{"attempts":1,"playable":39.9346947850152,"score":39.9346947850152},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.72914812164308,"score":28.72914812164308},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.602746186774525,"score":23.602746186774525},"GB2-08":{"attempts":1,"playable":52.27900680341929,"score":52.27900680341929}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:01Z","losses":1631,"max_score":58.7390484129797,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Minimax M3","model_slug":"minimax-minimax-m3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"MiniMax","provider_key":"minimax","rank":189,"rank_movement":3,"rank_movement_baseline_at":"2026-10-24T18:33:45Z","ranking_status":"ranked","rated_matches":3088,"rating_method":"bradley_terry_newton","raw_elo":1326.4551256575724,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.37734199593499,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":894},{"admitted_plugins":7,"attempted_matches":3608,"canonical_public_row_identity":"publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b","capped_draws":305,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.13485595000000003,"mean":0.031792056250000006,"median":0.0158481,"min":0.0111232,"recorded_attempt_count":14,"run_count":9,"total":0.38919240000000005},"codegen_evaluated_cells":9,"conditional_success_score":35.00598950203652,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":814,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":55.237211899093474,"score":55.237211899093474},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":30.557911384038643,"score":30.557911384038643},"GB2-04":{"attempts":1,"playable":42.31255022830733,"score":42.31255022830733},"GB2-05":{"attempts":1,"playable":61.9150209611777,"score":61.9150209611777},"GB2-06":{"attempts":1,"playable":16.45075893209812,"score":16.45075893209812},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.951370066675437,"score":2.4756850333377187},"GB2-08":{"attempts":1,"playable":33.61710304286491,"score":33.61710304286491}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:03:01Z","losses":2013,"max_score":61.9150209611777,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"model_display_name":"Nemotron 3 Ultra 550B A55B","model_slug":"nvidia-nemotron-3-ultra-550b-a55b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.7777777777777778,"provider":"NVIDIA","provider_key":"nvidia","rank":190,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T18:50:01Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1221.2060375823391,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.2222222222222222,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.320780185114735,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":781},{"admitted_plugins":6,"attempted_matches":3056,"canonical_public_row_identity":"publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92","capped_draws":304,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"codegen_evaluated_cells":8,"conditional_success_score":40.4224462817714,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":1069,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"tencent/hy3-preview","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":78.40222463538099,"score":78.40222463538099},"GB2-02":{"attempts":1,"playable":37.7172997033114,"score":37.7172997033114},"GB2-03":{"attempts":1,"playable":32.17182072697564,"score":32.17182072697564},"GB2-04":{"attempts":1,"playable":48.21741162726638,"score":48.21741162726638},"GB2-05":{"attempts":1,"playable":15.281248469109165,"score":15.281248469109165},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":30.744672528584836,"score":30.744672528584836}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:31Z","losses":1351,"max_score":78.40222463538099,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Hy3 Preview","model_slug":"tencent-hy3-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Tencent","provider_key":"tencent","rank":191,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:13:37Z","ranking_status":"ranked","rated_matches":3056,"rating_method":"bradley_terry_newton","raw_elo":1330.0464548990878,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.31683471132855,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":636},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gemini-3-1-pro-preview:adc4d8ce7526e784","capped_draws":347,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.06018799999999999,"mean":0.04587999999999999,"median":0.044081999999999996,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.36704000000000003},"codegen_evaluated_cells":8,"conditional_success_score":30.23223996080397,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1172,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"google","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gemini-3.1-pro-preview","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":40.92260870065246,"score":40.92260870065246},"GB2-02":{"attempts":1,"playable":42.59335095030837,"score":42.59335095030837},"GB2-03":{"attempts":1,"playable":28.2878023249647,"score":28.2878023249647},"GB2-04":{"attempts":1,"playable":42.61885107841961,"score":42.61885107841961},"GB2-05":{"attempts":1,"playable":16.048554982735062,"score":16.048554982735062},"GB2-06":{"attempts":1,"playable":14.965279068230211,"score":14.965279068230211},"GB2-07":{"attempts":1,"playable":24.38856478275738,"score":24.38856478275738},"GB2-08":{"attempts":1,"playable":32.032907798363944,"score":32.032907798363944}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:21Z","losses":2357,"max_score":42.61885107841961,"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":1.0,"provider":"Google","provider_key":"google","rank":192,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:03:33Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1194.9640630541396,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"google","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"ec4a49f2df11b5c73f719dd004f08e19276bc81ad04cf24cd1a0ae4ecebd4ec4","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.23223996080397,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":559},{"admitted_plugins":14,"attempted_matches":7186,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737","capped_draws":398,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.004911942999999999,"mean":0.0031858331662499998,"median":0.002947833025,"min":0.001831717,"recorded_attempt_count":24,"run_count":16,"total":0.05097333066},"codegen_evaluated_cells":14,"conditional_success_score":30.160865139714087,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1540,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-flash","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":10,"first_pass_rate":0.7142857142857143,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":40.79451288386059,"score":40.79451288386059},"GB2-02":{"attempts":2,"playable":39.0907729790556,"score":39.0907729790556},"GB2-03":{"attempts":1,"playable":40.87431185420583,"score":40.87431185420583},"GB2-04":{"attempts":1,"playable":41.39310769434979,"score":41.39310769434979},"GB2-05":{"attempts":2,"playable":13.266582873824856,"score":13.266582873824856},"GB2-06":{"attempts":2,"playable":14.602815999174927,"score":14.602815999174927},"GB2-07":{"attempts":2,"playable":20.027561708178887,"score":20.027561708178887},"GB2-08":{"attempts":2,"playable":31.237255125062195,"score":31.237255125062195}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-03","GB2-04"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:26Z","losses":4515,"max_score":41.39310769434979,"measured_at":null,"min_score":13.266582873824856,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"DeepSeek V4 Flash","model_slug":"deepseek-deepseek-v4-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"DeepSeek","provider_key":"deepseek","rank":193,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:14:41Z","ranking_status":"ranked","rated_matches":7185,"rating_method":"bradley_terry_newton","raw_elo":1152.064972970717,"reasoning_bracket":"balanced","reasoning_level":"Medium (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium (historical request variant 2)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-2","reasoning_bucket_label":"Medium (historical request variant 2)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced-variant-2"},"reasoning_setting":"historical-provider-setting-balanced-variant-2","repaired_admitted":4,"repaired_rate":0.2857142857142857,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.160865139714087,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1130},{"admitted_plugins":7,"attempted_matches":3590,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c","capped_draws":261,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832},"codegen_evaluated_cells":8,"conditional_success_score":34.071165458140015,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":756,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5-pro","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"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":37.2655929750953,"score":37.2655929750953},"GB2-02":{"attempts":1,"playable":39.09761928198411,"score":39.09761928198411},"GB2-03":{"attempts":1,"playable":34.527363294170684,"score":34.527363294170684},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.309841128608433,"score":19.309841128608433},"GB2-06":{"attempts":1,"playable":38.409119656428196,"score":38.409119656428196},"GB2-07":{"attempts":1,"playable":49.27165629070595,"score":49.27165629070595},"GB2-08":{"attempts":1,"playable":20.616965579987426,"score":20.616965579987426}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:54Z","losses":2079,"max_score":49.27165629070595,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"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":0.875,"provider":"Xiaomi","provider_key":"xiaomi","rank":194,"rank_movement":2,"rank_movement_baseline_at":"2026-10-24T19:23:59Z","ranking_status":"ranked","rated_matches":3590,"rating_method":"bradley_terry_newton","raw_elo":1252.2207846927763,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.812269775872515,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":755},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046","capped_draws":249,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01196465,"mean":0.00854730625,"median":0.008640199999999999,"min":0.00555765,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":15},"recorded_attempt_count":15,"run_count":9,"total":0.07763975},"codegen_evaluated_cells":9,"conditional_success_score":30.890223513319974,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1063,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling-small","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":9.439054404701363,"score":9.439054404701363},"GB2-02":{"attempts":1,"playable":42.1702722263371,"score":42.1702722263371},"GB2-03":{"attempts":1,"playable":40.14521690712411,"score":40.14521690712411},"GB2-04":{"attempts":1,"playable":45.06591040934613,"score":45.06591040934613},"GB2-05":{"attempts":1,"playable":10.097402999951962,"score":10.097402999951962},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.70284515345578,"score":8.85142257672789},"GB2-07":{"attempts":1,"playable":56.02269229466545,"score":56.02269229466545},"GB2-08":{"attempts":1,"playable":26.478393710977922,"score":26.478393710977922}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:35Z","losses":2382,"max_score":56.02269229466545,"measured_at":null,"min_score":8.85142257672789,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"model_display_name":"Inkling Small","model_slug":"thinkingmachines-inkling-small","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.8888888888888888,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":195,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:18:51Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1191.5211527823762,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":4,"repaired_rate":0.4444444444444444,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.78379569122899,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":643},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4-mini:9285646640165917","capped_draws":347,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525},"codegen_evaluated_cells":8,"conditional_success_score":29.546809505638855,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1408,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4-mini","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":33.893929052009675,"score":33.893929052009675},"GB2-02":{"attempts":1,"playable":41.53531315649431,"score":41.53531315649431},"GB2-03":{"attempts":1,"playable":45.26640895865987,"score":45.26640895865987},"GB2-04":{"attempts":1,"playable":43.537203285336005,"score":43.537203285336005},"GB2-05":{"attempts":1,"playable":11.058386954422868,"score":11.058386954422868},"GB2-06":{"attempts":1,"playable":30.97096724237314,"score":30.97096724237314},"GB2-07":{"attempts":1,"playable":6.4148569893735035,"score":6.4148569893735035},"GB2-08":{"attempts":1,"playable":23.697410406441467,"score":23.697410406441467}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:58Z","losses":2280,"max_score":45.26640895865987,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":196,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:10:19Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1162.6591853166265,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.546809505638855,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":400},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650","capped_draws":186,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.014791950000000002,"mean":0.007616140625,"median":0.005694875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":9,"total":0.072064},"codegen_evaluated_cells":9,"conditional_success_score":30.49497098599306,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1102,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling-small","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":21.800098368324253,"score":21.800098368324253},"GB2-02":{"attempts":1,"playable":41.00587206875293,"score":41.00587206875293},"GB2-03":{"attempts":1,"playable":56.9002243892639,"score":56.9002243892639},"GB2-04":{"attempts":1,"playable":43.945090981756195,"score":43.945090981756195},"GB2-05":{"attempts":1,"playable":5.47119175608054,"score":5.47119175608054},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.792700159045285,"score":8.396350079522643},"GB2-07":{"attempts":1,"playable":31.963370070627274,"score":31.963370070627274},"GB2-08":{"attempts":1,"playable":26.081220094094103,"score":26.081220094094103}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:14Z","losses":2390,"max_score":56.9002243892639,"measured_at":null,"min_score":5.47119175608054,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"model_display_name":"Inkling Small","model_slug":"thinkingmachines-inkling-small","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.8888888888888888,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":197,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:01:26Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1173.8285561370335,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling-small","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.3333333333333333,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.44542722605273,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":596},{"admitted_plugins":14,"attempted_matches":7198,"canonical_public_row_identity":"publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296","capped_draws":622,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.021206376000000002,"mean":0.01337795025,"median":0.01381146,"min":0.006392298,"recorded_attempt_count":38,"run_count":16,"total":0.21404720400000002},"codegen_evaluated_cells":16,"conditional_success_score":34.8714182629611,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1562,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meituan/longcat-2.0","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":42.64792367967752,"score":42.64792367967752},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.47615436428729,"score":20.238077182143645},"GB2-03":{"attempts":2,"playable":34.74533844001101,"score":34.74533844001101},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":46.490509638186836,"score":23.245254819093418},"GB2-05":{"attempts":2,"playable":12.113565622089428,"score":12.113565622089428},"GB2-06":{"attempts":2,"playable":37.062036466520084,"score":37.062036466520084},"GB2-07":{"attempts":2,"playable":34.98958517305047,"score":34.98958517305047},"GB2-08":{"attempts":2,"playable":30.446232719866195,"score":30.446232719866195}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:47Z","losses":4183,"max_score":42.64792367967752,"measured_at":null,"min_score":12.113565622089428,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"LongCat 2.0","model_slug":"meituan-longcat-2-0","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Meituan","provider_key":"meituan","rank":198,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:18:28Z","ranking_status":"ranked","rated_matches":7198,"rating_method":"bradley_terry_newton","raw_elo":1230.61895630033,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":6,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.436001762806473,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1453},{"admitted_plugins":7,"attempted_matches":3572,"canonical_public_row_identity":"publication-row.v1:mixed:mistralai-mistral-medium-3-5:8de2e9417bacc9d3","capped_draws":256,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281},"codegen_evaluated_cells":8,"conditional_success_score":33.0533889749281,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1088,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"mistralai/mistral-medium-3-5","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01"],"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":44.600427873465655,"score":44.600427873465655},"GB2-03":{"attempts":1,"playable":37.717213210184646,"score":37.717213210184646},"GB2-04":{"attempts":1,"playable":39.8589469664451,"score":39.8589469664451},"GB2-05":{"attempts":1,"playable":37.405769033347546,"score":37.405769033347546},"GB2-06":{"attempts":1,"playable":25.760472170355964,"score":25.760472170355964},"GB2-07":{"attempts":1,"playable":13.007677305839454,"score":13.007677305839454},"GB2-08":{"attempts":1,"playable":33.02321626485831,"score":33.02321626485831}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:45Z","losses":1937,"max_score":44.600427873465655,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Mistral Medium 3.5","model_slug":"mistralai-mistral-medium-3-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Mistral","provider_key":"mistral","rank":199,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:06:11Z","ranking_status":"ranked","rated_matches":3572,"rating_method":"bradley_terry_newton","raw_elo":1226.80079084137,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":4,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":28.921715353062087,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":547},{"admitted_plugins":6,"attempted_matches":3078,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-pro-0813:45ec16f47504b5f5","capped_draws":226,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784},"codegen_evaluated_cells":8,"conditional_success_score":38.00017736184483,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":794,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro-0813","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-05"],"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":35.58112687581995,"score":35.58112687581995},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.23182617727008,"score":36.23182617727008},"GB2-04":{"attempts":1,"playable":44.65848911173256,"score":44.65848911173256},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.54592532752725,"score":61.54592532752725},"GB2-07":{"attempts":1,"playable":23.406016232255876,"score":23.406016232255876},"GB2-08":{"attempts":1,"playable":26.57768044646329,"score":26.57768044646329}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T23:06:11Z","losses":1598,"max_score":61.54592532752725,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"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":0.75,"provider":"DeepSeek","provider_key":"deepseek","rank":200,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:18:37Z","ranking_status":"ranked","rated_matches":3078,"rating_method":"bradley_terry_newton","raw_elo":1317.6029364536969,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":28.500133021383622,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":686},{"admitted_plugins":6,"attempted_matches":3106,"canonical_public_row_identity":"publication-row.v1:mixed:deepseek-deepseek-v4-pro:c11fecb63644464d","capped_draws":280,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100005},"codegen_evaluated_cells":8,"conditional_success_score":37.61003439690057,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":769,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"deepseek/deepseek-v4-pro","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-06"],"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":29.11477386369124,"score":29.11477386369124},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.453259736857405,"score":42.453259736857405},"GB2-04":{"attempts":1,"playable":45.16773876484072,"score":45.16773876484072},"GB2-05":{"attempts":1,"playable":34.512499131279434,"score":34.512499131279434},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":54.39129070925759,"score":54.39129070925759},"GB2-08":{"attempts":1,"playable":20.020644175477056,"score":20.020644175477056}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:27:54Z","losses":1622,"max_score":54.39129070925759,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"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":0.75,"provider":"DeepSeek","provider_key":"deepseek","rank":201,"rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T19:04:02Z","ranking_status":"ranked","rated_matches":3106,"rating_method":"bradley_terry_newton","raw_elo":1309.3074714709257,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":28.20752579767543,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":715},{"admitted_plugins":6,"attempted_matches":3114,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash:a0af36e4d0bc99b5","capped_draws":218,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.122172,"mean":0.06676931250000001,"median":0.06893550000000001,"min":0.025422,"recorded_attempt_count":14,"run_count":8,"total":0.5341545},"codegen_evaluated_cells":8,"conditional_success_score":37.6074197484865,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":539,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash","reasoning_catalog_sha256":"36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":60.19476545017041,"score":60.19476545017041},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.945090981756195,"score":43.945090981756195},"GB2-05":{"attempts":1,"playable":17.77496945660652,"score":17.77496945660652},"GB2-06":{"attempts":1,"playable":18.610392496017614,"score":18.610392496017614},"GB2-07":{"attempts":1,"playable":54.57289357501711,"score":54.57289357501711},"GB2-08":{"attempts":1,"playable":30.54640653135114,"score":30.54640653135114}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:28:03Z","losses":1738,"max_score":60.19476545017041,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"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":0.75,"provider":"Google","provider_key":"google","rank":202,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:03:33Z","ranking_status":"ranked","rated_matches":3114,"rating_method":"bradley_terry_newton","raw_elo":1263.9243423871405,"reasoning_bracket":"baseline","reasoning_level":"Low (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low (historical request variant 1)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-1","reasoning_bucket_label":"Low (historical request variant 1)","reasoning_catalog_sha256":"36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline-variant-1"},"reasoning_setting":"historical-provider-setting-baseline-variant-1","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":28.205564811364873,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":837},{"admitted_plugins":12,"attempted_matches":6128,"canonical_public_row_identity":"publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e","capped_draws":354,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395},"codegen_evaluated_cells":16,"conditional_success_score":38.21150270835112,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1608,"eligibility_flag":true,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":19.983883028509617,"score":19.983883028509617},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.967075478045246,"score":21.983537739022623},"GB2-03":{"attempts":2,"playable":49.256787729934594,"score":49.256787729934594},"GB2-04":{"attempts":2,"playable":41.28931268099445,"score":41.28931268099445},"GB2-05":{"attempts":2,"playable":27.48232370441826,"score":27.48232370441826},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.38405496426927,"score":13.692027482134636},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":23.602746186774525,"score":11.801373093387262},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.72583789386302,"score":36.36291894693151}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:58:44Z","losses":3196,"max_score":49.256787729934594,"measured_at":null,"min_score":11.801373093387262,"model_code_failure_rate":0.25,"model_code_failures":4,"model_display_name":"Inkling","model_slug":"thinkingmachines-inkling","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":203,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:15:25Z","ranking_status":"ranked","rated_matches":6125,"rating_method":"bradley_terry_newton","raw_elo":1297.5107930814056,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":5,"repaired_rate":0.3125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":27.73152055066662,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1321},{"admitted_plugins":6,"attempted_matches":3070,"canonical_public_row_identity":"publication-row.v1:mixed:stealth-space-bunny-alpha:24efcb34bbc5a31b","capped_draws":144,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16},"recorded_attempt_count":16,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":36.85468135544677,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":942,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stealth/space-bunny-alpha","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":40.89995054217238,"score":40.89995054217238},"GB2-03":{"attempts":1,"playable":36.019168742653534,"score":36.019168742653534},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":1,"playable":43.57277847647596,"score":43.57277847647596},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.150349823323733,"score":26.150349823323733},"GB2-08":{"attempts":1,"playable":30.744672528584836,"score":30.744672528584836}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:59Z","losses":1539,"max_score":43.74116801947021,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Space Bunny Alpha","model_slug":"stealth-space-bunny-alpha","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Other","provider_key":"other","rank":204,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:16:18Z","ranking_status":"ranked","rated_matches":3070,"rating_method":"bradley_terry_newton","raw_elo":1301.2969286174637,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"0cd5f7de722e38bb7fca8c8391c8fb3d3706fdcb857e0f80c5d271dcce91369a","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":5,"repaired_rate":0.625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":27.64101101658508,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":589},{"admitted_plugins":14,"attempted_matches":7169,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7","capped_draws":576,"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0481474,"mean":0.03800683125,"median":0.037386975,"min":0.02957195,"recorded_attempt_count":48,"run_count":16,"total":0.6081093000000001},"codegen_evaluated_cells":16,"conditional_success_score":31.25603935635757,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1904,"eligibility_flag":true,"entry_count":14,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.5-flash-lite","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":41.02127603100788,"score":41.02127603100788},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.65023818652617,"score":21.825119093263083},"GB2-03":{"attempts":2,"playable":42.13899389304992,"score":42.13899389304992},"GB2-04":{"attempts":2,"playable":42.46492327063312,"score":42.46492327063312},"GB2-05":{"attempts":2,"playable":15.760817483559318,"score":15.760817483559318},"GB2-06":{"attempts":2,"playable":13.87579640274205,"score":13.87579640274205},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.838205128007385,"score":10.419102564003692},"GB2-08":{"attempts":2,"playable":30.298064455334675,"score":30.298064455334675}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:07:53Z","losses":4151,"max_score":42.46492327063312,"measured_at":null,"min_score":10.419102564003692,"model_code_failure_rate":0.125,"model_code_failures":2,"model_display_name":"Gemini 3.5 Flash Lite","model_slug":"google-gemini-3-5-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Google","provider_key":"google","rank":205,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:11:18Z","ranking_status":"ranked","rated_matches":7166,"rating_method":"bradley_terry_newton","raw_elo":1193.1372316093682,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":27.225511649199216,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1111},{"admitted_plugins":12,"attempted_matches":6170,"canonical_public_row_identity":"publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8","capped_draws":252,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.103943664,"mean":0.0866474535,"median":0.088847748,"min":0.062759676,"recorded_attempt_count":70,"run_count":16,"total":1.386359256},"codegen_evaluated_cells":16,"conditional_success_score":36.72306142822723,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1320,"eligibility_flag":true,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meituan/longcat-2.0","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.227623284677975,"score":21.613811642338987},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.61869369407654,"score":19.80934684703827},"GB2-04":{"attempts":2,"playable":38.345326347520455,"score":38.345326347520455},"GB2-05":{"attempts":2,"playable":33.459854477038505,"score":33.459854477038505},"GB2-06":{"attempts":2,"playable":25.080195711838712,"score":25.080195711838712},"GB2-07":{"attempts":2,"playable":37.718099359302876,"score":37.718099359302876},"GB2-08":{"attempts":2,"playable":39.61163712313554,"score":39.61163712313554}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:53Z","losses":3431,"max_score":39.61163712313554,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":4,"model_display_name":"LongCat 2.0","model_slug":"meituan-longcat-2-0","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Meituan","provider_key":"meituan","rank":206,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:17:03Z","ranking_status":"ranked","rated_matches":6169,"rating_method":"bradley_terry_newton","raw_elo":1256.772796373362,"reasoning_bracket":"balanced","reasoning_level":"Enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Enabled","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.1875,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.954783938526667,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":59,"wins":1418},{"admitted_plugins":12,"attempted_matches":6156,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063","capped_draws":415,"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575},"codegen_evaluated_cells":16,"conditional_success_score":34.38361069458283,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":1275,"eligibility_flag":true,"entry_count":12,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.4-nano","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.3125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":46.370858714507264,"score":46.370858714507264},"GB2-02":{"attempts":2,"playable":40.317173409221304,"score":40.317173409221304},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.634106411260305,"score":17.317053205630152},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.365680401084564,"score":8.365680401084564},"GB2-06":{"attempts":2,"playable":41.57725407458532,"score":41.57725407458532},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":21.23452636920462,"score":10.61726318460231},"GB2-08":{"attempts":2,"playable":48.185675482216446,"score":48.185675482216446}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:49Z","losses":3477,"max_score":48.185675482216446,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":4,"model_display_name":"GPT-5.4 Nano","model_slug":"gpt-5-4-nano","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"OpenAI","provider_key":"openai","rank":207,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:42Z","ranking_status":"ranked","rated_matches":6156,"rating_method":"bradley_terry_newton","raw_elo":1245.6915040731417,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":7,"repaired_rate":0.4375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.59386980898092,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1404},{"admitted_plugins":6,"attempted_matches":3110,"canonical_public_row_identity":"publication-row.v1:mixed:stepfun-step-3-7-flash:c3a29f7356dfe558","capped_draws":379,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0442025,"mean":0.017142385,"median":0.01322286,"min":0.01037917,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.13713908},"codegen_evaluated_cells":8,"conditional_success_score":35.24710527286814,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":489,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-3.7-flash","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":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":10.356509846524498,"score":10.356509846524498},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":34.847507100089665,"score":34.847507100089665},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":50.6790792678975,"score":50.6790792678975},"GB2-06":{"attempts":1,"playable":45.34389370282634,"score":45.34389370282634},"GB2-07":{"attempts":1,"playable":39.01539001530872,"score":39.01539001530872},"GB2-08":{"attempts":1,"playable":31.240251704562134,"score":31.240251704562134}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:58:20Z","losses":1849,"max_score":50.6790792678975,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Step 3.7 Flash","model_slug":"stepfun-step-3-7-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"StepFun","provider_key":"stepfun","rank":208,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:58:20Z","ranking_status":"ranked","rated_matches":3110,"rating_method":"bradley_terry_newton","raw_elo":1262.2459477996617,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.435328954651105,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":772},{"admitted_plugins":7,"attempted_matches":3609,"canonical_public_row_identity":"publication-row.v1:mixed:bytedance-seed-seed-2-0-code:e037862ab5c7ecb3","capped_draws":409,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998},"codegen_evaluated_cells":8,"conditional_success_score":29.8828096032802,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":843,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"bytedance-seed/seed-2.0-code","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":23.809971725447504,"score":23.809971725447504},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.99221229282847,"score":45.99221229282847},"GB2-04":{"attempts":1,"playable":42.82300100995158,"score":42.82300100995158},"GB2-05":{"attempts":1,"playable":16.815836246691234,"score":16.815836246691234},"GB2-06":{"attempts":1,"playable":18.043488233941947,"score":18.043488233941947},"GB2-07":{"attempts":1,"playable":29.0679929757488,"score":29.0679929757488},"GB2-08":{"attempts":1,"playable":32.62716473835184,"score":32.62716473835184}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:02:43Z","losses":2195,"max_score":45.99221229282847,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"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":0.875,"provider":"ByteDance","provider_key":"bytedance-seed","rank":209,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:23:41Z","ranking_status":"ranked","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1181.3322338754683,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":26.147458402870175,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":570},{"admitted_plugins":8,"attempted_matches":4088,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5","capped_draws":192,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"codegen_evaluated_cells":8,"conditional_success_score":25.851694678407355,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1103,"eligibility_flag":true,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-5.6-luna","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":26.115784110806082,"score":26.115784110806082},"GB2-02":{"attempts":1,"playable":42.38183447863047,"score":42.38183447863047},"GB2-03":{"attempts":1,"playable":29.69456742461558,"score":29.69456742461558},"GB2-04":{"attempts":1,"playable":38.93742781528057,"score":38.93742781528057},"GB2-05":{"attempts":1,"playable":24.49539898711905,"score":24.49539898711905},"GB2-06":{"attempts":1,"playable":19.176222096442736,"score":19.176222096442736},"GB2-07":{"attempts":1,"playable":15.03523943046976,"score":15.03523943046976},"GB2-08":{"attempts":1,"playable":10.977083083894604,"score":10.977083083894604}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:43Z","losses":2569,"max_score":42.38183447863047,"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":1.0,"provider":"OpenAI","provider_key":"openai","rank":210,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:15:32Z","ranking_status":"ranked","rated_matches":4088,"rating_method":"bradley_terry_newton","raw_elo":1146.8398458065342,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":25.851694678407355,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":416},{"admitted_plugins":11,"attempted_matches":5640,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3","capped_draws":451,"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.00295601625,"mean":0.0023887339375,"median":0.002303478175,"min":0.0017364400000000001,"recorded_attempt_count":25,"run_count":16,"total":0.038219743},"codegen_evaluated_cells":16,"conditional_success_score":35.59420974621313,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1439,"eligibility_flag":true,"entry_count":11,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":46.27747280682601,"score":46.27747280682601},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":41.21768189954597,"score":20.608840949772986},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"playable":42.006153905963735,"score":42.006153905963735},"GB2-05":{"attempts":2,"playable":16.24034668491148,"score":16.24034668491148},"GB2-06":{"attempts":2,"playable":40.24215751293782,"score":40.24215751293782},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":29.26169882068973,"score":14.630849410344865},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":33.91395659261711,"score":16.956978296308556}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:08:58Z","losses":3029,"max_score":46.27747280682601,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.3125,"model_code_failures":5,"model_display_name":"MiMo-V2.5","model_slug":"xiaomi-mimo-v2-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.6875,"provider":"Xiaomi","provider_key":"xiaomi","rank":211,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:13:30Z","ranking_status":"ranked","rated_matches":5640,"rating_method":"bradley_terry_newton","raw_elo":1264.8479276284413,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled (historical request variant 1)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-1","reasoning_bucket_label":"Reasoning disabled (historical request variant 1)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline-variant-1"},"reasoning_setting":"historical-provider-setting-baseline-variant-1","repaired_admitted":4,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":24.62034994588318,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1172},{"admitted_plugins":6,"attempted_matches":3088,"canonical_public_row_identity":"publication-row.v1:mixed:openai-gpt-oss-120b:07d17099885c6bdb","capped_draws":309,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999},"codegen_evaluated_cells":8,"conditional_success_score":32.43136792654443,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":824,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"openai/gpt-oss-120b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":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":41.02127603100788,"score":41.02127603100788},"GB2-02":{"attempts":1,"playable":43.33329461578827,"score":43.33329461578827},"GB2-03":{"attempts":1,"playable":36.33811190496322,"score":36.33811190496322},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.66490775172327,"score":15.66490775172327},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.874188292553626,"score":28.874188292553626},"GB2-08":{"attempts":1,"playable":29.356428963230368,"score":29.356428963230368}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:44:02Z","losses":1749,"max_score":43.33329461578827,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"GPT-OSS 120B","model_slug":"openai-gpt-oss-120b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"OpenAI","provider_key":"openai","rank":212,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:32Z","ranking_status":"ranked","rated_matches":3088,"rating_method":"bradley_terry_newton","raw_elo":1229.7574917922695,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":24.323525944908326,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":515},{"admitted_plugins":5,"attempted_matches":2504,"canonical_public_row_identity":"publication-row.v1:mixed:inception-mercury-2-5-preview:df3dbf369397b893","capped_draws":25,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612510000000001},"codegen_evaluated_cells":8,"conditional_success_score":38.73745480702932,"contributing_entrants":null,"distinct_rated_opponents":253,"draws":881,"eligibility_flag":true,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-2.5-preview","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.27605906017271,"score":42.27605906017271},"GB2-03":{"attempts":1,"playable":45.99221229282847,"score":45.99221229282847},"GB2-04":{"attempts":1,"playable":44.04703672763066,"score":44.04703672763066},"GB2-05":{"attempts":1,"playable":39.71974051850676,"score":39.71974051850676},"GB2-06":{"attempts":1,"playable":21.652225436008024,"score":21.652225436008024},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T00:22:52Z","losses":1154,"max_score":45.99221229282847,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.375,"model_code_failures":3,"model_display_name":"Mercury 2.5 Preview","model_slug":"inception-mercury-2-5-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.625,"provider":"Inception","provider_key":"inception","rank":213,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:23:53Z","ranking_status":"ranked","rated_matches":2504,"rating_method":"bradley_terry_newton","raw_elo":1305.8882209903363,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":24.21090925439333,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":469},{"admitted_plugins":9,"attempted_matches":4612,"canonical_public_row_identity":"publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89","capped_draws":536,"codegen_cost_usd":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0456916,"mean":0.031545040625,"median":0.035551075,"min":0.01864685,"recorded_attempt_count":35,"run_count":16,"total":0.5047206500000001},"codegen_evaluated_cells":14,"conditional_success_score":34.08551596993852,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1638,"eligibility_flag":true,"entry_count":9,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.14285714285714285,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.615015535438562,"score":12.807507767719281},"GB2-02":{"attempts":2,"playable":40.95190563954942,"score":40.95190563954942},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":2,"playable":30.280124901292105,"score":30.280124901292105},"GB2-06":{"attempts":1,"playable":34.048295254900594,"score":34.048295254900594},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":32.42907596665441,"score":32.42907596665441}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:54Z","losses":2315,"max_score":41.18867852179604,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.35714285714285715,"model_code_failures":5,"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":0.6428571428571429,"provider":"NVIDIA","provider_key":"nvidia","rank":214,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:21:09Z","ranking_status":"ranked","rated_matches":4612,"rating_method":"bradley_terry_newton","raw_elo":1260.275066393005,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":7,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":23.96319850648898,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":659},{"admitted_plugins":6,"attempted_matches":3106,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-glimmer-30b:a614a905445f79d1","capped_draws":291,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.05850166},"codegen_evaluated_cells":8,"conditional_success_score":31.570812110626317,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":793,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-glimmer-30b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-06"],"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,"playable":36.275058031055394,"score":36.275058031055394},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.643130090378534,"score":44.643130090378534},"GB2-04":{"attempts":1,"playable":43.74116801947021,"score":43.74116801947021},"GB2-05":{"attempts":1,"playable":7.787744588818808,"score":7.787744588818808},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.12544240344881,"score":27.12544240344881},"GB2-08":{"attempts":1,"playable":29.852329530586164,"score":29.852329530586164}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:42Z","losses":1805,"max_score":44.643130090378534,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Muse Glimmer 30B","model_slug":"meta-muse-glimmer-30b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Meta","provider_key":"meta","rank":215,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:04:49Z","ranking_status":"ranked","rated_matches":3106,"rating_method":"bradley_terry_newton","raw_elo":1198.9374369162947,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":23.678109082969737,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":508},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:recursive-flint-v1-0:4c8db66aef6b8bdb","capped_draws":75,"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":26.993335499421814,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":733,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"recursive/flint-v1.0:free","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","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":[],"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":0.875,"provider":"Other","provider_key":"other","rank":216,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:56Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1137.2510862621018,"reasoning_bracket":"balanced","reasoning_level":"Enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"recursive/flint-v1.0","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"unknown_legacy","provider_setting_label":"Enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":23.619168561994087,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":532},{"admitted_plugins":6,"attempted_matches":3092,"canonical_public_row_identity":"publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3","capped_draws":111,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":31.167893300840642,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":532,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"cohere/north-mini-code:free","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":3,"first_pass_rate":0.375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":21.734159723041202,"score":21.734159723041202},"GB2-04":{"attempts":1,"playable":41.18867852179604,"score":41.18867852179604},"GB2-05":{"attempts":1,"playable":46.457859448926094,"score":46.457859448926094},"GB2-06":{"attempts":1,"playable":17.24808744063479,"score":17.24808744063479},"GB2-07":{"attempts":1,"playable":30.22875643334849,"score":30.22875643334849},"GB2-08":{"attempts":1,"playable":30.149818237297243,"score":30.149818237297243}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:34Z","losses":1927,"max_score":46.457859448926094,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"North Mini Code","model_slug":"cohere-north-mini-code","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Cohere","provider_key":"cohere","rank":217,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:23:41Z","ranking_status":"ranked","rated_matches":3092,"rating_method":"bradley_terry_newton","raw_elo":1207.7906799120262,"reasoning_bracket":"balanced","reasoning_level":"Enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"unknown_legacy","provider_setting_label":"Enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":23.37591997563048,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":633},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8","capped_draws":122,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.09705768000000001,"mean":0.0730637925,"median":0.07051098,"min":0.05225028,"recorded_attempt_count":17,"run_count":8,"total":0.58451034},"codegen_evaluated_cells":8,"conditional_success_score":26.425793456895867,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":812,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"minimax/minimax-m3","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":18.574661114006865,"score":18.574661114006865},"GB2-02":{"attempts":1,"playable":39.840133013450746,"score":39.840133013450746},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":1,"playable":2.1672981238426035,"score":2.1672981238426035},"GB2-06":{"attempts":1,"playable":17.1342988476045,"score":17.1342988476045},"GB2-07":{"attempts":1,"playable":42.40144571404132,"score":42.40144571404132},"GB2-08":{"attempts":1,"playable":24.49214374103919,"score":24.49214374103919}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:28Z","losses":2310,"max_score":42.40144571404132,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Minimax M3","model_slug":"minimax-minimax-m3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"MiniMax","provider_key":"minimax","rank":218,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T19:07:40Z","ranking_status":"ranked","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1105.7630945891465,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":7,"repaired_rate":0.875,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":23.122569274783885,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":472},{"admitted_plugins":7,"attempted_matches":3558,"canonical_public_row_identity":"publication-row.v1:mixed:mistralai-mistral-medium-3-5:e327e1c801399a5f","capped_draws":171,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167188},"codegen_evaluated_cells":8,"conditional_success_score":26.09843363254638,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":888,"eligibility_flag":true,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"mistralai/mistral-medium-3-5","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":12.087417348913485,"score":12.087417348913485},"GB2-02":{"attempts":1,"playable":41.111782530814864,"score":41.111782530814864},"GB2-03":{"attempts":1,"playable":34.527363294170684,"score":34.527363294170684},"GB2-04":{"attempts":1,"playable":33.80482228941814,"score":33.80482228941814},"GB2-05":{"attempts":1,"playable":12.978696108137019,"score":12.978696108137019},"GB2-06":{"attempts":1,"playable":17.929981650115,"score":17.929981650115},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":30.248972206255498,"score":30.248972206255498}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:10Z","losses":2263,"max_score":41.111782530814864,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.125,"model_code_failures":1,"model_display_name":"Mistral Medium 3.5","model_slug":"mistralai-mistral-medium-3-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.875,"provider":"Mistral","provider_key":"mistral","rank":219,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:14:34Z","ranking_status":"ranked","rated_matches":3558,"rating_method":"bradley_terry_newton","raw_elo":1147.8079820201995,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"41a4f70a9c981ec0af3df7dbcf4a7205c7cc0055a2d425c452253f557de740ff","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":22.836129428478085,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":407},{"admitted_plugins":6,"attempted_matches":3064,"canonical_public_row_identity":"publication-row.v1:mixed:inception-mercury-2-5-preview:ff9c957a999941a2","capped_draws":312,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001},"codegen_evaluated_cells":8,"conditional_success_score":28.181506932714928,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1052,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-2.5-preview","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-05"],"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":27.416518712100512,"score":27.416518712100512},"GB2-02":{"attempts":1,"playable":42.487598451954895,"score":42.487598451954895},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.039855920000804,"score":39.039855920000804},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":15.079751586405402,"score":15.079751586405402},"GB2-07":{"attempts":1,"playable":14.023281885914468,"score":14.023281885914468},"GB2-08":{"attempts":1,"playable":31.0420350399135,"score":31.0420350399135}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:13Z","losses":1740,"max_score":42.487598451954895,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Mercury 2.5 Preview","model_slug":"inception-mercury-2-5-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Inception","provider_key":"inception","rank":220,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:24:11Z","ranking_status":"ranked","rated_matches":3064,"rating_method":"bradley_terry_newton","raw_elo":1172.1941467629624,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":21.136130199536197,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":272},{"admitted_plugins":6,"attempted_matches":3078,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemma-4-31b-it:abc3570dbe96b52d","capped_draws":276,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.00371018,"mean":0.00186558375,"median":0.00131646,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.01492467},"codegen_evaluated_cells":8,"conditional_success_score":27.118516508055745,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":947,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemma-4-31b-it","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.94616361682421,"score":39.94616361682421},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":45.981972677383034,"score":45.981972677383034},"GB2-05":{"attempts":1,"playable":16.815836246691234,"score":16.815836246691234},"GB2-06":{"attempts":1,"playable":16.792700159045285,"score":16.792700159045285},"GB2-07":{"attempts":1,"playable":10.349223513274715,"score":10.349223513274715},"GB2-08":{"attempts":1,"playable":32.82520283511599,"score":32.82520283511599}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:37Z","losses":1835,"max_score":45.981972677383034,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"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":0.75,"provider":"Google","provider_key":"google","rank":221,"rank_movement":1,"rank_movement_baseline_at":"2026-10-24T17:49:37Z","ranking_status":"ranked","rated_matches":3078,"rating_method":"bradley_terry_newton","raw_elo":1122.879480987074,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":20.338887381041808,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":296},{"admitted_plugins":6,"attempted_matches":3078,"canonical_public_row_identity":"publication-row.v1:mixed:inception-mercury-2-5-preview:f07bc2e66f8341c5","capped_draws":288,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"codegen_evaluated_cells":8,"conditional_success_score":27.105840250628034,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1024,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-2.5-preview","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.227623284677975,"score":43.227623284677975},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.779703297584575,"score":40.779703297584575},"GB2-05":{"attempts":1,"playable":16.815836246691234,"score":16.815836246691234},"GB2-06":{"attempts":1,"playable":18.043488233941947,"score":18.043488233941947},"GB2-07":{"attempts":1,"playable":10.349223513274715,"score":10.349223513274715},"GB2-08":{"attempts":1,"playable":33.41916692759774,"score":33.41916692759774}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:49Z","losses":1798,"max_score":43.227623284677975,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Mercury 2.5 Preview","model_slug":"inception-mercury-2-5-preview","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Inception","provider_key":"inception","rank":222,"rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T19:23:41Z","ranking_status":"ranked","rated_matches":3078,"rating_method":"bradley_terry_newton","raw_elo":1125.1197613709048,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":20.329380187971026,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":256},{"admitted_plugins":6,"attempted_matches":3114,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af","capped_draws":377,"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":2,"max":0.0149315,"mean":0.0101355,"median":0.010566625,"min":0.00402875,"recorded_attempt_count":18,"run_count":8,"total":0.081084},"codegen_evaluated_cells":8,"conditional_success_score":26.819741832901318,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":708,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.1-flash-lite","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.25,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":33.79459575009096,"score":33.79459575009096},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.43520532438199,"score":43.43520532438199},"GB2-05":{"attempts":1,"playable":17.007657862391902,"score":17.007657862391902},"GB2-06":{"attempts":1,"playable":22.99271296083545,"score":22.99271296083545},"GB2-07":{"attempts":1,"playable":6.414856989373502,"score":6.414856989373502},"GB2-08":{"attempts":1,"playable":37.27342211033409,"score":37.27342211033409}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:36Z","losses":1990,"max_score":43.43520532438199,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Gemini 3.1 Flash Lite","model_slug":"google-gemini-3-1-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Google","provider_key":"google","rank":223,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:55:15Z","ranking_status":"ranked","rated_matches":3114,"rating_method":"bradley_terry_newton","raw_elo":1111.052391732184,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":4,"repaired_rate":0.5,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":20.11480637467599,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":416},{"admitted_plugins":5,"attempted_matches":2576,"canonical_public_row_identity":"publication-row.v1:mixed:elorian-glimpse:555f4fac924f658c","capped_draws":42,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.18443460000000003},"codegen_evaluated_cells":8,"conditional_success_score":31.169050116073436,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":413,"eligibility_flag":true,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"elorian/glimpse","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-05","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":12.697609082628016,"score":12.697609082628016},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":54.58569099801185,"score":54.58569099801185},"GB2-04":{"attempts":1,"playable":40.67743529617756,"score":40.67743529617756},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":16.446067400476796,"score":16.446067400476796},"GB2-08":{"attempts":1,"playable":31.43844780307297,"score":31.43844780307297}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":1632,"max_score":54.58569099801185,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.375,"model_code_failures":3,"model_display_name":"Glimpse","model_slug":"elorian-glimpse","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.625,"provider":"Other","provider_key":"other","rank":224,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:56Z","ranking_status":"ranked","rated_matches":2576,"rating_method":"bradley_terry_newton","raw_elo":1214.6846598118118,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":19.480656322545897,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":531},{"admitted_plugins":6,"attempted_matches":3072,"canonical_public_row_identity":"publication-row.v1:mixed:thinkingmachines-inkling:642fa454e575cb98","capped_draws":79,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04901556,"mean":0.031135205,"median":0.02897688,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.24908164000000002},"codegen_evaluated_cells":8,"conditional_success_score":25.621038507287825,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":692,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"thinkingmachines/inkling","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":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":17.867482377220473,"score":17.867482377220473},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":37.07559594034441,"score":37.07559594034441},"GB2-04":{"attempts":1,"playable":41.69967780442835,"score":41.69967780442835},"GB2-05":{"attempts":1,"playable":14.130138135939301,"score":14.130138135939301},"GB2-06":{"attempts":1,"playable":24.10397630500886,"score":24.10397630500886},"GB2-07":{"attempts":1,"playable":18.849360480785553,"score":18.849360480785553},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:27:50Z","losses":2012,"max_score":41.69967780442835,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":2,"model_display_name":"Inkling","model_slug":"thinkingmachines-inkling","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Thinking Machines","provider_key":"thinkingmachines","rank":225,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T16:27:50Z","ranking_status":"ranked","rated_matches":3071,"rating_method":"bradley_terry_newton","raw_elo":1131.7143380254963,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":19.21577888046587,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":367},{"admitted_plugins":10,"attempted_matches":5078,"canonical_public_row_identity":"publication-row.v1:mixed:inclusionai-ling-3-0-flash:24f19899613f595d","capped_draws":422,"codegen_cost_usd":{"admitted_cell_count":10,"cell_count":8,"cost_basis_counts":{"provider_reported":40},"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":40,"run_count":16,"total":0.0},"codegen_evaluated_cells":16,"conditional_success_score":32.374396733504135,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1457,"eligibility_flag":true,"entry_count":10,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inclusionai/ling-3.0-flash:free","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":6,"first_pass_rate":0.375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"playable":35.66701204114969,"score":35.66701204114969},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.58211986231627,"score":20.291059931158134},"GB2-03":{"attempts":2,"playable":28.97412060092674,"score":28.97412060092674},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.65848911173256,"score":22.32924455586628},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.413527979148201,"score":9.413527979148201},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":34.95111080575137,"score":34.95111080575137}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:03:01Z","losses":2919,"max_score":35.66701204114969,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.375,"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":0.625,"provider":"InclusionAI","provider_key":"inclusionai","rank":226,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:55:41Z","ranking_status":"ranked","rated_matches":5078,"rating_method":"bradley_terry_newton","raw_elo":1167.1705656815589,"reasoning_bracket":"baseline","reasoning_level":"None (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None (historical request variant 2)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-2","reasoning_bucket_label":"None (historical request variant 2)","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline-variant-2"},"reasoning_setting":"historical-provider-setting-baseline-variant-2","repaired_admitted":4,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":18.95325948925005,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":702},{"admitted_plugins":6,"attempted_matches":3056,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a","capped_draws":108,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696000000001},"codegen_evaluated_cells":9,"conditional_success_score":25.93731532554575,"contributing_entrants":null,"distinct_rated_opponents":254,"draws":800,"eligibility_flag":true,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.7-plus","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-03","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":18.978501132405704,"score":9.489250566202852},"GB2-02":{"attempts":1,"playable":38.67309283043393,"score":38.67309283043393},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.76186614472562,"score":43.76186614472562},"GB2-05":{"attempts":1,"playable":32.19822597201881,"score":32.19822597201881},"GB2-06":{"attempts":1,"playable":13.933614538180397,"score":13.933614538180397},"GB2-07":{"attempts":1,"playable":8.07859133551002,"score":8.07859133551002},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-25T21:42:33Z","losses":1918,"max_score":43.76186614472562,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.3333333333333333,"model_code_failures":3,"model_display_name":"Qwen3.7 Plus","model_slug":"qwen-qwen3-7-plus","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.6666666666666666,"provider":"Alibaba","provider_key":"qwen","rank":227,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:24:23Z","ranking_status":"ranked","rated_matches":3055,"rating_method":"bradley_terry_newton","raw_elo":1130.7292961346693,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.2222222222222222,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":18.266830173383955,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":337},{"admitted_plugins":5,"attempted_matches":2599,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8","capped_draws":259,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0422995,"mean":0.027492531250000004,"median":0.025548,"min":0.0204145,"recorded_attempt_count":19,"run_count":8,"total":0.21994025},"codegen_evaluated_cells":8,"conditional_success_score":27.78773145254372,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":621,"eligibility_flag":true,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.1-flash-lite","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.2311783551885,"score":43.2311783551885},"GB2-05":{"attempts":1,"playable":10.674072031668008,"score":10.674072031668008},"GB2-06":{"attempts":1,"playable":18.61039249601762,"score":18.61039249601762},"GB2-07":{"attempts":1,"playable":33.49880171248045,"score":33.49880171248045},"GB2-08":{"attempts":1,"playable":32.92421266736403,"score":32.92421266736403}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:05:09Z","losses":1622,"max_score":43.2311783551885,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.375,"model_code_failures":3,"model_display_name":"Gemini 3.1 Flash Lite","model_slug":"google-gemini-3-1-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.625,"provider":"Google","provider_key":"google","rank":228,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:18:56Z","ranking_status":"ranked","rated_matches":2598,"rating_method":"bradley_terry_newton","raw_elo":1122.6744831552094,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":5,"repaired_rate":0.625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":17.367332157839826,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":355},{"admitted_plugins":5,"attempted_matches":2616,"canonical_public_row_identity":"publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515","capped_draws":145,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005},"codegen_evaluated_cells":8,"conditional_success_score":24.858643749356936,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":155,"eligibility_flag":true,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-3.7-flash","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"first_pass_admitted":0,"first_pass_rate":0.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":9.74494813775178,"score":9.74494813775178},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":39.33415746968565,"score":39.33415746968565},"GB2-06":{"attempts":1,"playable":33.09908901644075,"score":33.09908901644075},"GB2-07":{"attempts":1,"playable":24.97678665828656,"score":24.97678665828656},"GB2-08":{"attempts":1,"playable":17.13823746461996,"score":17.13823746461996}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:52:55Z","losses":1943,"max_score":39.33415746968565,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.375,"model_code_failures":3,"model_display_name":"Step 3.7 Flash","model_slug":"stepfun-step-3-7-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.625,"provider":"StepFun","provider_key":"stepfun","rank":229,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T19:20:25Z","ranking_status":"ranked","rated_matches":2616,"rating_method":"bradley_terry_newton","raw_elo":1115.6324387619018,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":5,"repaired_rate":0.625,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":15.536652343348086,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":518},{"admitted_plugins":5,"attempted_matches":2558,"canonical_public_row_identity":"publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60","capped_draws":89,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.00870475,"mean":0.005883593750000001,"median":0.006313125,"min":0.003432,"recorded_attempt_count":13,"run_count":8,"total":0.04706875},"codegen_evaluated_cells":8,"conditional_success_score":17.769550201675052,"contributing_entrants":null,"distinct_rated_opponents":252,"draws":473,"eligibility_flag":true,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"google/gemini-3.1-flash-lite","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":12.799269350143435,"score":12.799269350143435},"GB2-02":{"attempts":1,"playable":42.804821402339726,"score":42.804821402339726},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":6.051182302607571,"score":6.051182302607571},"GB2-06":{"attempts":1,"playable":24.54694960961289,"score":24.54694960961289},"GB2-07":{"attempts":1,"playable":2.645528343671625,"score":2.645528343671625},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":[],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:06:26Z","losses":1920,"max_score":42.804821402339726,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.375,"model_code_failures":3,"model_display_name":"Gemini 3.1 Flash Lite","model_slug":"google-gemini-3-1-flash-lite","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.625,"provider":"Google","provider_key":"google","rank":230,"rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:55:37Z","ranking_status":"ranked","rated_matches":2558,"rating_method":"bradley_terry_newton","raw_elo":934.8138952665635,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":11.105968876046907,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":165},{"admitted_plugins":1,"attempted_matches":538,"canonical_public_row_identity":"publication-row.v1:mixed:stepfun-step-5-preview:41a348315849a4db","capped_draws":2,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1820682,"mean":0.1820682,"median":0.1820682,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1820682},"codegen_evaluated_cells":1,"conditional_success_score":82.98469083668653,"contributing_entrants":null,"distinct_rated_opponents":241,"draws":2,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-5-preview","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","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":82.98469083668653,"score":82.98469083668653}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:59:01Z","losses":101,"max_score":82.98469083668653,"measured_at":null,"min_score":82.98469083668653,"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":1.0,"provider":"StepFun","provider_key":"stepfun","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":538,"rating_method":"bradley_terry_newton","raw_elo":1963.6358207439525,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":82.98469083668653,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":435},{"admitted_plugins":8,"attempted_matches":3630,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k3-1-pro:e64342c5890f5b99","capped_draws":232,"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":0.228888,"mean":0.1761925,"median":0.1786566,"min":0.1389952,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.4095399999999998},"codegen_evaluated_cells":8,"conditional_success_score":82.25744477813679,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":468,"eligibility_flag":false,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k3.1-pro","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":8,"first_pass_rate":1.0,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":61.260978179454206,"score":61.260978179454206},"GB2-02":{"attempts":1,"playable":76.03122628576318,"score":76.03122628576318},"GB2-03":{"attempts":1,"playable":88.7307271728901,"score":88.7307271728901},"GB2-04":{"attempts":1,"playable":82.15998971270707,"score":82.15998971270707},"GB2-05":{"attempts":1,"playable":80.97524285754415,"score":80.97524285754415},"GB2-06":{"attempts":1,"playable":92.1050424297417,"score":92.1050424297417},"GB2-07":{"attempts":1,"playable":85.11872824703423,"score":85.11872824703423},"GB2-08":{"attempts":1,"playable":91.67762333995961,"score":91.67762333995961}},"ineligibility_reason_codes":["fixed_coverage_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":473,"max_score":92.1050424297417,"measured_at":null,"min_score":61.260978179454206,"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":1.0,"provider":"Moonshot","provider_key":"moonshotai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3600,"rating_method":"bradley_terry_newton","raw_elo":1929.4560600938505,"reasoning_bracket":"balanced","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3.1-pro","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":82.25744477813679,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":30,"wins":2659},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:claude-haiku-5-5:42fefd9bf78265c1","capped_draws":38,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.04782545,"median":0.046146,"min":0.0294405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.3826036},"codegen_evaluated_cells":7,"conditional_success_score":74.85461771544894,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":410,"eligibility_flag":false,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"anthropic","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"claude-haiku-5-5","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":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":41.51447974442542,"score":41.51447974442542},"GB2-02":{"attempts":1,"playable":70.50235193557407,"score":70.50235193557407},"GB2-04":{"attempts":1,"playable":79.96961832899599,"score":79.96961832899599},"GB2-05":{"attempts":1,"playable":86.37309679864593,"score":86.37309679864593},"GB2-06":{"attempts":1,"playable":91.83900036619863,"score":91.83900036619863},"GB2-07":{"attempts":1,"playable":67.08694959374789,"score":67.08694959374789},"GB2-08":{"attempts":1,"playable":86.69682724055463,"score":86.69682724055463}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:04Z","losses":747,"max_score":91.83900036619863,"measured_at":null,"min_score":41.51447974442542,"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":1.0,"provider":"Anthropic","provider_key":"anthropic","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1836.8915845303602,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"anthropic","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":74.85461771544894,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2437},{"admitted_plugins":7,"attempted_matches":3610,"canonical_public_row_identity":"publication-row.v1:mixed:meta-muse-spark-open:d9bba0e6b5c7a98a","capped_draws":8,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333794999999999},"codegen_evaluated_cells":7,"conditional_success_score":63.6342594029209,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":344,"eligibility_flag":false,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"meta/muse-spark-open","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":7,"first_pass_rate":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":92.30699442734611,"score":92.30699442734611},"GB2-03":{"attempts":1,"playable":67.72454367206943,"score":67.72454367206943},"GB2-04":{"attempts":1,"playable":39.44947595905667,"score":39.44947595905667},"GB2-05":{"attempts":1,"playable":40.68351463237852,"score":40.68351463237852},"GB2-06":{"attempts":1,"playable":50.025467562234596,"score":50.025467562234596},"GB2-07":{"attempts":1,"playable":74.25776604435315,"score":74.25776604435315},"GB2-08":{"attempts":1,"playable":80.99205352300777,"score":80.99205352300777}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:26Z","losses":1211,"max_score":92.30699442734611,"measured_at":null,"min_score":39.44947595905667,"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":1.0,"provider":"Meta","provider_key":"meta","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3608,"rating_method":"bradley_terry_newton","raw_elo":1640.450677184443,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-open","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":63.6342594029209,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":2053},{"admitted_plugins":5,"attempted_matches":2530,"canonical_public_row_identity":"publication-row.v1:mixed:inception-mercury-3:2abf7719d897e8a4","capped_draws":260,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003},"codegen_evaluated_cells":5,"conditional_success_score":59.55849753741169,"contributing_entrants":null,"distinct_rated_opponents":255,"draws":727,"eligibility_flag":false,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-3","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":2,"first_pass_rate":0.4,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_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":50.06164504511567,"score":50.06164504511567},"GB2-02":{"attempts":1,"playable":44.17824088266641,"score":44.17824088266641},"GB2-03":{"attempts":1,"playable":62.16771778328458,"score":62.16771778328458},"GB2-06":{"attempts":1,"playable":79.63955354616625,"score":79.63955354616625},"GB2-08":{"attempts":1,"playable":61.74533042982549,"score":61.74533042982549}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-04","GB2-05","GB2-07"],"infra_failures_excluded":3,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:50:12Z","losses":725,"max_score":79.63955354616625,"measured_at":null,"min_score":44.17824088266641,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Mercury 3","model_slug":"inception-mercury-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Inception","provider_key":"inception","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":2530,"rating_method":"bradley_terry_newton","raw_elo":1584.2969660424887,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-3","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.6,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":59.55849753741169,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1078},{"admitted_plugins":6,"attempted_matches":3114,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302","capped_draws":311,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302952},"codegen_evaluated_cells":6,"conditional_success_score":46.785793220027806,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":577,"eligibility_flag":false,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5-pro","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":71.37373256693535,"score":71.37373256693535},"GB2-04":{"attempts":1,"playable":47.60829699628472,"score":47.60829699628472},"GB2-05":{"attempts":1,"playable":25.456917724816257,"score":25.456917724816257},"GB2-06":{"attempts":1,"playable":67.16410028755743,"score":67.16410028755743},"GB2-07":{"attempts":1,"playable":41.83910358067528,"score":41.83910358067528},"GB2-08":{"attempts":1,"playable":27.272608163897793,"score":27.272608163897793}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:59:46Z","losses":1447,"max_score":71.37373256693535,"measured_at":null,"min_score":25.456917724816257,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"MiMo-V2.5-Pro","model_slug":"xiaomi-mimo-v2-5-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3114,"rating_method":"bradley_terry_newton","raw_elo":1405.92184762123,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":6,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":46.785793220027806,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":1090},{"admitted_plugins":3,"attempted_matches":1548,"canonical_public_row_identity":"publication-row.v1:mixed:inception-mercury-3:7c52fdcabfa0313e","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715},"codegen_evaluated_cells":4,"conditional_success_score":59.96425070612094,"contributing_entrants":null,"distinct_rated_opponents":255,"draws":335,"eligibility_flag":false,"entry_count":3,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inception/mercury-3","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":2,"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":{"GB2-02":{"attempts":1,"playable":46.39253976872338,"score":46.39253976872338},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":77.8944751985715,"score":77.8944751985715},"GB2-08":{"attempts":1,"playable":55.605737151067956,"score":55.605737151067956}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"infra_failures_excluded":4,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":477,"max_score":77.8944751985715,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.25,"model_code_failures":1,"model_display_name":"Mercury 3","model_slug":"inception-mercury-3","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.75,"provider":"Inception","provider_key":"inception","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1548,"rating_method":"bradley_terry_newton","raw_elo":1585.1517123041824,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":44.97318802959071,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":736},{"admitted_plugins":6,"attempted_matches":3092,"canonical_public_row_identity":"publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0","capped_draws":42,"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":1.283003154},"codegen_evaluated_cells":7,"conditional_success_score":47.38818105190071,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":694,"eligibility_flag":false,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"moonshotai/kimi-k2.7-code","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-06"],"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":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:59Z","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":0.8571428571428571,"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":1442.4958276226616,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":6,"repaired_rate":0.8571428571428571,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":40.61844090162918,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":1,"wins":1060},{"admitted_plugins":7,"attempted_matches":3572,"canonical_public_row_identity":"publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633","capped_draws":196,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998},"codegen_evaluated_cells":7,"conditional_success_score":37.0360616076723,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":1114,"eligibility_flag":false,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nex-agi/nex-n2-pro","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"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":1,"playable":34.7408210165092,"score":34.7408210165092},"GB2-04":{"attempts":1,"playable":42.006158892138465,"score":42.006158892138465},"GB2-05":{"attempts":1,"playable":30.65596351338465,"score":30.65596351338465},"GB2-06":{"attempts":1,"playable":11.172029953674063,"score":11.172029953674063},"GB2-07":{"attempts":1,"playable":64.61361474216501,"score":64.61361474216501},"GB2-08":{"attempts":1,"playable":39.83496884593718,"score":39.83496884593718}},"ineligibility_reason_codes":["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":9,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:57:28Z","losses":1759,"max_score":64.61361474216501,"measured_at":null,"min_score":11.172029953674063,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Nex N2 Pro","model_slug":"nex-agi-nex-n2-pro","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Nex AGI","provider_key":"nex-agi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3572,"rating_method":"bradley_terry_newton","raw_elo":1280.695429832596,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":7,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":37.0360616076723,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":699},{"admitted_plugins":5,"attempted_matches":2534,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a","capped_draws":397,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844},"codegen_evaluated_cells":5,"conditional_success_score":35.85861319556868,"contributing_entrants":null,"distinct_rated_opponents":257,"draws":1108,"eligibility_flag":false,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"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":23.508780088691488,"score":23.508780088691488},"GB2-02":{"attempts":1,"playable":44.07266414671792,"score":44.07266414671792},"GB2-04":{"attempts":1,"playable":39.55185774658149,"score":39.55185774658149},"GB2-06":{"attempts":1,"playable":49.05847406271931,"score":49.05847406271931},"GB2-08":{"attempts":1,"playable":23.10128993313319,"score":23.10128993313319}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-03","GB2-05","GB2-07"],"infra_failures_excluded":3,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:50:17Z","losses":1136,"max_score":49.05847406271931,"measured_at":null,"min_score":23.10128993313319,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"MiMo-V2.5","model_slug":"xiaomi-mimo-v2-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":2534,"rating_method":"bradley_terry_newton","raw_elo":1302.7550088853304,"reasoning_bracket":"intensive","reasoning_level":"High","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"High","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":5,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":35.85861319556868,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":290},{"admitted_plugins":1,"attempted_matches":538,"canonical_public_row_identity":"publication-row.v1:mixed:stepfun-step-5-preview:2c0cd5d1a17232a3","capped_draws":275,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1898863,"median":0.1898863,"min":0.1898863,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":2,"run_count":1,"total":0.1898863},"codegen_evaluated_cells":1,"conditional_success_score":34.30966376677716,"contributing_entrants":null,"distinct_rated_opponents":241,"draws":275,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"stepfun/step-5-preview","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","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":34.30966376677716,"score":34.30966376677716}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:32Z","losses":230,"max_score":34.30966376677716,"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":1.0,"provider":"StepFun","provider_key":"stepfun","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":538,"rating_method":"bradley_terry_newton","raw_elo":1217.0406498419302,"reasoning_bracket":"baseline","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-5-preview","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.30966376677716,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":33},{"admitted_plugins":7,"attempted_matches":3594,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2","capped_draws":122,"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"codegen_evaluated_cells":7,"conditional_success_score":34.117825849976725,"contributing_entrants":null,"distinct_rated_opponents":258,"draws":830,"eligibility_flag":false,"entry_count":7,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"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":32.60183738521237,"score":32.60183738521237},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-04":{"attempts":1,"playable":40.37057364428585,"score":40.37057364428585},"GB2-05":{"attempts":1,"playable":27.766255047335402,"score":27.766255047335402},"GB2-06":{"attempts":1,"playable":21.87615289214184,"score":21.87615289214184},"GB2-07":{"attempts":1,"playable":23.602746186774525,"score":23.602746186774525},"GB2-08":{"attempts":1,"playable":50.6485513629397,"score":50.6485513629397}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-03","GB2-08"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:01:11Z","losses":2032,"max_score":50.6485513629397,"measured_at":null,"min_score":21.87615289214184,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"MiMo-V2.5","model_slug":"xiaomi-mimo-v2-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3594,"rating_method":"bradley_terry_newton","raw_elo":1248.4299594358529,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled (historical request variant 2)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-2","reasoning_bucket_label":"Reasoning enabled (historical request variant 2)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced-variant-2"},"reasoning_setting":"historical-provider-setting-balanced-variant-2","repaired_admitted":7,"repaired_rate":1.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":34.117825849976725,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":732},{"admitted_plugins":1,"attempted_matches":538,"canonical_public_row_identity":"publication-row.v1:mixed:inclusionai-ling-3-1-flash:125bb925e6a856d1","capped_draws":287,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":2},"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":2,"run_count":1,"total":0.0},"codegen_evaluated_cells":1,"conditional_success_score":33.32018896021172,"contributing_entrants":null,"distinct_rated_opponents":241,"draws":287,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inclusionai/ling-3.1-flash","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":["generation_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:48:39Z","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":1.0,"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":1206.4331012892305,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":33.32018896021172,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":22},{"admitted_plugins":6,"attempted_matches":3056,"canonical_public_row_identity":"publication-row.v1:mixed:inclusionai-ling-3-0-flash:c37de043ed46ddf4","capped_draws":129,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":52,"run_count":16,"total":0.0},"codegen_evaluated_cells":6,"conditional_success_score":30.555504181654875,"contributing_entrants":null,"distinct_rated_opponents":255,"draws":809,"eligibility_flag":false,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inclusionai/ling-3.0-flash:free","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":1,"first_pass_rate":0.16666666666666666,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_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":19.48303399859258,"score":19.48303399859258},"GB2-02":{"attempts":1,"playable":37.504788276235715,"score":37.504788276235715},"GB2-04":{"attempts":1,"playable":39.96129123978842,"score":39.96129123978842},"GB2-06":{"attempts":1,"playable":19.85374889848047,"score":19.85374889848047},"GB2-07":{"attempts":2,"playable":35.974658495177195,"score":35.974658495177195}},"ineligibility_reason_codes":["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":"2026-10-26T02:02:47Z","losses":1756,"max_score":39.96129123978842,"measured_at":null,"min_score":19.48303399859258,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Ling 3.0 Flash","model_slug":"inclusionai-ling-3-0-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"provider":"InclusionAI","provider_key":"inclusionai","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3056,"rating_method":"bradley_terry_newton","raw_elo":1236.3728883152273,"reasoning_bracket":"balanced","reasoning_level":"Enabled (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Enabled (historical request variant 2)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-2","reasoning_bucket_label":"Enabled (historical request variant 2)","reasoning_catalog_sha256":"d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced-variant-2"},"reasoning_setting":"historical-provider-setting-balanced-variant-2","repaired_admitted":5,"repaired_rate":0.8333333333333334,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.555504181654875,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":491},{"admitted_plugins":1,"attempted_matches":538,"canonical_public_row_identity":"publication-row.v1:mixed:inclusionai-ling-3-0-flash:3b88e1a0c679f412","capped_draws":276,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0032674799999999997,"mean":0.0032674799999999997,"median":0.0032674799999999997,"min":0.0032674799999999997,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":3,"run_count":1,"total":0.0032674799999999997},"codegen_evaluated_cells":1,"conditional_success_score":30.248972206255498,"contributing_entrants":null,"distinct_rated_opponents":241,"draws":276,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"inclusionai/ling-3.0-flash","reasoning_catalog_sha256":"6b8f18b146369a39d996a663731a80672d2a64ff72f3eaded5e316439d40f85f","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":[],"first_pass_admitted":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":30.248972206255498,"score":30.248972206255498}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:50Z","losses":250,"max_score":30.248972206255498,"measured_at":null,"min_score":30.248972206255498,"model_code_failure_rate":0.0,"model_code_failures":0,"model_display_name":"Ling 3.0 Flash","model_slug":"inclusionai-ling-3-0-flash","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":1.0,"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":1173.1979182483526,"reasoning_bracket":"baseline","reasoning_level":"None (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None (historical request variant 1)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-1","reasoning_bucket_label":"None (historical request variant 1)","reasoning_catalog_sha256":"6b8f18b146369a39d996a663731a80672d2a64ff72f3eaded5e316439d40f85f","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline-variant-1"},"reasoning_setting":"historical-provider-setting-baseline-variant-1","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":30.248972206255498,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":12},{"admitted_plugins":8,"attempted_matches":4070,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83","capped_draws":279,"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":32},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0265755425,"mean":0.018416099712499998,"median":0.017703669999999998,"min":0.0109615788,"recorded_attempt_count":32,"run_count":15,"total":0.2720731754},"codegen_evaluated_cells":9,"conditional_success_score":30.937123308571874,"contributing_entrants":null,"distinct_rated_opponents":259,"draws":1626,"eligibility_flag":false,"entry_count":8,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.1111111111111111,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_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":27.21652353760761,"score":27.21652353760761},"GB2-02":{"attempts":2,"playable":42.64558781172434,"score":42.64558781172434},"GB2-04":{"attempts":2,"playable":38.015146542457636,"score":38.015146542457636},"GB2-05":{"attempts":1,"playable":21.037258480066118,"score":21.037258480066118},"GB2-07":{"attempts":1,"playable":37.88027711625232,"score":37.88027711625232},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":18.827946363323203,"score":9.413973181661602}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-07"],"infra_failures_excluded":6,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:09:58Z","losses":1983,"max_score":42.64558781172434,"measured_at":null,"min_score":9.413973181661602,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"model_display_name":"MiMo-V2.5","model_slug":"xiaomi-mimo-v2-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.8888888888888888,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":4070,"rating_method":"bradley_terry_newton","raw_elo":1274.5096162743966,"reasoning_bracket":"balanced","reasoning_level":"Medium (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium (historical request variant 1)","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced-variant-1","reasoning_bucket_label":"Medium (historical request variant 1)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_pre_845b695_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced-variant-1"},"reasoning_setting":"historical-provider-setting-balanced-variant-1","repaired_admitted":7,"repaired_rate":0.7777777777777778,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":29.368127778294937,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":461},{"admitted_plugins":5,"attempted_matches":2566,"canonical_public_row_identity":"publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be","capped_draws":206,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"codegen_evaluated_cells":7,"conditional_success_score":38.79840581632838,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":589,"eligibility_flag":false,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04"],"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":57.184068748285824,"score":57.184068748285824},"GB2-02":{"attempts":1,"playable":41.00587206875293,"score":41.00587206875293},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":56.4086180600745,"score":56.4086180600745},"GB2-07":{"attempts":1,"playable":9.9378527732446,"score":9.9378527732446},"GB2-08":{"attempts":1,"playable":29.455617431284093,"score":29.455617431284093}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T02:00:24Z","losses":1345,"max_score":57.184068748285824,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.2857142857142857,"model_code_failures":2,"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":0.7142857142857143,"provider":"NVIDIA","provider_key":"nvidia","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":2566,"rating_method":"bradley_terry_newton","raw_elo":1291.4610380720223,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":5,"repaired_rate":0.7142857142857143,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":27.713147011663132,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":632},{"admitted_plugins":6,"attempted_matches":3112,"canonical_public_row_identity":"publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc","capped_draws":315,"codegen_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0097359,"mean":0.0038356840999999994,"median":0.0020557588,"min":0.0014804776,"recorded_attempt_count":12,"run_count":8,"total":0.0306854728},"codegen_evaluated_cells":7,"conditional_success_score":31.54610907769958,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":478,"eligibility_flag":false,"entry_count":6,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"xiaomi/mimo-v2.5","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-02"],"first_pass_admitted":5,"first_pass_rate":0.7142857142857143,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":35.58112687581995,"score":35.58112687581995},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.68133277644017,"score":45.68133277644017},"GB2-05":{"attempts":1,"playable":50.6790792678975,"score":50.6790792678975},"GB2-06":{"attempts":1,"playable":18.38375771085726,"score":18.38375771085726},"GB2-07":{"attempts":1,"playable":11.579486151304309,"score":11.579486151304309},"GB2-08":{"attempts":1,"playable":27.37187168387828,"score":27.37187168387828}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-04"],"infra_failures_excluded":1,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:56:59Z","losses":1964,"max_score":50.6790792678975,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"model_display_name":"MiMo-V2.5","model_slug":"xiaomi-mimo-v2-5","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.8571428571428571,"provider":"Xiaomi","provider_key":"xiaomi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":3110,"rating_method":"bradley_terry_newton","raw_elo":1185.7972726692153,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled (historical request variant 2)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline-variant-2","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled (historical request variant 2)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-2","reasoning_bucket_label":"Reasoning disabled (historical request variant 2)","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline-variant-2"},"reasoning_setting":"historical-provider-setting-baseline-variant-2","repaired_admitted":1,"repaired_rate":0.14285714285714285,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":27.039522066599638,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":668},{"admitted_plugins":1,"attempted_matches":530,"canonical_public_row_identity":"publication-row.v1:mixed:nex-agi-nex-n2-5-pro:9576a686705edef8","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":10,"run_count":8,"total":0.04440505},"codegen_evaluated_cells":2,"conditional_success_score":41.275962779983715,"contributing_entrants":null,"distinct_rated_opponents":240,"draws":0,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nex-agi/nex-n2.5-pro","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"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":{"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":41.275962779983715,"score":41.275962779983715}},"ineligibility_reason_codes":["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":"2026-10-24T17:05:20Z","losses":325,"max_score":41.275962779983715,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.5,"model_code_failures":1,"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":0.5,"provider":"Nex AGI","provider_key":"nex-agi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":530,"rating_method":"bradley_terry_newton","raw_elo":1338.8822889338762,"reasoning_bracket":"intensive","reasoning_level":"High (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-pro","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"High (historical request variant 1)","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive-variant-1","reasoning_bucket_label":"High (historical request variant 1)","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive-variant-1"},"reasoning_setting":"historical-provider-setting-intensive-variant-1","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":20.637981389991857,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":205},{"admitted_plugins":4,"attempted_matches":2042,"canonical_public_row_identity":"publication-row.v1:mixed:nex-agi-nex-n2-5-pro:d45c3e0ca6cdddbe","capped_draws":35,"codegen_cost_usd":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0041446518750000005,"median":0.0034028549999999998,"min":0.001882405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.033157215},"codegen_evaluated_cells":8,"conditional_success_score":37.26865450867181,"contributing_entrants":null,"distinct_rated_opponents":255,"draws":498,"eligibility_flag":false,"entry_count":4,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nex-agi/nex-n2.5-pro","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"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":1,"playable":45.88861566334852,"score":45.88861566334852},"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":1,"playable":34.83741580639468,"score":34.83741580639468},"GB2-08":{"attempts":1,"playable":30.843798288708303,"score":30.843798288708303}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","losses":1089,"max_score":45.88861566334852,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.5,"model_code_failures":4,"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":0.5,"provider":"Nex AGI","provider_key":"nex-agi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":2042,"rating_method":"bradley_terry_newton","raw_elo":1300.7763803728633,"reasoning_bracket":"baseline","reasoning_level":"None (historical request variant 1)","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-pro","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline-variant-1","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None (historical request variant 1)","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline-variant-1","reasoning_bucket_label":"None (historical request variant 1)","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline-variant-1"},"reasoning_setting":"historical-provider-setting-baseline-variant-1","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":18.634327254335904,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":455},{"admitted_plugins":4,"attempted_matches":1992,"canonical_public_row_identity":"publication-row.v1:mixed:qwen-qwen3-8-27b:aaed07b05e57b9e7","capped_draws":174,"codegen_cost_usd":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.028626384999999997,"mean":0.021101813124999997,"median":0.024224999999999997,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.16881450499999998},"codegen_evaluated_cells":8,"conditional_success_score":34.99235948732984,"contributing_entrants":null,"distinct_rated_opponents":249,"draws":631,"eligibility_flag":false,"entry_count":4,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"qwen/qwen3.8-27b","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":24.91348009565777,"score":24.91348009565777},"GB2-02":{"attempts":1,"playable":41.95866443114737,"score":41.95866443114737},"GB2-03":{"attempts":1,"playable":42.6623790200342,"score":42.6623790200342},"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":30.434914402480022,"score":30.434914402480022},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T15:32:02Z","losses":1038,"max_score":42.6623790200342,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.5,"model_code_failures":4,"model_display_name":"Qwen3.8 27B","model_slug":"qwen-qwen3-8-27b","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.5,"provider":"Alibaba","provider_key":"qwen","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1992,"rating_method":"bradley_terry_newton","raw_elo":1277.7798236541814,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":17.49617974366492,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":323},{"admitted_plugins":5,"attempted_matches":2594,"canonical_public_row_identity":"publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0","capped_draws":20,"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.13491350000000002,"mean":0.10247140625000001,"median":0.113468875,"min":0.061553000000000004,"recorded_attempt_count":17,"run_count":8,"total":0.8197712500000001},"codegen_evaluated_cells":6,"conditional_success_score":19.075301962913493,"contributing_entrants":null,"distinct_rated_opponents":256,"draws":199,"eligibility_flag":false,"entry_count":5,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"enabled","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nex-agi/nex-n2-pro","reasoning_catalog_sha256":"unknown_legacy","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-04"],"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":{"GB2-03":{"attempts":1,"playable":31.41945336453417,"score":31.41945336453417},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.4426069613079,"score":11.4426069613079},"GB2-06":{"attempts":1,"playable":15.65161477192967,"score":15.65161477192967},"GB2-07":{"attempts":1,"playable":23.7993654995253,"score":23.7993654995253},"GB2-08":{"attempts":1,"playable":13.063469217270422,"score":13.063469217270422}},"ineligibility_reason_codes":["generation_incomplete"],"infra_excluded_game_aliases":["GB2-01","GB2-02"],"infra_failures_excluded":2,"is_recent_addition":false,"last_measured_at":"2026-10-26T01:53:02Z","losses":2056,"max_score":31.41945336453417,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.16666666666666666,"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":0.8333333333333334,"provider":"Nex AGI","provider_key":"nex-agi","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":2594,"rating_method":"bradley_terry_newton","raw_elo":1006.6620240395038,"reasoning_bracket":"balanced","reasoning_level":"Reasoning enabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning enabled","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Reasoning enabled","reasoning_catalog_sha256":"f417b76bcde48e1d4e9e2cc05a6515195647f58f2d33c78f0fa69f5e70b5b925","reasoning_policy_version":"legacy_reasoning_845b695_to_kimi_k3_max_v1","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":5,"repaired_rate":0.8333333333333334,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":15.896084969094579,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":339},{"admitted_plugins":3,"attempted_matches":1562,"canonical_public_row_identity":"publication-row.v1:mixed:upstage-solar-mini4:5447a345c16e3b01","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.02342595,"mean":0.01633628125,"median":0.016221199999999998,"min":0.011361950000000001,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.13069025},"codegen_evaluated_cells":8,"conditional_success_score":36.82693588431312,"contributing_entrants":null,"distinct_rated_opponents":252,"draws":7,"eligibility_flag":false,"entry_count":3,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"xhigh","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"upstage/solar-mini4","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":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,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":46.073471504282615,"score":46.073471504282615},"GB2-06":{"attempts":1,"playable":31.291830205303434,"score":31.291830205303434},"GB2-07":{"attempts":1,"playable":33.11550594335333,"score":33.11550594335333},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:28:00Z","losses":1024,"max_score":46.073471504282615,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.625,"model_code_failures":5,"model_display_name":"Solar Mini 4","model_slug":"upstage-solar-mini4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.375,"provider":"Upstage","provider_key":"upstage","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1562,"rating_method":"bradley_terry_newton","raw_elo":1253.2620773574206,"reasoning_bracket":"intensive","reasoning_level":"XHigh","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"XHigh","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"XHigh","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":3,"repaired_rate":0.375,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":13.810100956617422,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":531},{"admitted_plugins":3,"attempted_matches":1476,"canonical_public_row_identity":"publication-row.v1:mixed:gpt-4-1-nano:2c8ea7d6cb6a2989","capped_draws":21,"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":0.017506999999999998},"codegen_evaluated_cells":8,"conditional_success_score":31.473648639398352,"contributing_entrants":null,"distinct_rated_opponents":249,"draws":680,"eligibility_flag":false,"entry_count":3,"evaluated_setting_identity":{"canonical_provider_route":"openai","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"gpt-4.1-nano","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"omitted","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":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T16:19:43Z","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":0.375,"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":1209.4645214833643,"reasoning_bracket":"baseline","reasoning_level":"Reasoning field omitted","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"omitted","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openai","provider_setting_label":"Reasoning field omitted","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning field omitted","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"omitted","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":11.802618239774382,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":83},{"admitted_plugins":3,"attempted_matches":1566,"canonical_public_row_identity":"publication-row.v1:mixed:nvidia-nemotron-3-5-super-vl:eb510fd9678b8478","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.02850254},"codegen_evaluated_cells":8,"conditional_success_score":31.203652071831257,"contributing_entrants":null,"distinct_rated_opponents":255,"draws":349,"eligibility_flag":false,"entry_count":3,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"nvidia/nemotron-3.5-super-vl","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.33319700499054,"score":43.33319700499054},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.7993654995253,"score":23.7993654995253},"GB2-08":{"attempts":1,"playable":26.478393710977922,"score":26.478393710977922}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:50Z","losses":939,"max_score":43.33319700499054,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.625,"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":0.375,"provider":"NVIDIA","provider_key":"nvidia","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1566,"rating_method":"bradley_terry_newton","raw_elo":1219.3901753364798,"reasoning_bracket":"baseline","reasoning_level":"Reasoning disabled","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Reasoning disabled","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Reasoning disabled","reasoning_catalog_sha256":"2ca548aa19517293a18383eda23c7a73c74cb186b1802c50788cdd326761f6ea","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":2,"repaired_rate":0.25,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":11.701369526936721,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":278},{"admitted_plugins":3,"attempted_matches":1598,"canonical_public_row_identity":"publication-row.v1:mixed:cohere-north-mini-code:fcf5325e62b8199d","capped_draws":283,"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"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-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.0},"codegen_evaluated_cells":8,"conditional_success_score":17.880410917457098,"contributing_entrants":null,"distinct_rated_opponents":253,"draws":283,"eligibility_flag":false,"entry_count":3,"evaluated_setting_identity":{"canonical_provider_route":"unknown_legacy","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"cohere/north-mini-code:free","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"toggle","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":2,"first_pass_rate":0.25,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.885549928473093,"score":19.885549928473093},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.019980501241687,"score":2.019980501241687},"GB2-08":{"attempts":1,"playable":31.73570232265651,"score":31.73570232265651}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:33Z","losses":1192,"max_score":31.73570232265651,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.625,"model_code_failures":5,"model_display_name":"North Mini Code","model_slug":"cohere-north-mini-code","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.375,"provider":"Cohere","provider_key":"cohere","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1598,"rating_method":"bradley_terry_newton","raw_elo":886.7133689339753,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"toggle","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"unknown_legacy","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"toggle","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":6.705154094046412,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":123},{"admitted_plugins":2,"attempted_matches":1018,"canonical_public_row_identity":"publication-row.v1:mixed:upstage-solar-mini4:a1bf9f173eece558","capped_draws":79,"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.012110200000000002,"mean":0.0072751125,"median":0.0080226,"min":0.00114085,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":8,"total":0.0582009},"codegen_evaluated_cells":7,"conditional_success_score":19.792886071226498,"contributing_entrants":null,"distinct_rated_opponents":246,"draws":84,"eligibility_flag":false,"entry_count":2,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"medium","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"upstage/solar-mini4","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"playable":19.28125641080402,"score":19.28125641080402},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"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":20.304515731648973,"score":20.304515731648973},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":["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":797,"max_score":20.304515731648973,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.7142857142857143,"model_code_failures":5,"model_display_name":"Solar Mini 4","model_slug":"upstage-solar-mini4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.2857142857142857,"provider":"Upstage","provider_key":"upstage","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":1018,"rating_method":"bradley_terry_newton","raw_elo":1054.041990315617,"reasoning_bracket":"balanced","reasoning_level":"Medium","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Medium","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Medium","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.14285714285714285,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":5.655110306064714,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":137},{"admitted_plugins":1,"attempted_matches":498,"canonical_public_row_identity":"publication-row.v1:mixed:upstage-solar-mini4:940ac6b1f1f40086","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0023752,"mean":0.0015195812500000002,"median":0.00138595,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":16},"recorded_attempt_count":16,"run_count":8,"total":0.012156650000000001},"codegen_evaluated_cells":8,"conditional_success_score":40.5751576693377,"contributing_entrants":null,"distinct_rated_opponents":227,"draws":346,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"upstage/solar-mini4","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.125,"first_seen_at":null,"game_alias":null,"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"headline_games":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.5751576693377,"score":40.5751576693377},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"infra_excluded_game_aliases":[],"infra_failures_excluded":0,"is_recent_addition":false,"last_measured_at":"2026-10-24T15:42:14Z","losses":131,"max_score":40.5751576693377,"measured_at":null,"min_score":0.0,"model_code_failure_rate":0.875,"model_code_failures":7,"model_display_name":"Solar Mini 4","model_slug":"upstage-solar-mini4","performance_rejected_game_aliases":[],"performance_rejections":0,"plugin_success_rate":0.125,"provider":"Upstage","provider_key":"upstage","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":498,"rating_method":"bradley_terry_newton","raw_elo":1401.9308314236346,"reasoning_bracket":"baseline","reasoning_level":"None","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"None","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"None","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":5.071894708667212,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":21},{"admitted_plugins":1,"attempted_matches":498,"canonical_public_row_identity":"publication-row.v1:mixed:ibm-granite-granite-4-2-8b:ae025949d07a831b","capped_draws":0,"codegen_cost_usd":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.00328117,"mean":0.0022631475,"median":0.0021966650000000004,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":19},"recorded_attempt_count":19,"run_count":8,"total":0.018105180000000002},"codegen_evaluated_cells":8,"conditional_success_score":38.83499052329622,"contributing_entrants":null,"distinct_rated_opponents":227,"draws":317,"eligibility_flag":false,"entry_count":1,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"low","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"ibm-granite/granite-4.2-8b","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","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":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":38.83499052329622,"score":38.83499052329622},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"ineligibility_reason_codes":["below_generation_quality_threshold"],"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":0.875,"model_code_failures":7,"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":0.125,"provider":"IBM","provider_key":"ibm","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":498,"rating_method":"bradley_terry_newton","raw_elo":1388.2049214936515,"reasoning_bracket":"balanced","reasoning_level":"Low","reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"ibm","provider_model":"ibm-granite/granite-4.2-8b","provider_reasoning_params":{"bracket":"balanced","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-balanced","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Low","reasoning_bracket":"balanced","reasoning_bucket":"historical-provider-setting-balanced","reasoning_bucket_label":"Low","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-balanced"},"reasoning_setting":"historical-provider-setting-balanced","repaired_admitted":1,"repaired_rate":0.125,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":4.8543738154120275,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":27},{"admitted_plugins":0,"attempted_matches":0,"canonical_public_row_identity":"publication-row.v1:mixed:ibm-granite-granite-4-2-8b:6aa9972946afffdc","capped_draws":0,"codegen_cost_usd":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":0,"draws":null,"eligibility_flag":false,"entry_count":0,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"none","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"ibm-granite/granite-4.2-8b","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":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,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"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":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"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":null,"losses":null,"max_score":0.0,"measured_at":null,"min_score":0.0,"model_code_failure_rate":1.0,"model_code_failures":8,"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":0.0,"provider":"IBM","provider_key":"ibm","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":0,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":"baseline","reasoning_level":"Non-thinking","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"baseline","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-baseline","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Non-thinking","reasoning_bracket":"baseline","reasoning_bucket":"historical-provider-setting-baseline","reasoning_bucket_label":"Non-thinking","reasoning_catalog_sha256":"d889884bf473f28216c6a2ab2c563431ef5a7cdabb08f26586f15b4860fc9346","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-baseline"},"reasoning_setting":"historical-provider-setting-baseline","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":0.0,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":null},{"admitted_plugins":0,"attempted_matches":0,"canonical_public_row_identity":"publication-row.v1:mixed:ibm-granite-granite-4-2-8b:bcfb9d13b496f68f","capped_draws":0,"codegen_cost_usd":{"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.01113168,"mean":0.0083819225,"median":0.007854965,"min":0.00635193,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":18},"recorded_attempt_count":18,"run_count":8,"total":0.06705538},"codegen_evaluated_cells":8,"conditional_success_score":null,"contributing_entrants":null,"distinct_rated_opponents":0,"draws":null,"eligibility_flag":false,"entry_count":0,"evaluated_setting_identity":{"canonical_provider_route":"openrouter","effective_request_value":"high","output_mode":"unknown_legacy","prompt_identity":"full_freedom","prompt_profile_identity":"unknown_legacy","provider_model":"ibm-granite/granite-4.2-8b","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","request_mode":"effort","resolution_status":"opaque_historical","schema_version":"evaluated_setting_identity.v1"},"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":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,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"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":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"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":null,"losses":null,"max_score":0.0,"measured_at":null,"min_score":0.0,"model_code_failure_rate":1.0,"model_code_failures":8,"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":0.0,"provider":"IBM","provider_key":"ibm","rank":null,"rank_movement":null,"rank_movement_baseline_at":null,"ranking_status":"provisional","rated_matches":0,"rating_method":"bradley_terry_newton","raw_elo":null,"reasoning_bracket":"intensive","reasoning_level":"Full","reasoning_provenance":{"code_output_mode":"unknown_legacy","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":"intensive","bracket_eligible":false,"evidence_status":"retained_literal_legacy","request_mode":"effort","requested_effort":"historical-provider-setting-intensive","source":"retained_generation_evidence","track_id":"full_freedom/mixed"},"provider_route":"openrouter","provider_setting_label":"Full","reasoning_bracket":"intensive","reasoning_bucket":"historical-provider-setting-intensive","reasoning_bucket_label":"Full","reasoning_catalog_sha256":"c18407704dcc8da9be337976fe58c30b139b90d4e7f000a6dd7df762b49a4c7d","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":"effort","requested_reasoning_effort":"historical-provider-setting-intensive"},"reasoning_setting":"historical-provider-setting-intensive","repaired_admitted":0,"repaired_rate":0.0,"results_cut_id":"gb2-20261026-cb69502a12d9","row_kind":"track","score":0.0,"score_basis":"mean across games; each plugin generation attempt that failed for a model cause counts 0 beside the working plugins","scoring_policy_version":"attributed_fault_loss_official_qualification_v17","snapshot_id":"20261026_022724","suite_line_id":"gamebench2","suite_version":"2-known8-r3","track_id":"full_freedom/mixed","track_name":"Reasoning Variants","uncertainty":null,"unilateral_faults":0,"wins":null}],"schema_version":12,"snapshot_id":"20261026_022724","track_id":"full_freedom/mixed"}