{"benchmark_line":"gamebench2","economics_chart":{"eligible_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"enabled":true},"game_order":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"games":[{"alias":"GB2-01","name":"Go","slug":"go"},{"alias":"GB2-02","name":"Chess","slug":"chess"},{"alias":"GB2-03","name":"Shogi","slug":"shogi"},{"alias":"GB2-04","name":"Xiangqi","slug":"xiangqi"},{"alias":"GB2-05","name":"Hex","slug":"hex"},{"alias":"GB2-06","name":"International Draughts","slug":"international-draughts"},{"alias":"GB2-07","name":"Game of the Amazons","slug":"game-of-the-amazons"},{"alias":"GB2-08","name":"Tumbleweed","slug":"tumbleweed"}],"generated_at":"2026-10-16T18:41:28Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:42003ea533b21c57","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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":1.9134900000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":3.2723400000000002},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":10.42744}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":0.6505529166666667,"median":0.40659249999999997,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":24},"run_count":24,"token_priced_attempt_count":24,"total":15.613270000000004},"codegen_output_tokens":{"attempt_count":24,"output_max":27674,"output_mean":11074.333333333334,"output_min":2260,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27674,"output_mean":24131.875,"output_min":19038,"run_count":8},"medium":{"attempt_count":8,"output_max":7733,"output_mean":6244.125,"output_min":3722,"run_count":8},"none":{"attempt_count":8,"output_max":3278,"output_mean":2847.0,"output_min":2260,"run_count":8}},"display_name":"GPT-6 Astra","economics":{"all":89.42643037837217,"highest":94.53441838718366,"medium":88.96771407143386,"none":84.77715867649901},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"total_output_tokens":265784,"total_reasoning_output_tokens":150836,"total_visible_output_tokens":114948,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-astra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":88.78028530987746,"score":88.78028530987746},"GB2-02":{"attempts":3,"playable":82.8400221599152,"score":82.8400221599152},"GB2-03":{"attempts":3,"playable":87.84101516898984,"score":87.84101516898984},"GB2-04":{"attempts":3,"playable":89.26331808619189,"score":89.26331808619189},"GB2-05":{"attempts":3,"playable":95.4638091753876,"score":95.4638091753876},"GB2-06":{"attempts":3,"playable":87.0150944361323,"score":87.0150944361323},"GB2-07":{"attempts":3,"playable":96.44480265301559,"score":96.44480265301559},"GB2-08":{"attempts":3,"playable":87.76309603746756,"score":87.76309603746756}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":97.15599752536322,"score":97.15599752536322},"GB2-02":{"attempts":1,"playable":95.9096540094851,"score":95.9096540094851},"GB2-03":{"attempts":1,"playable":97.70332695248499,"score":97.70332695248499},"GB2-04":{"attempts":1,"playable":92.95100217565731,"score":92.95100217565731},"GB2-05":{"attempts":1,"playable":98.93806772575145,"score":98.93806772575145},"GB2-06":{"attempts":1,"playable":88.38617610719459,"score":88.38617610719459},"GB2-07":{"attempts":1,"playable":97.82508206828581,"score":97.82508206828581},"GB2-08":{"attempts":1,"playable":87.4060405332468,"score":87.4060405332468}},"medium":{"GB2-01":{"attempts":1,"playable":76.19719081317574,"score":76.19719081317574},"GB2-02":{"attempts":1,"playable":80.45981479621958,"score":80.45981479621958},"GB2-03":{"attempts":1,"playable":90.91795801849986,"score":90.91795801849986},"GB2-04":{"attempts":1,"playable":91.68066265797752,"score":91.68066265797752},"GB2-05":{"attempts":1,"playable":92.84346701541763,"score":92.84346701541763},"GB2-06":{"attempts":1,"playable":89.0645990728552,"score":89.0645990728552},"GB2-07":{"attempts":1,"playable":96.74306475988472,"score":96.74306475988472},"GB2-08":{"attempts":1,"playable":93.83495543744058,"score":93.83495543744058}},"none":{"GB2-01":{"attempts":1,"playable":92.98766759109343,"score":92.98766759109343},"GB2-02":{"attempts":1,"playable":72.15059767404092,"score":72.15059767404092},"GB2-03":{"attempts":1,"playable":74.90176053598466,"score":74.90176053598466},"GB2-04":{"attempts":1,"playable":83.15828942494088,"score":83.15828942494088},"GB2-05":{"attempts":1,"playable":94.60989278499368,"score":94.60989278499368},"GB2-06":{"attempts":1,"playable":83.5945081283471,"score":83.5945081283471},"GB2-07":{"attempts":1,"playable":94.76626113087619,"score":94.76626113087619},"GB2-08":{"attempts":1,"playable":82.04829214171528,"score":82.04829214171528}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-10-14T17:24:37Z","match_totals_all":{"draws":1174,"losses":1073,"wins":12441},"match_totals_tracks":{"highest":{"draws":128,"losses":212,"wins":4540},"medium":{"draws":393,"losses":379,"wins":4130},"none":{"draws":653,"losses":482,"wins":3771}},"model_slug":"gpt-6-astra","overall":{"max":98.93806772575145,"mean":89.42643037837217,"min":72.15059767404092},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":97.15599752536322,"GB2-02":95.9096540094851,"GB2-03":97.70332695248499,"GB2-04":92.95100217565731,"GB2-05":98.93806772575145,"GB2-06":88.38617610719459,"GB2-07":97.82508206828581,"GB2-08":87.4060405332468},"per_game_all":{"GB2-01":88.78028530987746,"GB2-02":82.8400221599152,"GB2-03":87.84101516898984,"GB2-04":89.26331808619189,"GB2-05":95.4638091753876,"GB2-06":87.0150944361323,"GB2-07":96.44480265301559,"GB2-08":87.76309603746756},"per_game_match_totals_all":{"GB2-01":{"draws":73,"losses":201,"wins":1582},"GB2-02":{"draws":493,"losses":65,"wins":1152},"GB2-03":{"draws":297,"losses":103,"wins":1426},"GB2-04":{"draws":190,"losses":114,"wins":1474},"GB2-05":{"draws":0,"losses":77,"wins":1831},"GB2-06":{"draws":121,"losses":200,"wins":1501},"GB2-07":{"draws":0,"losses":57,"wins":1821},"GB2-08":{"draws":0,"losses":256,"wins":1654}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":19,"wins":599},"GB2-02":{"draws":26,"losses":9,"wins":527},"GB2-03":{"draws":12,"losses":6,"wins":588},"GB2-04":{"draws":46,"losses":22,"wins":524},"GB2-05":{"draws":0,"losses":3,"wins":633},"GB2-06":{"draws":44,"losses":55,"wins":503},"GB2-07":{"draws":0,"losses":10,"wins":616},"GB2-08":{"draws":0,"losses":88,"wins":550}},"medium":{"GB2-01":{"draws":45,"losses":146,"wins":429},"GB2-02":{"draws":191,"losses":21,"wins":350},"GB2-03":{"draws":69,"losses":29,"wins":514},"GB2-04":{"draws":55,"losses":26,"wins":511},"GB2-05":{"draws":0,"losses":43,"wins":593},"GB2-06":{"draws":33,"losses":56,"wins":529},"GB2-07":{"draws":0,"losses":17,"wins":609},"GB2-08":{"draws":0,"losses":41,"wins":595}},"none":{"GB2-01":{"draws":28,"losses":36,"wins":554},"GB2-02":{"draws":276,"losses":35,"wins":275},"GB2-03":{"draws":216,"losses":68,"wins":324},"GB2-04":{"draws":89,"losses":66,"wins":439},"GB2-05":{"draws":0,"losses":31,"wins":605},"GB2-06":{"draws":44,"losses":89,"wins":469},"GB2-07":{"draws":0,"losses":30,"wins":596},"GB2-08":{"draws":0,"losses":127,"wins":509}}},"per_game_raw_elo_all":{"GB2-01":2044.9731460835146,"GB2-02":1855.8208032898003,"GB2-03":2041.174352317815,"GB2-04":1923.4669190293905,"GB2-05":2648.8788216372554,"GB2-06":2138.7864396601076,"GB2-07":2558.4416026345275,"GB2-08":2086.4171242220423},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2287.589580809066,"GB2-02":2137.6125650511876,"GB2-03":2400.7593515850635,"GB2-04":2002.5422699678925,"GB2-05":2988.575393624503,"GB2-06":2169.95796767158,"GB2-07":2671.9399807243663,"GB2-08":2057.553896568002},"medium":{"GB2-01":1761.2933294918735,"GB2-02":1763.613387720062,"GB2-03":2025.9520659861942,"GB2-04":1966.4613224888508,"GB2-05":2427.423531291061,"GB2-06":2187.5501050841735,"GB2-07":2571.409349252246,"GB2-08":2278.046464856864},"none":{"GB2-01":2086.0365279496045,"GB2-02":1666.2364570981515,"GB2-03":1696.8116393821872,"GB2-04":1801.3971646314285,"GB2-05":2530.6375399962017,"GB2-06":2058.85124622457,"GB2-07":2431.9754779269692,"GB2-08":1923.6510112412616}},"per_game_tracks":{"highest":{"GB2-01":97.15599752536322,"GB2-02":95.9096540094851,"GB2-03":97.70332695248499,"GB2-04":92.95100217565731,"GB2-05":98.93806772575145,"GB2-06":88.38617610719459,"GB2-07":97.82508206828581,"GB2-08":87.4060405332468},"medium":{"GB2-01":76.19719081317574,"GB2-02":80.45981479621958,"GB2-03":90.91795801849986,"GB2-04":91.68066265797752,"GB2-05":92.84346701541763,"GB2-06":89.0645990728552,"GB2-07":96.74306475988472,"GB2-08":93.83495543744058},"none":{"GB2-01":92.98766759109343,"GB2-02":72.15059767404092,"GB2-03":74.90176053598466,"GB2-04":83.15828942494088,"GB2-05":94.60989278499368,"GB2-06":83.5945081283471,"GB2-07":94.76626113087619,"GB2-08":82.04829214171528}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":94.53441838718366,"medium":88.96771407143386,"none":84.77715867649901},"reasoning_agg":{"highest":{"max":98.93806772575145,"mean":94.53441838718366,"min":87.4060405332468},"medium":{"max":96.74306475988472,"mean":88.96771407143386,"min":76.19719081317574},"none":{"max":94.76626113087619,"mean":84.77715867649901,"min":72.15059767404092}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.75725971068465}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:d42a4c4c0f7d3cdf","codegen_cost_by_reasoning":{"highest":{"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":17.677191999999998},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":3.0063079999999998},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292},"codegen_output_tokens":{"attempt_count":30,"output_max":149830,"output_mean":37334.40740740741,"output_min":2400,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":149830,"output_mean":94967.22222222222,"output_min":65515,"run_count":9},"medium":{"attempt_count":10,"output_max":31033,"output_mean":13777.666666666666,"output_min":6104,"run_count":9},"none":{"attempt_count":9,"output_max":3890,"output_mean":3258.3333333333335,"output_min":2400,"run_count":9}},"display_name":"Claude Opus 5.5","economics":{"all":88.60153300042957,"highest":95.16780469797959,"medium":92.81916713663082,"none":77.81762716667828},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":30,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[65536,128000],"total_output_tokens":1008029,"total_reasoning_output_tokens":820640,"total_visible_output_tokens":187389,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.1111111111111111},"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":9,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":89.65010533081058,"score":89.65010533081058},"GB2-02":{"attempts":3,"playable":90.7127276307286,"score":90.7127276307286},"GB2-03":{"attempts":3,"playable":80.72411333590075,"score":80.72411333590075},"GB2-04":{"attempts":3,"playable":84.1348439501474,"score":84.1348439501474},"GB2-05":{"attempts":3,"playable":93.44112559138972,"score":93.44112559138972},"GB2-06":{"attempts":3,"playable":89.1743132080174,"score":89.1743132080174},"GB2-07":{"attempts":3,"playable":94.33305257274817,"score":94.33305257274817},"GB2-08":{"attempts":5,"playable":86.6419823836939,"score":86.6419823836939}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.76023955188815,"score":84.76023955188815},"GB2-02":{"attempts":1,"playable":96.14533272936411,"score":96.14533272936411},"GB2-03":{"attempts":1,"playable":97.21150643384125,"score":97.21150643384125},"GB2-04":{"attempts":1,"playable":94.08298779163772,"score":94.08298779163772},"GB2-05":{"attempts":1,"playable":98.04161368981381,"score":98.04161368981381},"GB2-06":{"attempts":1,"playable":99.2709827491228,"score":99.2709827491228},"GB2-07":{"attempts":1,"playable":97.88575718016352,"score":97.88575718016352},"GB2-08":{"attempts":1,"playable":93.94401745800536,"score":93.94401745800536}},"medium":{"GB2-01":{"attempts":1,"playable":93.36305091954922,"score":93.36305091954922},"GB2-02":{"attempts":1,"playable":95.49375583271785,"score":95.49375583271785},"GB2-03":{"attempts":1,"playable":92.2594377394535,"score":92.2594377394535},"GB2-04":{"attempts":1,"playable":89.08217087686022,"score":89.08217087686022},"GB2-05":{"attempts":1,"playable":90.18097204081677,"score":90.18097204081677},"GB2-06":{"attempts":1,"playable":91.27905602081383,"score":91.27905602081383},"GB2-07":{"attempts":1,"playable":93.7645730208039,"score":93.7645730208039},"GB2-08":{"attempts":2,"playable":97.13032064203128,"score":97.13032064203128}},"none":{"GB2-01":{"attempts":1,"playable":90.82702552099437,"score":90.82702552099437},"GB2-02":{"attempts":1,"playable":80.49909433010383,"score":80.49909433010383},"GB2-03":{"attempts":1,"playable":52.701395834407506,"score":52.701395834407506},"GB2-04":{"attempts":1,"playable":69.23937318194425,"score":69.23937318194425},"GB2-05":{"attempts":1,"playable":92.10079104353858,"score":92.10079104353858},"GB2-06":{"attempts":1,"playable":76.97290085411554,"score":76.97290085411554},"GB2-07":{"attempts":1,"playable":91.34882751727712,"score":91.34882751727712},"GB2-08":{"attempts":2,"playable":68.85160905104507,"score":68.85160905104507}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-13T23:00:37Z","match_totals_all":{"draws":882,"losses":999,"wins":10173},"match_totals_tracks":{"highest":{"draws":75,"losses":133,"wins":3486},"medium":{"draws":116,"losses":216,"wins":3848},"none":{"draws":691,"losses":650,"wins":2839}},"model_slug":"claude-opus-5-5","overall":{"max":99.2709827491228,"mean":88.60153300042957,"min":52.701395834407506},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.76023955188815,"GB2-02":96.14533272936411,"GB2-03":97.21150643384125,"GB2-04":94.08298779163772,"GB2-05":98.04161368981381,"GB2-06":99.2709827491228,"GB2-07":97.88575718016352,"GB2-08":93.94401745800536},"per_game_all":{"GB2-01":89.65010533081058,"GB2-02":90.7127276307286,"GB2-03":80.72411333590075,"GB2-04":84.1348439501474,"GB2-05":93.44112559138972,"GB2-06":89.1743132080174,"GB2-07":94.33305257274817,"GB2-08":86.6419823836939},"per_game_match_totals_all":{"GB2-01":{"draws":59,"losses":118,"wins":1227},"GB2-02":{"draws":128,"losses":57,"wins":1111},"GB2-03":{"draws":326,"losses":111,"wins":901},"GB2-04":{"draws":282,"losses":80,"wins":982},"GB2-05":{"draws":0,"losses":91,"wins":1361},"GB2-06":{"draws":61,"losses":114,"wins":1193},"GB2-07":{"draws":0,"losses":73,"wins":1349},"GB2-08":{"draws":26,"losses":355,"wins":2049}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":69,"wins":391},"GB2-02":{"draws":23,"losses":4,"wins":405},"GB2-03":{"draws":3,"losses":10,"wins":433},"GB2-04":{"draws":40,"losses":7,"wins":401},"GB2-05":{"draws":0,"losses":7,"wins":477},"GB2-06":{"draws":1,"losses":0,"wins":455},"GB2-07":{"draws":0,"losses":7,"wins":467},"GB2-08":{"draws":0,"losses":29,"wins":457}},"medium":{"GB2-01":{"draws":30,"losses":16,"wins":422},"GB2-02":{"draws":9,"losses":14,"wins":409},"GB2-03":{"draws":21,"losses":26,"wins":399},"GB2-04":{"draws":34,"losses":34,"wins":380},"GB2-05":{"draws":0,"losses":47,"wins":437},"GB2-06":{"draws":22,"losses":27,"wins":407},"GB2-07":{"draws":0,"losses":27,"wins":447},"GB2-08":{"draws":0,"losses":25,"wins":947}},"none":{"GB2-01":{"draws":21,"losses":33,"wins":414},"GB2-02":{"draws":96,"losses":39,"wins":297},"GB2-03":{"draws":302,"losses":75,"wins":69},"GB2-04":{"draws":208,"losses":39,"wins":201},"GB2-05":{"draws":0,"losses":37,"wins":447},"GB2-06":{"draws":38,"losses":87,"wins":331},"GB2-07":{"draws":0,"losses":39,"wins":435},"GB2-08":{"draws":26,"losses":301,"wins":645}}},"per_game_raw_elo_all":{"GB2-01":2003.5319629809758,"GB2-02":2010.3593379591475,"GB2-03":1963.8892389057453,"GB2-04":1861.4285933362546,"GB2-05":2506.397398094095,"GB2-06":2331.701441583105,"GB2-07":2432.6923554539967,"GB2-08":2149.3349856792274},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1890.3227504511722,"GB2-02":2150.400072141608,"GB2-03":2354.230351217036,"GB2-04":2039.7452085849195,"GB2-05":2835.138274238142,"GB2-06":2820.2615813042153,"GB2-07":2678.542793718105,"GB2-08":2282.971151621857},"medium":{"GB2-01":2098.989903440073,"GB2-02":2116.531684128586,"GB2-03":2074.7429788957925,"GB2-04":1905.231822129821,"GB2-05":2295.648611534419,"GB2-06":2250.327744719152,"GB2-07":2372.281660041339,"GB2-08":2494.309381831962},"none":{"GB2-01":2021.283235051683,"GB2-02":1764.1462576072483,"GB2-03":1462.6943866044064,"GB2-04":1639.308749294024,"GB2-05":2388.405308509724,"GB2-06":1924.5149987259472,"GB2-07":2247.252612602546,"GB2-08":1670.7244235838637}},"per_game_tracks":{"highest":{"GB2-01":84.76023955188815,"GB2-02":96.14533272936411,"GB2-03":97.21150643384125,"GB2-04":94.08298779163772,"GB2-05":98.04161368981381,"GB2-06":99.2709827491228,"GB2-07":97.88575718016352,"GB2-08":93.94401745800536},"medium":{"GB2-01":93.36305091954922,"GB2-02":95.49375583271785,"GB2-03":92.2594377394535,"GB2-04":89.08217087686022,"GB2-05":90.18097204081677,"GB2-06":91.27905602081383,"GB2-07":93.7645730208039,"GB2-08":97.13032064203128},"none":{"GB2-01":90.82702552099437,"GB2-02":80.49909433010383,"GB2-03":52.701395834407506,"GB2-04":69.23937318194425,"GB2-05":92.10079104353858,"GB2-06":76.97290085411554,"GB2-07":91.34882751727712,"GB2-08":68.85160905104507}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":95.16780469797959,"medium":92.81916713663082,"none":77.81762716667828},"reasoning_agg":{"highest":{"max":99.2709827491228,"mean":95.16780469797959,"min":84.76023955188815},"medium":{"max":97.13032064203128,"mean":92.81916713663082,"min":89.08217087686022},"none":{"max":92.10079104353858,"mean":77.81762716667828,"min":52.701395834407506}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.350177531301313}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:bbc1e2b29dda8249","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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":6.339052010326089}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":9.233549636276067},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781585},"codegen_output_tokens":{"attempt_count":35,"output_max":231035,"output_mean":46647.59375,"output_min":5610,"run_count":32},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":231035,"output_mean":80471.125,"output_min":38285,"run_count":16},"medium":{"attempt_count":9,"output_max":25949,"output_mean":17238.625,"output_min":9715,"run_count":8},"none":{"attempt_count":8,"output_max":10198,"output_mean":8409.5,"output_min":5610,"run_count":8}},"display_name":"Claude Fable 5.1","economics":{"all":88.4111522567455,"highest":94.08804105081191,"medium":85.12357473307895,"none":86.02184098634565},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[128000],"finish_reason_observations":30,"finish_reasons":["end_turn","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"requested_max_output_token_observations":10,"requested_max_output_tokens":[128000],"total_output_tokens":1492723,"total_reasoning_output_tokens":1266567,"total_visible_output_tokens":226156,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5-1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":11,"evaluated_cells":11,"first_pass_admitted":9,"first_pass_rate":0.8181818181818182,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.18181818181818182}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":85.28867416376646,"score":85.28867416376646},"GB2-02":{"attempts":3,"playable":89.50919288910758,"score":89.50919288910758},"GB2-03":{"attempts":4,"playable":92.18636031478864,"score":92.18636031478864},"GB2-04":{"attempts":4,"playable":75.12509895160144,"score":75.12509895160144},"GB2-05":{"attempts":3,"playable":91.48484266342223,"score":91.48484266342223},"GB2-06":{"attempts":3,"playable":89.54405718963669,"score":89.54405718963669},"GB2-07":{"attempts":4,"playable":92.09018246265877,"score":92.09018246265877},"GB2-08":{"attempts":3,"playable":92.0608094189822,"score":92.0608094189822}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.92052536041967,"score":92.92052536041967},"GB2-02":{"attempts":1,"playable":94.53388309434065,"score":94.53388309434065},"GB2-03":{"attempts":2,"playable":95.13688039336647,"score":95.13688039336647},"GB2-04":{"attempts":2,"playable":87.42739467186593,"score":87.42739467186593},"GB2-05":{"attempts":1,"playable":93.13442512721471,"score":93.13442512721471},"GB2-06":{"attempts":1,"playable":97.9132349324676,"score":97.9132349324676},"GB2-07":{"attempts":2,"playable":94.09498393455453,"score":94.09498393455453},"GB2-08":{"attempts":1,"playable":97.54300089226564,"score":97.54300089226564}},"medium":{"GB2-01":{"attempts":1,"playable":73.79781901193421,"score":73.79781901193421},"GB2-02":{"attempts":1,"playable":91.61732895032009,"score":91.61732895032009},"GB2-03":{"attempts":1,"playable":90.77669415048375,"score":90.77669415048375},"GB2-04":{"attempts":1,"playable":65.68367287319914,"score":65.68367287319914},"GB2-05":{"attempts":1,"playable":88.73515326223021,"score":88.73515326223021},"GB2-06":{"attempts":1,"playable":87.18500651482474,"score":87.18500651482474},"GB2-07":{"attempts":1,"playable":93.87286624675612,"score":93.87286624675612},"GB2-08":{"attempts":1,"playable":89.32005685488333,"score":89.32005685488333}},"none":{"GB2-01":{"attempts":1,"playable":89.14767811894549,"score":89.14767811894549},"GB2-02":{"attempts":1,"playable":82.37636662266202,"score":82.37636662266202},"GB2-03":{"attempts":1,"playable":90.6455064005157,"score":90.6455064005157},"GB2-04":{"attempts":1,"playable":72.26422930973928,"score":72.26422930973928},"GB2-05":{"attempts":1,"playable":92.58494960082176,"score":92.58494960082176},"GB2-06":{"attempts":1,"playable":83.5339301216177,"score":83.5339301216177},"GB2-07":{"attempts":1,"playable":88.30269720666566,"score":88.30269720666566},"GB2-08":{"attempts":1,"playable":89.31937050979765,"score":89.31937050979765}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-10-15T06:45:21Z","match_totals_all":{"draws":995,"losses":1454,"wins":14025},"match_totals_tracks":{"highest":{"draws":165,"losses":356,"wins":6173},"medium":{"draws":371,"losses":596,"wins":3916},"none":{"draws":459,"losses":502,"wins":3936}},"model_slug":"claude-fable-5-1","overall":{"max":97.9132349324676,"mean":88.4111522567455,"min":65.68367287319914},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":92.92052536041967,"GB2-02":94.53388309434065,"GB2-03":95.13688039336647,"GB2-04":87.42739467186593,"GB2-05":93.13442512721471,"GB2-06":97.9132349324676,"GB2-07":94.09498393455453,"GB2-08":97.54300089226564},"per_game_all":{"GB2-01":85.28867416376646,"GB2-02":89.50919288910758,"GB2-03":92.18636031478864,"GB2-04":75.12509895160144,"GB2-05":91.48484266342223,"GB2-06":89.54405718963669,"GB2-07":92.09018246265877,"GB2-08":92.0608094189822},"per_game_match_totals_all":{"GB2-01":{"draws":3,"losses":49,"wins":566},"GB2-02":{"draws":27,"losses":17,"wins":518},"GB2-03":{"draws":6,"losses":24,"wins":572},"GB2-04":{"draws":56,"losses":41,"wins":495},"GB2-05":{"draws":0,"losses":41,"wins":595},"GB2-06":{"draws":9,"losses":6,"wins":587},"GB2-07":{"draws":0,"losses":34,"wins":592},"GB2-08":{"draws":0,"losses":14,"wins":622}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":49,"wins":566},"GB2-02":{"draws":27,"losses":17,"wins":518},"GB2-03":{"draws":6,"losses":24,"wins":572},"GB2-04":{"draws":56,"losses":41,"wins":495},"GB2-05":{"draws":0,"losses":41,"wins":595},"GB2-06":{"draws":9,"losses":6,"wins":587},"GB2-07":{"draws":0,"losses":34,"wins":592},"GB2-08":{"draws":0,"losses":14,"wins":622}}},"per_game_raw_elo_all":{"GB2-01":1931.3411604116372,"GB2-02":1946.4556680600047,"GB2-03":2082.7370048402568,"GB2-04":1716.7464486328627,"GB2-05":2362.9678766337584,"GB2-06":2262.6494911339782,"GB2-07":2297.15763935269,"GB2-08":2245.5646965415663},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2083.782809232819,"GB2-02":2073.6840342891155,"GB2-03":2210.2136220410775,"GB2-04":1874.5987974636932,"GB2-05":2443.3079200207476,"GB2-06":2590.189987539922,"GB2-07":2391.3992506530085,"GB2-08":2510.054011443904},"medium":{"GB2-01":1730.9284571757216,"GB2-02":1974.9643637666156,"GB2-03":2021.1841589419366,"GB2-04":1606.4558008549152,"GB2-05":2231.990372593369,"GB2-06":2140.208320835904,"GB2-07":2378.483564424358,"GB2-08":2113.3305705089706},"none":{"GB2-01":1979.3122148263715,"GB2-02":1790.7186061242824,"GB2-03":2016.8132335377559,"GB2-04":1669.1847475799796,"GB2-05":2413.605337287159,"GB2-06":2057.550165026109,"GB2-07":2121.5901029807033,"GB2-08":2113.3095076718246}},"per_game_tracks":{"highest":{"GB2-01":92.92052536041967,"GB2-02":94.53388309434065,"GB2-03":95.13688039336647,"GB2-04":87.42739467186593,"GB2-05":93.13442512721471,"GB2-06":97.9132349324676,"GB2-07":94.09498393455453,"GB2-08":97.54300089226564},"medium":{"GB2-01":73.79781901193421,"GB2-02":91.61732895032009,"GB2-03":90.77669415048375,"GB2-04":65.68367287319914,"GB2-05":88.73515326223021,"GB2-06":87.18500651482474,"GB2-07":93.87286624675612,"GB2-08":89.32005685488333},"none":{"GB2-01":89.14767811894549,"GB2-02":82.37636662266202,"GB2-03":90.6455064005157,"GB2-04":72.26422930973928,"GB2-05":92.58494960082176,"GB2-06":83.5339301216177,"GB2-07":88.30269720666566,"GB2-08":89.31937050979765}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":94.08804105081191,"medium":85.12357473307895,"none":86.02184098634565},"reasoning_agg":{"highest":{"max":97.9132349324676,"mean":94.08804105081191,"min":87.42739467186593},"medium":{"max":93.87286624675612,"mean":85.12357473307895,"min":65.68367287319914},"none":{"max":92.58494960082176,"mean":86.02184098634565,"min":72.26422930973928}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.964466317732956}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:4769998e8ac60f55","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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":0.38850799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.6746989999999999},"historical-provider-setting-baseline":{"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":0.388508},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.355686,"mean":0.133143125,"median":0.0768835,"min":0.0400035,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":3.195435},"codegen_latency_ms":{"attempt_count":25,"max_ms":926657,"mean_ms":272565.25,"min_ms":42196,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":926657,"mean_ms":625149.0,"min_ms":331732,"run_count":8},"medium":{"attempt_count":9,"max_ms":198934,"mean_ms":135760.75,"min_ms":63072,"run_count":8},"none":{"attempt_count":8,"max_ms":73464,"mean_ms":56786.0,"min_ms":42196,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":33557,"output_mean":11287.458333333334,"output_min":2159,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":33557,"output_mean":24715.125,"output_min":14936,"run_count":8},"medium":{"attempt_count":9,"output_max":9484,"output_mean":6228.625,"output_min":3242,"run_count":8},"none":{"attempt_count":8,"output_max":3711,"output_mean":2918.625,"output_min":2159,"run_count":8}},"display_name":"GPT-6.1 Sol","economics":{"all":85.75355455486427,"highest":92.67534801502262,"medium":87.22615426505574,"none":77.35916138451445},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[128000],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[128000],"total_output_tokens":270899,"total_reasoning_output_tokens":149779,"total_visible_output_tokens":121120,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6.1-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":67.8312307334295,"score":67.8312307334295},"GB2-02":{"attempts":3,"playable":79.27008508920109,"score":79.27008508920109},"GB2-03":{"attempts":3,"playable":93.50975265678021,"score":93.50975265678021},"GB2-04":{"attempts":3,"playable":85.16003490078386,"score":85.16003490078386},"GB2-05":{"attempts":3,"playable":94.99634212658385,"score":94.99634212658385},"GB2-06":{"attempts":3,"playable":86.26872711273386,"score":86.26872711273386},"GB2-07":{"attempts":3,"playable":95.39683701260822,"score":95.39683701260822},"GB2-08":{"attempts":3,"playable":83.59542680679358,"score":83.59542680679358}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.84659524979985,"score":76.84659524979985},"GB2-02":{"attempts":1,"playable":94.62393555968747,"score":94.62393555968747},"GB2-03":{"attempts":1,"playable":98.29255193107728,"score":98.29255193107728},"GB2-04":{"attempts":1,"playable":95.0075203626499,"score":95.0075203626499},"GB2-05":{"attempts":1,"playable":98.04161368981381,"score":98.04161368981381},"GB2-06":{"attempts":1,"playable":89.03470799394982,"score":89.03470799394982},"GB2-07":{"attempts":1,"playable":95.80671523735789,"score":95.80671523735789},"GB2-08":{"attempts":1,"playable":93.74914409584491,"score":93.74914409584491}},"medium":{"GB2-01":{"attempts":1,"playable":75.69576819747549,"score":75.69576819747549},"GB2-02":{"attempts":1,"playable":78.83739261952189,"score":78.83739261952189},"GB2-03":{"attempts":1,"playable":96.91521221774138,"score":96.91521221774138},"GB2-04":{"attempts":1,"playable":87.18203182709716,"score":87.18203182709716},"GB2-05":{"attempts":1,"playable":95.23181068906672,"score":95.23181068906672},"GB2-06":{"attempts":1,"playable":90.20886582615641,"score":90.20886582615641},"GB2-07":{"attempts":1,"playable":95.80671523735789,"score":95.80671523735789},"GB2-08":{"attempts":1,"playable":77.93143750602894,"score":77.93143750602894}},"none":{"GB2-01":{"attempts":1,"playable":50.95132875301318,"score":50.95132875301318},"GB2-02":{"attempts":1,"playable":64.34892708839389,"score":64.34892708839389},"GB2-03":{"attempts":1,"playable":85.32149382152194,"score":85.32149382152194},"GB2-04":{"attempts":1,"playable":73.29055251260452,"score":73.29055251260452},"GB2-05":{"attempts":1,"playable":91.71560200087104,"score":91.71560200087104},"GB2-06":{"attempts":1,"playable":79.56260751809529,"score":79.56260751809529},"GB2-07":{"attempts":1,"playable":94.5770805631089,"score":94.5770805631089},"GB2-08":{"attempts":1,"playable":79.10569881850691,"score":79.10569881850691}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-13T22:14:54Z","match_totals_all":{"draws":838,"losses":1171,"wins":9073},"match_totals_tracks":{"highest":{"draws":101,"losses":214,"wins":3379},"medium":{"draws":208,"losses":372,"wins":3114},"none":{"draws":529,"losses":585,"wins":2580}},"model_slug":"gpt-6-1-sol","overall":{"max":98.29255193107728,"mean":85.75355455486427,"min":50.95132875301318},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.84659524979985,"GB2-02":94.62393555968747,"GB2-03":98.29255193107728,"GB2-04":95.0075203626499,"GB2-05":98.04161368981381,"GB2-06":89.03470799394982,"GB2-07":95.80671523735789,"GB2-08":93.74914409584491},"per_game_all":{"GB2-01":67.8312307334295,"GB2-02":79.27008508920109,"GB2-03":93.50975265678021,"GB2-04":85.16003490078386,"GB2-05":94.99634212658385,"GB2-06":86.26872711273386,"GB2-07":95.39683701260822,"GB2-08":83.59542680679358},"per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":428,"wins":909},"GB2-02":{"draws":410,"losses":71,"wins":815},"GB2-03":{"draws":33,"losses":74,"wins":1231},"GB2-04":{"draws":216,"losses":99,"wins":1029},"GB2-05":{"draws":0,"losses":67,"wins":1385},"GB2-06":{"draws":110,"losses":130,"wins":1128},"GB2-07":{"draws":0,"losses":57,"wins":1365},"GB2-08":{"draws":2,"losses":245,"wins":1211}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":111,"wins":357},"GB2-02":{"draws":27,"losses":9,"wins":396},"GB2-03":{"draws":2,"losses":5,"wins":439},"GB2-04":{"draws":31,"losses":7,"wins":410},"GB2-05":{"draws":0,"losses":7,"wins":477},"GB2-06":{"draws":41,"losses":28,"wins":387},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":30,"wins":456}},"medium":{"GB2-01":{"draws":11,"losses":111,"wins":346},"GB2-02":{"draws":127,"losses":31,"wins":274},"GB2-03":{"draws":4,"losses":11,"wins":431},"GB2-04":{"draws":34,"losses":43,"wins":371},"GB2-05":{"draws":0,"losses":21,"wins":463},"GB2-06":{"draws":32,"losses":27,"wins":397},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":111,"wins":375}},"none":{"GB2-01":{"draws":56,"losses":206,"wins":206},"GB2-02":{"draws":256,"losses":31,"wins":145},"GB2-03":{"draws":27,"losses":58,"wins":361},"GB2-04":{"draws":151,"losses":49,"wins":248},"GB2-05":{"draws":0,"losses":39,"wins":445},"GB2-06":{"draws":37,"losses":75,"wins":344},"GB2-07":{"draws":0,"losses":23,"wins":451},"GB2-08":{"draws":2,"losses":104,"wins":380}}},"per_game_raw_elo_all":{"GB2-01":1672.0362445978208,"GB2-02":1804.0458968751363,"GB2-03":2223.8861982274343,"GB2-04":1874.2033063431102,"GB2-05":2592.022778499338,"GB2-06":2127.0437674664713,"GB2-07":2473.9041789918,"GB2-08":1989.5994908149053},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1769.8374746496465,"GB2-02":2077.4126424532183,"GB2-03":2468.395817802536,"GB2-04":2075.035859848238,"GB2-05":2835.138274238142,"GB2-06":2186.761397185457,"GB2-07":2500.7174373426883,"GB2-08":2274.217307941074},"medium":{"GB2-01":1754.7966521409771,"GB2-02":1742.333177740789,"GB2-03":2329.236463415094,"GB2-04":1867.7607220461741,"GB2-05":2571.99841858992,"GB2-06":2218.819969001309,"GB2-07":2500.7174373426883,"GB2-08":1835.175572581501},"none":{"GB2-01":1491.4746070028389,"GB2-02":1592.391870431402,"GB2-03":1874.0263134646743,"GB2-04":1679.8133371349186,"GB2-05":2368.9316426699525,"GB2-06":1975.5499362126473,"GB2-07":2420.2776622900237,"GB2-08":1859.405591922141}},"per_game_tracks":{"highest":{"GB2-01":76.84659524979985,"GB2-02":94.62393555968747,"GB2-03":98.29255193107728,"GB2-04":95.0075203626499,"GB2-05":98.04161368981381,"GB2-06":89.03470799394982,"GB2-07":95.80671523735789,"GB2-08":93.74914409584491},"medium":{"GB2-01":75.69576819747549,"GB2-02":78.83739261952189,"GB2-03":96.91521221774138,"GB2-04":87.18203182709716,"GB2-05":95.23181068906672,"GB2-06":90.20886582615641,"GB2-07":95.80671523735789,"GB2-08":77.93143750602894},"none":{"GB2-01":50.95132875301318,"GB2-02":64.34892708839389,"GB2-03":85.32149382152194,"GB2-04":73.29055251260452,"GB2-05":91.71560200087104,"GB2-06":79.56260751809529,"GB2-07":94.5770805631089,"GB2-08":79.10569881850691}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":92.67534801502262,"medium":87.22615426505574,"none":77.35916138451445},"reasoning_agg":{"highest":{"max":98.29255193107728,"mean":92.67534801502262,"min":76.84659524979985},"medium":{"max":96.91521221774138,"mean":87.22615426505574,"min":75.69576819747549},"none":{"max":94.5770805631089,"mean":77.35916138451445,"min":50.95132875301318}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":15.31618663050817}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:092cc29c5fe928e5","codegen_cost_by_reasoning":{"highest":{"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":22.074450000000002},"medium":{"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},"none":{"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":4.570125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":7.138875},"historical-provider-setting-baseline":{"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":4.570125},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":41,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":48},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":7,"max":2.09943,"mean":0.703821875,"median":0.48028875,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":48},"run_count":48,"token_priced_attempt_count":48,"total":33.78345},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":77.47898556856653,"highest":85.95461844089186,"medium":76.65476005388787,"none":72.30112651900082},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":48,"finish_reasons":["end_turn"],"indexed_attempts":48,"output_token_observations":48,"reasoning_token_observations":48,"requested_max_output_token_observations":48,"requested_max_output_tokens":[128000],"total_output_tokens":1230744,"total_reasoning_output_tokens":878158,"total_visible_output_tokens":352586,"visible_token_observations":48},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":2},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"first_pass_admitted":14,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":2},"intensive":{"admitted_plugins":13,"evaluated_cells":16,"first_pass_admitted":13,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"performance_rejections":2},"GB2-07":{"admitted":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06","GB2-07"],"performance_rejections":3}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":72.04838196367835,"score":72.04838196367835},"GB2-02":{"attempts":6,"playable":75.193733734861,"score":75.193733734861},"GB2-03":{"attempts":6,"playable":78.45435691427316,"score":78.45435691427316},"GB2-04":{"attempts":6,"playable":58.54949501073761,"score":58.54949501073761},"GB2-05":{"attempts":6,"playable":90.46292427281408,"score":90.46292427281408},"GB2-06":{"attempts":1,"playable":89.61596467556714,"score":89.61596467556714},"GB2-07":{"attempts":4,"playable":85.57586197975326,"score":85.57586197975326},"GB2-08":{"attempts":6,"playable":82.06814510384832,"score":82.06814510384832}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":68.93506500024736,"score":68.93506500024736},"GB2-02":{"attempts":2,"playable":82.37459933067481,"score":82.37459933067481},"GB2-03":{"attempts":2,"playable":95.13405881366245,"score":95.13405881366245},"GB2-04":{"attempts":2,"playable":82.17887217517122,"score":82.17887217517122},"GB2-05":{"attempts":2,"playable":93.25382058705209,"score":93.25382058705209},"GB2-07":{"attempts":1,"playable":95.82016127869862,"score":95.82016127869862},"GB2-08":{"attempts":2,"playable":83.98575190073647,"score":83.98575190073647}},"medium":{"GB2-01":{"attempts":2,"playable":71.8000601829836,"score":71.8000601829836},"GB2-02":{"attempts":2,"playable":71.44394376703443,"score":71.44394376703443},"GB2-03":{"attempts":2,"playable":86.86526411112825,"score":86.86526411112825},"GB2-04":{"attempts":2,"playable":44.337186337449964,"score":44.337186337449964},"GB2-05":{"attempts":2,"playable":88.83782803681936,"score":88.83782803681936},"GB2-07":{"attempts":2,"playable":84.2405775241937,"score":84.2405775241937},"GB2-08":{"attempts":2,"playable":89.05846041760569,"score":89.05846041760569}},"none":{"GB2-01":{"attempts":2,"playable":75.41002070780411,"score":75.41002070780411},"GB2-02":{"attempts":2,"playable":71.76265810687374,"score":71.76265810687374},"GB2-03":{"attempts":2,"playable":53.363747818028806,"score":53.363747818028806},"GB2-04":{"attempts":2,"playable":49.13242651959162,"score":49.13242651959162},"GB2-05":{"attempts":2,"playable":89.29712419457078,"score":89.29712419457078},"GB2-06":{"attempts":1,"playable":89.61596467556714,"score":89.61596467556714},"GB2-07":{"attempts":1,"playable":76.66684713636744,"score":76.66684713636744},"GB2-08":{"attempts":2,"playable":73.16022299320284,"score":73.16022299320284}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-14T17:54:41Z","match_totals_all":{"draws":3133,"losses":3962,"wins":16603},"match_totals_tracks":{"highest":{"draws":414,"losses":916,"wins":5918},"medium":{"draws":1101,"losses":1385,"wins":5659},"none":{"draws":1618,"losses":1661,"wins":5026}},"model_slug":"claude-opus-5","overall":{"max":95.82016127869862,"mean":78.30350167126018,"min":44.337186337449964},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.93506500024736,"GB2-02":82.37459933067481,"GB2-03":95.13405881366245,"GB2-04":82.17887217517122,"GB2-05":93.25382058705209,"GB2-07":95.82016127869862,"GB2-08":83.98575190073647},"per_game_all":{"GB2-01":72.04838196367835,"GB2-02":75.193733734861,"GB2-03":78.45435691427316,"GB2-04":58.54949501073761,"GB2-05":90.46292427281408,"GB2-07":85.57586197975326,"GB2-08":82.06814510384832},"per_game_match_totals_all":{"GB2-01":{"draws":569,"losses":714,"wins":2132},"GB2-02":{"draws":1114,"losses":278,"wins":1837},"GB2-03":{"draws":192,"losses":651,"wins":2327},"GB2-04":{"draws":1138,"losses":874,"wins":1438},"GB2-05":{"draws":0,"losses":350,"wins":3172},"GB2-06":{"draws":30,"losses":40,"wins":512},"GB2-07":{"draws":0,"losses":346,"wins":2052},"GB2-08":{"draws":90,"losses":709,"wins":3133}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":18,"losses":339,"wins":733},"GB2-02":{"draws":222,"losses":85,"wins":739},"GB2-03":{"draws":10,"losses":51,"wins":959},"GB2-04":{"draws":164,"losses":127,"wins":845},"GB2-05":{"draws":0,"losses":82,"wins":1056},"GB2-07":{"draws":0,"losses":19,"wins":565},"GB2-08":{"draws":0,"losses":213,"wins":1021}},"medium":{"GB2-01":{"draws":116,"losses":287,"wins":751},"GB2-02":{"draws":444,"losses":97,"wins":532},"GB2-03":{"draws":19,"losses":146,"wins":905},"GB2-04":{"draws":520,"losses":390,"wins":258},"GB2-05":{"draws":0,"losses":138,"wins":1054},"GB2-07":{"draws":0,"losses":184,"wins":1026},"GB2-08":{"draws":2,"losses":143,"wins":1133}},"none":{"GB2-01":{"draws":435,"losses":88,"wins":648},"GB2-02":{"draws":448,"losses":96,"wins":566},"GB2-03":{"draws":163,"losses":454,"wins":463},"GB2-04":{"draws":454,"losses":357,"wins":335},"GB2-05":{"draws":0,"losses":130,"wins":1062},"GB2-06":{"draws":30,"losses":40,"wins":512},"GB2-07":{"draws":0,"losses":143,"wins":461},"GB2-08":{"draws":88,"losses":353,"wins":979}}},"per_game_raw_elo_all":{"GB2-01":1747.0722684036045,"GB2-02":1706.6273154604467,"GB2-03":1863.0335329500465,"GB2-04":1569.4539240677052,"GB2-05":2368.7717430815997,"GB2-07":2128.610411829464,"GB2-08":1953.6258358105497},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1732.8050821181796,"GB2-02":1795.5192012913076,"GB2-03":2210.5052388099257,"GB2-04":1802.3400286739798,"GB2-05":2599.5108209715095,"GB2-07":2501.663348885077,"GB2-08":1993.6321801419272},"medium":{"GB2-01":1720.3186539008716,"GB2-02":1659.0699115364419,"GB2-03":1909.9261042042663,"GB2-04":1434.1852227988024,"GB2-05":2250.60047235247,"GB2-07":2052.352864146514,"GB2-08":2119.9616757869358},"none":{"GB2-01":1788.0930691917622,"GB2-02":1665.2928335535908,"GB2-03":1468.6692558359473,"GB2-04":1471.8365207303332,"GB2-05":2256.2039359208184,"GB2-06":2202.3440660838855,"GB2-07":1831.8150224568008,"GB2-08":1747.2836515027866}},"per_game_tracks":{"highest":{"GB2-01":68.93506500024736,"GB2-02":82.37459933067481,"GB2-03":95.13405881366245,"GB2-04":82.17887217517122,"GB2-05":93.25382058705209,"GB2-07":95.82016127869862,"GB2-08":83.98575190073647},"medium":{"GB2-01":71.8000601829836,"GB2-02":71.44394376703443,"GB2-03":86.86526411112825,"GB2-04":44.337186337449964,"GB2-05":88.83782803681936,"GB2-07":84.2405775241937,"GB2-08":89.05846041760569},"none":{"GB2-01":75.41002070780411,"GB2-02":71.76265810687374,"GB2-03":53.363747818028806,"GB2-04":49.13242651959162,"GB2-05":89.29712419457078,"GB2-06":89.61596467556714,"GB2-07":76.66684713636744,"GB2-08":73.16022299320284}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":85.95461844089186,"medium":76.65476005388787,"none":72.30112651900082},"reasoning_agg":{"highest":{"max":95.82016127869862,"mean":85.95461844089186,"min":68.93506500024736},"medium":{"max":89.05846041760569,"mean":76.65476005388787,"min":44.337186337449964},"none":{"max":89.61596467556714,"mean":72.30112651900082,"min":49.13242651959162}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.653491921891046}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:bcc368392551468c","codegen_cost_by_reasoning":{"highest":{"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":1.654358},"medium":{"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},"none":{"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":0.34556800000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.3455680000000001},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425000000005},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":74.50072898492553,"highest":80.69479938060783,"medium":76.15031207520994,"none":66.65707549895882},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[65536],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[65536],"total_output_tokens":214370,"total_reasoning_output_tokens":129853,"total_visible_output_tokens":84517,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":37.28963911404955,"score":37.28963911404955},"GB2-02":{"attempts":3,"playable":68.2597703459449,"score":68.2597703459449},"GB2-03":{"attempts":3,"playable":83.67078726957641,"score":83.67078726957641},"GB2-04":{"attempts":3,"playable":68.42773344393223,"score":68.42773344393223},"GB2-05":{"attempts":3,"playable":88.03225404498966,"score":88.03225404498966},"GB2-06":{"attempts":3,"playable":81.63357889305274,"score":81.63357889305274},"GB2-07":{"attempts":3,"playable":82.2294120512517,"score":82.2294120512517},"GB2-08":{"attempts":3,"playable":86.4626567166071,"score":86.4626567166071}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":10.02697601149701,"score":10.02697601149701},"GB2-02":{"attempts":1,"playable":83.80805197155979,"score":83.80805197155979},"GB2-03":{"attempts":1,"playable":94.1408061074648,"score":94.1408061074648},"GB2-04":{"attempts":1,"playable":88.13358055877055,"score":88.13358055877055},"GB2-05":{"attempts":1,"playable":94.04519202061846,"score":94.04519202061846},"GB2-06":{"attempts":1,"playable":89.99513652247934,"score":89.99513652247934},"GB2-07":{"attempts":1,"playable":94.78105232937035,"score":94.78105232937035},"GB2-08":{"attempts":1,"playable":90.62759952310238,"score":90.62759952310238}},"medium":{"GB2-01":{"attempts":1,"playable":39.59256827010571,"score":39.59256827010571},"GB2-02":{"attempts":1,"playable":68.99069158375235,"score":68.99069158375235},"GB2-03":{"attempts":1,"playable":74.96058695847562,"score":74.96058695847562},"GB2-04":{"attempts":1,"playable":73.29055251260452,"score":73.29055251260452},"GB2-05":{"attempts":1,"playable":91.71560200087104,"score":91.71560200087104},"GB2-06":{"attempts":1,"playable":81.0202793423623,"score":81.0202793423623},"GB2-07":{"attempts":1,"playable":94.37346467331318,"score":94.37346467331318},"GB2-08":{"attempts":1,"playable":85.25875126019481,"score":85.25875126019481}},"none":{"GB2-01":{"attempts":1,"playable":62.24937306054592,"score":62.24937306054592},"GB2-02":{"attempts":1,"playable":51.980567482522545,"score":51.980567482522545},"GB2-03":{"attempts":1,"playable":81.91096874278881,"score":81.91096874278881},"GB2-04":{"attempts":1,"playable":43.859067260421604,"score":43.859067260421604},"GB2-05":{"attempts":1,"playable":78.33596811347945,"score":78.33596811347945},"GB2-06":{"attempts":1,"playable":73.88532081431659,"score":73.88532081431659},"GB2-07":{"attempts":1,"playable":57.53371915107157,"score":57.53371915107157},"GB2-08":{"attempts":1,"playable":83.50161936652408,"score":83.50161936652408}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-13T22:40:34Z","match_totals_all":{"draws":1477,"losses":2134,"wins":7471},"match_totals_tracks":{"highest":{"draws":224,"losses":606,"wins":2864},"medium":{"draws":600,"losses":596,"wins":2498},"none":{"draws":653,"losses":932,"wins":2109}},"model_slug":"gpt-6-sol","overall":{"max":94.78105232937035,"mean":74.50072898492553,"min":10.02697601149701},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.02697601149701,"GB2-02":83.80805197155979,"GB2-03":94.1408061074648,"GB2-04":88.13358055877055,"GB2-05":94.04519202061846,"GB2-06":89.99513652247934,"GB2-07":94.78105232937035,"GB2-08":90.62759952310238},"per_game_all":{"GB2-01":37.28963911404955,"GB2-02":68.2597703459449,"GB2-03":83.67078726957641,"GB2-04":68.42773344393223,"GB2-05":88.03225404498966,"GB2-06":81.63357889305274,"GB2-07":82.2294120512517,"GB2-08":86.4626567166071},"per_game_match_totals_all":{"GB2-01":{"draws":197,"losses":794,"wins":413},"GB2-02":{"draws":579,"losses":134,"wins":583},"GB2-03":{"draws":72,"losses":202,"wins":1064},"GB2-04":{"draws":474,"losses":200,"wins":670},"GB2-05":{"draws":0,"losses":173,"wins":1279},"GB2-06":{"draws":131,"losses":186,"wins":1051},"GB2-07":{"draws":0,"losses":255,"wins":1167},"GB2-08":{"draws":24,"losses":190,"wins":1244}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":410,"wins":29},"GB2-02":{"draws":112,"losses":16,"wins":304},"GB2-03":{"draws":4,"losses":25,"wins":417},"GB2-04":{"draws":49,"losses":31,"wins":368},"GB2-05":{"draws":0,"losses":27,"wins":457},"GB2-06":{"draws":28,"losses":30,"wins":398},"GB2-07":{"draws":0,"losses":22,"wins":452},"GB2-08":{"draws":2,"losses":45,"wins":439}},"medium":{"GB2-01":{"draws":155,"losses":210,"wins":103},"GB2-02":{"draws":199,"losses":39,"wins":194},"GB2-03":{"draws":37,"losses":104,"wins":305},"GB2-04":{"draws":145,"losses":52,"wins":251},"GB2-05":{"draws":0,"losses":39,"wins":445},"GB2-06":{"draws":53,"losses":60,"wins":343},"GB2-07":{"draws":0,"losses":24,"wins":450},"GB2-08":{"draws":11,"losses":68,"wins":407}},"none":{"GB2-01":{"draws":13,"losses":174,"wins":281},"GB2-02":{"draws":268,"losses":79,"wins":85},"GB2-03":{"draws":31,"losses":73,"wins":342},"GB2-04":{"draws":280,"losses":117,"wins":51},"GB2-05":{"draws":0,"losses":107,"wins":377},"GB2-06":{"draws":50,"losses":96,"wins":310},"GB2-07":{"draws":0,"losses":209,"wins":265},"GB2-08":{"draws":11,"losses":77,"wins":398}}},"per_game_raw_elo_all":{"GB2-01":1325.9799663413205,"GB2-02":1646.244061056778,"GB2-03":1886.8144147759797,"GB2-04":1665.4311592581382,"GB2-05":2253.8128688171887,"GB2-06":2027.6733866645825,"GB2-07":2128.8228638267615,"GB2-08":2037.7675309858362},"per_game_raw_elo_tracks":{"highest":{"GB2-01":993.1862767753497,"GB2-02":1812.6366824370295,"GB2-03":2156.8273354087023,"GB2-04":1885.9060128632989,"GB2-05":2495.6835847315433,"GB2-06":2212.808110243033,"GB2-07":2432.899222060706,"GB2-08":2155.142231603745},"medium":{"GB2-01":1382.1091551451618,"GB2-02":1634.8897494732043,"GB2-03":1697.6091670373805,"GB2-04":1679.8133371349186,"GB2-05":2368.9316426699525,"GB2-06":2005.0003782916365,"GB2-07":2407.9198398367193,"GB2-08":2000.6644526834448},"none":{"GB2-01":1602.6444671034499,"GB2-02":1491.2057512601002,"GB2-03":1806.006741881856,"GB2-04":1430.5741277761972,"GB2-05":1896.8233790500706,"GB2-06":1865.2116714590782,"GB2-07":1545.6495295828583,"GB2-08":1957.4959086703186}},"per_game_tracks":{"highest":{"GB2-01":10.02697601149701,"GB2-02":83.80805197155979,"GB2-03":94.1408061074648,"GB2-04":88.13358055877055,"GB2-05":94.04519202061846,"GB2-06":89.99513652247934,"GB2-07":94.78105232937035,"GB2-08":90.62759952310238},"medium":{"GB2-01":39.59256827010571,"GB2-02":68.99069158375235,"GB2-03":74.96058695847562,"GB2-04":73.29055251260452,"GB2-05":91.71560200087104,"GB2-06":81.0202793423623,"GB2-07":94.37346467331318,"GB2-08":85.25875126019481},"none":{"GB2-01":62.24937306054592,"GB2-02":51.980567482522545,"GB2-03":81.91096874278881,"GB2-04":43.859067260421604,"GB2-05":78.33596811347945,"GB2-06":73.88532081431659,"GB2-07":57.53371915107157,"GB2-08":83.50161936652408}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":80.69479938060783,"medium":76.15031207520994,"none":66.65707549895882},"reasoning_agg":{"highest":{"max":94.78105232937035,"mean":80.69479938060783,"min":10.02697601149701},"medium":{"max":94.37346467331318,"mean":76.15031207520994,"min":39.59256827010571},"none":{"max":83.50161936652408,"mean":66.65707549895882,"min":43.859067260421604}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.037723881649015}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:21b3ef9c75b3fd07","codegen_cost_by_reasoning":{"highest":{"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":6.372553749999999},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":1.832505},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983749999998},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":68.4771843013825,"highest":81.30864119505256,"medium":66.69156035642061,"none":57.43135135267428},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":266468,"total_reasoning_output_tokens":151113,"total_visible_output_tokens":115355,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":74.41740649557418,"score":74.41740649557418},"GB2-02":{"attempts":3,"playable":62.89605594261303,"score":62.89605594261303},"GB2-03":{"attempts":3,"playable":66.81442182287257,"score":66.81442182287257},"GB2-04":{"attempts":3,"playable":68.53972564197838,"score":68.53972564197838},"GB2-05":{"attempts":3,"playable":68.85462008214523,"score":68.85462008214523},"GB2-06":{"attempts":3,"playable":62.16365328362613,"score":62.16365328362613},"GB2-07":{"attempts":3,"playable":69.95727347654862,"score":69.95727347654862},"GB2-08":{"attempts":3,"playable":74.17431766570174,"score":74.17431766570174}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.62335407079283,"score":75.62335407079283},"GB2-02":{"attempts":1,"playable":76.43405653070981,"score":76.43405653070981},"GB2-03":{"attempts":1,"playable":83.19723097067929,"score":83.19723097067929},"GB2-04":{"attempts":1,"playable":85.02300500300579,"score":85.02300500300579},"GB2-05":{"attempts":1,"playable":75.13854037645318,"score":75.13854037645318},"GB2-06":{"attempts":1,"playable":85.81477225189565,"score":85.81477225189565},"GB2-07":{"attempts":1,"playable":88.8703299531251,"score":88.8703299531251},"GB2-08":{"attempts":1,"playable":80.36784040375883,"score":80.36784040375883}},"medium":{"GB2-01":{"attempts":1,"playable":68.17438604501133,"score":68.17438604501133},"GB2-02":{"attempts":1,"playable":65.89311394910375,"score":65.89311394910375},"GB2-03":{"attempts":1,"playable":64.12684099346163,"score":64.12684099346163},"GB2-04":{"attempts":1,"playable":79.08209058840787,"score":79.08209058840787},"GB2-05":{"attempts":1,"playable":77.19133342490979,"score":77.19133342490979},"GB2-06":{"attempts":1,"playable":39.43483946850125,"score":39.43483946850125},"GB2-07":{"attempts":1,"playable":72.6610104549538,"score":72.6610104549538},"GB2-08":{"attempts":1,"playable":66.96886792701552,"score":66.96886792701552}},"none":{"GB2-01":{"attempts":1,"playable":79.45447937091839,"score":79.45447937091839},"GB2-02":{"attempts":1,"playable":46.36099734802552,"score":46.36099734802552},"GB2-03":{"attempts":1,"playable":53.11919350447681,"score":53.11919350447681},"GB2-04":{"attempts":1,"playable":41.51408133452148,"score":41.51408133452148},"GB2-05":{"attempts":1,"playable":54.23398644507272,"score":54.23398644507272},"GB2-06":{"attempts":1,"playable":61.24134813048149,"score":61.24134813048149},"GB2-07":{"attempts":1,"playable":48.34048002156697,"score":48.34048002156697},"GB2-08":{"attempts":1,"playable":75.18624466633088,"score":75.18624466633088}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-10-13T22:45:33Z","match_totals_all":{"draws":2557,"losses":4423,"wins":10059},"match_totals_tracks":{"highest":{"draws":402,"losses":893,"wins":4191},"medium":{"draws":820,"losses":1555,"wins":3178},"none":{"draws":1335,"losses":1975,"wins":2690}},"model_slug":"gpt-5-6-sol","overall":{"max":88.8703299531251,"mean":68.47718430138248,"min":39.43483946850125},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.62335407079283,"GB2-02":76.43405653070981,"GB2-03":83.19723097067929,"GB2-04":85.02300500300579,"GB2-05":75.13854037645318,"GB2-06":85.81477225189565,"GB2-07":88.8703299531251,"GB2-08":80.36784040375883},"per_game_all":{"GB2-01":74.41740649557418,"GB2-02":62.89605594261303,"GB2-03":66.81442182287257,"GB2-04":68.53972564197838,"GB2-05":68.85462008214523,"GB2-06":62.16365328362613,"GB2-07":69.95727347654862,"GB2-08":74.17431766570174},"per_game_match_totals_all":{"GB2-01":{"draws":171,"losses":527,"wins":1382},"GB2-02":{"draws":1055,"losses":219,"wins":666},"GB2-03":{"draws":336,"losses":613,"wins":1181},"GB2-04":{"draws":741,"losses":322,"wins":1000},"GB2-05":{"draws":0,"losses":718,"wins":1524},"GB2-06":{"draws":67,"losses":788,"wins":1318},"GB2-07":{"draws":0,"losses":702,"wins":1515},"GB2-08":{"draws":187,"losses":534,"wins":1473}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":184,"wins":485},"GB2-02":{"draws":223,"losses":41,"wins":364},"GB2-03":{"draws":12,"losses":119,"wins":549},"GB2-04":{"draws":103,"losses":54,"wins":505},"GB2-05":{"draws":0,"losses":186,"wins":534},"GB2-06":{"draws":43,"losses":81,"wins":562},"GB2-07":{"draws":0,"losses":73,"wins":627},"GB2-08":{"draws":0,"losses":155,"wins":565}},"medium":{"GB2-01":{"draws":148,"losses":179,"wins":369},"GB2-02":{"draws":306,"losses":72,"wins":254},"GB2-03":{"draws":75,"losses":240,"wins":367},"GB2-04":{"draws":162,"losses":66,"wins":431},"GB2-05":{"draws":0,"losses":170,"wins":552},"GB2-06":{"draws":11,"losses":403,"wins":286},"GB2-07":{"draws":0,"losses":210,"wins":520},"GB2-08":{"draws":118,"losses":215,"wins":399}},"none":{"GB2-01":{"draws":2,"losses":164,"wins":528},"GB2-02":{"draws":526,"losses":106,"wins":48},"GB2-03":{"draws":249,"losses":254,"wins":265},"GB2-04":{"draws":476,"losses":202,"wins":64},"GB2-05":{"draws":0,"losses":362,"wins":438},"GB2-06":{"draws":13,"losses":304,"wins":470},"GB2-07":{"draws":0,"losses":419,"wins":368},"GB2-08":{"draws":69,"losses":164,"wins":509}}},"per_game_raw_elo_all":{"GB2-01":1741.7468048947812,"GB2-02":1589.014453317528,"GB2-03":1622.5214473375097,"GB2-04":1662.8869923712612,"GB2-05":1733.8365855690354,"GB2-06":1677.3234570766679,"GB2-07":1777.9720804991366,"GB2-08":1769.6136023972233},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1753.8653835122018,"GB2-02":1713.0998435457893,"GB2-03":1830.1446337158236,"GB2-04":1830.3515782675165,"GB2-05":1826.0411173213215,"GB2-06":2108.0324434752365,"GB2-07":2142.582979854658,"GB2-08":1886.3141013484933},"medium":{"GB2-01":1665.5536568109585,"GB2-02":1606.1366364331284,"GB2-03":1570.9977061178674,"GB2-04":1745.9747210899868,"GB2-05":1870.2494954509232,"GB2-06":1287.9179709776406,"GB2-07":1762.678606110455,"GB2-08":1641.1873261322835},"none":{"GB2-01":1805.8213743611832,"GB2-02":1447.806879973667,"GB2-03":1466.4220021788376,"GB2-04":1412.3346777562801,"GB2-05":1505.2191439348612,"GB2-06":1636.0199567771258,"GB2-07":1428.654655532297,"GB2-08":1781.3393797108934}},"per_game_tracks":{"highest":{"GB2-01":75.62335407079283,"GB2-02":76.43405653070981,"GB2-03":83.19723097067929,"GB2-04":85.02300500300579,"GB2-05":75.13854037645318,"GB2-06":85.81477225189565,"GB2-07":88.8703299531251,"GB2-08":80.36784040375883},"medium":{"GB2-01":68.17438604501133,"GB2-02":65.89311394910375,"GB2-03":64.12684099346163,"GB2-04":79.08209058840787,"GB2-05":77.19133342490979,"GB2-06":39.43483946850125,"GB2-07":72.6610104549538,"GB2-08":66.96886792701552},"none":{"GB2-01":79.45447937091839,"GB2-02":46.36099734802552,"GB2-03":53.11919350447681,"GB2-04":41.51408133452148,"GB2-05":54.23398644507272,"GB2-06":61.24134813048149,"GB2-07":48.34048002156697,"GB2-08":75.18624466633088}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":81.30864119505256,"medium":66.69156035642061,"none":57.43135135267428},"reasoning_agg":{"highest":{"max":88.8703299531251,"mean":81.30864119505256,"min":75.13854037645318},"medium":{"max":79.08209058840787,"mean":66.69156035642061,"min":39.43483946850125},"none":{"max":79.45447937091839,"mean":57.43135135267428,"min":41.51408133452148}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":23.877289842378282}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:cd329d16ad5e23ab","codegen_cost_by_reasoning":{"highest":{"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":11.76455},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":2.3088499999999996},"historical-provider-setting-intensive":{"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":11.76455}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.2605},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":67.15035765071795,"highest":74.78781135690537,"medium":66.0143640987815,"none":60.648897496467015},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":304913,"total_reasoning_output_tokens":206534,"total_visible_output_tokens":98379,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-fable-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":78.18877853463535,"score":78.18877853463535},"GB2-02":{"attempts":3,"playable":60.34043184437843,"score":60.34043184437843},"GB2-03":{"attempts":3,"playable":47.082808452859446,"score":47.082808452859446},"GB2-04":{"attempts":3,"playable":60.12061715889438,"score":60.12061715889438},"GB2-05":{"attempts":3,"playable":64.66122352117522,"score":64.66122352117522},"GB2-06":{"attempts":3,"playable":82.28874631013174,"score":82.28874631013174},"GB2-07":{"attempts":3,"playable":67.16714450143904,"score":67.16714450143904},"GB2-08":{"attempts":3,"playable":77.35311088222998,"score":77.35311088222998}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":87.36851466007347,"score":87.36851466007347},"GB2-02":{"attempts":1,"playable":78.2770511644101,"score":78.2770511644101},"GB2-03":{"attempts":1,"playable":84.07645518885141,"score":84.07645518885141},"GB2-04":{"attempts":1,"playable":85.31746457790403,"score":85.31746457790403},"GB2-05":{"attempts":1,"playable":55.650027663967826,"score":55.650027663967826},"GB2-06":{"attempts":1,"playable":86.9754994829678,"score":86.9754994829678},"GB2-07":{"attempts":1,"playable":67.27043954254206,"score":67.27043954254206},"GB2-08":{"attempts":1,"playable":53.36703857452615,"score":53.36703857452615}},"medium":{"GB2-01":{"attempts":1,"playable":75.59244249241637,"score":75.59244249241637},"GB2-02":{"attempts":1,"playable":58.70459970393264,"score":58.70459970393264},"GB2-03":{"attempts":1,"playable":21.415140667222374,"score":21.415140667222374},"GB2-04":{"attempts":1,"playable":55.11984000425563,"score":55.11984000425563},"GB2-05":{"attempts":1,"playable":69.30031918212958,"score":69.30031918212958},"GB2-06":{"attempts":1,"playable":82.06449215888364,"score":82.06449215888364},"GB2-07":{"attempts":1,"playable":73.1232123738905,"score":73.1232123738905},"GB2-08":{"attempts":1,"playable":92.79486620752118,"score":92.79486620752118}},"none":{"GB2-01":{"attempts":1,"playable":71.60537845141623,"score":71.60537845141623},"GB2-02":{"attempts":1,"playable":44.03964466479253,"score":44.03964466479253},"GB2-03":{"attempts":1,"playable":35.756829502504566,"score":35.756829502504566},"GB2-04":{"attempts":1,"playable":39.92454689452347,"score":39.92454689452347},"GB2-05":{"attempts":1,"playable":69.03332371742825,"score":69.03332371742825},"GB2-06":{"attempts":1,"playable":77.8262472885438,"score":77.8262472885438},"GB2-07":{"attempts":1,"playable":61.10778158788456,"score":61.10778158788456},"GB2-08":{"attempts":1,"playable":85.89742786464265,"score":85.89742786464265}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-10-13T22:00:28Z","match_totals_all":{"draws":2836,"losses":3835,"wins":8285},"match_totals_tracks":{"highest":{"draws":697,"losses":1040,"wins":3209},"medium":{"draws":921,"losses":1323,"wins":2708},"none":{"draws":1218,"losses":1472,"wins":2368}},"model_slug":"claude-fable-5","overall":{"max":92.79486620752118,"mean":67.15035765071796,"min":21.415140667222374},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":87.36851466007347,"GB2-02":78.2770511644101,"GB2-03":84.07645518885141,"GB2-04":85.31746457790403,"GB2-05":55.650027663967826,"GB2-06":86.9754994829678,"GB2-07":67.27043954254206,"GB2-08":53.36703857452615},"per_game_all":{"GB2-01":78.18877853463535,"GB2-02":60.34043184437843,"GB2-03":47.082808452859446,"GB2-04":60.12061715889438,"GB2-05":64.66122352117522,"GB2-06":82.28874631013174,"GB2-07":67.16714450143904,"GB2-08":77.35311088222998},"per_game_match_totals_all":{"GB2-01":{"draws":133,"losses":396,"wins":1325},"GB2-02":{"draws":950,"losses":219,"wins":533},"GB2-03":{"draws":504,"losses":746,"wins":582},"GB2-04":{"draws":841,"losses":374,"wins":667},"GB2-05":{"draws":0,"losses":762,"wins":1220},"GB2-06":{"draws":95,"losses":314,"wins":1397},"GB2-07":{"draws":0,"losses":704,"wins":1250},"GB2-08":{"draws":313,"losses":320,"wins":1311}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":90,"wins":526},"GB2-02":{"draws":170,"losses":47,"wins":349},"GB2-03":{"draws":105,"losses":58,"wins":441},"GB2-04":{"draws":85,"losses":55,"wins":466},"GB2-05":{"draws":0,"losses":314,"wins":372},"GB2-06":{"draws":26,"losses":74,"wins":502},"GB2-07":{"draws":0,"losses":230,"wins":394},"GB2-08":{"draws":311,"losses":172,"wins":159}},"medium":{"GB2-01":{"draws":52,"losses":145,"wins":419},"GB2-02":{"draws":340,"losses":78,"wins":150},"GB2-03":{"draws":142,"losses":416,"wins":54},"GB2-04":{"draws":341,"losses":119,"wins":150},"GB2-05":{"draws":0,"losses":225,"wins":425},"GB2-06":{"draws":46,"losses":99,"wins":457},"GB2-07":{"draws":0,"losses":191,"wins":439},"GB2-08":{"draws":0,"losses":50,"wins":614}},"none":{"GB2-01":{"draws":81,"losses":161,"wins":380},"GB2-02":{"draws":440,"losses":94,"wins":34},"GB2-03":{"draws":257,"losses":272,"wins":87},"GB2-04":{"draws":415,"losses":200,"wins":51},"GB2-05":{"draws":0,"losses":223,"wins":423},"GB2-06":{"draws":23,"losses":141,"wins":438},"GB2-07":{"draws":0,"losses":283,"wins":417},"GB2-08":{"draws":2,"losses":98,"wins":538}}},"per_game_raw_elo_all":{"GB2-01":1799.4537796003444,"GB2-02":1569.9600546705406,"GB2-03":1444.9144187291943,"GB2-04":1584.3898645725549,"GB2-05":1652.057348303472,"GB2-06":2034.2919059693886,"GB2-07":1680.9862991120435,"GB2-08":1904.5845462614222},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1940.2935364551627,"GB2-02":1735.290473783702,"GB2-03":1847.6465857183468,"GB2-04":1835.184946347715,"GB2-05":1523.3588819396973,"GB2-06":2135.1781764597067,"GB2-07":1679.57617626831,"GB2-08":1462.650159943393},"medium":{"GB2-01":1753.4683761682247,"GB2-02":1544.667246100895,"GB2-03":1172.4596176322837,"GB2-04":1518.1199565537706,"GB2-05":1718.6147098724766,"GB2-06":2026.519112023851,"GB2-07":1770.2681117346392,"GB2-08":2234.043865715763},"none":{"GB2-01":1704.599426177646,"GB2-02":1429.9224441270242,"GB2-03":1314.637052836952,"GB2-04":1399.8646908161793,"GB2-05":1714.198453098242,"GB2-06":1941.1784294246086,"GB2-07":1593.114609333181,"GB2-08":2017.059613125111}},"per_game_tracks":{"highest":{"GB2-01":87.36851466007347,"GB2-02":78.2770511644101,"GB2-03":84.07645518885141,"GB2-04":85.31746457790403,"GB2-05":55.650027663967826,"GB2-06":86.9754994829678,"GB2-07":67.27043954254206,"GB2-08":53.36703857452615},"medium":{"GB2-01":75.59244249241637,"GB2-02":58.70459970393264,"GB2-03":21.415140667222374,"GB2-04":55.11984000425563,"GB2-05":69.30031918212958,"GB2-06":82.06449215888364,"GB2-07":73.1232123738905,"GB2-08":92.79486620752118},"none":{"GB2-01":71.60537845141623,"GB2-02":44.03964466479253,"GB2-03":35.756829502504566,"GB2-04":39.92454689452347,"GB2-05":69.03332371742825,"GB2-06":77.8262472885438,"GB2-07":61.10778158788456,"GB2-08":85.89742786464265}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":74.78781135690537,"medium":66.0143640987815,"none":60.648897496467015},"reasoning_agg":{"highest":{"max":87.36851466007347,"mean":74.78781135690537,"min":53.36703857452615},"medium":{"max":92.79486620752118,"mean":66.0143640987815,"min":21.415140667222374},"none":{"max":85.89742786464265,"mean":60.648897496467015,"min":35.756829502504566}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.13891386043835}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:15240191bfce2009","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.9656476},"historical-provider-setting-intensive":{"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":3.9007551999999994}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.680268,"mean":0.2861911833333333,"median":0.206604,"min":0.09556,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":30},"recorded_attempt_count":30,"run_count":24,"total":6.868588399999999},"codegen_latency_ms":{"attempt_count":30,"max_ms":235793,"mean_ms":83718.41666666667,"min_ms":17910,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":235793,"mean_ms":170391.375,"min_ms":123596,"run_count":8},"medium":{"attempt_count":11,"max_ms":84789,"mean_ms":58477.125,"min_ms":40383,"run_count":8},"none":{"attempt_count":10,"max_ms":29743,"mean_ms":22286.75,"min_ms":17910,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":29674,"output_mean":12261.208333333334,"output_min":3304,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":29674,"output_mean":22547.25,"output_min":16651,"run_count":8},"medium":{"attempt_count":11,"output_max":17493,"output_mean":10166.125,"output_min":6634,"run_count":8},"none":{"attempt_count":10,"output_max":5361,"output_mean":4070.25,"output_min":3304,"run_count":8}},"display_name":"Muse Wonder","economics":{"all":66.24457581375358,"highest":78.50842231335812,"medium":63.538699238747924,"none":56.686605889154684},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[943718],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[943718],"total_output_tokens":294269,"total_reasoning_output_tokens":154600,"total_visible_output_tokens":139669,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-wonder","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":69.42408001198635,"score":69.42408001198635},"GB2-02":{"attempts":3,"playable":54.99432893404197,"score":54.99432893404197},"GB2-03":{"attempts":3,"playable":45.474446439389304,"score":45.474446439389304},"GB2-04":{"attempts":3,"playable":58.35558510215154,"score":58.35558510215154},"GB2-05":{"attempts":3,"playable":87.72892162382799,"score":87.72892162382799},"GB2-06":{"attempts":3,"playable":76.77073931311611,"score":76.77073931311611},"GB2-07":{"attempts":3,"playable":71.42488321850225,"score":71.42488321850225},"GB2-08":{"attempts":3,"playable":65.78362186701314,"score":65.78362186701314}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":85.691346444134,"score":85.691346444134},"GB2-02":{"attempts":1,"playable":66.73045047934345,"score":66.73045047934345},"GB2-03":{"attempts":1,"playable":83.32004765455117,"score":83.32004765455117},"GB2-04":{"attempts":1,"playable":81.20346367106342,"score":81.20346367106342},"GB2-05":{"attempts":1,"playable":92.87433505659686,"score":92.87433505659686},"GB2-06":{"attempts":1,"playable":83.95272543767891,"score":83.95272543767891},"GB2-07":{"attempts":1,"playable":72.99722882492925,"score":72.99722882492925},"GB2-08":{"attempts":1,"playable":61.297780938567904,"score":61.297780938567904}},"medium":{"GB2-01":{"attempts":1,"playable":53.91292530402338,"score":53.91292530402338},"GB2-02":{"attempts":1,"playable":55.89458578294961,"score":55.89458578294961},"GB2-03":{"attempts":1,"playable":36.307173985455314,"score":36.307173985455314},"GB2-04":{"attempts":1,"playable":39.80246084286214,"score":39.80246084286214},"GB2-05":{"attempts":1,"playable":85.3524804036429,"score":85.3524804036429},"GB2-06":{"attempts":1,"playable":76.97290085411551,"score":76.97290085411551},"GB2-07":{"attempts":1,"playable":87.5428767466874,"score":87.5428767466874},"GB2-08":{"attempts":1,"playable":72.5241899902472,"score":72.5241899902472}},"none":{"GB2-01":{"attempts":1,"playable":68.66796828780166,"score":68.66796828780166},"GB2-02":{"attempts":1,"playable":42.35795053983284,"score":42.35795053983284},"GB2-03":{"attempts":1,"playable":16.79611767816141,"score":16.79611767816141},"GB2-04":{"attempts":1,"playable":54.06083079252907,"score":54.06083079252907},"GB2-05":{"attempts":1,"playable":84.95994941124415,"score":84.95994941124415},"GB2-06":{"attempts":1,"playable":69.38659164755391,"score":69.38659164755391},"GB2-07":{"attempts":1,"playable":53.73454408389007,"score":53.73454408389007},"GB2-08":{"attempts":1,"playable":63.528894672224325,"score":63.528894672224325}}},"id":"meta/muse-wonder","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:31Z","match_totals_all":{"draws":2049,"losses":2781,"wins":6252},"match_totals_tracks":{"highest":{"draws":475,"losses":580,"wins":2639},"medium":{"draws":607,"losses":1060,"wins":2027},"none":{"draws":967,"losses":1141,"wins":1586}},"model_slug":"meta-muse-wonder","overall":{"max":92.87433505659686,"mean":66.24457581375357,"min":16.79611767816141},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":85.691346444134,"GB2-02":66.73045047934345,"GB2-03":83.32004765455117,"GB2-04":81.20346367106342,"GB2-05":92.87433505659686,"GB2-06":83.95272543767891,"GB2-07":72.99722882492925,"GB2-08":61.297780938567904},"per_game_all":{"GB2-01":69.42408001198635,"GB2-02":54.99432893404197,"GB2-03":45.474446439389304,"GB2-04":58.35558510215154,"GB2-05":87.72892162382799,"GB2-06":76.77073931311611,"GB2-07":71.42488321850225,"GB2-08":65.78362186701314},"per_game_match_totals_all":{"GB2-01":{"draws":161,"losses":358,"wins":885},"GB2-02":{"draws":850,"losses":174,"wins":272},"GB2-03":{"draws":239,"losses":640,"wins":459},"GB2-04":{"draws":529,"losses":310,"wins":505},"GB2-05":{"draws":0,"losses":179,"wins":1273},"GB2-06":{"draws":91,"losses":276,"wins":1001},"GB2-07":{"draws":0,"losses":417,"wins":1005},"GB2-08":{"draws":179,"losses":427,"wins":852}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":66,"wins":397},"GB2-02":{"draws":239,"losses":29,"wins":164},"GB2-03":{"draws":71,"losses":46,"wins":329},"GB2-04":{"draws":54,"losses":61,"wins":333},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":27,"losses":59,"wins":370},"GB2-07":{"draws":0,"losses":131,"wins":343},"GB2-08":{"draws":79,"losses":155,"wins":252}},"medium":{"GB2-01":{"draws":4,"losses":218,"wins":246},"GB2-02":{"draws":272,"losses":60,"wins":100},"GB2-03":{"draws":86,"losses":255,"wins":105},"GB2-04":{"draws":194,"losses":178,"wins":76},"GB2-05":{"draws":0,"losses":72,"wins":412},"GB2-06":{"draws":26,"losses":93,"wins":337},"GB2-07":{"draws":0,"losses":58,"wins":416},"GB2-08":{"draws":25,"losses":126,"wins":335}},"none":{"GB2-01":{"draws":152,"losses":74,"wins":242},"GB2-02":{"draws":339,"losses":85,"wins":8},"GB2-03":{"draws":82,"losses":339,"wins":25},"GB2-04":{"draws":281,"losses":71,"wins":96},"GB2-05":{"draws":0,"losses":74,"wins":410},"GB2-06":{"draws":38,"losses":124,"wins":294},"GB2-07":{"draws":0,"losses":228,"wins":246},"GB2-08":{"draws":75,"losses":146,"wins":265}}},"per_game_raw_elo_all":{"GB2-01":1699.4509753728025,"GB2-02":1517.5520509513874,"GB2-03":1422.3633948512813,"GB2-04":1560.7667140375297,"GB2-05":2205.727442290365,"GB2-06":1924.0650314047737,"GB2-07":1786.6158469504214,"GB2-08":1627.846560484485},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1907.3386577730635,"GB2-02":1613.7434755990198,"GB2-03":1832.5378123862595,"GB2-04":1773.6533938860907,"GB2-05":2429.091571032076,"GB2-06":2066.584375789969,"GB2-07":1768.1906879780133,"GB2-08":1560.1750011504646},"medium":{"GB2-01":1519.9833879361106,"GB2-02":1522.001442036913,"GB2-03":1319.548920137041,"GB2-04":1398.9023467171296,"GB2-05":2100.887200768473,"GB2-06":1924.514998725947,"GB2-07":2095.0212895746363,"GB2-08":1732.64276140283},"none":{"GB2-01":1671.030880409234,"GB2-02":1416.9112352182294,"GB2-03":1115.0034520305435,"GB2-04":1509.7444015093686,"GB2-05":2087.2035550705473,"GB2-06":1781.0957196984052,"GB2-07":1496.6355632986147,"GB2-08":1590.7219189001607}},"per_game_tracks":{"highest":{"GB2-01":85.691346444134,"GB2-02":66.73045047934345,"GB2-03":83.32004765455117,"GB2-04":81.20346367106342,"GB2-05":92.87433505659686,"GB2-06":83.95272543767891,"GB2-07":72.99722882492925,"GB2-08":61.297780938567904},"medium":{"GB2-01":53.91292530402338,"GB2-02":55.89458578294961,"GB2-03":36.307173985455314,"GB2-04":39.80246084286214,"GB2-05":85.3524804036429,"GB2-06":76.97290085411551,"GB2-07":87.5428767466874,"GB2-08":72.5241899902472},"none":{"GB2-01":68.66796828780166,"GB2-02":42.35795053983284,"GB2-03":16.79611767816141,"GB2-04":54.06083079252907,"GB2-05":84.95994941124415,"GB2-06":69.38659164755391,"GB2-07":53.73454408389007,"GB2-08":63.528894672224325}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":78.50842231335812,"medium":63.538699238747924,"none":56.686605889154684},"reasoning_agg":{"highest":{"max":92.87433505659686,"mean":78.50842231335812,"min":61.297780938567904},"medium":{"max":87.5428767466874,"mean":63.538699238747924,"min":36.307173985455314},"none":{"max":84.95994941124415,"mean":56.686605889154684,"min":16.79611767816141}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":21.82181642420344}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:6c8ebe2f37004c96","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":1.2555551600000001},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":1.2555551600000001},"historical-provider-setting-baseline":{"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":0.43181687999999996},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.9384062,"mean":0.2535328433333333,"median":0.1720692,"min":0.0217974,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":28,"run_count":24,"total":6.084788240000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":4051923,"mean_ms":1012660.4583333334,"min_ms":28293,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":4051923,"mean_ms":2278758.375,"min_ms":1011583,"run_count":8},"medium":{"attempt_count":10,"max_ms":1900345,"mean_ms":621701.25,"min_ms":106081,"run_count":8},"none":{"attempt_count":8,"max_ms":420991,"mean_ms":137521.75,"min_ms":28293,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":206676,"output_mean":54914.25,"output_min":2671,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":206676,"output_mean":121740.75,"output_min":61533,"run_count":8},"medium":{"attempt_count":10,"output_max":49662,"output_mean":33008.75,"output_min":15862,"run_count":8},"none":{"attempt_count":8,"output_max":33431,"output_mean":9993.25,"output_min":2671,"run_count":8}},"display_name":"GLM-5.3","economics":{"all":68.88359151868065,"highest":83.67543350586115,"medium":71.78399211646442,"none":50.98959532629186},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":29,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":84,"requested_max_output_token_observations":10,"requested_max_output_tokens":[131072],"total_output_tokens":1317942,"total_reasoning_output_tokens":1189870,"total_visible_output_tokens":128072,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":60.680656095392344,"score":40.45377073026156},"GB2-02":{"attempts":3,"playable":57.48483619018981,"score":57.48483619018981},"GB2-03":{"attempts":3,"playable":68.757251435423,"score":68.757251435423},"GB2-04":{"attempts":3,"playable":69.33219379893397,"score":69.33219379893397},"GB2-05":{"attempts":3,"playable":72.04442424936418,"score":72.04442424936418},"GB2-06":{"attempts":3,"playable":78.08844839346041,"score":78.08844839346041},"GB2-07":{"attempts":3,"playable":75.49595803522595,"score":75.49595803522595},"GB2-08":{"attempts":3,"playable":60.98202852816723,"score":60.98202852816723}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.48691491307868,"score":73.48691491307868},"GB2-03":{"attempts":1,"playable":84.02202646434827,"score":84.02202646434827},"GB2-04":{"attempts":1,"playable":76.6649877840426,"score":76.6649877840426},"GB2-05":{"attempts":1,"playable":89.79791334230656,"score":89.79791334230656},"GB2-06":{"attempts":1,"playable":90.42270086540265,"score":90.42270086540265},"GB2-07":{"attempts":1,"playable":78.7543581362227,"score":78.7543581362227},"GB2-08":{"attempts":1,"playable":92.57913303562661,"score":92.57913303562661}},"medium":{"GB2-01":{"attempts":1,"playable":53.311968676256484,"score":53.311968676256484},"GB2-02":{"attempts":1,"playable":54.85510683473508,"score":54.85510683473508},"GB2-03":{"attempts":1,"playable":78.5245422844285,"score":78.5245422844285},"GB2-04":{"attempts":1,"playable":84.26654252532613,"score":84.26654252532613},"GB2-05":{"attempts":1,"playable":67.08573777593831,"score":67.08573777593831},"GB2-06":{"attempts":1,"playable":93.18762913179197,"score":93.18762913179197},"GB2-07":{"attempts":1,"playable":76.4766794174891,"score":76.4766794174891},"GB2-08":{"attempts":1,"playable":66.56373028574978,"score":66.56373028574978}},"none":{"GB2-01":{"attempts":1,"playable":68.0493435145282,"score":68.0493435145282},"GB2-02":{"attempts":1,"playable":44.11248682275568,"score":44.11248682275568},"GB2-03":{"attempts":1,"playable":43.7251855574922,"score":43.7251855574922},"GB2-04":{"attempts":1,"playable":47.065051087433204,"score":47.065051087433204},"GB2-05":{"attempts":1,"playable":59.24962162984768,"score":59.24962162984768},"GB2-06":{"attempts":1,"playable":50.65501518318661,"score":50.65501518318661},"GB2-07":{"attempts":1,"playable":71.25683655196605,"score":71.25683655196605},"GB2-08":{"attempts":1,"playable":23.803222263125267,"score":23.803222263125267}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-10-15T06:55:25Z","match_totals_all":{"draws":2743,"losses":3325,"wins":7343},"match_totals_tracks":{"highest":{"draws":337,"losses":366,"wins":2523},"medium":{"draws":845,"losses":1122,"wins":3042},"none":{"draws":1561,"losses":1837,"wins":1778}},"model_slug":"z-ai-glm-5-3","overall":{"max":93.18762913179197,"mean":65.32986392012826,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-02":73.48691491307868,"GB2-03":84.02202646434827,"GB2-04":76.6649877840426,"GB2-05":89.79791334230656,"GB2-06":90.42270086540265,"GB2-07":78.7543581362227,"GB2-08":92.57913303562661},"per_game_all":{"GB2-02":57.48483619018981,"GB2-03":68.757251435423,"GB2-04":69.33219379893397,"GB2-05":72.04442424936418,"GB2-06":78.08844839346041,"GB2-07":75.49595803522595,"GB2-08":60.98202852816723},"per_game_match_totals_all":{"GB2-01":{"draws":232,"losses":442,"wins":646},"GB2-02":{"draws":1107,"losses":192,"wins":333},"GB2-03":{"draws":248,"losses":504,"wins":968},"GB2-04":{"draws":623,"losses":215,"wins":817},"GB2-05":{"draws":0,"losses":566,"wins":1244},"GB2-06":{"draws":74,"losses":407,"wins":1283},"GB2-07":{"draws":0,"losses":471,"wins":1261},"GB2-08":{"draws":459,"losses":528,"wins":791}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":191,"losses":23,"wins":218},"GB2-03":{"draws":4,"losses":76,"wins":366},"GB2-04":{"draws":122,"losses":48,"wins":278},"GB2-05":{"draws":0,"losses":49,"wins":435},"GB2-06":{"draws":20,"losses":32,"wins":404},"GB2-07":{"draws":0,"losses":102,"wins":372},"GB2-08":{"draws":0,"losses":36,"wins":450}},"medium":{"GB2-01":{"draws":122,"losses":274,"wins":294},"GB2-02":{"draws":403,"losses":68,"wins":101},"GB2-03":{"draws":44,"losses":130,"wins":430},"GB2-04":{"draws":102,"losses":52,"wins":449},"GB2-05":{"draws":0,"losses":231,"wins":409},"GB2-06":{"draws":33,"losses":27,"wins":558},"GB2-07":{"draws":0,"losses":164,"wins":464},"GB2-08":{"draws":141,"losses":176,"wins":337}},"none":{"GB2-01":{"draws":110,"losses":168,"wins":352},"GB2-02":{"draws":513,"losses":101,"wins":14},"GB2-03":{"draws":200,"losses":298,"wins":172},"GB2-04":{"draws":399,"losses":115,"wins":90},"GB2-05":{"draws":0,"losses":286,"wins":400},"GB2-06":{"draws":21,"losses":348,"wins":321},"GB2-07":{"draws":0,"losses":205,"wins":425},"GB2-08":{"draws":318,"losses":316,"wins":4}}},"per_game_raw_elo_all":{"GB2-02":1541.4931365934397,"GB2-03":1660.055714513781,"GB2-04":1663.5145580721717,"GB2-05":1843.9544095189983,"GB2-06":2000.3407413178281,"GB2-07":1813.354643537451,"GB2-08":1670.9784589927585},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1680.2460188340713,"GB2-03":1846.5374628376983,"GB2-04":1716.915798397639,"GB2-05":2278.3075911647484,"GB2-06":2224.9219561050077,"GB2-07":1871.5949286722798,"GB2-08":2225.5030060768195},"medium":{"GB2-01":1514.1771278087654,"GB2-02":1513.7487323043517,"GB2-03":1749.2622937752526,"GB2-04":1818.27615730042,"GB2-05":1682.9911012343232,"GB2-06":2314.2279475175683,"GB2-07":1828.3382496167542,"GB2-08":1635.0152888351968},"none":{"GB2-01":1664.1728209840023,"GB2-02":1430.484658641896,"GB2-03":1384.3673869283923,"GB2-04":1455.3517185184553,"GB2-05":1570.5645361579227,"GB2-06":1461.8723203309082,"GB2-07":1740.130752323319,"GB2-08":1152.4170820662598}},"per_game_tracks":{"highest":{"GB2-02":73.48691491307868,"GB2-03":84.02202646434827,"GB2-04":76.6649877840426,"GB2-05":89.79791334230656,"GB2-06":90.42270086540265,"GB2-07":78.7543581362227,"GB2-08":92.57913303562661},"medium":{"GB2-01":53.311968676256484,"GB2-02":54.85510683473508,"GB2-03":78.5245422844285,"GB2-04":84.26654252532613,"GB2-05":67.08573777593831,"GB2-06":93.18762913179197,"GB2-07":76.4766794174891,"GB2-08":66.56373028574978},"none":{"GB2-01":68.0493435145282,"GB2-02":44.11248682275568,"GB2-03":43.7251855574922,"GB2-04":47.065051087433204,"GB2-05":59.24962162984768,"GB2-06":50.65501518318661,"GB2-07":71.25683655196605,"GB2-08":23.803222263125267}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":73.2160043176285,"medium":71.78399211646442,"none":50.98959532629186},"reasoning_agg":{"highest":{"max":92.57913303562661,"mean":73.2160043176285,"min":0.0},"medium":{"max":93.18762913179197,"mean":71.78399211646442,"min":53.311968676256484},"none":{"max":71.25683655196605,"mean":50.98959532629186,"min":23.803222263125267}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":22.22640899133664}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:e41547632cf0ace6","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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":0.663736}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":1.2177,"mean":0.4203770833333333,"median":0.380795,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":10.089049999999999},"codegen_latency_ms":{"attempt_count":29,"max_ms":2516111,"mean_ms":895095.7083333334,"min_ms":107275,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2516111,"mean_ms":1632486.25,"min_ms":1212881,"run_count":8},"medium":{"attempt_count":9,"max_ms":1551665,"mean_ms":884117.375,"min_ms":472109,"run_count":8},"none":{"attempt_count":10,"max_ms":283828,"mean_ms":168683.5,"min_ms":107275,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":195136,"output_mean":67634.29166666667,"output_min":8421,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":195136,"output_mean":126135.375,"output_min":92484,"run_count":8},"medium":{"attempt_count":9,"output_max":95241,"output_mean":63372.625,"output_min":32426,"run_count":8},"none":{"attempt_count":10,"output_max":23276,"output_mean":13394.875,"output_min":8421,"run_count":8}},"display_name":"Grok 4.7","economics":{"all":72.73639922100257,"highest":83.86506086801235,"medium":83.91216513152223,"none":55.253201134878566},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[450000],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[450000],"total_output_tokens":1623223,"total_reasoning_output_tokens":1401661,"total_visible_output_tokens":221562,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":450000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.806009398311126,"score":55.806009398311126},"GB2-02":{"attempts":3,"playable":74.00282503955643,"score":74.00282503955643},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.68317954500054,"score":53.78878636333369},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.84451427092058,"score":45.22967618061372},"GB2-05":{"attempts":3,"playable":76.4099150381124,"score":76.4099150381124},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.55580699700567,"score":57.70387133133712},"GB2-07":{"attempts":3,"playable":70.15471826791541,"score":70.15471826791541},"GB2-08":{"attempts":3,"playable":87.30852836111744,"score":87.30852836111744}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":59.50872458525915,"score":59.50872458525915},"GB2-02":{"attempts":1,"playable":88.62995197874791,"score":88.62995197874791},"GB2-03":{"attempts":1,"playable":88.79801923159218,"score":88.79801923159218},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":92.87433505659686,"score":92.87433505659686},"GB2-06":{"attempts":1,"playable":90.20886582615641,"score":90.20886582615641},"GB2-07":{"attempts":1,"playable":78.55538538079682,"score":78.55538538079682},"GB2-08":{"attempts":1,"playable":88.48014401693706,"score":88.48014401693706}},"medium":{"GB2-01":{"attempts":1,"playable":80.08358918754259,"score":80.08358918754259},"GB2-02":{"attempts":1,"playable":81.0519092998844,"score":81.0519092998844},"GB2-03":{"attempts":1,"playable":72.5683398584089,"score":72.5683398584089},"GB2-04":{"attempts":1,"playable":92.84310128629693,"score":92.84310128629693},"GB2-05":{"attempts":1,"playable":93.45797244389293,"score":93.45797244389293},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":75.97189868543506,"score":75.97189868543506},"GB2-08":{"attempts":1,"playable":91.40834515919485,"score":91.40834515919485}},"none":{"GB2-01":{"attempts":1,"playable":27.825714422131654,"score":27.825714422131654},"GB2-02":{"attempts":1,"playable":52.32661384003697,"score":52.32661384003697},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.84592725554424,"score":42.84592725554424},"GB2-05":{"attempts":1,"playable":42.89743761384742,"score":42.89743761384742},"GB2-06":{"attempts":1,"playable":82.90274816785494,"score":82.90274816785494},"GB2-07":{"attempts":1,"playable":55.93687073751434,"score":55.93687073751434},"GB2-08":{"attempts":1,"playable":82.03709590722038,"score":82.03709590722038}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-13T22:40:21Z","match_totals_all":{"draws":943,"losses":2074,"wins":6715},"match_totals_tracks":{"highest":{"draws":137,"losses":465,"wins":2644},"medium":{"draws":188,"losses":441,"wins":2609},"none":{"draws":618,"losses":1168,"wins":1462}},"model_slug":"x-ai-grok-4-7","overall":{"max":93.45797244389293,"mean":65.05054124753717,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.50872458525915,"GB2-02":88.62995197874791,"GB2-03":88.79801923159218,"GB2-05":92.87433505659686,"GB2-06":90.20886582615641,"GB2-07":78.55538538079682,"GB2-08":88.48014401693706},"per_game_all":{"GB2-01":55.806009398311126,"GB2-02":74.00282503955643,"GB2-05":76.4099150381124,"GB2-07":70.15471826791541,"GB2-08":87.30852836111744},"per_game_match_totals_all":{"GB2-01":{"draws":191,"losses":536,"wins":677},"GB2-02":{"draws":446,"losses":123,"wins":727},"GB2-03":{"draws":92,"losses":142,"wins":658},"GB2-04":{"draws":151,"losses":219,"wins":526},"GB2-05":{"draws":0,"losses":340,"wins":1112},"GB2-06":{"draws":63,"losses":89,"wins":760},"GB2-07":{"draws":0,"losses":436,"wins":986},"GB2-08":{"draws":0,"losses":189,"wins":1269}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":187,"wins":268},"GB2-02":{"draws":46,"losses":27,"wins":359},"GB2-03":{"draws":66,"losses":21,"wins":359},"GB2-05":{"draws":0,"losses":33,"wins":451},"GB2-06":{"draws":12,"losses":37,"wins":407},"GB2-07":{"draws":0,"losses":103,"wins":371},"GB2-08":{"draws":0,"losses":57,"wins":429}},"medium":{"GB2-01":{"draws":31,"losses":80,"wins":357},"GB2-02":{"draws":97,"losses":36,"wins":299},"GB2-03":{"draws":26,"losses":121,"wins":299},"GB2-04":{"draws":34,"losses":16,"wins":398},"GB2-05":{"draws":0,"losses":30,"wins":454},"GB2-07":{"draws":0,"losses":116,"wins":358},"GB2-08":{"draws":0,"losses":42,"wins":444}},"none":{"GB2-01":{"draws":147,"losses":269,"wins":52},"GB2-02":{"draws":303,"losses":60,"wins":69},"GB2-04":{"draws":117,"losses":203,"wins":128},"GB2-05":{"draws":0,"losses":277,"wins":207},"GB2-06":{"draws":51,"losses":52,"wins":353},"GB2-07":{"draws":0,"losses":217,"wins":257},"GB2-08":{"draws":0,"losses":90,"wins":396}}},"per_game_raw_elo_all":{"GB2-01":1549.8523567750206,"GB2-02":1722.3533930536632,"GB2-05":2084.2407239447953,"GB2-07":1737.2587231871446,"GB2-08":2064.5069667239295},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1574.9137418134346,"GB2-02":1901.4172075839492,"GB2-03":1960.4125714329546,"GB2-05":2429.091571032076,"GB2-06":2218.819969001309,"GB2-07":1867.6642871505787,"GB2-08":2088.1605088612764},"medium":{"GB2-01":1814.9580527966489,"GB2-02":1771.7414943266403,"GB2-03":1666.3800210664224,"GB2-04":1999.2706543060913,"GB2-05":2461.422533176016,"GB2-07":1819.2157887612013,"GB2-08":2181.964257192777},"none":{"GB2-01":1259.6852757149782,"GB2-02":1493.9014772504006,"GB2-04":1422.712236522903,"GB2-05":1362.208067626294,"GB2-06":2044.1015923133878,"GB2-07":1524.896093649653,"GB2-08":1923.396134117735}},"per_game_tracks":{"highest":{"GB2-01":59.50872458525915,"GB2-02":88.62995197874791,"GB2-03":88.79801923159218,"GB2-05":92.87433505659686,"GB2-06":90.20886582615641,"GB2-07":78.55538538079682,"GB2-08":88.48014401693706},"medium":{"GB2-01":80.08358918754259,"GB2-02":81.0519092998844,"GB2-03":72.5683398584089,"GB2-04":92.84310128629693,"GB2-05":93.45797244389293,"GB2-07":75.97189868543506,"GB2-08":91.40834515919485},"none":{"GB2-01":27.825714422131654,"GB2-02":52.32661384003697,"GB2-04":42.84592725554424,"GB2-05":42.89743761384742,"GB2-06":82.90274816785494,"GB2-07":55.93687073751434,"GB2-08":82.03709590722038}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":73.3819282595108,"medium":73.42314449008195,"none":48.346550993018745},"reasoning_agg":{"highest":{"max":92.87433505659686,"mean":73.3819282595108,"min":0.0},"medium":{"max":93.45797244389293,"mean":73.42314449008195,"min":0.0},"none":{"max":82.90274816785494,"mean":48.346550993018745,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.076593497063207}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:a3e3cdfd27bf0fcd","codegen_cost_by_reasoning":{"highest":{"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":4.385362},"medium":{"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":0.48637800000000003},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":4.385362}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.72702,"mean":0.21663491666666665,"median":0.058081,"min":0.035834,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":5.199237999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":70064,"output_mean":18803.166666666668,"output_min":1228,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":70064,"output_mean":51989.0,"output_min":25995,"run_count":8},"medium":{"attempt_count":11,"output_max":4348,"output_mean":2842.75,"output_min":1552,"run_count":8},"none":{"attempt_count":8,"output_max":2376,"output_mean":1577.75,"output_min":1228,"run_count":8}},"display_name":"Claude Sonnet 5.5","economics":{"all":61.603594439832165,"highest":91.55324130880604,"medium":52.13377592983007,"none":41.12376608086037},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":451276,"total_reasoning_output_tokens":352227,"total_visible_output_tokens":99049,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.501046504403256,"score":59.501046504403256},"GB2-02":{"attempts":3,"playable":61.45754143602625,"score":61.45754143602625},"GB2-03":{"attempts":3,"playable":58.64597503108201,"score":58.64597503108201},"GB2-04":{"attempts":3,"playable":56.93552146309349,"score":56.93552146309349},"GB2-05":{"attempts":3,"playable":43.498897675567434,"score":43.498897675567434},"GB2-06":{"attempts":3,"playable":61.33093493323233,"score":61.33093493323233},"GB2-07":{"attempts":3,"playable":71.07788350477024,"score":71.07788350477024},"GB2-08":{"attempts":3,"playable":80.38095497048228,"score":80.38095497048228}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":79.24922136479377,"score":79.24922136479377},"GB2-02":{"attempts":1,"playable":95.81965590661629,"score":95.81965590661629},"GB2-03":{"attempts":1,"playable":95.42967930302824,"score":95.42967930302824},"GB2-04":{"attempts":1,"playable":83.99075327802362,"score":83.99075327802362},"GB2-05":{"attempts":1,"playable":97.03882101853787,"score":97.03882101853787},"GB2-06":{"attempts":1,"playable":88.50212526666608,"score":88.50212526666608},"GB2-07":{"attempts":1,"playable":93.56219612434326,"score":93.56219612434326},"GB2-08":{"attempts":1,"playable":98.83347820843915,"score":98.83347820843915}},"medium":{"GB2-01":{"attempts":1,"playable":47.667629343186235,"score":47.667629343186235},"GB2-02":{"attempts":1,"playable":42.4744102652483,"score":42.4744102652483},"GB2-03":{"attempts":1,"playable":31.27566098858375,"score":31.27566098858375},"GB2-04":{"attempts":1,"playable":41.719413978646074,"score":41.719413978646074},"GB2-05":{"attempts":1,"playable":19.358937475208112,"score":19.358937475208112},"GB2-06":{"attempts":1,"playable":77.59294617789291,"score":77.59294617789291},"GB2-07":{"attempts":1,"playable":72.60100788529205,"score":72.60100788529205},"GB2-08":{"attempts":1,"playable":84.38020132458315,"score":84.38020132458315}},"none":{"GB2-01":{"attempts":1,"playable":51.58628880522975,"score":51.58628880522975},"GB2-02":{"attempts":1,"playable":46.078558136214156,"score":46.078558136214156},"GB2-03":{"attempts":1,"playable":49.23258480163404,"score":49.23258480163404},"GB2-04":{"attempts":1,"playable":45.096397132610754,"score":45.096397132610754},"GB2-05":{"attempts":1,"playable":14.098934532956322,"score":14.098934532956322},"GB2-06":{"attempts":1,"playable":17.89773335513799,"score":17.89773335513799},"GB2-07":{"attempts":1,"playable":47.07044650467542,"score":47.07044650467542},"GB2-08":{"attempts":1,"playable":57.92918537842454,"score":57.92918537842454}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-13T23:00:16Z","match_totals_all":{"draws":1949,"losses":3360,"wins":5773},"match_totals_tracks":{"highest":{"draws":287,"losses":163,"wins":3244},"medium":{"draws":857,"losses":1366,"wins":1471},"none":{"draws":805,"losses":1831,"wins":1058}},"model_slug":"claude-sonnet-5-5","overall":{"max":98.83347820843915,"mean":61.603594439832165,"min":14.098934532956322},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.24922136479377,"GB2-02":95.81965590661629,"GB2-03":95.42967930302824,"GB2-04":83.99075327802362,"GB2-05":97.03882101853787,"GB2-06":88.50212526666608,"GB2-07":93.56219612434326,"GB2-08":98.83347820843915},"per_game_all":{"GB2-01":59.501046504403256,"GB2-02":61.45754143602625,"GB2-03":58.64597503108201,"GB2-04":56.93552146309349,"GB2-05":43.498897675567434,"GB2-06":61.33093493323233,"GB2-07":71.07788350477024,"GB2-08":80.38095497048228},"per_game_match_totals_all":{"GB2-01":{"draws":198,"losses":481,"wins":725},"GB2-02":{"draws":691,"losses":164,"wins":441},"GB2-03":{"draws":301,"losses":431,"wins":606},"GB2-04":{"draws":622,"losses":282,"wins":440},"GB2-05":{"draws":0,"losses":820,"wins":632},"GB2-06":{"draws":62,"losses":505,"wins":801},"GB2-07":{"draws":0,"losses":422,"wins":1000},"GB2-08":{"draws":75,"losses":255,"wins":1128}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":143,"losses":28,"wins":297},"GB2-02":{"draws":20,"losses":7,"wins":405},"GB2-03":{"draws":1,"losses":20,"wins":425},"GB2-04":{"draws":76,"losses":37,"wins":335},"GB2-05":{"draws":0,"losses":12,"wins":472},"GB2-06":{"draws":40,"losses":31,"wins":385},"GB2-07":{"draws":0,"losses":28,"wins":446},"GB2-08":{"draws":7,"losses":0,"wins":479}},"medium":{"GB2-01":{"draws":11,"losses":244,"wins":213},"GB2-02":{"draws":338,"losses":85,"wins":9},"GB2-03":{"draws":195,"losses":222,"wins":29},"GB2-04":{"draws":289,"losses":122,"wins":37},"GB2-05":{"draws":0,"losses":391,"wins":93},"GB2-06":{"draws":16,"losses":95,"wins":345},"GB2-07":{"draws":0,"losses":133,"wins":341},"GB2-08":{"draws":8,"losses":74,"wins":404}},"none":{"GB2-01":{"draws":44,"losses":209,"wins":215},"GB2-02":{"draws":333,"losses":72,"wins":27},"GB2-03":{"draws":105,"losses":189,"wins":152},"GB2-04":{"draws":257,"losses":123,"wins":68},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":6,"losses":379,"wins":71},"GB2-07":{"draws":0,"losses":261,"wins":213},"GB2-08":{"draws":60,"losses":181,"wins":245}}},"per_game_raw_elo_all":{"GB2-01":1586.831904087514,"GB2-02":1665.4485564329104,"GB2-03":1644.0775200205492,"GB2-04":1556.0255684893955,"GB2-05":1541.9115590209942,"GB2-06":1687.346731898917,"GB2-07":1845.1139748164198,"GB2-08":2057.0956065192117},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1802.881912538189,"GB2-02":2132.897898498969,"GB2-03":2226.4452310759634,"GB2-04":1813.9893683764244,"GB2-05":2719.613135248813,"GB2-06":2172.920554434001,"GB2-07":2360.8414812321853,"GB2-08":2675.674664446993},"medium":{"GB2-01":1460.046378998732,"GB2-02":1417.8145634089035,"GB2-03":1273.6641539280752,"GB2-04":1413.9383206759378,"GB2-05":1006.6041005082816,"GB2-06":1936.6091567282842,"GB2-07":1761.6997157158955,"GB2-08":1978.746554668598},"none":{"GB2-01":1497.5674207256202,"GB2-02":1445.6332073908588,"GB2-03":1432.1231750576092,"GB2-04":1440.1490164158242,"GB2-05":899.5174413058886,"GB2-06":952.5104845344645,"GB2-07":1412.800727501179,"GB2-08":1516.8656004420443}},"per_game_tracks":{"highest":{"GB2-01":79.24922136479377,"GB2-02":95.81965590661629,"GB2-03":95.42967930302824,"GB2-04":83.99075327802362,"GB2-05":97.03882101853787,"GB2-06":88.50212526666608,"GB2-07":93.56219612434326,"GB2-08":98.83347820843915},"medium":{"GB2-01":47.667629343186235,"GB2-02":42.4744102652483,"GB2-03":31.27566098858375,"GB2-04":41.719413978646074,"GB2-05":19.358937475208112,"GB2-06":77.59294617789291,"GB2-07":72.60100788529205,"GB2-08":84.38020132458315},"none":{"GB2-01":51.58628880522975,"GB2-02":46.078558136214156,"GB2-03":49.23258480163404,"GB2-04":45.096397132610754,"GB2-05":14.098934532956322,"GB2-06":17.89773335513799,"GB2-07":47.07044650467542,"GB2-08":57.92918537842454}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":91.55324130880604,"medium":52.13377592983007,"none":41.12376608086037},"reasoning_agg":{"highest":{"max":98.83347820843915,"mean":91.55324130880604,"min":79.24922136479377},"medium":{"max":84.38020132458315,"mean":52.13377592983007,"min":19.358937475208112},"none":{"max":57.92918537842454,"mean":41.12376608086037,"min":14.098934532956322}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":50.429475227945666}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:b16b290371c28436","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.145718000000001},"codegen_latency_ms":{"attempt_count":27,"max_ms":669574,"mean_ms":286694.0416666667,"min_ms":31621,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":669574,"mean_ms":551119.125,"min_ms":414817,"run_count":8},"medium":{"attempt_count":10,"max_ms":376458,"mean_ms":270365.25,"min_ms":196147,"run_count":8},"none":{"attempt_count":8,"max_ms":49571,"mean_ms":38597.75,"min_ms":31621,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":43739,"output_mean":18621.333333333332,"output_min":1925,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":43739,"output_mean":35745.125,"output_min":27954,"run_count":8},"medium":{"attempt_count":10,"output_max":24183,"output_mean":17614.25,"output_min":12541,"run_count":8},"none":{"attempt_count":8,"output_max":3323,"output_mean":2504.625,"output_min":1925,"run_count":8}},"display_name":"Grok 4.6","economics":{"all":60.75470691548956,"highest":65.20337879079396,"medium":72.02236225836793,"none":45.03837969730678},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":128,"total_output_tokens":446912,"total_reasoning_output_tokens":311255,"total_visible_output_tokens":135657,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.6","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":60.84120444574817,"score":60.84120444574817},"GB2-02":{"attempts":3,"playable":60.678848381117916,"score":60.678848381117916},"GB2-03":{"attempts":3,"playable":54.367676052690676,"score":54.367676052690676},"GB2-04":{"attempts":3,"playable":55.21887355606873,"score":55.21887355606873},"GB2-05":{"attempts":3,"playable":73.28997052015849,"score":73.28997052015849},"GB2-06":{"attempts":3,"playable":53.10623189882543,"score":53.10623189882543},"GB2-07":{"attempts":3,"playable":70.01705816187645,"score":70.01705816187645},"GB2-08":{"attempts":3,"playable":58.517792307430625,"score":58.517792307430625}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":52.02516709236853,"score":52.02516709236853},"GB2-02":{"attempts":1,"playable":82.98802698716054,"score":82.98802698716054},"GB2-03":{"attempts":1,"playable":51.94818770532827,"score":51.94818770532827},"GB2-04":{"attempts":1,"playable":57.145678179244044,"score":57.145678179244044},"GB2-05":{"attempts":1,"playable":85.67642299196721,"score":85.67642299196721},"GB2-06":{"attempts":1,"playable":65.46062148187949,"score":65.46062148187949},"GB2-07":{"attempts":1,"playable":75.79313037684908,"score":75.79313037684908},"GB2-08":{"attempts":1,"playable":50.589795511554584,"score":50.589795511554584}},"medium":{"GB2-01":{"attempts":1,"playable":63.09250074271422,"score":63.09250074271422},"GB2-02":{"attempts":1,"playable":54.93685788860837,"score":54.93685788860837},"GB2-03":{"attempts":1,"playable":68.3746749524683,"score":68.3746749524683},"GB2-04":{"attempts":1,"playable":65.71031625922956,"score":65.71031625922956},"GB2-05":{"attempts":1,"playable":82.34240792841496,"score":82.34240792841496},"GB2-06":{"attempts":1,"playable":80.1781425859964,"score":80.1781425859964},"GB2-07":{"attempts":1,"playable":76.33061474500231,"score":76.33061474500231},"GB2-08":{"attempts":1,"playable":85.21338296450934,"score":85.21338296450934}},"none":{"GB2-01":{"attempts":1,"playable":67.40594550216174,"score":67.40594550216174},"GB2-02":{"attempts":1,"playable":44.11166026758484,"score":44.11166026758484},"GB2-03":{"attempts":1,"playable":42.780165500275444,"score":42.780165500275444},"GB2-04":{"attempts":1,"playable":42.80062622973258,"score":42.80062622973258},"GB2-05":{"attempts":1,"playable":51.85108064009331,"score":51.85108064009331},"GB2-06":{"attempts":1,"playable":13.679931628600395,"score":13.679931628600395},"GB2-07":{"attempts":1,"playable":57.927429363777975,"score":57.927429363777975},"GB2-08":{"attempts":1,"playable":39.750198446227955,"score":39.750198446227955}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-10-13T20:28:24Z","match_totals_all":{"draws":4073,"losses":4332,"wins":6904},"match_totals_tracks":{"highest":{"draws":1214,"losses":1346,"wins":2595},"medium":{"draws":962,"losses":1014,"wins":2936},"none":{"draws":1897,"losses":1972,"wins":1373}},"model_slug":"x-ai-grok-4-6","overall":{"max":85.67642299196721,"mean":60.75470691548956,"min":13.679931628600395},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":52.02516709236853,"GB2-02":82.98802698716054,"GB2-03":51.94818770532827,"GB2-04":57.145678179244044,"GB2-05":85.67642299196721,"GB2-06":65.46062148187949,"GB2-07":75.79313037684908,"GB2-08":50.589795511554584},"per_game_all":{"GB2-01":60.84120444574817,"GB2-02":60.678848381117916,"GB2-03":54.367676052690676,"GB2-04":55.21887355606873,"GB2-05":73.28997052015849,"GB2-06":53.10623189882543,"GB2-07":70.01705816187645,"GB2-08":58.517792307430625},"per_game_match_totals_all":{"GB2-01":{"draws":594,"losses":540,"wins":848},"GB2-02":{"draws":922,"losses":236,"wins":559},"GB2-03":{"draws":783,"losses":538,"wins":591},"GB2-04":{"draws":1012,"losses":396,"wins":520},"GB2-05":{"draws":0,"losses":556,"wins":1398},"GB2-06":{"draws":96,"losses":860,"wins":864},"GB2-07":{"draws":0,"losses":642,"wins":1320},"GB2-08":{"draws":666,"losses":564,"wins":804}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":355,"losses":168,"wins":171},"GB2-02":{"draws":82,"losses":60,"wins":419},"GB2-03":{"draws":145,"losses":277,"wins":264},"GB2-04":{"draws":323,"losses":133,"wins":212},"GB2-05":{"draws":0,"losses":94,"wins":542},"GB2-06":{"draws":51,"losses":225,"wins":338},"GB2-07":{"draws":0,"losses":167,"wins":459},"GB2-08":{"draws":258,"losses":222,"wins":190}},"medium":{"GB2-01":{"draws":160,"losses":177,"wins":289},"GB2-02":{"draws":372,"losses":86,"wins":122},"GB2-03":{"draws":127,"losses":162,"wins":321},"GB2-04":{"draws":266,"losses":87,"wins":243},"GB2-05":{"draws":0,"losses":118,"wins":518},"GB2-06":{"draws":37,"losses":117,"wins":448},"GB2-07":{"draws":0,"losses":163,"wins":461},"GB2-08":{"draws":0,"losses":104,"wins":534}},"none":{"GB2-01":{"draws":79,"losses":195,"wins":388},"GB2-02":{"draws":468,"losses":90,"wins":18},"GB2-03":{"draws":511,"losses":99,"wins":6},"GB2-04":{"draws":423,"losses":176,"wins":65},"GB2-05":{"draws":0,"losses":344,"wins":338},"GB2-06":{"draws":8,"losses":518,"wins":78},"GB2-07":{"draws":0,"losses":312,"wins":400},"GB2-08":{"draws":408,"losses":238,"wins":80}}},"per_game_raw_elo_all":{"GB2-01":1590.0723222734612,"GB2-02":1581.5881113687385,"GB2-03":1482.933212770895,"GB2-04":1521.1235778773014,"GB2-05":1863.627027928939,"GB2-06":1524.2297322347347,"GB2-07":1730.8363372673757,"GB2-08":1583.3560780917044},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1501.783921561493,"GB2-02":1799.8904904402057,"GB2-03":1456.0021626306452,"GB2-04":1534.316265945035,"GB2-05":2112.4117250722643,"GB2-06":1709.9139215050418,"GB2-07":1816.0208358348682,"GB2-08":1431.6125686721907},"medium":{"GB2-01":1611.3235892565606,"GB2-02":1514.3955640725148,"GB2-03":1616.6046812547681,"GB2-04":1606.6943463439213,"GB2-05":2003.4262011234543,"GB2-06":1987.9110245025677,"GB2-07":1825.6828873215172,"GB2-08":1999.5151254288435},"none":{"GB2-01":1657.10945600233,"GB2-02":1430.4782795934957,"GB2-03":1376.192794427271,"GB2-04":1422.3601213429479,"GB2-05":1475.0431575910982,"GB2-06":874.8642506965944,"GB2-07":1550.8052886457413,"GB2-08":1318.9405401740796}},"per_game_tracks":{"highest":{"GB2-01":52.02516709236853,"GB2-02":82.98802698716054,"GB2-03":51.94818770532827,"GB2-04":57.145678179244044,"GB2-05":85.67642299196721,"GB2-06":65.46062148187949,"GB2-07":75.79313037684908,"GB2-08":50.589795511554584},"medium":{"GB2-01":63.09250074271422,"GB2-02":54.93685788860837,"GB2-03":68.3746749524683,"GB2-04":65.71031625922956,"GB2-05":82.34240792841496,"GB2-06":80.1781425859964,"GB2-07":76.33061474500231,"GB2-08":85.21338296450934},"none":{"GB2-01":67.40594550216174,"GB2-02":44.11166026758484,"GB2-03":42.780165500275444,"GB2-04":42.80062622973258,"GB2-05":51.85108064009331,"GB2-06":13.679931628600395,"GB2-07":57.927429363777975,"GB2-08":39.750198446227955}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.20337879079396,"medium":72.02236225836793,"none":45.03837969730678},"reasoning_agg":{"highest":{"max":85.67642299196721,"mean":65.20337879079396,"min":50.589795511554584},"medium":{"max":85.21338296450934,"mean":72.02236225836793,"min":54.93685788860837},"none":{"max":67.40594550216174,"mean":45.03837969730678,"min":13.679931628600395}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":26.983982561061154}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:0c5ad1b0c55c8061","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.9756462500000003},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":60.498307434140344,"highest":65.59023714508044,"medium":60.11297727301764,"none":55.79170788432293},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":482300,"total_reasoning_output_tokens":300593,"total_visible_output_tokens":181707,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":61.244041639142516,"score":61.244041639142516},"GB2-02":{"attempts":3,"playable":49.79967637873719,"score":49.79967637873719},"GB2-03":{"attempts":3,"playable":70.46930433640237,"score":70.46930433640237},"GB2-04":{"attempts":3,"playable":50.70389862736267,"score":50.70389862736267},"GB2-05":{"attempts":3,"playable":59.95657905468406,"score":59.95657905468406},"GB2-06":{"attempts":3,"playable":80.39061092455852,"score":80.39061092455852},"GB2-07":{"attempts":3,"playable":56.09821848600956,"score":56.09821848600956},"GB2-08":{"attempts":3,"playable":55.324130026225795,"score":55.324130026225795}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.4831795295822,"score":55.4831795295822},"GB2-02":{"attempts":1,"playable":68.773922729352,"score":68.773922729352},"GB2-03":{"attempts":1,"playable":73.34383458074768,"score":73.34383458074768},"GB2-04":{"attempts":1,"playable":49.095629359662205,"score":49.095629359662205},"GB2-05":{"attempts":1,"playable":66.89413546092608,"score":66.89413546092608},"GB2-06":{"attempts":1,"playable":86.55135097649156,"score":86.55135097649156},"GB2-07":{"attempts":1,"playable":69.03015309148938,"score":69.03015309148938},"GB2-08":{"attempts":1,"playable":55.54969143239234,"score":55.54969143239234}},"medium":{"GB2-01":{"attempts":1,"playable":71.68600626808946,"score":71.68600626808946},"GB2-02":{"attempts":1,"playable":40.156561681279136,"score":40.156561681279136},"GB2-03":{"attempts":1,"playable":84.4574513428933,"score":84.4574513428933},"GB2-04":{"attempts":1,"playable":56.61919138910319,"score":56.61919138910319},"GB2-05":{"attempts":1,"playable":56.9861937545838,"score":56.9861937545838},"GB2-06":{"attempts":1,"playable":79.70095378200662,"score":79.70095378200662},"GB2-07":{"attempts":1,"playable":56.90639753066365,"score":56.90639753066365},"GB2-08":{"attempts":1,"playable":34.39106243552196,"score":34.39106243552196}},"none":{"GB2-01":{"attempts":1,"playable":56.562939119755896,"score":56.562939119755896},"GB2-02":{"attempts":1,"playable":40.46854472558044,"score":40.46854472558044},"GB2-03":{"attempts":1,"playable":53.6066270855661,"score":53.6066270855661},"GB2-04":{"attempts":1,"playable":46.39687513332262,"score":46.39687513332262},"GB2-05":{"attempts":1,"playable":55.98940794854232,"score":55.98940794854232},"GB2-06":{"attempts":1,"playable":74.91952801517738,"score":74.91952801517738},"GB2-07":{"attempts":1,"playable":42.358104835875636,"score":42.358104835875636},"GB2-08":{"attempts":1,"playable":76.03163621076308,"score":76.03163621076308}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-15T06:05:37Z","match_totals_all":{"draws":3521,"losses":4655,"wins":7053},"match_totals_tracks":{"highest":{"draws":770,"losses":1513,"wins":2759},"medium":{"draws":1462,"losses":1440,"wins":2201},"none":{"draws":1289,"losses":1702,"wins":2093}},"model_slug":"google-gemini-3-8-flash","overall":{"max":86.55135097649156,"mean":60.49830743414034,"min":34.39106243552196},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.4831795295822,"GB2-02":68.773922729352,"GB2-03":73.34383458074768,"GB2-04":49.095629359662205,"GB2-05":66.89413546092608,"GB2-06":86.55135097649156,"GB2-07":69.03015309148938,"GB2-08":55.54969143239234},"per_game_all":{"GB2-01":61.244041639142516,"GB2-02":49.79967637873719,"GB2-03":70.46930433640237,"GB2-04":50.70389862736267,"GB2-05":59.95657905468406,"GB2-06":80.39061092455852,"GB2-07":56.09821848600956,"GB2-08":55.324130026225795},"per_game_match_totals_all":{"GB2-01":{"draws":415,"losses":628,"wins":951},"GB2-02":{"draws":1149,"losses":288,"wins":268},"GB2-03":{"draws":286,"losses":486,"wins":1102},"GB2-04":{"draws":839,"losses":523,"wins":466},"GB2-05":{"draws":0,"losses":859,"wins":1109},"GB2-06":{"draws":107,"losses":349,"wins":1350},"GB2-07":{"draws":0,"losses":910,"wins":1084},"GB2-08":{"draws":725,"losses":612,"wins":723}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":292,"wins":338},"GB2-02":{"draws":232,"losses":75,"wins":263},"GB2-03":{"draws":26,"losses":175,"wins":403},"GB2-04":{"draws":108,"losses":265,"wins":221},"GB2-05":{"draws":0,"losses":242,"wins":406},"GB2-06":{"draws":50,"losses":65,"wins":487},"GB2-07":{"draws":0,"losses":221,"wins":409},"GB2-08":{"draws":298,"losses":178,"wins":232}},"medium":{"GB2-01":{"draws":90,"losses":158,"wins":376},"GB2-02":{"draws":457,"losses":109,"wins":3},"GB2-03":{"draws":119,"losses":50,"wins":437},"GB2-04":{"draws":379,"losses":99,"wins":160},"GB2-05":{"draws":0,"losses":299,"wins":339},"GB2-06":{"draws":30,"losses":124,"wins":448},"GB2-07":{"draws":0,"losses":324,"wins":396},"GB2-08":{"draws":387,"losses":277,"wins":42}},"none":{"GB2-01":{"draws":269,"losses":178,"wins":237},"GB2-02":{"draws":460,"losses":104,"wins":2},"GB2-03":{"draws":141,"losses":261,"wins":262},"GB2-04":{"draws":352,"losses":159,"wins":85},"GB2-05":{"draws":0,"losses":318,"wins":364},"GB2-06":{"draws":27,"losses":160,"wins":415},"GB2-07":{"draws":0,"losses":365,"wins":279},"GB2-08":{"draws":40,"losses":157,"wins":449}}},"per_game_raw_elo_all":{"GB2-01":1595.5139561402177,"GB2-02":1478.2538028699307,"GB2-03":1667.513792046966,"GB2-04":1483.7713561314388,"GB2-05":1582.8060201246642,"GB2-06":1996.1206366549595,"GB2-07":1532.416533244247,"GB2-08":1516.8514515607328},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1535.2234904168674,"GB2-02":1632.8197945053425,"GB2-03":1676.2453694059323,"GB2-04":1471.0376364900726,"GB2-05":1680.0095049698873,"GB2-06":2125.1224436732937,"GB2-07":1705.7471851767232,"GB2-08":1488.0261985970114},"medium":{"GB2-01":1705.546735466725,"GB2-02":1399.7489391980268,"GB2-03":1855.510096347588,"GB2-04":1530.0826718076032,"GB2-05":1540.6720851260416,"GB2-06":1978.3193141999689,"GB2-07":1537.4673271999436,"GB2-08":1265.0139791633126},"none":{"GB2-01":1545.771642537061,"GB2-02":1402.1926749064226,"GB2-03":1470.7859103873777,"GB2-04":1450.1937600966405,"GB2-05":1527.7364702780633,"GB2-06":1884.9201520916156,"GB2-07":1354.0350873560742,"GB2-08":1797.5141769218744}},"per_game_tracks":{"highest":{"GB2-01":55.4831795295822,"GB2-02":68.773922729352,"GB2-03":73.34383458074768,"GB2-04":49.095629359662205,"GB2-05":66.89413546092608,"GB2-06":86.55135097649156,"GB2-07":69.03015309148938,"GB2-08":55.54969143239234},"medium":{"GB2-01":71.68600626808946,"GB2-02":40.156561681279136,"GB2-03":84.4574513428933,"GB2-04":56.61919138910319,"GB2-05":56.9861937545838,"GB2-06":79.70095378200662,"GB2-07":56.90639753066365,"GB2-08":34.39106243552196},"none":{"GB2-01":56.562939119755896,"GB2-02":40.46854472558044,"GB2-03":53.6066270855661,"GB2-04":46.39687513332262,"GB2-05":55.98940794854232,"GB2-06":74.91952801517738,"GB2-07":42.358104835875636,"GB2-08":76.03163621076308}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.59023714508044,"medium":60.11297727301764,"none":55.79170788432293},"reasoning_agg":{"highest":{"max":86.55135097649156,"mean":65.59023714508044,"min":49.095629359662205},"medium":{"max":84.4574513428933,"mean":60.11297727301764,"min":34.39106243552196},"none":{"max":76.03163621076308,"mean":55.79170788432293,"min":40.46854472558044}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":9.798529260757505}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:47f41b32a19bbda4","codegen_cost_by_reasoning":{"highest":{"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":1.9894712499999998},"medium":{"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":0.41740125},"none":{"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":0.19110975}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.41740125},"historical-provider-setting-baseline":{"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":0.19110975},"historical-provider-setting-intensive":{"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":1.9894712499999998}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.358603,"mean":0.10824926041666667,"median":0.050446875,"min":0.017614,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":27,"run_count":24,"total":2.59798225},"codegen_latency_ms":{"attempt_count":27,"max_ms":344702,"mean_ms":125679.0,"min_ms":18724,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":344702,"mean_ms":258574.75,"min_ms":141477,"run_count":8},"medium":{"attempt_count":8,"max_ms":148027,"mean_ms":92816.75,"min_ms":70623,"run_count":8},"none":{"attempt_count":9,"max_ms":39588,"mean_ms":25645.5,"min_ms":18724,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":82251,"output_mean":22811.583333333332,"output_min":2043,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":82251,"output_mean":55365.125,"output_min":27171,"run_count":8},"medium":{"attempt_count":8,"output_max":15366,"output_mean":10008.75,"output_min":7655,"run_count":8},"none":{"attempt_count":9,"output_max":5638,"output_mean":3060.875,"output_min":2043,"run_count":8}},"display_name":"Muse Spark 1.3","economics":{"all":59.43400426956577,"highest":70.70735147338237,"medium":66.32295068687876,"none":41.2717106484362},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":79,"requested_max_output_token_observations":10,"requested_max_output_tokens":[943718],"total_output_tokens":547478,"total_reasoning_output_tokens":432530,"total_visible_output_tokens":114948,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":59.71738411011722,"score":59.71738411011722},"GB2-02":{"attempts":3,"playable":55.44742419762711,"score":55.44742419762711},"GB2-03":{"attempts":3,"playable":67.70525487038186,"score":67.70525487038186},"GB2-04":{"attempts":3,"playable":52.383137281840725,"score":52.383137281840725},"GB2-05":{"attempts":3,"playable":59.02317292149897,"score":59.02317292149897},"GB2-06":{"attempts":3,"playable":69.44847455903229,"score":69.44847455903229},"GB2-07":{"attempts":3,"playable":50.39780409195262,"score":50.39780409195262},"GB2-08":{"attempts":3,"playable":61.34938212407536,"score":61.34938212407536}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.4738694778933,"score":77.4738694778933},"GB2-02":{"attempts":1,"playable":62.6428480919169,"score":62.6428480919169},"GB2-03":{"attempts":1,"playable":83.2196288813942,"score":83.2196288813942},"GB2-04":{"attempts":1,"playable":50.93052016452388,"score":50.93052016452388},"GB2-05":{"attempts":1,"playable":79.15124704781323,"score":79.15124704781323},"GB2-06":{"attempts":1,"playable":84.16308268691833,"score":84.16308268691833},"GB2-07":{"attempts":1,"playable":57.733066703220494,"score":57.733066703220494},"GB2-08":{"attempts":1,"playable":70.34454873337855,"score":70.34454873337855}},"medium":{"GB2-01":{"attempts":1,"playable":75.16858424257485,"score":75.16858424257485},"GB2-02":{"attempts":1,"playable":56.88219599733964,"score":56.88219599733964},"GB2-03":{"attempts":1,"playable":63.56626030021225,"score":63.56626030021225},"GB2-04":{"attempts":1,"playable":63.801053345431214,"score":63.801053345431214},"GB2-05":{"attempts":1,"playable":57.81212558239724,"score":57.81212558239724},"GB2-06":{"attempts":1,"playable":81.54242987424425,"score":81.54242987424425},"GB2-07":{"attempts":1,"playable":54.95123438920412,"score":54.95123438920412},"GB2-08":{"attempts":1,"playable":76.85972176362642,"score":76.85972176362642}},"none":{"GB2-01":{"attempts":1,"playable":26.509698609883525,"score":26.509698609883525},"GB2-02":{"attempts":1,"playable":46.817228503624776,"score":46.817228503624776},"GB2-03":{"attempts":1,"playable":56.329875429539136,"score":56.329875429539136},"GB2-04":{"attempts":1,"playable":42.41783833556706,"score":42.41783833556706},"GB2-05":{"attempts":1,"playable":40.10614613428644,"score":40.10614613428644},"GB2-06":{"attempts":1,"playable":42.63991111593429,"score":42.63991111593429},"GB2-07":{"attempts":1,"playable":38.50911118343324,"score":38.50911118343324},"GB2-08":{"attempts":1,"playable":36.843875875221116,"score":36.843875875221116}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-10-14T17:55:04Z","match_totals_all":{"draws":2816,"losses":4525,"wins":6505},"match_totals_tracks":{"highest":{"draws":490,"losses":869,"wins":2335},"medium":{"draws":785,"losses":1460,"wins":2809},"none":{"draws":1541,"losses":2196,"wins":1361}},"model_slug":"meta-muse-spark-1-3","overall":{"max":84.16308268691833,"mean":59.434004269565776,"min":26.509698609883525},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.4738694778933,"GB2-02":62.6428480919169,"GB2-03":83.2196288813942,"GB2-04":50.93052016452388,"GB2-05":79.15124704781323,"GB2-06":84.16308268691833,"GB2-07":57.733066703220494,"GB2-08":70.34454873337855},"per_game_all":{"GB2-01":59.71738411011722,"GB2-02":55.44742419762711,"GB2-03":67.70525487038186,"GB2-04":52.383137281840725,"GB2-05":59.02317292149897,"GB2-06":69.44847455903229,"GB2-07":50.39780409195262,"GB2-08":61.34938212407536},"per_game_match_totals_all":{"GB2-01":{"draws":147,"losses":658,"wins":897},"GB2-02":{"draws":1082,"losses":201,"wins":311},"GB2-03":{"draws":265,"losses":529,"wins":966},"GB2-04":{"draws":747,"losses":431,"wins":476},"GB2-05":{"draws":0,"losses":797,"wins":1031},"GB2-06":{"draws":78,"losses":512,"wins":1114},"GB2-07":{"draws":0,"losses":908,"wins":876},"GB2-08":{"draws":497,"losses":489,"wins":834}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":107,"wins":359},"GB2-02":{"draws":249,"losses":42,"wins":141},"GB2-03":{"draws":36,"losses":64,"wins":346},"GB2-04":{"draws":119,"losses":166,"wins":163},"GB2-05":{"draws":0,"losses":103,"wins":381},"GB2-06":{"draws":33,"losses":55,"wins":368},"GB2-07":{"draws":0,"losses":208,"wins":266},"GB2-08":{"draws":51,"losses":124,"wins":311}},"medium":{"GB2-01":{"draws":0,"losses":177,"wins":443},"GB2-02":{"draws":368,"losses":73,"wins":125},"GB2-03":{"draws":86,"losses":216,"wins":324},"GB2-04":{"draws":283,"losses":93,"wins":230},"GB2-05":{"draws":0,"losses":301,"wins":355},"GB2-06":{"draws":23,"losses":115,"wins":482},"GB2-07":{"draws":0,"losses":327,"wins":365},"GB2-08":{"draws":25,"losses":158,"wins":485}},"none":{"GB2-01":{"draws":145,"losses":374,"wins":95},"GB2-02":{"draws":465,"losses":86,"wins":45},"GB2-03":{"draws":143,"losses":249,"wins":296},"GB2-04":{"draws":345,"losses":172,"wins":83},"GB2-05":{"draws":0,"losses":393,"wins":295},"GB2-06":{"draws":22,"losses":342,"wins":264},"GB2-07":{"draws":0,"losses":373,"wins":245},"GB2-08":{"draws":421,"losses":207,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1590.3226033007559,"GB2-02":1519.6032046074,"GB2-03":1630.4503819854165,"GB2-04":1498.1648106488353,"GB2-05":1598.0930531436834,"GB2-06":1807.9558453529119,"GB2-07":1455.3572056898845,"GB2-08":1599.5422805838837},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1778.2379706415156,"GB2-02":1577.5882098020747,"GB2-03":1830.5798665308478,"GB2-04":1485.2600033849637,"GB2-05":1916.702959196812,"GB2-06":2071.158158756585,"GB2-07":1548.2580147865735,"GB2-08":1695.1870896883922},"medium":{"GB2-01":1748.0558264297106,"GB2-02":1529.9036810586047,"GB2-03":1565.2616277031898,"GB2-04":1589.8518944983716,"GB2-05":1551.4892461436405,"GB2-06":2015.7115521249784,"GB2-07":1512.2009835846795,"GB2-08":1813.7026700447184},"none":{"GB2-01":1244.6740128310414,"GB2-02":1451.3177229615205,"GB2-03":1495.509651722212,"GB2-04":1419.3825340631704,"GB2-05":1326.0869540905976,"GB2-06":1336.997825177172,"GB2-07":1305.6126186984,"GB2-08":1289.7370820185401}},"per_game_tracks":{"highest":{"GB2-01":77.4738694778933,"GB2-02":62.6428480919169,"GB2-03":83.2196288813942,"GB2-04":50.93052016452388,"GB2-05":79.15124704781323,"GB2-06":84.16308268691833,"GB2-07":57.733066703220494,"GB2-08":70.34454873337855},"medium":{"GB2-01":75.16858424257485,"GB2-02":56.88219599733964,"GB2-03":63.56626030021225,"GB2-04":63.801053345431214,"GB2-05":57.81212558239724,"GB2-06":81.54242987424425,"GB2-07":54.95123438920412,"GB2-08":76.85972176362642},"none":{"GB2-01":26.509698609883525,"GB2-02":46.817228503624776,"GB2-03":56.329875429539136,"GB2-04":42.41783833556706,"GB2-05":40.10614613428644,"GB2-06":42.63991111593429,"GB2-07":38.50911118343324,"GB2-08":36.843875875221116}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":70.70735147338237,"medium":66.32295068687876,"none":41.2717106484362},"reasoning_agg":{"highest":{"max":84.16308268691833,"mean":70.70735147338237,"min":50.93052016452388},"medium":{"max":81.54242987424425,"mean":66.32295068687876,"min":54.95123438920412},"none":{"max":56.329875429539136,"mean":41.2717106484362,"min":26.509698609883525}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.435640824946177}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:a01200a91e174a41","codegen_cost_by_reasoning":{"highest":{"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":0.5964052},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.5964052}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998544},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":57.85916692079428,"highest":63.075265203976286,"medium":61.54263084519188,"none":48.959604713214645},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"reasoning_token_observations":34,"total_output_tokens":187391,"total_reasoning_output_tokens":5791,"total_visible_output_tokens":181600,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":73.68941905529626,"score":73.68941905529626},"GB2-02":{"attempts":3,"playable":51.604208594991206,"score":51.604208594991206},"GB2-03":{"attempts":3,"playable":38.82673764133893,"score":38.82673764133893},"GB2-04":{"attempts":3,"playable":42.869041569738776,"score":42.869041569738776},"GB2-05":{"attempts":3,"playable":61.7929962092251,"score":61.7929962092251},"GB2-06":{"attempts":3,"playable":47.02227470026847,"score":47.02227470026847},"GB2-07":{"attempts":3,"playable":60.946196656253385,"score":60.946196656253385},"GB2-08":{"attempts":3,"playable":86.12246093924203,"score":86.12246093924203}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.97965094895021,"score":84.97965094895021},"GB2-02":{"attempts":1,"playable":59.196702059692655,"score":59.196702059692655},"GB2-03":{"attempts":1,"playable":44.389486641520925,"score":44.389486641520925},"GB2-04":{"attempts":1,"playable":43.40657121434968,"score":43.40657121434968},"GB2-05":{"attempts":1,"playable":74.143248459468,"score":74.143248459468},"GB2-06":{"attempts":1,"playable":52.21672943285366,"score":52.21672943285366},"GB2-07":{"attempts":1,"playable":56.504224165175934,"score":56.504224165175934},"GB2-08":{"attempts":1,"playable":89.7655087097992,"score":89.7655087097992}},"medium":{"GB2-01":{"attempts":1,"playable":84.36921680397818,"score":84.36921680397818},"GB2-02":{"attempts":1,"playable":51.80267064249071,"score":51.80267064249071},"GB2-03":{"attempts":1,"playable":55.614516081011544,"score":55.614516081011544},"GB2-04":{"attempts":1,"playable":42.56348899577041,"score":42.56348899577041},"GB2-05":{"attempts":1,"playable":67.8680305093404,"score":67.8680305093404},"GB2-06":{"attempts":1,"playable":44.196437671360336,"score":44.196437671360336},"GB2-07":{"attempts":1,"playable":58.524867241792414,"score":58.524867241792414},"GB2-08":{"attempts":1,"playable":87.40181881579102,"score":87.40181881579102}},"none":{"GB2-01":{"attempts":1,"playable":51.719389412960396,"score":51.719389412960396},"GB2-02":{"attempts":1,"playable":43.81325308279026,"score":43.81325308279026},"GB2-03":{"attempts":1,"playable":16.476210201484303,"score":16.476210201484303},"GB2-04":{"attempts":1,"playable":42.63706449909622,"score":42.63706449909622},"GB2-05":{"attempts":1,"playable":43.36770965886693,"score":43.36770965886693},"GB2-06":{"attempts":1,"playable":44.653656996591415,"score":44.653656996591415},"GB2-07":{"attempts":1,"playable":67.8094985617918,"score":67.8094985617918},"GB2-08":{"attempts":1,"playable":81.20005529213587,"score":81.20005529213587}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-10-15T06:38:09Z","match_totals_all":{"draws":3814,"losses":5403,"wins":7797},"match_totals_tracks":{"highest":{"draws":1080,"losses":1738,"wins":3251},"medium":{"draws":1017,"losses":1355,"wins":2404},"none":{"draws":1717,"losses":2310,"wins":2142}},"model_slug":"x-ai-grok-4-5","overall":{"max":89.7655087097992,"mean":57.85916692079427,"min":16.476210201484303},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.97965094895021,"GB2-02":59.196702059692655,"GB2-03":44.389486641520925,"GB2-04":43.40657121434968,"GB2-05":74.143248459468,"GB2-06":52.21672943285366,"GB2-07":56.504224165175934,"GB2-08":89.7655087097992},"per_game_all":{"GB2-01":73.68941905529626,"GB2-02":51.604208594991206,"GB2-03":38.82673764133893,"GB2-04":42.869041569738776,"GB2-05":61.7929962092251,"GB2-06":47.02227470026847,"GB2-07":60.946196656253385,"GB2-08":86.12246093924203},"per_game_match_totals_all":{"GB2-01":{"draws":624,"losses":341,"wins":1201},"GB2-02":{"draws":1255,"losses":332,"wins":356},"GB2-03":{"draws":515,"losses":1007,"wins":471},"GB2-04":{"draws":1268,"losses":502,"wins":256},"GB2-05":{"draws":0,"losses":839,"wins":1314},"GB2-06":{"draws":141,"losses":1164,"wins":1010},"GB2-07":{"draws":0,"losses":895,"wins":1321},"GB2-08":{"draws":11,"losses":323,"wins":1868}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":152,"losses":57,"wins":541},"GB2-02":{"draws":344,"losses":117,"wins":219},"GB2-03":{"draws":229,"losses":288,"wins":210},"GB2-04":{"draws":310,"losses":239,"wins":163},"GB2-05":{"draws":0,"losses":207,"wins":549},"GB2-06":{"draws":39,"losses":383,"wins":414},"GB2-07":{"draws":0,"losses":366,"wins":464},"GB2-08":{"draws":6,"losses":81,"wins":691}},"medium":{"GB2-01":{"draws":48,"losses":71,"wins":455},"GB2-02":{"draws":360,"losses":97,"wins":107},"GB2-03":{"draws":139,"losses":175,"wins":216},"GB2-04":{"draws":422,"losses":125,"wins":43},"GB2-05":{"draws":0,"losses":198,"wins":404},"GB2-06":{"draws":43,"losses":342,"wins":257},"GB2-07":{"draws":0,"losses":267,"wins":363},"GB2-08":{"draws":5,"losses":80,"wins":559}},"none":{"GB2-01":{"draws":424,"losses":213,"wins":205},"GB2-02":{"draws":551,"losses":118,"wins":30},"GB2-03":{"draws":147,"losses":544,"wins":45},"GB2-04":{"draws":536,"losses":138,"wins":50},"GB2-05":{"draws":0,"losses":434,"wins":361},"GB2-06":{"draws":59,"losses":439,"wins":339},"GB2-07":{"draws":0,"losses":262,"wins":494},"GB2-08":{"draws":0,"losses":162,"wins":618}}},"per_game_raw_elo_all":{"GB2-01":1758.8392876224689,"GB2-02":1488.8984226048444,"GB2-03":1329.8988607174883,"GB2-04":1422.8900073604611,"GB2-05":1623.1807861339964,"GB2-06":1405.2484968536353,"GB2-07":1592.8039143279827,"GB2-08":2029.733612185869},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1894.2591825667068,"GB2-02":1548.6992568808425,"GB2-03":1390.1106610683637,"GB2-04":1427.0657011612793,"GB2-05":1806.0004208402863,"GB2-06":1486.7351053695434,"GB2-07":1532.2420037188492,"GB2-08":2127.1855526149407},"medium":{"GB2-01":1883.4129862760212,"GB2-02":1489.8215263251252,"GB2-03":1488.9534121168995,"GB2-04":1420.5159922638368,"GB2-05":1695.3230822925934,"GB2-06":1360.9735994622351,"GB2-07":1558.6607722654578,"GB2-08":2057.436739935382},"none":{"GB2-01":1498.8456940246786,"GB2-02":1428.174484608566,"GB2-03":1110.6325089672018,"GB2-04":1421.0883286562673,"GB2-05":1368.2188552691093,"GB2-06":1368.0367857291274,"GB2-07":1687.5089669996407,"GB2-08":1904.5785440072846}},"per_game_tracks":{"highest":{"GB2-01":84.97965094895021,"GB2-02":59.196702059692655,"GB2-03":44.389486641520925,"GB2-04":43.40657121434968,"GB2-05":74.143248459468,"GB2-06":52.21672943285366,"GB2-07":56.504224165175934,"GB2-08":89.7655087097992},"medium":{"GB2-01":84.36921680397818,"GB2-02":51.80267064249071,"GB2-03":55.614516081011544,"GB2-04":42.56348899577041,"GB2-05":67.8680305093404,"GB2-06":44.196437671360336,"GB2-07":58.524867241792414,"GB2-08":87.40181881579102},"none":{"GB2-01":51.719389412960396,"GB2-02":43.81325308279026,"GB2-03":16.476210201484303,"GB2-04":42.63706449909622,"GB2-05":43.36770965886693,"GB2-06":44.653656996591415,"GB2-07":67.8094985617918,"GB2-08":81.20005529213587}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.075265203976286,"medium":61.54263084519188,"none":48.959604713214645},"reasoning_agg":{"highest":{"max":89.7655087097992,"mean":63.075265203976286,"min":43.40657121434968},"medium":{"max":87.40181881579102,"mean":61.54263084519188,"min":42.56348899577041},"none":{"max":81.20005529213587,"mean":48.959604713214645,"min":16.476210201484303}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":14.115660490761641}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:8d0d4b30b8e6e2f5","codegen_cost_by_reasoning":{"highest":{"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":0.48296143999999996},"medium":{"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":0.21156557999999998},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.03177873833333334,"median":0.025158225,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":0.7626897199999999},"codegen_latency_ms":{"attempt_count":29,"max_ms":579647,"mean_ms":182597.75,"min_ms":15305,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":579647,"mean_ms":375199.125,"min_ms":217884,"run_count":8},"medium":{"attempt_count":11,"max_ms":196176,"mean_ms":145630.0,"min_ms":61522,"run_count":8},"none":{"attempt_count":10,"max_ms":51111,"mean_ms":26964.125,"min_ms":15305,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":74293,"output_mean":22693.125,"output_min":2253,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":74293,"output_mean":46016.5,"output_min":25493,"run_count":8},"medium":{"attempt_count":11,"output_max":25418,"output_mean":18052.125,"output_min":8262,"run_count":8},"none":{"attempt_count":10,"output_max":6651,"output_mean":4010.75,"output_min":2253,"run_count":8}},"display_name":"GLM-5.3 FlashX","economics":{"all":57.46034870534182,"highest":68.26906177489275,"medium":52.18099631035094,"none":51.9309880307818},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[131072],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[131072],"total_output_tokens":544635,"total_reasoning_output_tokens":454317,"total_visible_output_tokens":90318,"visible_token_observations":29},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":62.06019531517072,"score":62.06019531517072},"GB2-02":{"attempts":3,"playable":54.47480012132047,"score":54.47480012132047},"GB2-03":{"attempts":3,"playable":63.344581757569415,"score":63.344581757569415},"GB2-04":{"attempts":3,"playable":62.576995453894945,"score":62.576995453894945},"GB2-05":{"attempts":3,"playable":56.31427123388056,"score":56.31427123388056},"GB2-06":{"attempts":3,"playable":67.0068289962338,"score":67.0068289962338},"GB2-07":{"attempts":3,"playable":65.86580805353373,"score":65.86580805353373},"GB2-08":{"attempts":3,"playable":28.039308711130946,"score":28.039308711130946}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.040391136065615,"score":42.040391136065615},"GB2-02":{"attempts":1,"playable":69.6672187768348,"score":69.6672187768348},"GB2-03":{"attempts":1,"playable":84.82231986089548,"score":84.82231986089548},"GB2-04":{"attempts":1,"playable":78.83130272416771,"score":78.83130272416771},"GB2-05":{"attempts":1,"playable":78.54003359020365,"score":78.54003359020365},"GB2-06":{"attempts":1,"playable":81.64671265195327,"score":81.64671265195327},"GB2-07":{"attempts":1,"playable":73.9881534700766,"score":73.9881534700766},"GB2-08":{"attempts":1,"playable":36.61636198894479,"score":36.61636198894479}},"medium":{"GB2-01":{"attempts":1,"playable":78.10080210980087,"score":78.10080210980087},"GB2-02":{"attempts":1,"playable":51.86518972081734,"score":51.86518972081734},"GB2-03":{"attempts":1,"playable":57.895378450792336,"score":57.895378450792336},"GB2-04":{"attempts":1,"playable":56.40297688597641,"score":56.40297688597641},"GB2-05":{"attempts":1,"playable":40.59999002712337,"score":40.59999002712337},"GB2-06":{"attempts":1,"playable":54.97825484869916,"score":54.97825484869916},"GB2-07":{"attempts":1,"playable":58.52992467124022,"score":58.52992467124022},"GB2-08":{"attempts":1,"playable":19.075453768357843,"score":19.075453768357843}},"none":{"GB2-01":{"attempts":1,"playable":66.03939269964569,"score":66.03939269964569},"GB2-02":{"attempts":1,"playable":41.89199186630927,"score":41.89199186630927},"GB2-03":{"attempts":1,"playable":47.316046961020454,"score":47.316046961020454},"GB2-04":{"attempts":1,"playable":52.49670675154072,"score":52.49670675154072},"GB2-05":{"attempts":1,"playable":49.80279008431468,"score":49.80279008431468},"GB2-06":{"attempts":1,"playable":64.39551948804899,"score":64.39551948804899},"GB2-07":{"attempts":1,"playable":65.07934601928436,"score":65.07934601928436},"GB2-08":{"attempts":1,"playable":28.426110376090207,"score":28.426110376090207}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-15T06:51:36Z","match_totals_all":{"draws":2559,"losses":3581,"wins":4942},"match_totals_tracks":{"highest":{"draws":641,"losses":893,"wins":2160},"medium":{"draws":817,"losses":1416,"wins":1461},"none":{"draws":1101,"losses":1272,"wins":1321}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":84.82231986089548,"mean":57.46034870534183,"min":19.075453768357843},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.040391136065615,"GB2-02":69.6672187768348,"GB2-03":84.82231986089548,"GB2-04":78.83130272416771,"GB2-05":78.54003359020365,"GB2-06":81.64671265195327,"GB2-07":73.9881534700766,"GB2-08":36.61636198894479},"per_game_all":{"GB2-01":62.06019531517072,"GB2-02":54.47480012132047,"GB2-03":63.344581757569415,"GB2-04":62.576995453894945,"GB2-05":56.31427123388056,"GB2-06":67.0068289962338,"GB2-07":65.86580805353373,"GB2-08":28.039308711130946},"per_game_match_totals_all":{"GB2-01":{"draws":107,"losses":490,"wins":807},"GB2-02":{"draws":857,"losses":177,"wins":262},"GB2-03":{"draws":153,"losses":450,"wins":735},"GB2-04":{"draws":715,"losses":161,"wins":468},"GB2-05":{"draws":0,"losses":638,"wins":814},"GB2-06":{"draws":67,"losses":431,"wins":870},"GB2-07":{"draws":0,"losses":501,"wins":921},"GB2-08":{"draws":660,"losses":733,"wins":65}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":275,"wins":191},"GB2-02":{"draws":203,"losses":34,"wins":195},"GB2-03":{"draws":6,"losses":71,"wins":369},"GB2-04":{"draws":142,"losses":28,"wins":278},"GB2-05":{"draws":0,"losses":106,"wins":378},"GB2-06":{"draws":29,"losses":69,"wins":358},"GB2-07":{"draws":0,"losses":126,"wins":348},"GB2-08":{"draws":259,"losses":184,"wins":43}},"medium":{"GB2-01":{"draws":6,"losses":102,"wins":360},"GB2-02":{"draws":319,"losses":54,"wins":59},"GB2-03":{"draws":49,"losses":178,"wins":219},"GB2-04":{"draws":260,"losses":71,"wins":117},"GB2-05":{"draws":0,"losses":288,"wins":196},"GB2-06":{"draws":25,"losses":201,"wins":230},"GB2-07":{"draws":0,"losses":204,"wins":270},"GB2-08":{"draws":158,"losses":318,"wins":10}},"none":{"GB2-01":{"draws":99,"losses":113,"wins":256},"GB2-02":{"draws":335,"losses":89,"wins":8},"GB2-03":{"draws":98,"losses":201,"wins":147},"GB2-04":{"draws":313,"losses":62,"wins":73},"GB2-05":{"draws":0,"losses":244,"wins":240},"GB2-06":{"draws":13,"losses":161,"wins":282},"GB2-07":{"draws":0,"losses":171,"wins":303},"GB2-08":{"draws":243,"losses":231,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1611.6957827653823,"GB2-02":1515.004231711889,"GB2-03":1596.2290737468913,"GB2-04":1589.5539896091343,"GB2-05":1561.1909937393818,"GB2-06":1746.7211154023225,"GB2-07":1663.8190108222182,"GB2-08":1195.2149327792588},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1405.974285297092,"GB2-02":1641.4119032919098,"GB2-03":1863.20988203145,"GB2-04":1742.846286170895,"GB2-05":1901.7218130048107,"GB2-06":2017.862247368837,"GB2-07":1784.7159288621654,"GB2-08":1287.4499731999495},"medium":{"GB2-01":1786.7878691928945,"GB2-02":1490.3078701998618,"GB2-03":1510.0345578108227,"GB2-04":1528.3492569271639,"GB2-05":1332.5402691098855,"GB2-06":1531.3040837312017,"GB2-07":1558.72743936975,"GB2-08":1094.82153705803},"none":{"GB2-01":1642.3251938061599,"GB2-02":1413.2929216438947,"GB2-03":1415.4427813984016,"GB2-04":1497.4664257293443,"GB2-05":1449.3108991034496,"GB2-06":1690.9970151069292,"GB2-07":1648.0136642347388,"GB2-08":1203.3732880797966}},"per_game_tracks":{"highest":{"GB2-01":42.040391136065615,"GB2-02":69.6672187768348,"GB2-03":84.82231986089548,"GB2-04":78.83130272416771,"GB2-05":78.54003359020365,"GB2-06":81.64671265195327,"GB2-07":73.9881534700766,"GB2-08":36.61636198894479},"medium":{"GB2-01":78.10080210980087,"GB2-02":51.86518972081734,"GB2-03":57.895378450792336,"GB2-04":56.40297688597641,"GB2-05":40.59999002712337,"GB2-06":54.97825484869916,"GB2-07":58.52992467124022,"GB2-08":19.075453768357843},"none":{"GB2-01":66.03939269964569,"GB2-02":41.89199186630927,"GB2-03":47.316046961020454,"GB2-04":52.49670675154072,"GB2-05":49.80279008431468,"GB2-06":64.39551948804899,"GB2-07":65.07934601928436,"GB2-08":28.426110376090207}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":68.26906177489275,"medium":52.18099631035094,"none":51.9309880307818},"reasoning_agg":{"highest":{"max":84.82231986089548,"mean":68.26906177489275,"min":36.61636198894479},"medium":{"max":78.10080210980087,"mean":52.18099631035094,"min":19.075453768357843},"none":{"max":66.03939269964569,"mean":51.9309880307818,"min":28.426110376090207}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":16.33807374411095}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:a83d1736bfc7ecfa","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0653315,"mean":0.020964483333333336,"median":0.012623549999999999,"min":0.0020421000000000003,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":0.5031475999999999},"codegen_output_tokens":{"attempt_count":28,"output_max":128000,"output_mean":38910.541666666664,"output_min":1643,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":128000,"output_mean":92691.0,"output_min":56566,"run_count":8},"medium":{"attempt_count":9,"output_max":32619,"output_mean":20970.375,"output_min":8448,"run_count":8},"none":{"attempt_count":10,"output_max":6434,"output_mean":3070.25,"output_min":1643,"run_count":8}},"display_name":"Claude Haiku 5.5","economics":{"all":56.431298801654506,"highest":74.53866528960353,"medium":57.32758958188134,"none":39.393284765841024},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[128000],"finish_reason_observations":28,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[128000],"total_output_tokens":933853,"total_reasoning_output_tokens":827092,"total_visible_output_tokens":106761,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-haiku-5-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":41.28965924818732,"score":41.28965924818732},"GB2-02":{"attempts":3,"playable":57.955994653311244,"score":57.955994653311244},"GB2-03":{"attempts":2,"playable":55.240188487129615,"score":55.240188487129615},"GB2-04":{"attempts":3,"playable":62.98946086025529,"score":62.98946086025529},"GB2-05":{"attempts":3,"playable":53.67245720864392,"score":53.67245720864392},"GB2-06":{"attempts":3,"playable":69.80469149415379,"score":69.80469149415379},"GB2-07":{"attempts":3,"playable":58.31022611866998,"score":58.31022611866998},"GB2-08":{"attempts":3,"playable":50.996602028359945,"score":50.996602028359945}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.040391136065615,"score":42.040391136065615},"GB2-02":{"attempts":1,"playable":69.6672187768348,"score":69.6672187768348},"GB2-04":{"attempts":1,"playable":80.55769244488637,"score":80.55769244488637},"GB2-05":{"attempts":1,"playable":86.32893201138968,"score":86.32893201138968},"GB2-06":{"attempts":1,"playable":91.06481970989374,"score":91.06481970989374},"GB2-07":{"attempts":1,"playable":66.26715338164578,"score":66.26715338164578},"GB2-08":{"attempts":1,"playable":85.84444956650876,"score":85.84444956650876}},"medium":{"GB2-01":{"attempts":1,"playable":46.288976350933794,"score":46.288976350933794},"GB2-02":{"attempts":1,"playable":61.95928637276581,"score":61.95928637276581},"GB2-03":{"attempts":1,"playable":67.82766014556184,"score":67.82766014556184},"GB2-04":{"attempts":1,"playable":67.48032707019549,"score":67.48032707019549},"GB2-05":{"attempts":1,"playable":57.76162751248176,"score":57.76162751248176},"GB2-06":{"attempts":1,"playable":68.97879087427252,"score":68.97879087427252},"GB2-07":{"attempts":1,"playable":56.536134155258786,"score":56.536134155258786},"GB2-08":{"attempts":1,"playable":31.78791417358075,"score":31.78791417358075}},"none":{"GB2-01":{"attempts":1,"playable":35.53961025756255,"score":35.53961025756255},"GB2-02":{"attempts":1,"playable":42.24147881033311,"score":42.24147881033311},"GB2-03":{"attempts":1,"playable":42.652716828697386,"score":42.652716828697386},"GB2-04":{"attempts":1,"playable":40.930363065684006,"score":40.930363065684006},"GB2-05":{"attempts":1,"playable":16.926812102060314,"score":16.926812102060314},"GB2-06":{"attempts":1,"playable":49.37046389829511,"score":49.37046389829511},"GB2-07":{"attempts":1,"playable":52.127390819105365,"score":52.127390819105365},"GB2-08":{"attempts":1,"playable":35.35744234499034,"score":35.35744234499034}}},"id":"claude-haiku-5-5","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:08Z","match_totals_all":{"draws":2431,"losses":3564,"wins":4641},"match_totals_tracks":{"highest":{"draws":362,"losses":663,"wins":2223},"medium":{"draws":893,"losses":1188,"wins":1613},"none":{"draws":1176,"losses":1713,"wins":805}},"model_slug":"claude-haiku-5-5","overall":{"max":91.06481970989374,"mean":57.086513212441965,"min":16.926812102060314},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":18,"overall_ranking_status":"partial","per_game":{"GB2-01":42.040391136065615,"GB2-02":69.6672187768348,"GB2-04":80.55769244488637,"GB2-05":86.32893201138968,"GB2-06":91.06481970989374,"GB2-07":66.26715338164578,"GB2-08":85.84444956650876},"per_game_all":{"GB2-01":41.28965924818732,"GB2-02":57.955994653311244,"GB2-04":62.98946086025529,"GB2-05":53.67245720864392,"GB2-06":69.80469149415379,"GB2-07":58.31022611866998,"GB2-08":50.996602028359945},"per_game_match_totals_all":{"GB2-01":{"draws":239,"losses":719,"wins":446},"GB2-02":{"draws":774,"losses":173,"wins":349},"GB2-03":{"draws":252,"losses":301,"wins":339},"GB2-04":{"draws":582,"losses":221,"wins":541},"GB2-05":{"draws":0,"losses":676,"wins":776},"GB2-06":{"draws":57,"losses":396,"wins":915},"GB2-07":{"draws":0,"losses":615,"wins":807},"GB2-08":{"draws":527,"losses":463,"wins":468}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":32,"losses":260,"wins":176},"GB2-02":{"draws":193,"losses":39,"wins":200},"GB2-04":{"draws":102,"losses":40,"wins":306},"GB2-05":{"draws":0,"losses":67,"wins":417},"GB2-06":{"draws":34,"losses":22,"wins":400},"GB2-07":{"draws":0,"losses":165,"wins":309},"GB2-08":{"draws":1,"losses":70,"wins":415}},"medium":{"GB2-01":{"draws":124,"losses":194,"wins":150},"GB2-02":{"draws":235,"losses":52,"wins":145},"GB2-03":{"draws":87,"losses":113,"wins":246},"GB2-04":{"draws":190,"losses":56,"wins":202},"GB2-05":{"draws":0,"losses":206,"wins":278},"GB2-06":{"draws":6,"losses":142,"wins":308},"GB2-07":{"draws":0,"losses":214,"wins":260},"GB2-08":{"draws":251,"losses":211,"wins":24}},"none":{"GB2-01":{"draws":83,"losses":265,"wins":120},"GB2-02":{"draws":346,"losses":82,"wins":4},"GB2-03":{"draws":165,"losses":188,"wins":93},"GB2-04":{"draws":290,"losses":125,"wins":33},"GB2-05":{"draws":0,"losses":403,"wins":81},"GB2-06":{"draws":17,"losses":232,"wins":207},"GB2-07":{"draws":0,"losses":236,"wins":238},"GB2-08":{"draws":275,"losses":182,"wins":29}}},"per_game_raw_elo_all":{"GB2-01":1398.1833464837102,"GB2-02":1543.05898975143,"GB2-04":1598.5129434559556,"GB2-05":1548.7947564481717,"GB2-06":1819.6655485058352,"GB2-07":1557.9598345731035,"GB2-08":1509.647018979597},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1405.974285297092,"GB2-02":1641.4119032919098,"GB2-04":1764.9839264934878,"GB2-05":2136.272422826084,"GB2-06":2243.816093912371,"GB2-07":1664.9942127147785,"GB2-08":2015.68390791794},"medium":{"GB2-01":1446.8544256333093,"GB2-02":1571.7576480269672,"GB2-03":1610.4941328650937,"GB2-04":1622.7874951323392,"GB2-05":1550.8250831611274,"GB2-06":1773.6006483290578,"GB2-07":1532.6560414496512,"GB2-08":1238.4814894523558},"none":{"GB2-01":1341.7213285207297,"GB2-02":1416.0074179354133,"GB2-03":1375.0896470261284,"GB2-04":1407.767408742039,"GB2-05":959.2867633573028,"GB2-06":1441.5799032760765,"GB2-07":1476.2292495548804,"GB2-08":1274.7756595684953}},"per_game_tracks":{"highest":{"GB2-01":42.040391136065615,"GB2-02":69.6672187768348,"GB2-04":80.55769244488637,"GB2-05":86.32893201138968,"GB2-06":91.06481970989374,"GB2-07":66.26715338164578,"GB2-08":85.84444956650876},"medium":{"GB2-01":46.288976350933794,"GB2-02":61.95928637276581,"GB2-03":67.82766014556184,"GB2-04":67.48032707019549,"GB2-05":57.76162751248176,"GB2-06":68.97879087427252,"GB2-07":56.536134155258786,"GB2-08":31.78791417358075},"none":{"GB2-01":35.53961025756255,"GB2-02":42.24147881033311,"GB2-03":42.652716828697386,"GB2-04":40.930363065684006,"GB2-05":16.926812102060314,"GB2-06":49.37046389829511,"GB2-07":52.127390819105365,"GB2-08":35.35744234499034}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":74.53866528960353,"medium":57.32758958188134,"none":39.393284765841024},"reasoning_agg":{"highest":{"max":91.06481970989374,"mean":74.53866528960353,"min":42.040391136065615},"medium":{"max":68.97879087427252,"mean":57.32758958188134,"min":31.78791417358075},"none":{"max":52.127390819105365,"mean":39.393284765841024,"min":16.926812102060314}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":35.145380523762505}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:ef785d3860d1888f","codegen_cost_by_reasoning":{"highest":{"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":0.11920932499999999},"medium":{"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":0.046288649999999994},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.11920932499999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.195345875},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214245,"mean_ms":417506.625,"min_ms":32605,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1196482,"mean_ms":748510.375,"min_ms":448704,"run_count":8},"medium":{"attempt_count":8,"max_ms":672648,"mean_ms":296260.625,"min_ms":146516,"run_count":8},"none":{"attempt_count":11,"max_ms":1214245,"mean_ms":207748.875,"min_ms":32605,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":65809,"output_mean":27118.375,"output_min":2294,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":65809,"output_mean":50033.0,"output_min":27276,"run_count":8},"medium":{"attempt_count":8,"output_max":58608,"output_mean":20833.875,"output_min":10904,"run_count":8},"none":{"attempt_count":11,"output_max":54017,"output_mean":10488.25,"output_min":2294,"run_count":8}},"display_name":"GLM-5.3 Flash","economics":{"all":56.9658742786463,"highest":60.25780793590707,"medium":63.0633044602819,"none":47.57651043974991},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":134,"total_output_tokens":650841,"total_reasoning_output_tokens":555865,"total_visible_output_tokens":94976,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.64464855706722,"score":58.64464855706722},"GB2-02":{"attempts":3,"playable":52.411242190416594,"score":52.411242190416594},"GB2-03":{"attempts":3,"playable":70.16725039365572,"score":70.16725039365572},"GB2-04":{"attempts":3,"playable":72.38518762707002,"score":72.38518762707002},"GB2-05":{"attempts":3,"playable":52.71002917216973,"score":52.71002917216973},"GB2-06":{"attempts":3,"playable":47.72922712573804,"score":47.72922712573804},"GB2-07":{"attempts":3,"playable":72.33466085441559,"score":72.33466085441559},"GB2-08":{"attempts":3,"playable":29.344748308637474,"score":29.344748308637474}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":67.30093094068577,"score":67.30093094068577},"GB2-02":{"attempts":1,"playable":66.16268175788127,"score":66.16268175788127},"GB2-03":{"attempts":1,"playable":75.40985499306336,"score":75.40985499306336},"GB2-04":{"attempts":1,"playable":79.43854882042322,"score":79.43854882042322},"GB2-05":{"attempts":1,"playable":74.32565986195104,"score":74.32565986195104},"GB2-06":{"attempts":1,"playable":18.42555531911521,"score":18.42555531911521},"GB2-07":{"attempts":1,"playable":69.71330481040566,"score":69.71330481040566},"GB2-08":{"attempts":1,"playable":31.285926983731056,"score":31.285926983731056}},"medium":{"GB2-01":{"attempts":1,"playable":71.78603436176813,"score":71.78603436176813},"GB2-02":{"attempts":1,"playable":46.08580656296842,"score":46.08580656296842},"GB2-03":{"attempts":1,"playable":77.82001579036954,"score":77.82001579036954},"GB2-04":{"attempts":1,"playable":71.95843154045104,"score":71.95843154045104},"GB2-05":{"attempts":1,"playable":46.70178402428609,"score":46.70178402428609},"GB2-06":{"attempts":1,"playable":80.96145885686715,"score":80.96145885686715},"GB2-07":{"attempts":1,"playable":75.66087923111871,"score":75.66087923111871},"GB2-08":{"attempts":1,"playable":33.532025314426136,"score":33.532025314426136}},"none":{"GB2-01":{"attempts":1,"playable":36.846980368747744,"score":36.846980368747744},"GB2-02":{"attempts":1,"playable":44.98523825040008,"score":44.98523825040008},"GB2-03":{"attempts":1,"playable":57.27188039753427,"score":57.27188039753427},"GB2-04":{"attempts":1,"playable":65.75858252033579,"score":65.75858252033579},"GB2-05":{"attempts":1,"playable":37.10264363027208,"score":37.10264363027208},"GB2-06":{"attempts":1,"playable":43.80066720123175,"score":43.80066720123175},"GB2-07":{"attempts":1,"playable":71.62979852172242,"score":71.62979852172242},"GB2-08":{"attempts":1,"playable":23.216292627755216,"score":23.216292627755216}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-10-15T06:41:30Z","match_totals_all":{"draws":3601,"losses":5025,"wins":6494},"match_totals_tracks":{"highest":{"draws":964,"losses":1602,"wins":2444},"medium":{"draws":1134,"losses":1437,"wins":2469},"none":{"draws":1503,"losses":1986,"wins":1581}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":80.96145885686715,"mean":56.96587427864629,"min":18.42555531911521},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":67.30093094068577,"GB2-02":66.16268175788127,"GB2-03":75.40985499306336,"GB2-04":79.43854882042322,"GB2-05":74.32565986195104,"GB2-06":18.42555531911521,"GB2-07":69.71330481040566,"GB2-08":31.285926983731056},"per_game_all":{"GB2-01":58.64464855706722,"GB2-02":52.411242190416594,"GB2-03":70.16725039365572,"GB2-04":72.38518762707002,"GB2-05":52.71002917216973,"GB2-06":47.72922712573804,"GB2-07":72.33466085441559,"GB2-08":29.344748308637474},"per_game_match_totals_all":{"GB2-01":{"draws":332,"losses":701,"wins":935},"GB2-02":{"draws":1178,"losses":249,"wins":293},"GB2-03":{"draws":294,"losses":490,"wins":1062},"GB2-04":{"draws":553,"losses":261,"wins":982},"GB2-05":{"draws":0,"losses":946,"wins":1050},"GB2-06":{"draws":127,"losses":960,"wins":807},"GB2-07":{"draws":0,"losses":585,"wins":1317},"GB2-08":{"draws":1117,"losses":833,"wins":48}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":234,"wins":436},"GB2-02":{"draws":296,"losses":56,"wins":214},"GB2-03":{"draws":59,"losses":148,"wins":407},"GB2-04":{"draws":158,"losses":57,"wins":391},"GB2-05":{"draws":0,"losses":178,"wins":460},"GB2-06":{"draws":25,"losses":480,"wins":99},"GB2-07":{"draws":0,"losses":217,"wins":431},"GB2-08":{"draws":420,"losses":232,"wins":6}},"medium":{"GB2-01":{"draws":23,"losses":191,"wins":408},"GB2-02":{"draws":431,"losses":110,"wins":45},"GB2-03":{"draws":77,"losses":122,"wins":413},"GB2-04":{"draws":161,"losses":102,"wins":333},"GB2-05":{"draws":0,"losses":384,"wins":332},"GB2-06":{"draws":44,"losses":108,"wins":450},"GB2-07":{"draws":0,"losses":168,"wins":458},"GB2-08":{"draws":398,"losses":252,"wins":30}},"none":{"GB2-01":{"draws":303,"losses":276,"wins":91},"GB2-02":{"draws":451,"losses":83,"wins":34},"GB2-03":{"draws":158,"losses":220,"wins":242},"GB2-04":{"draws":234,"losses":102,"wins":258},"GB2-05":{"draws":0,"losses":384,"wins":258},"GB2-06":{"draws":58,"losses":372,"wins":258},"GB2-07":{"draws":0,"losses":200,"wins":428},"GB2-08":{"draws":299,"losses":349,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1572.52749073251,"GB2-02":1497.1588531801426,"GB2-03":1648.8181094504923,"GB2-04":1674.5556724508467,"GB2-05":1502.0461805393777,"GB2-06":1440.081922089379,"GB2-07":1758.617165285484,"GB2-08":1211.7482071721151},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1655.9630424406623,"GB2-02":1608.5731524828125,"GB2-03":1703.7534763084757,"GB2-04":1750.4706053244734,"GB2-05":1809.6113617599729,"GB2-06":961.5787713491669,"GB2-07":1716.13388785145,"GB2-08":1233.310676349388},"medium":{"GB2-01":1706.7240784729377,"GB2-02":1445.6889954258806,"GB2-03":1738.4818921840927,"GB2-04":1666.0696579878222,"GB2-05":1410.40977004787,"GB2-06":2003.7995352005241,"GB2-07":1813.6689017196147,"GB2-08":1256.3026318250293},"none":{"GB2-01":1354.8953512839303,"GB2-02":1437.2144116317354,"GB2-03":1504.2189598589084,"GB2-04":1607.1267540402446,"GB2-05":1286.1174098102902,"GB2-06":1354.8674597184458,"GB2-07":1746.048706285387,"GB2-08":1145.6313133419283}},"per_game_tracks":{"highest":{"GB2-01":67.30093094068577,"GB2-02":66.16268175788127,"GB2-03":75.40985499306336,"GB2-04":79.43854882042322,"GB2-05":74.32565986195104,"GB2-06":18.42555531911521,"GB2-07":69.71330481040566,"GB2-08":31.285926983731056},"medium":{"GB2-01":71.78603436176813,"GB2-02":46.08580656296842,"GB2-03":77.82001579036954,"GB2-04":71.95843154045104,"GB2-05":46.70178402428609,"GB2-06":80.96145885686715,"GB2-07":75.66087923111871,"GB2-08":33.532025314426136},"none":{"GB2-01":36.846980368747744,"GB2-02":44.98523825040008,"GB2-03":57.27188039753427,"GB2-04":65.75858252033579,"GB2-05":37.10264363027208,"GB2-06":43.80066720123175,"GB2-07":71.62979852172242,"GB2-08":23.216292627755216}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":60.25780793590707,"medium":63.0633044602819,"none":47.57651043974991},"reasoning_agg":{"highest":{"max":79.43854882042322,"mean":60.25780793590707,"min":18.42555531911521},"medium":{"max":80.96145885686715,"mean":63.0633044602819,"min":33.532025314426136},"none":{"max":71.62979852172242,"mean":47.57651043974991,"min":23.216292627755216}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":15.486794020531988}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:5642a8006ca19523","codegen_cost_by_reasoning":{"highest":{"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":12.152239999999999},"medium":{"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},"none":{"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":0.7687025}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.1879375},"codegen_output_tokens":{"attempt_count":27,"output_max":146534,"output_mean":40675.041666666664,"output_min":3180,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":146534,"output_mean":99672.5,"output_min":71368,"run_count":8},"medium":{"attempt_count":8,"output_max":26272,"output_mean":17600.375,"output_min":12941,"run_count":8},"none":{"attempt_count":10,"output_max":8643,"output_mean":4752.25,"output_min":3180,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":60.143484791049254,"highest":73.13221394675882,"medium":56.73304112235605,"none":47.94987944639682},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":91.80325008297183,"score":91.80325008297183},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.187840782650255,"score":28.79189385510017},"GB2-03":{"attempts":3,"playable":41.645650277667464,"score":41.645650277667464},"GB2-04":{"attempts":3,"playable":43.52514673822205,"score":43.52514673822205},"GB2-05":{"attempts":3,"playable":73.10770564786039,"score":73.10770564786039},"GB2-06":{"attempts":3,"playable":76.0861018626036,"score":76.0861018626036},"GB2-07":{"attempts":3,"playable":48.322990938614076,"score":48.322990938614076},"GB2-08":{"attempts":3,"playable":46.51354798940536,"score":46.51354798940536}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.30076712658199,"score":95.30076712658199},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.765334149357656,"score":45.765334149357656},"GB2-04":{"attempts":1,"playable":58.17406828923173,"score":58.17406828923173},"GB2-05":{"attempts":1,"playable":87.3442856220193,"score":87.3442856220193},"GB2-06":{"attempts":1,"playable":82.49911452647687,"score":82.49911452647687},"GB2-07":{"attempts":1,"playable":78.73078274134684,"score":78.73078274134684},"GB2-08":{"attempts":1,"playable":64.1111451722974,"score":64.1111451722974}},"medium":{"GB2-01":{"attempts":1,"playable":98.0284128361425,"score":98.0284128361425},"GB2-02":{"attempts":1,"playable":46.32955595011676,"score":46.32955595011676},"GB2-03":{"attempts":1,"playable":45.161107455696964,"score":45.161107455696964},"GB2-04":{"attempts":1,"playable":33.2333160586657,"score":33.2333160586657},"GB2-05":{"attempts":1,"playable":71.99225961644096,"score":71.99225961644096},"GB2-06":{"attempts":1,"playable":79.66908904794813,"score":79.66908904794813},"GB2-07":{"attempts":1,"playable":36.26376487586276,"score":36.26376487586276},"GB2-08":{"attempts":1,"playable":43.186823137974635,"score":43.186823137974635}},"none":{"GB2-01":{"attempts":1,"playable":82.080570286191,"score":82.080570286191},"GB2-02":{"attempts":1,"playable":40.04612561518374,"score":40.04612561518374},"GB2-03":{"attempts":1,"playable":34.01050922794776,"score":34.01050922794776},"GB2-04":{"attempts":1,"playable":39.16805586676872,"score":39.16805586676872},"GB2-05":{"attempts":1,"playable":59.98657170512091,"score":59.98657170512091},"GB2-06":{"attempts":1,"playable":66.0901020133858,"score":66.0901020133858},"GB2-07":{"attempts":1,"playable":29.974425198632627,"score":29.974425198632627},"GB2-08":{"attempts":1,"playable":32.242675657944034,"score":32.242675657944034}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-10-14T17:26:53Z","match_totals_all":{"draws":4242,"losses":4905,"wins":7220},"match_totals_tracks":{"highest":{"draws":754,"losses":1051,"wins":3164},"medium":{"draws":1745,"losses":1653,"wins":2302},"none":{"draws":1743,"losses":2201,"wins":1754}},"model_slug":"gpt-5-4","overall":{"max":98.0284128361425,"mean":56.22453592405562,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.30076712658199,"GB2-03":45.765334149357656,"GB2-04":58.17406828923173,"GB2-05":87.3442856220193,"GB2-06":82.49911452647687,"GB2-07":78.73078274134684,"GB2-08":64.1111451722974},"per_game_all":{"GB2-01":91.80325008297183,"GB2-03":41.645650277667464,"GB2-04":43.52514673822205,"GB2-05":73.10770564786039,"GB2-06":76.0861018626036,"GB2-07":48.322990938614076,"GB2-08":46.51354798940536},"per_game_match_totals_all":{"GB2-01":{"draws":90,"losses":154,"wins":1836},"GB2-02":{"draws":1021,"losses":223,"wins":51},"GB2-03":{"draws":872,"losses":871,"wins":435},"GB2-04":{"draws":1123,"losses":613,"wins":316},"GB2-05":{"draws":0,"losses":613,"wins":1563},"GB2-06":{"draws":137,"losses":485,"wins":1460},"GB2-07":{"draws":0,"losses":1176,"wins":1038},"GB2-08":{"draws":999,"losses":770,"wins":521}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":29,"wins":646},"GB2-03":{"draws":248,"losses":311,"wins":203},"GB2-04":{"draws":346,"losses":119,"wins":204},"GB2-05":{"draws":0,"losses":87,"wins":633},"GB2-06":{"draws":57,"losses":102,"wins":533},"GB2-07":{"draws":0,"losses":154,"wins":550},"GB2-08":{"draws":86,"losses":249,"wins":395}},"medium":{"GB2-01":{"draws":8,"losses":10,"wins":674},"GB2-02":{"draws":526,"losses":100,"wins":41},"GB2-03":{"draws":340,"losses":247,"wins":145},"GB2-04":{"draws":359,"losses":256,"wins":45},"GB2-05":{"draws":0,"losses":214,"wins":512},"GB2-06":{"draws":47,"losses":129,"wins":514},"GB2-07":{"draws":0,"losses":472,"wins":268},"GB2-08":{"draws":465,"losses":225,"wins":103}},"none":{"GB2-01":{"draws":65,"losses":115,"wins":516},"GB2-02":{"draws":495,"losses":123,"wins":10},"GB2-03":{"draws":284,"losses":313,"wins":87},"GB2-04":{"draws":418,"losses":238,"wins":67},"GB2-05":{"draws":0,"losses":312,"wins":418},"GB2-06":{"draws":33,"losses":254,"wins":413},"GB2-07":{"draws":0,"losses":550,"wins":220},"GB2-08":{"draws":448,"losses":296,"wins":23}}},"per_game_raw_elo_all":{"GB2-01":2129.0825557765666,"GB2-03":1365.895689755757,"GB2-04":1427.40076295752,"GB2-05":1840.3195519091398,"GB2-06":1911.4849107516595,"GB2-07":1447.2059295092247,"GB2-08":1398.609682077947},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2178.1578048049632,"GB2-03":1402.008289626615,"GB2-04":1542.6411928461785,"GB2-05":2175.1570972293357,"GB2-06":2035.5980955264713,"GB2-07":1871.127539084423,"GB2-08":1598.9644873550224},"medium":{"GB2-01":2363.7191345856445,"GB2-02":1447.564916939532,"GB2-03":1396.7819664304666,"GB2-04":1345.6713569464455,"GB2-05":1765.3186564519874,"GB2-06":1977.6810112480714,"GB2-07":1276.9383743661906,"GB2-08":1353.716099134097},"none":{"GB2-01":1845.370727939092,"GB2-02":1398.8828626511627,"GB2-03":1298.89681321019,"GB2-04":1393.8897390799368,"GB2-05":1580.482902046097,"GB2-06":1721.1756254804363,"GB2-07":1193.55187507706,"GB2-08":1243.1484597447218}},"per_game_tracks":{"highest":{"GB2-01":95.30076712658199,"GB2-03":45.765334149357656,"GB2-04":58.17406828923173,"GB2-05":87.3442856220193,"GB2-06":82.49911452647687,"GB2-07":78.73078274134684,"GB2-08":64.1111451722974},"medium":{"GB2-01":98.0284128361425,"GB2-02":46.32955595011676,"GB2-03":45.161107455696964,"GB2-04":33.2333160586657,"GB2-05":71.99225961644096,"GB2-06":79.66908904794813,"GB2-07":36.26376487586276,"GB2-08":43.186823137974635},"none":{"GB2-01":82.080570286191,"GB2-02":40.04612561518374,"GB2-03":34.01050922794776,"GB2-04":39.16805586676872,"GB2-05":59.98657170512091,"GB2-06":66.0901020133858,"GB2-07":29.974425198632627,"GB2-08":32.242675657944034}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.99068720341397,"medium":56.73304112235605,"none":47.94987944639682},"reasoning_agg":{"highest":{"max":95.30076712658199,"mean":63.99068720341397,"min":0.0},"medium":{"max":98.0284128361425,"mean":56.73304112235605,"min":33.2333160586657},"none":{"max":82.080570286191,"mean":47.94987944639682,"min":29.974425198632627}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.04080775701715}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:6d65a4dc2972889b","codegen_cost_by_reasoning":{"highest":{"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":3.189024},"medium":{"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":0.8737219999999999},"none":{"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":0.969774}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.9697740000000001},"historical-provider-setting-intensive":{"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":3.189024}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.518502,"mean":0.20968833333333334,"median":0.124697,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":19,"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":30,"run_count":24,"total":5.03252},"codegen_latency_ms":{"attempt_count":30,"max_ms":1906796,"mean_ms":726982.5833333334,"min_ms":135091,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1906796,"mean_ms":1528927.125,"min_ms":1229561,"run_count":8},"medium":{"attempt_count":10,"max_ms":878124,"mean_ms":297986.875,"min_ms":135091,"run_count":8},"none":{"attempt_count":10,"max_ms":640944,"mean_ms":354033.75,"min_ms":208254,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78760,"output_mean":31343.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":78760,"output_mean":62794.5,"output_min":52930,"run_count":8},"medium":{"attempt_count":10,"output_max":40870,"output_mean":14338.625,"output_min":6298,"run_count":8},"none":{"attempt_count":10,"output_max":30162,"output_mean":16898.125,"output_min":10952,"run_count":8}},"display_name":"Qwen3.8 Max 0902","economics":{"all":55.02187845748739,"highest":70.09754911652993,"medium":45.22029447776821,"none":49.74779177816403},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[131072],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":31,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"requested_max_output_token_observations":30,"requested_max_output_tokens":[131072],"total_output_tokens":752250,"total_reasoning_output_tokens":630868,"total_visible_output_tokens":121382,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":47.94684973706774,"score":47.94684973706774},"GB2-02":{"attempts":3,"playable":46.962911729068104,"score":46.962911729068104},"GB2-03":{"attempts":3,"playable":61.49014137956635,"score":61.49014137956635},"GB2-04":{"attempts":3,"playable":56.60567253643987,"score":56.60567253643987},"GB2-05":{"attempts":3,"playable":65.14440507232658,"score":65.14440507232658},"GB2-06":{"attempts":3,"playable":68.20000442229825,"score":68.20000442229825},"GB2-07":{"attempts":3,"playable":51.5549456076431,"score":51.5549456076431},"GB2-08":{"attempts":3,"playable":42.270097175489155,"score":42.270097175489155}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.00973130848584,"score":76.00973130848584},"GB2-02":{"attempts":1,"playable":49.55464631564423,"score":49.55464631564423},"GB2-03":{"attempts":1,"playable":71.20694474422693,"score":71.20694474422693},"GB2-04":{"attempts":1,"playable":85.37713572132029,"score":85.37713572132029},"GB2-05":{"attempts":1,"playable":92.68049552737617,"score":92.68049552737617},"GB2-06":{"attempts":1,"playable":63.98805755949066,"score":63.98805755949066},"GB2-07":{"attempts":1,"playable":76.76621749785912,"score":76.76621749785912},"GB2-08":{"attempts":1,"playable":45.19716425783624,"score":45.19716425783624}},"medium":{"GB2-01":{"attempts":1,"playable":26.535019026488083,"score":26.535019026488083},"GB2-02":{"attempts":1,"playable":48.976138331727235,"score":48.976138331727235},"GB2-03":{"attempts":1,"playable":56.906939555526314,"score":56.906939555526314},"GB2-04":{"attempts":1,"playable":46.66962179384154,"score":46.66962179384154},"GB2-05":{"attempts":1,"playable":42.47950296233451,"score":42.47950296233451},"GB2-06":{"attempts":1,"playable":60.00872117536397,"score":60.00872117536397},"GB2-07":{"attempts":1,"playable":37.39121562457737,"score":37.39121562457737},"GB2-08":{"attempts":1,"playable":42.7951973522867,"score":42.7951973522867}},"none":{"GB2-01":{"attempts":1,"playable":41.29579887622929,"score":41.29579887622929},"GB2-02":{"attempts":1,"playable":42.35795053983284,"score":42.35795053983284},"GB2-03":{"attempts":1,"playable":56.35653983894581,"score":56.35653983894581},"GB2-04":{"attempts":1,"playable":37.770260094157784,"score":37.770260094157784},"GB2-05":{"attempts":1,"playable":60.27321672726905,"score":60.27321672726905},"GB2-06":{"attempts":1,"playable":80.60323453204012,"score":80.60323453204012},"GB2-07":{"attempts":1,"playable":40.50740370049281,"score":40.50740370049281},"GB2-08":{"attempts":1,"playable":38.81792991634453,"score":38.81792991634453}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-13T22:11:48Z","match_totals_all":{"draws":2957,"losses":3649,"wins":4476},"match_totals_tracks":{"highest":{"draws":747,"losses":762,"wins":2185},"medium":{"draws":1010,"losses":1581,"wins":1103},"none":{"draws":1200,"losses":1306,"wins":1188}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":92.68049552737617,"mean":55.02187845748739,"min":26.535019026488083},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.00973130848584,"GB2-02":49.55464631564423,"GB2-03":71.20694474422693,"GB2-04":85.37713572132029,"GB2-05":92.68049552737617,"GB2-06":63.98805755949066,"GB2-07":76.76621749785912,"GB2-08":45.19716425783624},"per_game_all":{"GB2-01":47.94684973706774,"GB2-02":46.962911729068104,"GB2-03":61.49014137956635,"GB2-04":56.60567253643987,"GB2-05":65.14440507232658,"GB2-06":68.20000442229825,"GB2-07":51.5549456076431,"GB2-08":42.270097175489155},"per_game_match_totals_all":{"GB2-01":{"draws":284,"losses":601,"wins":519},"GB2-02":{"draws":948,"losses":230,"wins":118},"GB2-03":{"draws":240,"losses":437,"wins":661},"GB2-04":{"draws":634,"losses":280,"wins":430},"GB2-05":{"draws":0,"losses":507,"wins":945},"GB2-06":{"draws":92,"losses":401,"wins":875},"GB2-07":{"draws":0,"losses":713,"wins":709},"GB2-08":{"draws":759,"losses":480,"wins":219}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":114,"wins":352},"GB2-02":{"draws":297,"losses":75,"wins":60},"GB2-03":{"draws":77,"losses":102,"wins":267},"GB2-04":{"draws":77,"losses":30,"wins":341},"GB2-05":{"draws":0,"losses":34,"wins":450},"GB2-06":{"draws":45,"losses":147,"wins":264},"GB2-07":{"draws":0,"losses":112,"wins":362},"GB2-08":{"draws":249,"losses":148,"wins":89}},"medium":{"GB2-01":{"draws":89,"losses":304,"wins":75},"GB2-02":{"draws":322,"losses":65,"wins":45},"GB2-03":{"draws":82,"losses":166,"wins":198},"GB2-04":{"draws":287,"losses":101,"wins":60},"GB2-05":{"draws":0,"losses":279,"wins":205},"GB2-06":{"draws":14,"losses":182,"wins":260},"GB2-07":{"draws":0,"losses":308,"wins":166},"GB2-08":{"draws":216,"losses":176,"wins":94}},"none":{"GB2-01":{"draws":193,"losses":183,"wins":92},"GB2-02":{"draws":329,"losses":90,"wins":13},"GB2-03":{"draws":81,"losses":169,"wins":196},"GB2-04":{"draws":270,"losses":149,"wins":29},"GB2-05":{"draws":0,"losses":194,"wins":290},"GB2-06":{"draws":33,"losses":72,"wins":351},"GB2-07":{"draws":0,"losses":293,"wins":181},"GB2-08":{"draws":294,"losses":156,"wins":36}}},"per_game_raw_elo_all":{"GB2-01":1467.5226097534414,"GB2-02":1452.4203454219517,"GB2-03":1548.7294625780899,"GB2-04":1557.0800523540468,"GB2-05":1786.6335096505738,"GB2-06":1765.0921119867041,"GB2-07":1485.2891411633361,"GB2-08":1344.5491230321522},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1758.8545296691352,"GB2-02":1472.4067586640238,"GB2-03":1649.5991967660084,"GB2-04":1836.1739255730688,"GB2-05":2418.6814686020734,"GB2-06":1683.806846133118,"GB2-07":1833.640771848621,"GB2-08":1374.3532844327349},"medium":{"GB2-01":1244.966455299433,"GB2-02":1467.943042383602,"GB2-03":1500.8342283574136,"GB2-04":1452.2992788024003,"GB2-05":1356.8501690077967,"GB2-06":1614.959314010572,"GB2-07":1291.387586067634,"GB2-08":1349.726517958726},"none":{"GB2-01":1398.746844291756,"GB2-02":1416.9112352182294,"GB2-03":1495.754962610847,"GB2-04":1382.7669526866716,"GB2-05":1584.3688913418516,"GB2-06":1996.5101758164221,"GB2-07":1330.8390655737535,"GB2-08":1309.5675667049961}},"per_game_tracks":{"highest":{"GB2-01":76.00973130848584,"GB2-02":49.55464631564423,"GB2-03":71.20694474422693,"GB2-04":85.37713572132029,"GB2-05":92.68049552737617,"GB2-06":63.98805755949066,"GB2-07":76.76621749785912,"GB2-08":45.19716425783624},"medium":{"GB2-01":26.535019026488083,"GB2-02":48.976138331727235,"GB2-03":56.906939555526314,"GB2-04":46.66962179384154,"GB2-05":42.47950296233451,"GB2-06":60.00872117536397,"GB2-07":37.39121562457737,"GB2-08":42.7951973522867},"none":{"GB2-01":41.29579887622929,"GB2-02":42.35795053983284,"GB2-03":56.35653983894581,"GB2-04":37.770260094157784,"GB2-05":60.27321672726905,"GB2-06":80.60323453204012,"GB2-07":40.50740370049281,"GB2-08":38.81792991634453}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":70.09754911652993,"medium":45.22029447776821,"none":49.74779177816403},"reasoning_agg":{"highest":{"max":92.68049552737617,"mean":70.09754911652993,"min":45.19716425783624},"medium":{"max":60.00872117536397,"mean":45.22029447776821,"min":26.535019026488083},"none":{"max":80.60323453204012,"mean":49.74779177816403,"min":37.770260094157784}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.87725463876172}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:50f9212c2d1a966c","codegen_cost_by_reasoning":{"highest":{"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":3.454226856819533},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":3.454226856819533}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.470888},"codegen_output_tokens":{"attempt_count":27,"output_max":128921,"output_mean":35057.208333333336,"output_min":6291,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":128921,"output_mean":72806.0,"output_min":45821,"run_count":8},"medium":{"attempt_count":8,"output_max":25498,"output_mean":11826.75,"output_min":6291,"run_count":8},"none":{"attempt_count":9,"output_max":34088,"output_mean":20538.875,"output_min":10484,"run_count":8}},"display_name":"Qwen3.8 2.4T A95B","economics":{"all":54.331905882571526,"highest":68.57482491615735,"medium":43.56726294169622,"none":50.85362978986101},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":841373,"total_reasoning_output_tokens":733891,"total_visible_output_tokens":107482,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-2.4t-a95b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":49.12962605324386,"score":49.12962605324386},"GB2-02":{"attempts":3,"playable":49.135157584487615,"score":49.135157584487615},"GB2-03":{"attempts":3,"playable":57.19197273310292,"score":57.19197273310292},"GB2-04":{"attempts":3,"playable":45.12436227003318,"score":45.12436227003318},"GB2-05":{"attempts":3,"playable":51.88819511688652,"score":51.88819511688652},"GB2-06":{"attempts":3,"playable":63.1825835571394,"score":63.1825835571394},"GB2-07":{"attempts":3,"playable":48.331703317382654,"score":48.331703317382654},"GB2-08":{"attempts":3,"playable":70.67164642829601,"score":70.67164642829601}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":58.712344254534955,"score":58.712344254534955},"GB2-02":{"attempts":1,"playable":55.10395234378302,"score":55.10395234378302},"GB2-03":{"attempts":1,"playable":75.91189301898393,"score":75.91189301898393},"GB2-04":{"attempts":1,"playable":49.36775612797509,"score":49.36775612797509},"GB2-05":{"attempts":1,"playable":68.8901779983062,"score":68.8901779983062},"GB2-06":{"attempts":1,"playable":80.67062560655317,"score":80.67062560655317},"GB2-07":{"attempts":1,"playable":68.98096055615689,"score":68.98096055615689},"GB2-08":{"attempts":1,"playable":90.96088942296548,"score":90.96088942296548}},"medium":{"GB2-01":{"attempts":1,"playable":53.68448584032538,"score":53.68448584032538},"GB2-02":{"attempts":1,"playable":43.174341330319265,"score":43.174341330319265},"GB2-03":{"attempts":1,"playable":45.09208919910108,"score":45.09208919910108},"GB2-04":{"attempts":1,"playable":39.37657420560367,"score":39.37657420560367},"GB2-05":{"attempts":1,"playable":51.14575493623493,"score":51.14575493623493},"GB2-06":{"attempts":1,"playable":45.30163135493502,"score":45.30163135493502},"GB2-07":{"attempts":1,"playable":32.131494261118526,"score":32.131494261118526},"GB2-08":{"attempts":1,"playable":38.63173240593187,"score":38.63173240593187}},"none":{"GB2-01":{"attempts":1,"playable":34.99204806487125,"score":34.99204806487125},"GB2-02":{"attempts":1,"playable":49.12717907936056,"score":49.12717907936056},"GB2-03":{"attempts":1,"playable":50.57193598122377,"score":50.57193598122377},"GB2-04":{"attempts":1,"playable":46.62875647652079,"score":46.62875647652079},"GB2-05":{"attempts":1,"playable":35.628652416118435,"score":35.628652416118435},"GB2-06":{"attempts":1,"playable":63.57549370993003,"score":63.57549370993003},"GB2-07":{"attempts":1,"playable":43.88265513487256,"score":43.88265513487256},"GB2-08":{"attempts":1,"playable":82.42231745599071,"score":82.42231745599071}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-10-13T22:27:00Z","match_totals_all":{"draws":4284,"losses":5109,"wins":5943},"match_totals_tracks":{"highest":{"draws":1115,"losses":1137,"wins":2730},"medium":{"draws":1860,"losses":2071,"wins":1301},"none":{"draws":1309,"losses":1901,"wins":1912}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":90.96088942296548,"mean":54.331905882571526,"min":32.131494261118526},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":22,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.712344254534955,"GB2-02":55.10395234378302,"GB2-03":75.91189301898393,"GB2-04":49.36775612797509,"GB2-05":68.8901779983062,"GB2-06":80.67062560655317,"GB2-07":68.98096055615689,"GB2-08":90.96088942296548},"per_game_all":{"GB2-01":49.12962605324386,"GB2-02":49.135157584487615,"GB2-03":57.19197273310292,"GB2-04":45.12436227003318,"GB2-05":51.88819511688652,"GB2-06":63.1825835571394,"GB2-07":48.331703317382654,"GB2-08":70.67164642829601},"per_game_match_totals_all":{"GB2-01":{"draws":769,"losses":628,"wins":541},"GB2-02":{"draws":1300,"losses":285,"wins":191},"GB2-03":{"draws":460,"losses":685,"wins":795},"GB2-04":{"draws":1178,"losses":446,"wins":230},"GB2-05":{"draws":0,"losses":972,"wins":1036},"GB2-06":{"draws":167,"losses":671,"wins":1080},"GB2-07":{"draws":0,"losses":997,"wins":919},"GB2-08":{"draws":410,"losses":425,"wins":1151}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":208,"losses":193,"wins":289},"GB2-02":{"draws":387,"losses":75,"wins":106},"GB2-03":{"draws":107,"losses":116,"wins":387},"GB2-04":{"draws":349,"losses":143,"wins":104},"GB2-05":{"draws":0,"losses":227,"wins":423},"GB2-06":{"draws":62,"losses":101,"wins":439},"GB2-07":{"draws":0,"losses":221,"wins":409},"GB2-08":{"draws":2,"losses":61,"wins":573}},"medium":{"GB2-01":{"draws":309,"losses":167,"wins":154},"GB2-02":{"draws":453,"losses":122,"wins":23},"GB2-03":{"draws":266,"losses":268,"wins":156},"GB2-04":{"draws":370,"losses":169,"wins":53},"GB2-05":{"draws":0,"losses":354,"wins":368},"GB2-06":{"draws":58,"losses":329,"wins":265},"GB2-07":{"draws":0,"losses":422,"wins":214},"GB2-08":{"draws":404,"losses":240,"wins":68}},"none":{"GB2-01":{"draws":252,"losses":268,"wins":98},"GB2-02":{"draws":460,"losses":88,"wins":62},"GB2-03":{"draws":87,"losses":301,"wins":252},"GB2-04":{"draws":459,"losses":134,"wins":73},"GB2-05":{"draws":0,"losses":391,"wins":245},"GB2-06":{"draws":47,"losses":241,"wins":376},"GB2-07":{"draws":0,"losses":354,"wins":296},"GB2-08":{"draws":4,"losses":124,"wins":510}}},"per_game_raw_elo_all":{"GB2-01":1473.6351028382041,"GB2-02":1469.3542115308426,"GB2-03":1516.925610156936,"GB2-04":1440.2221260752558,"GB2-05":1481.3289422263726,"GB2-06":1684.1652261231263,"GB2-07":1433.6240136923243,"GB2-08":1802.1047611487022},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1566.9756476099305,"GB2-02":1515.7187863828324,"GB2-03":1710.7347637065361,"GB2-04":1473.1429922072507,"GB2-05":1711.8452465454368,"GB2-06":1997.8784114030532,"GB2-07":1705.004410121173,"GB2-08":2166.4020865819903},"medium":{"GB2-01":1517.7747334967698,"GB2-02":1423.2359054614756,"GB2-03":1396.1851541294402,"GB2-04":1395.5395648651338,"GB2-05":1466.1684244712417,"GB2-06":1378.0640871255143,"GB2-07":1222.7991061690973,"GB2-08":1307.6968641259234},"none":{"GB2-01":1336.154927407912,"GB2-02":1469.1079427482198,"GB2-03":1443.8569126348311,"GB2-04":1451.9838211533825,"GB2-05":1265.9731556624392,"GB2-06":1676.5531798408113,"GB2-07":1373.068524786703,"GB2-08":1932.2153327381934}},"per_game_tracks":{"highest":{"GB2-01":58.712344254534955,"GB2-02":55.10395234378302,"GB2-03":75.91189301898393,"GB2-04":49.36775612797509,"GB2-05":68.8901779983062,"GB2-06":80.67062560655317,"GB2-07":68.98096055615689,"GB2-08":90.96088942296548},"medium":{"GB2-01":53.68448584032538,"GB2-02":43.174341330319265,"GB2-03":45.09208919910108,"GB2-04":39.37657420560367,"GB2-05":51.14575493623493,"GB2-06":45.30163135493502,"GB2-07":32.131494261118526,"GB2-08":38.63173240593187},"none":{"GB2-01":34.99204806487125,"GB2-02":49.12717907936056,"GB2-03":50.57193598122377,"GB2-04":46.62875647652079,"GB2-05":35.628652416118435,"GB2-06":63.57549370993003,"GB2-07":43.88265513487256,"GB2-08":82.42231745599071}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":68.57482491615735,"medium":43.56726294169622,"none":50.85362978986101},"reasoning_agg":{"highest":{"max":90.96088942296548,"mean":68.57482491615735,"min":49.36775612797509},"medium":{"max":53.68448584032538,"mean":43.56726294169622,"min":32.131494261118526},"none":{"max":82.42231745599071,"mean":50.85362978986101,"min":34.99204806487125}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.007561974461133}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:25dfa6ac02cd1ccf","codegen_cost_by_reasoning":{"highest":{"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":0.9693815250000001},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.9693815250000001}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.1835153939999996},"codegen_latency_ms":{"attempt_count":28,"max_ms":1122981,"mean_ms":579882.5416666666,"min_ms":29109,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":995043,"mean_ms":822481.25,"min_ms":674828,"run_count":8},"medium":{"attempt_count":10,"max_ms":1122981,"mean_ms":860540.0,"min_ms":640692,"run_count":8},"none":{"attempt_count":9,"max_ms":99413,"mean_ms":56626.375,"min_ms":29109,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":69581,"output_mean":33844.916666666664,"output_min":1323,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":57331,"output_mean":47325.375,"output_min":39792,"run_count":8},"medium":{"attempt_count":10,"output_max":69581,"output_mean":50814.0,"output_min":36329,"run_count":8},"none":{"attempt_count":9,"output_max":6014,"output_mean":3395.375,"output_min":1323,"run_count":8}},"display_name":"Hy4 Preview","economics":{"all":55.44116393179983,"highest":65.23387854417791,"medium":58.15708559478825,"none":44.75202172745678},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":131,"total_output_tokens":812278,"total_reasoning_output_tokens":673611,"total_visible_output_tokens":138667,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy4-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":52.089470123325356,"score":52.089470123325356},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":61.361179384399435,"score":40.907452922932954},"GB2-03":{"attempts":3,"playable":58.33395191221458,"score":58.33395191221458},"GB2-04":{"attempts":3,"playable":44.592849416642345,"score":44.592849416642345},"GB2-05":{"attempts":3,"playable":57.67756791836433,"score":57.67756791836433},"GB2-06":{"attempts":3,"playable":60.114277061112126,"score":60.114277061112126},"GB2-07":{"attempts":3,"playable":60.963239502866166,"score":60.963239502866166},"GB2-08":{"attempts":3,"playable":54.3167915880739,"score":54.3167915880739}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.675508229131346,"score":55.675508229131346},"GB2-02":{"attempts":1,"playable":79.46337177294697,"score":79.46337177294697},"GB2-03":{"attempts":1,"playable":72.68445885551277,"score":72.68445885551277},"GB2-04":{"attempts":1,"playable":57.99864454145265,"score":57.99864454145265},"GB2-05":{"attempts":1,"playable":70.5458638505377,"score":70.5458638505377},"GB2-06":{"attempts":1,"playable":80.4697419664612,"score":80.4697419664612},"GB2-07":{"attempts":1,"playable":67.96745741166728,"score":67.96745741166728},"GB2-08":{"attempts":1,"playable":37.065981725713414,"score":37.065981725713414}},"medium":{"GB2-01":{"attempts":1,"playable":53.73618487588121,"score":53.73618487588121},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":39.51031814204273,"score":39.51031814204273},"GB2-04":{"attempts":1,"playable":34.635646852681255,"score":34.635646852681255},"GB2-05":{"attempts":1,"playable":51.613268479559835,"score":51.613268479559835},"GB2-06":{"attempts":1,"playable":59.76840784269473,"score":59.76840784269473},"GB2-07":{"attempts":1,"playable":77.55887274480267,"score":77.55887274480267},"GB2-08":{"attempts":1,"playable":90.2769002258553,"score":90.2769002258553}},"none":{"GB2-01":{"attempts":1,"playable":46.856717264963514,"score":46.856717264963514},"GB2-02":{"attempts":1,"playable":43.25898699585189,"score":43.25898699585189},"GB2-03":{"attempts":1,"playable":62.807078739088226,"score":62.807078739088226},"GB2-04":{"attempts":1,"playable":41.14425685579315,"score":41.14425685579315},"GB2-05":{"attempts":1,"playable":50.873571424995475,"score":50.873571424995475},"GB2-06":{"attempts":1,"playable":40.10468137418046,"score":40.10468137418046},"GB2-07":{"attempts":1,"playable":37.363388352128545,"score":37.363388352128545},"GB2-08":{"attempts":1,"playable":35.60749281265297,"score":35.60749281265297}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-10-15T06:38:39Z","match_totals_all":{"draws":3683,"losses":4875,"wins":6196},"match_totals_tracks":{"highest":{"draws":1373,"losses":1259,"wins":2466},"medium":{"draws":725,"losses":1580,"wins":2237},"none":{"draws":1585,"losses":2036,"wins":1493}},"model_slug":"tencent-hy4-preview","overall":{"max":90.2769002258553,"mean":53.624450055691476,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.675508229131346,"GB2-02":79.46337177294697,"GB2-03":72.68445885551277,"GB2-04":57.99864454145265,"GB2-05":70.5458638505377,"GB2-06":80.4697419664612,"GB2-07":67.96745741166728,"GB2-08":37.065981725713414},"per_game_all":{"GB2-01":52.089470123325356,"GB2-03":58.33395191221458,"GB2-04":44.592849416642345,"GB2-05":57.67756791836433,"GB2-06":60.114277061112126,"GB2-07":60.963239502866166,"GB2-08":54.3167915880739},"per_game_match_totals_all":{"GB2-01":{"draws":491,"losses":780,"wins":781},"GB2-02":{"draws":650,"losses":126,"wins":396},"GB2-03":{"draws":569,"losses":545,"wins":724},"GB2-04":{"draws":1044,"losses":480,"wins":274},"GB2-05":{"draws":0,"losses":918,"wins":1168},"GB2-06":{"draws":78,"losses":744,"wins":1092},"GB2-07":{"draws":0,"losses":767,"wins":1119},"GB2-08":{"draws":851,"losses":515,"wins":642}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":341,"losses":149,"wins":202},"GB2-02":{"draws":163,"losses":45,"wins":386},"GB2-03":{"draws":62,"losses":164,"wins":382},"GB2-04":{"draws":311,"losses":117,"wins":182},"GB2-05":{"draws":0,"losses":216,"wins":434},"GB2-06":{"draws":35,"losses":116,"wins":451},"GB2-07":{"draws":0,"losses":229,"wins":401},"GB2-08":{"draws":461,"losses":223,"wins":28}},"medium":{"GB2-01":{"draws":40,"losses":303,"wins":321},"GB2-03":{"draws":345,"losses":201,"wins":66},"GB2-04":{"draws":322,"losses":223,"wins":49},"GB2-05":{"draws":0,"losses":345,"wins":369},"GB2-06":{"draws":18,"losses":287,"wins":391},"GB2-07":{"draws":0,"losses":154,"wins":472},"GB2-08":{"draws":0,"losses":67,"wins":569}},"none":{"GB2-01":{"draws":110,"losses":328,"wins":258},"GB2-02":{"draws":487,"losses":81,"wins":10},"GB2-03":{"draws":162,"losses":180,"wins":276},"GB2-04":{"draws":411,"losses":140,"wins":43},"GB2-05":{"draws":0,"losses":357,"wins":365},"GB2-06":{"draws":25,"losses":341,"wins":250},"GB2-07":{"draws":0,"losses":384,"wins":246},"GB2-08":{"draws":390,"losses":225,"wins":45}}},"per_game_raw_elo_all":{"GB2-01":1502.5537162878943,"GB2-03":1524.4024951069289,"GB2-04":1435.995963605117,"GB2-05":1558.168262274922,"GB2-06":1634.2772307732878,"GB2-07":1609.7715661324085,"GB2-08":1570.9470514095767},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1537.097902327906,"GB2-02":1750.380865365432,"GB2-03":1667.8424580357994,"GB2-04":1541.2156730455135,"GB2-05":1739.7077260158435,"GB2-06":1993.803982269268,"GB2-07":1689.8471355875206,"GB2-08":1291.9691617638634},"medium":{"GB2-01":1518.274412844139,"GB2-03":1347.7814071124208,"GB2-04":1357.3297053290787,"GB2-05":1472.0487498539503,"GB2-06":1610.880523896394,"GB2-07":1848.435295882645,"GB2-08":2143.575741631711},"none":{"GB2-01":1452.2888336916378,"GB2-02":1423.8907027794949,"GB2-03":1557.583620172567,"GB2-04":1409.4425124407578,"GB2-05":1462.7483109549717,"GB2-06":1298.1471861542013,"GB2-07":1291.0322669270604,"GB2-08":1277.2962508331561}},"per_game_tracks":{"highest":{"GB2-01":55.675508229131346,"GB2-02":79.46337177294697,"GB2-03":72.68445885551277,"GB2-04":57.99864454145265,"GB2-05":70.5458638505377,"GB2-06":80.4697419664612,"GB2-07":67.96745741166728,"GB2-08":37.065981725713414},"medium":{"GB2-01":53.73618487588121,"GB2-03":39.51031814204273,"GB2-04":34.635646852681255,"GB2-05":51.613268479559835,"GB2-06":59.76840784269473,"GB2-07":77.55887274480267,"GB2-08":90.2769002258553},"none":{"GB2-01":46.856717264963514,"GB2-02":43.25898699585189,"GB2-03":62.807078739088226,"GB2-04":41.14425685579315,"GB2-05":50.873571424995475,"GB2-06":40.10468137418046,"GB2-07":37.363388352128545,"GB2-08":35.60749281265297}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.23387854417791,"medium":50.887449895439715,"none":44.75202172745678},"reasoning_agg":{"highest":{"max":80.4697419664612,"mean":65.23387854417791,"min":37.065981725713414},"medium":{"max":90.2769002258553,"mean":50.887449895439715,"min":0.0},"none":{"max":62.807078739088226,"mean":44.75202172745678,"min":35.60749281265297}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.481856816721134}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:c2e28936a24e27ca","codegen_cost_by_reasoning":{"highest":{"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":0.21121388999999996},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.392731284},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":53.377232346227174,"highest":68.4762105518924,"medium":55.199487915345195,"none":36.45599857144391},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[384000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[384000],"total_output_tokens":602101,"total_reasoning_output_tokens":512212,"total_visible_output_tokens":89889,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":384000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":58.752549773118254,"score":58.752549773118254},"GB2-02":{"attempts":3,"playable":52.87342500062482,"score":52.87342500062482},"GB2-03":{"attempts":3,"playable":54.90427803863725,"score":54.90427803863725},"GB2-04":{"attempts":3,"playable":50.64348318535618,"score":50.64348318535618},"GB2-05":{"attempts":3,"playable":54.97721413700676,"score":54.97721413700676},"GB2-06":{"attempts":3,"playable":62.576874918441064,"score":62.576874918441064},"GB2-07":{"attempts":3,"playable":56.222554662233144,"score":56.222554662233144},"GB2-08":{"attempts":3,"playable":36.06747905439986,"score":36.06747905439986}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.40802142728765,"score":63.40802142728765},"GB2-02":{"attempts":1,"playable":57.615697501766896,"score":57.615697501766896},"GB2-03":{"attempts":1,"playable":61.71117116124285,"score":61.71117116124285},"GB2-04":{"attempts":1,"playable":75.0346051655178,"score":75.0346051655178},"GB2-05":{"attempts":1,"playable":82.18119029193043,"score":82.18119029193043},"GB2-06":{"attempts":1,"playable":83.00761080038563,"score":83.00761080038563},"GB2-07":{"attempts":1,"playable":75.17806797846778,"score":75.17806797846778},"GB2-08":{"attempts":1,"playable":49.673320088540116,"score":49.673320088540116}},"medium":{"GB2-01":{"attempts":1,"playable":67.09117116457848,"score":67.09117116457848},"GB2-02":{"attempts":1,"playable":58.646626960274716,"score":58.646626960274716},"GB2-03":{"attempts":1,"playable":55.142489428760925,"score":55.142489428760925},"GB2-04":{"attempts":1,"playable":38.67376891794069,"score":38.67376891794069},"GB2-05":{"attempts":1,"playable":53.36359265550307,"score":53.36359265550307},"GB2-06":{"attempts":1,"playable":77.17948234803615,"score":77.17948234803615},"GB2-07":{"attempts":1,"playable":68.64187990513079,"score":68.64187990513079},"GB2-08":{"attempts":1,"playable":22.856891942536752,"score":22.856891942536752}},"none":{"GB2-01":{"attempts":1,"playable":45.758456727488635,"score":45.758456727488635},"GB2-02":{"attempts":1,"playable":42.35795053983284,"score":42.35795053983284},"GB2-03":{"attempts":1,"playable":47.85917352590797,"score":47.85917352590797},"GB2-04":{"attempts":1,"playable":38.22207547261005,"score":38.22207547261005},"GB2-05":{"attempts":1,"playable":29.386859463586774,"score":29.386859463586774},"GB2-06":{"attempts":1,"playable":27.543531606901407,"score":27.543531606901407},"GB2-07":{"attempts":1,"playable":24.84771610310088,"score":24.84771610310088},"GB2-08":{"attempts":1,"playable":35.672225132122705,"score":35.672225132122705}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-15T06:51:36Z","match_totals_all":{"draws":3116,"losses":3753,"wins":4212},"match_totals_tracks":{"highest":{"draws":760,"losses":821,"wins":2113},"medium":{"draws":1151,"losses":1125,"wins":1418},"none":{"draws":1205,"losses":1807,"wins":681}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":83.00761080038563,"mean":53.37723234622717,"min":22.856891942536752},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.40802142728765,"GB2-02":57.615697501766896,"GB2-03":61.71117116124285,"GB2-04":75.0346051655178,"GB2-05":82.18119029193043,"GB2-06":83.00761080038563,"GB2-07":75.17806797846778,"GB2-08":49.673320088540116},"per_game_all":{"GB2-01":58.752549773118254,"GB2-02":52.87342500062482,"GB2-03":54.90427803863725,"GB2-04":50.64348318535618,"GB2-05":54.97721413700676,"GB2-06":62.576874918441064,"GB2-07":56.222554662233144,"GB2-08":36.06747905439986},"per_game_match_totals_all":{"GB2-01":{"draws":436,"losses":373,"wins":595},"GB2-02":{"draws":906,"losses":174,"wins":216},"GB2-03":{"draws":286,"losses":504,"wins":547},"GB2-04":{"draws":659,"losses":349,"wins":336},"GB2-05":{"draws":0,"losses":657,"wins":795},"GB2-06":{"draws":89,"losses":478,"wins":801},"GB2-07":{"draws":0,"losses":640,"wins":782},"GB2-08":{"draws":740,"losses":578,"wins":140}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":165,"wins":283},"GB2-02":{"draws":267,"losses":55,"wins":110},"GB2-03":{"draws":52,"losses":159,"wins":235},"GB2-04":{"draws":139,"losses":47,"wins":262},"GB2-05":{"draws":0,"losses":88,"wins":396},"GB2-06":{"draws":28,"losses":63,"wins":365},"GB2-07":{"draws":0,"losses":120,"wins":354},"GB2-08":{"draws":254,"losses":124,"wins":108}},"medium":{"GB2-01":{"draws":271,"losses":22,"wins":175},"GB2-02":{"draws":288,"losses":40,"wins":104},"GB2-03":{"draws":122,"losses":154,"wins":170},"GB2-04":{"draws":238,"losses":161,"wins":49},"GB2-05":{"draws":0,"losses":227,"wins":257},"GB2-06":{"draws":30,"losses":90,"wins":336},"GB2-07":{"draws":0,"losses":153,"wins":321},"GB2-08":{"draws":202,"losses":278,"wins":6}},"none":{"GB2-01":{"draws":145,"losses":186,"wins":137},"GB2-02":{"draws":351,"losses":79,"wins":2},"GB2-03":{"draws":112,"losses":191,"wins":142},"GB2-04":{"draws":282,"losses":141,"wins":25},"GB2-05":{"draws":0,"losses":342,"wins":142},"GB2-06":{"draws":31,"losses":325,"wins":100},"GB2-07":{"draws":0,"losses":367,"wins":107},"GB2-08":{"draws":284,"losses":176,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1570.0142845187108,"GB2-02":1498.9735241910555,"GB2-03":1483.8278755950357,"GB2-04":1491.6293107213405,"GB2-05":1556.1513863884054,"GB2-06":1694.0058978131958,"GB2-07":1541.6876415970826,"GB2-08":1280.3380713846918},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1614.5916966393543,"GB2-02":1535.8157391660088,"GB2-03":1546.6716958550448,"GB2-04":1698.5435166065615,"GB2-05":1998.6659388863395,"GB2-06":2046.3227346596536,"GB2-07":1805.1643301222725,"GB2-08":1421.6331988591983},"medium":{"GB2-01":1653.678438978215,"GB2-02":1544.1935981889278,"GB2-03":1484.6526678427826,"GB2-04":1389.9695046449533,"GB2-05":1494.1544837085542,"GB2-06":1928.5366527622048,"GB2-07":1699.9027261213912,"GB2-08":1141.432537711189},"none":{"GB2-01":1441.7727179385631,"GB2-02":1416.9112352182294,"GB2-03":1420.1592630872794,"GB2-04":1386.3749109125065,"GB2-05":1175.6337365703223,"GB2-06":1107.1583060177295,"GB2-07":1119.9958685475835,"GB2-08":1277.948477583688}},"per_game_tracks":{"highest":{"GB2-01":63.40802142728765,"GB2-02":57.615697501766896,"GB2-03":61.71117116124285,"GB2-04":75.0346051655178,"GB2-05":82.18119029193043,"GB2-06":83.00761080038563,"GB2-07":75.17806797846778,"GB2-08":49.673320088540116},"medium":{"GB2-01":67.09117116457848,"GB2-02":58.646626960274716,"GB2-03":55.142489428760925,"GB2-04":38.67376891794069,"GB2-05":53.36359265550307,"GB2-06":77.17948234803615,"GB2-07":68.64187990513079,"GB2-08":22.856891942536752},"none":{"GB2-01":45.758456727488635,"GB2-02":42.35795053983284,"GB2-03":47.85917352590797,"GB2-04":38.22207547261005,"GB2-05":29.386859463586774,"GB2-06":27.543531606901407,"GB2-07":24.84771610310088,"GB2-08":35.672225132122705}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":68.4762105518924,"medium":55.199487915345195,"none":36.45599857144391},"reasoning_agg":{"highest":{"max":83.00761080038563,"mean":68.4762105518924,"min":49.673320088540116},"medium":{"max":77.17948234803615,"mean":55.199487915345195,"min":22.856891942536752},"none":{"max":47.85917352590797,"mean":36.45599857144391,"min":24.84771610310088}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":32.02021198044849}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:f823de08c5bf7106","codegen_cost_by_reasoning":{"highest":{"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":1.1471405000000001},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.7147190000000003},"codegen_latency_ms":{"attempt_count":27,"max_ms":194716,"mean_ms":65710.04166666667,"min_ms":14709,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":194716,"mean_ms":132597.5,"min_ms":94687,"run_count":8},"medium":{"attempt_count":9,"max_ms":66794,"mean_ms":45688.625,"min_ms":28293,"run_count":8},"none":{"attempt_count":9,"max_ms":26924,"mean_ms":18844.0,"min_ms":14709,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":46299,"output_mean":14240.0,"output_min":2554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":46299,"output_mean":31097.375,"output_min":22420,"run_count":8},"medium":{"attempt_count":9,"output_max":11293,"output_mean":8521.75,"output_min":5500,"run_count":8},"none":{"attempt_count":9,"output_max":3991,"output_mean":3100.875,"output_min":2554,"run_count":8}},"display_name":"Muse Spark 1.2","economics":{"all":55.79941146338149,"highest":59.63986214167984,"medium":58.05486716092893,"none":41.7812764636328},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[943718],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":87,"requested_max_output_token_observations":9,"requested_max_output_tokens":[943718],"total_output_tokens":341760,"total_reasoning_output_tokens":238816,"total_visible_output_tokens":102944,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-1.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":67.85494278930929,"score":67.85494278930929},"GB2-02":{"attempts":3,"playable":45.31120786437265,"score":45.31120786437265},"GB2-03":{"attempts":3,"playable":52.941956987189315,"score":52.941956987189315},"GB2-04":{"attempts":3,"playable":46.93178748793765,"score":46.93178748793765},"GB2-05":{"attempts":3,"playable":54.35429912395721,"score":54.35429912395721},"GB2-06":{"attempts":2,"playable":22.982769118996163,"score":22.982769118996163},"GB2-07":{"attempts":3,"playable":57.56430866693944,"score":57.56430866693944},"GB2-08":{"attempts":3,"playable":65.63737732396488,"score":65.63737732396488}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.64587090962158,"score":81.64587090962158},"GB2-02":{"attempts":1,"playable":48.28147888863603,"score":48.28147888863603},"GB2-03":{"attempts":1,"playable":59.97239335369442,"score":59.97239335369442},"GB2-04":{"attempts":1,"playable":49.922631510348495,"score":49.922631510348495},"GB2-05":{"attempts":1,"playable":61.946526867017724,"score":61.946526867017724},"GB2-06":{"attempts":1,"playable":26.16779575599386,"score":26.16779575599386},"GB2-07":{"attempts":1,"playable":75.17806797846778,"score":75.17806797846778},"GB2-08":{"attempts":1,"playable":74.00413186965886,"score":74.00413186965886}},"medium":{"GB2-01":{"attempts":1,"playable":85.00466777052532,"score":85.00466777052532},"GB2-02":{"attempts":1,"playable":46.312312690371485,"score":46.312312690371485},"GB2-03":{"attempts":1,"playable":50.88493772058917,"score":50.88493772058917},"GB2-04":{"attempts":1,"playable":42.478723853109265,"score":42.478723853109265},"GB2-05":{"attempts":1,"playable":50.02874620952247,"score":50.02874620952247},"GB2-07":{"attempts":1,"playable":64.0966668761972,"score":64.0966668761972},"GB2-08":{"attempts":1,"playable":67.57801500618757,"score":67.57801500618757}},"none":{"GB2-01":{"attempts":1,"playable":36.91428968778098,"score":36.91428968778098},"GB2-02":{"attempts":1,"playable":41.33983201411044,"score":41.33983201411044},"GB2-03":{"attempts":1,"playable":47.968539887284344,"score":47.968539887284344},"GB2-04":{"attempts":1,"playable":48.39400710035519,"score":48.39400710035519},"GB2-05":{"attempts":1,"playable":51.08762429533144,"score":51.08762429533144},"GB2-06":{"attempts":1,"playable":19.797742481998466,"score":19.797742481998466},"GB2-07":{"attempts":1,"playable":33.41819114615332,"score":33.41819114615332},"GB2-08":{"attempts":1,"playable":55.32998509604824,"score":55.32998509604824}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:48Z","match_totals_all":{"draws":3203,"losses":5518,"wins":5844},"match_totals_tracks":{"highest":{"draws":629,"losses":1209,"wins":1856},"medium":{"draws":1202,"losses":1595,"wins":2278},"none":{"draws":1372,"losses":2714,"wins":1710}},"model_slug":"meta-muse-spark-1-2","overall":{"max":85.00466777052532,"mean":53.15866858874719,"min":19.797742481998466},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.64587090962158,"GB2-02":48.28147888863603,"GB2-03":59.97239335369442,"GB2-04":49.922631510348495,"GB2-05":61.946526867017724,"GB2-06":26.16779575599386,"GB2-07":75.17806797846778,"GB2-08":74.00413186965886},"per_game_all":{"GB2-01":67.85494278930929,"GB2-02":45.31120786437265,"GB2-03":52.941956987189315,"GB2-04":46.93178748793765,"GB2-05":54.35429912395721,"GB2-07":57.56430866693944,"GB2-08":65.63737732396488},"per_game_match_totals_all":{"GB2-01":{"draws":298,"losses":489,"wins":1055},"GB2-02":{"draws":1313,"losses":310,"wins":112},"GB2-03":{"draws":321,"losses":836,"wins":795},"GB2-04":{"draws":1111,"losses":428,"wins":293},"GB2-05":{"draws":0,"losses":976,"wins":1120},"GB2-06":{"draws":23,"losses":910,"wins":241},"GB2-07":{"draws":0,"losses":886,"wins":1054},"GB2-08":{"draws":137,"losses":683,"wins":1174}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":87,"wins":379},"GB2-02":{"draws":332,"losses":63,"wins":37},"GB2-03":{"draws":18,"losses":184,"wins":244},"GB2-04":{"draws":248,"losses":106,"wins":94},"GB2-05":{"draws":0,"losses":186,"wins":298},"GB2-06":{"draws":19,"losses":337,"wins":100},"GB2-07":{"draws":0,"losses":120,"wins":354},"GB2-08":{"draws":10,"losses":126,"wins":350}},"medium":{"GB2-01":{"draws":30,"losses":105,"wins":553},"GB2-02":{"draws":499,"losses":113,"wins":53},"GB2-03":{"draws":190,"losses":292,"wins":262},"GB2-04":{"draws":370,"losses":193,"wins":107},"GB2-05":{"draws":0,"losses":403,"wins":409},"GB2-07":{"draws":0,"losses":282,"wins":450},"GB2-08":{"draws":113,"losses":207,"wins":444}},"none":{"GB2-01":{"draws":266,"losses":297,"wins":123},"GB2-02":{"draws":482,"losses":134,"wins":22},"GB2-03":{"draws":113,"losses":360,"wins":289},"GB2-04":{"draws":493,"losses":129,"wins":92},"GB2-05":{"draws":0,"losses":387,"wins":413},"GB2-06":{"draws":4,"losses":573,"wins":141},"GB2-07":{"draws":0,"losses":484,"wins":250},"GB2-08":{"draws":14,"losses":350,"wins":380}}},"per_game_raw_elo_all":{"GB2-01":1696.2776787846126,"GB2-02":1439.6725491167851,"GB2-03":1465.8187983211421,"GB2-04":1454.3033067748365,"GB2-05":1508.3283645371869,"GB2-07":1559.743840977889,"GB2-08":1631.7730467749018},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1838.552788223775,"GB2-02":1462.5893854389965,"GB2-03":1529.7359693278383,"GB2-04":1477.4396196540897,"GB2-05":1607.40261757632,"GB2-06":1086.0090485272908,"GB2-07":1805.1643301222725,"GB2-08":1759.3030873682496},"medium":{"GB2-01":1894.710787020118,"GB2-02":1447.4322171877761,"GB2-03":1446.6105342274438,"GB2-04":1419.8564218684014,"GB2-05":1452.1446821259326,"GB2-07":1634.177438307918,"GB2-08":1650.5881512305546},"none":{"GB2-01":1355.5694611099455,"GB2-02":1408.9960447235826,"GB2-03":1421.109891408145,"GB2-04":1465.6138788020187,"GB2-05":1465.4377939093083,"GB2-06":984.6764451569395,"GB2-07":1239.8897545034765,"GB2-08":1485.4279017259018}},"per_game_tracks":{"highest":{"GB2-01":81.64587090962158,"GB2-02":48.28147888863603,"GB2-03":59.97239335369442,"GB2-04":49.922631510348495,"GB2-05":61.946526867017724,"GB2-06":26.16779575599386,"GB2-07":75.17806797846778,"GB2-08":74.00413186965886},"medium":{"GB2-01":85.00466777052532,"GB2-02":46.312312690371485,"GB2-03":50.88493772058917,"GB2-04":42.478723853109265,"GB2-05":50.02874620952247,"GB2-07":64.0966668761972,"GB2-08":67.57801500618757},"none":{"GB2-01":36.91428968778098,"GB2-02":41.33983201411044,"GB2-03":47.968539887284344,"GB2-04":48.39400710035519,"GB2-05":51.08762429533144,"GB2-06":19.797742481998466,"GB2-07":33.41819114615332,"GB2-08":55.32998509604824}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":59.63986214167984,"medium":58.05486716092893,"none":41.7812764636328},"reasoning_agg":{"highest":{"max":81.64587090962158,"mean":59.63986214167984,"min":26.16779575599386},"medium":{"max":85.00466777052532,"mean":58.05486716092893,"min":42.478723853109265},"none":{"max":55.32998509604824,"mean":41.7812764636328,"min":19.797742481998466}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.858585678047042}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:3aefb0e11d772bd6","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":1.139997},"none":{"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":0.5826720000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.508434,"mean":0.171409,"median":0.146631,"min":0.054066,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":28,"run_count":24,"total":4.113816000000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":413691,"mean_ms":128683.25,"min_ms":28133,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":413691,"mean_ms":243828.625,"min_ms":115297,"run_count":8},"medium":{"attempt_count":10,"max_ms":159798,"mean_ms":101243.125,"min_ms":39983,"run_count":8},"none":{"attempt_count":9,"max_ms":84315,"mean_ms":40978.0,"min_ms":28133,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":30544,"output_mean":9612.333333333334,"output_min":2170,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":30544,"output_mean":18138.375,"output_min":8542,"run_count":8},"medium":{"attempt_count":10,"output_max":11696,"output_mean":7576.625,"output_min":3317,"run_count":8},"none":{"attempt_count":9,"output_max":6625,"output_mean":3122.0,"output_min":2170,"run_count":8}},"display_name":"Ember-1","economics":{"all":52.83094715088848,"highest":65.02592197921729,"medium":54.48763716491097,"none":38.97928230853715},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[262144],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[262144],"total_output_tokens":230696,"total_reasoning_output_tokens":146257,"total_visible_output_tokens":84439,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"fireworks","provider_model":"fireworks/ember-1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":60.03642266552842,"score":60.03642266552842},"GB2-02":{"attempts":3,"playable":44.56819777921003,"score":44.56819777921003},"GB2-03":{"attempts":3,"playable":59.445149262256614,"score":59.445149262256614},"GB2-04":{"attempts":3,"playable":44.747525153011885,"score":44.747525153011885},"GB2-05":{"attempts":3,"playable":44.583180409575796,"score":44.583180409575796},"GB2-06":{"attempts":3,"playable":52.23070281120781,"score":52.23070281120781},"GB2-07":{"attempts":3,"playable":59.07409850475651,"score":59.07409850475651},"GB2-08":{"attempts":3,"playable":57.96230062156068,"score":57.96230062156068}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":78.10080210980087,"score":78.10080210980087},"GB2-02":{"attempts":1,"playable":43.28928995530674,"score":43.28928995530674},"GB2-03":{"attempts":1,"playable":80.79881025038243,"score":80.79881025038243},"GB2-04":{"attempts":1,"playable":40.25371761545779,"score":40.25371761545779},"GB2-05":{"attempts":1,"playable":63.827619010512734,"score":63.827619010512734},"GB2-06":{"attempts":1,"playable":52.703186836214265,"score":52.703186836214265},"GB2-07":{"attempts":1,"playable":76.17043124225552,"score":76.17043124225552},"GB2-08":{"attempts":1,"playable":85.06351881380796,"score":85.06351881380796}},"medium":{"GB2-01":{"attempts":1,"playable":50.73963386733398,"score":50.73963386733398},"GB2-02":{"attempts":1,"playable":45.49806011864702,"score":45.49806011864702},"GB2-03":{"attempts":1,"playable":61.92785212938763,"score":61.92785212938763},"GB2-04":{"attempts":1,"playable":52.72028110380567,"score":52.72028110380567},"GB2-05":{"attempts":1,"playable":47.91820861968938,"score":47.91820861968938},"GB2-06":{"attempts":1,"playable":57.139630424018286,"score":57.139630424018286},"GB2-07":{"attempts":1,"playable":64.28716200688727,"score":64.28716200688727},"GB2-08":{"attempts":1,"playable":55.67026904951855,"score":55.67026904951855}},"none":{"GB2-01":{"attempts":1,"playable":51.26883201945041,"score":51.26883201945041},"GB2-02":{"attempts":1,"playable":44.917243263676326,"score":44.917243263676326},"GB2-03":{"attempts":1,"playable":35.60878540699978,"score":35.60878540699978},"GB2-04":{"attempts":1,"playable":41.26857673977222,"score":41.26857673977222},"GB2-05":{"attempts":1,"playable":22.003713598525277,"score":22.003713598525277},"GB2-06":{"attempts":1,"playable":46.8492911733909,"score":46.8492911733909},"GB2-07":{"attempts":1,"playable":36.76470226512673,"score":36.76470226512673},"GB2-08":{"attempts":1,"playable":33.15311400135553,"score":33.15311400135553}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-15T06:51:25Z","match_totals_all":{"draws":3056,"losses":3833,"wins":4193},"match_totals_tracks":{"highest":{"draws":665,"losses":981,"wins":2048},"medium":{"draws":1089,"losses":1186,"wins":1419},"none":{"draws":1302,"losses":1666,"wins":726}},"model_slug":"fireworks-ember-1","overall":{"max":85.06351881380796,"mean":52.83094715088847,"min":22.003713598525277},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":78.10080210980087,"GB2-02":43.28928995530674,"GB2-03":80.79881025038243,"GB2-04":40.25371761545779,"GB2-05":63.827619010512734,"GB2-06":52.703186836214265,"GB2-07":76.17043124225552,"GB2-08":85.06351881380796},"per_game_all":{"GB2-01":60.03642266552842,"GB2-02":44.56819777921003,"GB2-03":59.445149262256614,"GB2-04":44.747525153011885,"GB2-05":44.583180409575796,"GB2-06":52.23070281120781,"GB2-07":59.07409850475651,"GB2-08":57.96230062156068},"per_game_match_totals_all":{"GB2-01":{"draws":435,"losses":355,"wins":614},"GB2-02":{"draws":986,"losses":242,"wins":68},"GB2-03":{"draws":268,"losses":445,"wins":625},"GB2-04":{"draws":820,"losses":349,"wins":175},"GB2-05":{"draws":0,"losses":808,"wins":644},"GB2-06":{"draws":84,"losses":638,"wins":646},"GB2-07":{"draws":0,"losses":601,"wins":821},"GB2-08":{"draws":463,"losses":395,"wins":600}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":101,"wins":359},"GB2-02":{"draws":333,"losses":84,"wins":15},"GB2-03":{"draws":14,"losses":87,"wins":345},"GB2-04":{"draws":284,"losses":131,"wins":33},"GB2-05":{"draws":0,"losses":177,"wins":307},"GB2-06":{"draws":21,"losses":214,"wins":221},"GB2-07":{"draws":0,"losses":115,"wins":359},"GB2-08":{"draws":5,"losses":72,"wins":409}},"medium":{"GB2-01":{"draws":240,"losses":115,"wins":113},"GB2-02":{"draws":328,"losses":77,"wins":27},"GB2-03":{"draws":36,"losses":166,"wins":244},"GB2-04":{"draws":273,"losses":81,"wins":94},"GB2-05":{"draws":0,"losses":253,"wins":231},"GB2-06":{"draws":30,"losses":188,"wins":238},"GB2-07":{"draws":0,"losses":175,"wins":299},"GB2-08":{"draws":182,"losses":131,"wins":173}},"none":{"GB2-01":{"draws":187,"losses":139,"wins":142},"GB2-02":{"draws":325,"losses":81,"wins":26},"GB2-03":{"draws":218,"losses":192,"wins":36},"GB2-04":{"draws":263,"losses":137,"wins":48},"GB2-05":{"draws":0,"losses":378,"wins":106},"GB2-06":{"draws":33,"losses":236,"wins":187},"GB2-07":{"draws":0,"losses":311,"wins":163},"GB2-08":{"draws":276,"losses":192,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1590.251024645875,"GB2-02":1433.9933256492404,"GB2-03":1549.5006601181242,"GB2-04":1437.362228380019,"GB2-05":1371.5272280563813,"GB2-06":1487.8166214380517,"GB2-07":1581.0010756588338,"GB2-08":1579.2122700183143},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1786.7878691928945,"GB2-02":1424.1250785301434,"GB2-03":1786.3761189911963,"GB2-04":1402.4558999050157,"GB2-05":1634.116606950344,"GB2-06":1494.5270010148754,"GB2-07":1822.7856326670549,"GB2-08":1995.7324936849704},"medium":{"GB2-01":1489.444997591598,"GB2-02":1441.1644245607395,"GB2-03":1548.8138093030855,"GB2-04":1499.215476844532,"GB2-05":1425.6835816592518,"GB2-06":1566.8194631852348,"GB2-07":1636.845469120572,"GB2-08":1489.4565845796753},"none":{"GB2-01":1494.5202071531328,"GB2-02":1436.6904738568378,"GB2-03":1313.3120520600908,"GB2-04":1410.4153083905092,"GB2-05":1054.7814955595481,"GB2-06":1402.1034001140451,"GB2-07":1283.3721251888742,"GB2-08":1252.4477317902965}},"per_game_tracks":{"highest":{"GB2-01":78.10080210980087,"GB2-02":43.28928995530674,"GB2-03":80.79881025038243,"GB2-04":40.25371761545779,"GB2-05":63.827619010512734,"GB2-06":52.703186836214265,"GB2-07":76.17043124225552,"GB2-08":85.06351881380796},"medium":{"GB2-01":50.73963386733398,"GB2-02":45.49806011864702,"GB2-03":61.92785212938763,"GB2-04":52.72028110380567,"GB2-05":47.91820861968938,"GB2-06":57.139630424018286,"GB2-07":64.28716200688727,"GB2-08":55.67026904951855},"none":{"GB2-01":51.26883201945041,"GB2-02":44.917243263676326,"GB2-03":35.60878540699978,"GB2-04":41.26857673977222,"GB2-05":22.003713598525277,"GB2-06":46.8492911733909,"GB2-07":36.76470226512673,"GB2-08":33.15311400135553}},"provider_color":"#6720FF","provider_company":"Fireworks AI","provider_key":"fireworks","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.02592197921729,"medium":54.48763716491097,"none":38.97928230853715},"reasoning_agg":{"highest":{"max":85.06351881380796,"mean":65.02592197921729,"min":40.25371761545779},"medium":{"max":64.28716200688727,"mean":54.48763716491097,"min":45.49806011864702},"none":{"max":51.26883201945041,"mean":38.97928230853715,"min":22.003713598525277}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.046639670680136}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:925bbdc6068158b7","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":79,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":112,"run_count":88,"total":0.0},"codegen_latency_ms":{"attempt_count":112,"max_ms":1487583,"mean_ms":467860.5227272727,"min_ms":38538,"run_count":88},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":31,"max_ms":1487583,"mean_ms":1029047.25,"min_ms":343277,"run_count":28},"medium":{"attempt_count":39,"max_ms":676327,"mean_ms":324151.5,"min_ms":151453,"run_count":30},"none":{"attempt_count":42,"max_ms":287181,"mean_ms":87795.26666666666,"min_ms":38538,"run_count":30}},"codegen_output_tokens":{"attempt_count":112,"output_max":85105,"output_mean":23027.329545454544,"output_min":1660,"run_count":88},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":31,"output_max":85105,"output_mean":50628.67857142857,"output_min":15800,"run_count":28},"medium":{"attempt_count":39,"output_max":33467,"output_mean":16156.733333333334,"output_min":6647,"run_count":30},"none":{"attempt_count":42,"output_max":9871,"output_mean":4136.666666666667,"output_min":1660,"run_count":30}},"display_name":"Ox Alpha","economics":{"all":54.3484529813012,"highest":68.29644554364616,"medium":51.050402907416476,"none":43.69851049284095},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":101,"effective_max_output_tokens":[131072],"finish_reason_observations":110,"finish_reasons":["stop"],"indexed_attempts":114,"output_token_observations":112,"provider_post_attempt_observations":113,"provider_post_attempts":113,"reasoning_token_observations":112,"reconciliation_get_attempt_observations":113,"reconciliation_get_attempts":534,"requested_max_output_token_observations":102,"requested_max_output_tokens":[131072],"total_output_tokens":2026405,"total_visible_output_tokens":2026405,"visible_token_observations":112},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/ox-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":26,"evaluated_cells":30,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":21,"first_pass_rate":0.7241379310344828,"game_attempts":{"GB2-01":{"admitted":2,"model_code_failures":1},"GB2-02":{"admitted":3},"GB2-03":{"admitted":7,"model_code_failures":2},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":2,"performance_rejections":1},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.10344827586206896,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":5,"repaired_rate":0.1724137931034483},"baseline":{"admitted_plugins":28,"evaluated_cells":30,"failed_game_aliases":["GB2-03","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6333333333333333,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":8,"model_code_failures":1},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":2,"model_code_failures":1}},"model_code_failure_rate":0.06666666666666667,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":9,"repaired_rate":0.3},"intensive":{"admitted_plugins":25,"evaluated_cells":25,"first_pass_admitted":22,"first_pass_rate":0.88,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":5,"infra_failures_excluded":4},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.12}},"headline_games_all":{"GB2-01":{"attempts":9,"failed_attempts":1,"playable":55.35367099048784,"score":48.26794816510034},"GB2-02":{"attempts":8,"playable":56.116372345337396,"score":56.116372345337396},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":57.684836370967055,"score":51.728836312515334},"GB2-04":{"attempts":9,"playable":59.917687025887716,"score":59.917687025887716},"GB2-05":{"attempts":9,"playable":54.55718012546035,"score":54.55718012546035},"GB2-06":{"attempts":8,"playable":46.3374161885258,"score":46.3374161885258},"GB2-07":{"attempts":9,"playable":50.46022728038373,"score":50.46022728038373},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":53.82172954294544,"score":50.205446912887055}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":58.98938239677276,"score":58.98938239677276},"GB2-02":{"attempts":2,"playable":74.86438081039262,"score":74.86438081039262},"GB2-03":{"attempts":5,"playable":70.30869959667567,"score":70.30869959667567},"GB2-04":{"attempts":3,"playable":72.63413336502286,"score":72.63413336502286},"GB2-05":{"attempts":3,"playable":62.543758151817265,"score":62.543758151817265},"GB2-06":{"attempts":3,"playable":69.02820382688274,"score":69.02820382688274},"GB2-07":{"attempts":3,"playable":66.67259698276774,"score":66.67259698276774},"GB2-08":{"attempts":3,"playable":71.33040921883757,"score":71.33040921883757}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":63.771505428487494,"score":42.514336952324996},"GB2-02":{"attempts":3,"playable":49.9945470499213,"score":49.9945470499213},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":58.066192061970995,"score":45.16259382597744},"GB2-04":{"attempts":3,"playable":57.609250239159245,"score":57.609250239159245},"GB2-05":{"attempts":3,"playable":48.63441066620925,"score":48.63441066620925},"GB2-06":{"attempts":2,"playable":27.047994469655592,"score":27.047994469655592},"GB2-07":{"attempts":3,"playable":45.6910876044547,"score":45.6910876044547},"GB2-08":{"attempts":3,"playable":57.58823573947325,"score":57.58823573947325}},"none":{"GB2-01":{"attempts":3,"playable":43.30012514620328,"score":43.30012514620328},"GB2-02":{"attempts":3,"playable":43.490189175698276,"score":43.490189175698276},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":44.6796174542545,"score":39.71521551489289},"GB2-04":{"attempts":3,"playable":49.509677473481055,"score":49.509677473481055},"GB2-05":{"attempts":3,"playable":52.493371558354546,"score":52.493371558354546},"GB2-06":{"attempts":3,"playable":42.93605026903908,"score":42.93605026903908},"GB2-07":{"attempts":3,"playable":39.016997253928736,"score":39.016997253928736},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.546543670525494,"score":21.69769578035033}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-10-15T06:42:24Z","match_totals_all":{"draws":11637,"losses":18226,"wins":20606},"match_totals_tracks":{"highest":{"draws":1857,"losses":4608,"wins":9320},"medium":{"draws":3827,"losses":6345,"wins":6448},"none":{"draws":5953,"losses":7273,"wins":4838}},"model_slug":"stealth-ox-alpha","overall":{"max":74.86438081039262,"mean":52.19888929451221,"min":21.69769578035033},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.989382396772754,"GB2-02":74.86438081039262,"GB2-03":70.30869959667567,"GB2-04":72.63413336502286,"GB2-05":62.54375815181726,"GB2-06":69.02820382688274,"GB2-07":66.67259698276776,"GB2-08":71.33040921883757},"per_game_all":{"GB2-01":55.35367099048784,"GB2-02":56.116372345337396,"GB2-03":57.68483637096705,"GB2-04":60.45619100630196,"GB2-05":54.55718012546035,"GB2-06":46.3374161885258,"GB2-07":50.46022728038373,"GB2-08":53.82172954294544},"per_game_match_totals_all":{"GB2-01":{"draws":854,"losses":2072,"wins":2288},"GB2-02":{"draws":3090,"losses":644,"wins":880},"GB2-03":{"draws":2907,"losses":4523,"wins":5155},"GB2-04":{"draws":2825,"losses":941,"wins":1756},"GB2-05":{"draws":0,"losses":2780,"wins":3222},"GB2-06":{"draws":272,"losses":2661,"wins":2385},"GB2-07":{"draws":0,"losses":3078,"wins":2916},"GB2-08":{"draws":1689,"losses":1527,"wins":2004}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":95,"losses":816,"wins":1021},"GB2-02":{"draws":414,"losses":95,"wins":619},"GB2-03":{"draws":308,"losses":894,"wins":1873},"GB2-04":{"draws":633,"losses":210,"wins":941},"GB2-05":{"draws":0,"losses":796,"wins":1196},"GB2-06":{"draws":171,"losses":576,"wins":1205},"GB2-07":{"draws":0,"losses":720,"wins":1274},"GB2-08":{"draws":236,"losses":501,"wins":1191}},"medium":{"GB2-01":{"draws":273,"losses":382,"wins":659},"GB2-02":{"draws":1285,"losses":243,"wins":206},"GB2-03":{"draws":620,"losses":1724,"wins":2114},"GB2-04":{"draws":992,"losses":318,"wins":494},"GB2-05":{"draws":0,"losses":1026,"wins":970},"GB2-06":{"draws":48,"losses":942,"wins":348},"GB2-07":{"draws":0,"losses":1091,"wins":861},"GB2-08":{"draws":609,"losses":619,"wins":796}},"none":{"GB2-01":{"draws":486,"losses":874,"wins":608},"GB2-02":{"draws":1391,"losses":306,"wins":55},"GB2-03":{"draws":1979,"losses":1905,"wins":1168},"GB2-04":{"draws":1200,"losses":413,"wins":321},"GB2-05":{"draws":0,"losses":958,"wins":1056},"GB2-06":{"draws":53,"losses":1143,"wins":832},"GB2-07":{"draws":0,"losses":1267,"wins":781},"GB2-08":{"draws":844,"losses":407,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1535.9942631525166,"GB2-02":1535.7454625492737,"GB2-03":1528.527085884182,"GB2-04":1576.3658637501712,"GB2-05":1513.0006537610209,"GB2-06":1393.4820853146566,"GB2-07":1451.6749616121524,"GB2-08":1506.1122369331217},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1572.774536418874,"GB2-02":1705.5529212721158,"GB2-03":1665.3249206094893,"GB2-04":1703.5612736783598,"GB2-05":1620.7918793247038,"GB2-06":1801.5350650751952,"GB2-07":1675.464426908605,"GB2-08":1745.3542357857334},"medium":{"GB2-01":1619.2398075244369,"GB2-02":1476.013840450213,"GB2-03":1528.2663571142991,"GB2-04":1538.4456662713183,"GB2-05":1434.4525938487013,"GB2-06":1034.6104355158668,"GB2-07":1384.5721977072324,"GB2-08":1526.7298226212213},"none":{"GB2-01":1415.9684455142387,"GB2-02":1425.669625925492,"GB2-03":1391.9899799287573,"GB2-04":1487.0906513008358,"GB2-05":1483.757488109658,"GB2-06":1344.300755352908,"GB2-07":1294.98826022062,"GB2-08":1246.252652392411}},"per_game_tracks":{"highest":{"GB2-01":58.989382396772754,"GB2-02":74.86438081039262,"GB2-03":70.30869959667567,"GB2-04":72.63413336502286,"GB2-05":62.54375815181726,"GB2-06":69.02820382688274,"GB2-07":66.67259698276776,"GB2-08":71.33040921883757},"medium":{"GB2-01":63.771505428487494,"GB2-02":49.9945470499213,"GB2-03":58.06619206197099,"GB2-04":57.609250239159245,"GB2-05":48.63441066620925,"GB2-06":27.047994469655592,"GB2-07":45.6910876044547,"GB2-08":57.58823573947325},"none":{"GB2-01":43.30012514620328,"GB2-02":43.49018917569828,"GB2-03":44.6796174542545,"GB2-04":51.12518941472375,"GB2-05":52.493371558354546,"GB2-06":42.93605026903908,"GB2-07":39.016997253928736,"GB2-08":32.546543670525494}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":68.29644554364616,"medium":46.780307068396965,"none":41.519915271493524},"reasoning_agg":{"highest":{"max":74.86438081039262,"mean":68.29644554364616,"min":58.98938239677276},"medium":{"max":57.609250239159245,"mean":46.780307068396965,"min":27.047994469655592},"none":{"max":52.493371558354546,"mean":41.519915271493524,"min":21.69769578035033}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.776530272152634}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:bbbf1d6020828606","codegen_cost_by_reasoning":{"highest":{"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":0.28979720625000005,"recorded_attempt_count":57,"run_count":20,"total":8.014536974999999},"medium":{"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":4.169687700000001},"none":{"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":0.8934513}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.8934513},"historical-provider-setting-intensive":{"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":0.28979720625000005,"recorded_attempt_count":57,"run_count":20,"total":8.014536975}},"codegen_cost_usd":{"admitted_cell_count":46,"cell_count":24,"cost_basis_counts":{"provider_reported":130},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.531673125,"mean":0.24710551171874998,"median":0.24728879999999998,"min":0.0411735,"recorded_attempt_count":130,"run_count":52,"total":13.077675975},"codegen_latency_ms":{"attempt_count":126,"max_ms":348942,"mean_ms":134334.75,"min_ms":17298,"run_count":52},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":53,"max_ms":348942,"mean_ms":213753.4,"min_ms":85578,"run_count":20},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":130,"output_max":100087,"output_mean":31640.134615384617,"output_min":2060,"run_count":52},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":57,"output_max":100087,"output_mean":54101.95,"output_min":17027,"run_count":20},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":53.947573429263244,"highest":63.36124824891649,"medium":58.42187446591142,"none":40.059597572961835},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[65536],"finish_reason_observations":126,"finish_reasons":["length","stop"],"indexed_attempts":131,"output_token_observations":130,"provider_post_attempt_observations":4,"provider_post_attempts":4,"reasoning_token_observations":86,"reconciliation_get_attempt_observations":4,"reconciliation_get_attempts":19,"requested_max_output_token_observations":5,"requested_max_output_tokens":[65536],"total_output_tokens":1645287,"total_reasoning_output_tokens":844369,"total_visible_output_tokens":229233,"visible_token_observations":86},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":14,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":1,"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25},"intensive":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":12,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2,"infra_failures_excluded":2},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2,"infra_failures_excluded":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-02","GB2-03","GB2-07"],"infra_failures_excluded":5,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":52.63989804992124,"score":52.63989804992124},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.41463187820074,"score":38.04900673479704},"GB2-03":{"attempts":6,"playable":57.006912076598894,"score":57.006912076598894},"GB2-04":{"attempts":6,"playable":47.78755348284873,"score":47.78755348284873},"GB2-05":{"attempts":6,"playable":67.36037649035804,"score":67.36037649035804},"GB2-06":{"attempts":6,"playable":62.78019870043201,"score":62.78019870043201},"GB2-07":{"attempts":6,"playable":48.31575659091891,"score":48.31575659091891},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":51.27526016482741,"score":39.921010908446085}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":54.60624717866746,"score":54.60624717866746},"GB2-02":{"attempts":2,"playable":54.5268553158629,"score":54.5268553158629},"GB2-03":{"attempts":2,"playable":69.75726254767585,"score":69.75726254767585},"GB2-04":{"attempts":2,"playable":59.58591828557907,"score":59.58591828557907},"GB2-05":{"attempts":2,"playable":84.21086144901206,"score":84.21086144901206},"GB2-06":{"attempts":2,"playable":83.0234743922216,"score":83.0234743922216},"GB2-07":{"attempts":2,"playable":50.565184085962315,"score":50.565184085962315},"GB2-08":{"attempts":2,"playable":50.61418273635069,"score":50.61418273635069}},"medium":{"GB2-01":{"attempts":2,"playable":72.03364186916929,"score":72.03364186916929},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":38.19375086042222,"score":19.09687543021111},"GB2-03":{"attempts":2,"playable":46.920511826623446,"score":46.920511826623446},"GB2-04":{"attempts":2,"playable":41.22864724945737,"score":41.22864724945737},"GB2-05":{"attempts":2,"playable":70.41749928023121,"score":70.41749928023121},"GB2-06":{"attempts":2,"playable":83.15636604953903,"score":83.15636604953903},"GB2-07":{"attempts":2,"playable":47.29908305356081,"score":47.29908305356081},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":68.12549553828795,"score":34.062747769143975}},"none":{"GB2-01":{"attempts":2,"playable":31.27980510192699,"score":31.27980510192699},"GB2-02":{"attempts":2,"playable":40.523289458317095,"score":40.523289458317095},"GB2-03":{"attempts":2,"playable":54.342961855497386,"score":54.342961855497386},"GB2-04":{"attempts":2,"playable":42.548094913509765,"score":42.548094913509765},"GB2-05":{"attempts":2,"playable":47.45276874183084,"score":47.45276874183084},"GB2-06":{"attempts":2,"playable":22.16075565953539,"score":22.16075565953539},"GB2-07":{"attempts":2,"playable":47.083002633233605,"score":47.083002633233605},"GB2-08":{"attempts":2,"playable":35.086102219843596,"score":35.086102219843596}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-15T06:51:18Z","match_totals_all":{"draws":8278,"losses":11270,"wins":13539},"match_totals_tracks":{"highest":{"draws":2162,"losses":2938,"wins":5652},"medium":{"draws":2173,"losses":3038,"wins":4820},"none":{"draws":3943,"losses":5294,"wins":3067}},"model_slug":"google-gemini-3-6-flash","overall":{"max":84.21086144901206,"mean":51.73258912929012,"min":19.09687543021111},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.60624717866746,"GB2-02":54.5268553158629,"GB2-03":69.75726254767585,"GB2-04":59.58591828557907,"GB2-05":84.21086144901206,"GB2-06":83.0234743922216,"GB2-07":50.565184085962315,"GB2-08":50.61418273635069},"per_game_all":{"GB2-01":52.63989804992124,"GB2-02":44.41463187820074,"GB2-03":57.006912076598894,"GB2-04":47.78755348284873,"GB2-05":67.36037649035804,"GB2-06":62.78019870043201,"GB2-07":48.31575659091891,"GB2-08":51.27526016482741},"per_game_match_totals_all":{"GB2-01":{"draws":1138,"losses":1605,"wins":1619},"GB2-02":{"draws":2077,"losses":500,"wins":214},"GB2-03":{"draws":644,"losses":1599,"wins":1899},"GB2-04":{"draws":2486,"losses":934,"wins":792},"GB2-05":{"draws":0,"losses":1600,"wins":3225},"GB2-06":{"draws":291,"losses":1529,"wins":2648},"GB2-07":{"draws":0,"losses":2234,"wins":2111},"GB2-08":{"draws":1642,"losses":1269,"wins":1031}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":390,"losses":506,"wins":582},"GB2-02":{"draws":527,"losses":140,"wins":197},"GB2-03":{"draws":74,"losses":346,"wins":730},"GB2-04":{"draws":572,"losses":288,"wins":560},"GB2-05":{"draws":0,"losses":245,"wins":1271},"GB2-06":{"draws":47,"losses":247,"wins":1178},"GB2-07":{"draws":0,"losses":664,"wins":638},"GB2-08":{"draws":552,"losses":502,"wins":496}},"medium":{"GB2-01":{"draws":443,"losses":233,"wins":710},"GB2-02":{"draws":430,"losses":133,"wins":7},"GB2-03":{"draws":215,"losses":681,"wins":532},"GB2-04":{"draws":863,"losses":333,"wins":123},"GB2-05":{"draws":0,"losses":487,"wins":1125},"GB2-06":{"draws":106,"losses":207,"wins":1175},"GB2-07":{"draws":0,"losses":751,"wins":717},"GB2-08":{"draws":116,"losses":213,"wins":431}},"none":{"GB2-01":{"draws":305,"losses":866,"wins":327},"GB2-02":{"draws":1120,"losses":227,"wins":10},"GB2-03":{"draws":355,"losses":572,"wins":637},"GB2-04":{"draws":1051,"losses":313,"wins":109},"GB2-05":{"draws":0,"losses":868,"wins":829},"GB2-06":{"draws":138,"losses":1075,"wins":295},"GB2-07":{"draws":0,"losses":819,"wins":756},"GB2-08":{"draws":974,"losses":554,"wins":104}}},"per_game_raw_elo_all":{"GB2-01":1541.7267819703045,"GB2-02":1433.3771336444752,"GB2-03":1508.391537044294,"GB2-04":1463.570812333258,"GB2-05":1798.3350117643213,"GB2-06":1713.315477038118,"GB2-07":1428.903557026797,"GB2-08":1464.7521897589857},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1532.6645482984372,"GB2-02":1513.2564866587015,"GB2-03":1632.5536484340537,"GB2-04":1560.5461217267598,"GB2-05":2109.8295866814597,"GB2-06":2072.4654047875433,"GB2-07":1456.5477433475755,"GB2-08":1463.060101492857},"medium":{"GB2-01":1795.7258418053684,"GB2-02":1384.2642674454037,"GB2-03":1414.7225010313632,"GB2-04":1409.941832460316,"GB2-05":1865.4219119028749,"GB2-06":2049.955641287227,"GB2-07":1416.3331870072907,"GB2-08":1659.1633580911357},"none":{"GB2-01":1296.7899558071074,"GB2-02":1402.61064682932,"GB2-03":1477.8984616674652,"GB2-04":1420.2244828126975,"GB2-05":1419.753536708629,"GB2-06":1017.5253850395828,"GB2-07":1413.829740725525,"GB2-08":1272.0331096929635}},"per_game_tracks":{"highest":{"GB2-01":54.60624717866746,"GB2-02":54.5268553158629,"GB2-03":69.75726254767585,"GB2-04":59.58591828557907,"GB2-05":84.21086144901206,"GB2-06":83.0234743922216,"GB2-07":50.565184085962315,"GB2-08":50.61418273635069},"medium":{"GB2-01":72.03364186916929,"GB2-02":38.19375086042222,"GB2-03":46.920511826623446,"GB2-04":41.22864724945737,"GB2-05":70.41749928023121,"GB2-06":83.15636604953903,"GB2-07":47.29908305356081,"GB2-08":68.12549553828795},"none":{"GB2-01":31.27980510192699,"GB2-02":40.523289458317095,"GB2-03":54.342961855497386,"GB2-04":42.548094913509765,"GB2-05":47.45276874183084,"GB2-06":22.16075565953539,"GB2-07":47.083002633233605,"GB2-08":35.086102219843596}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.36124824891649,"medium":51.77692156599203,"none":40.059597572961835},"reasoning_agg":{"highest":{"max":84.21086144901206,"mean":63.36124824891649,"min":50.565184085962315},"medium":{"max":83.15636604953903,"mean":51.77692156599203,"min":19.09687543021111},"none":{"max":54.342961855497386,"mean":40.059597572961835,"min":22.16075565953539}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":23.301650675954654}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:9f1d6d50ef1e21fb","codegen_cost_by_reasoning":{"highest":{"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":7.44989},"medium":{"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":1.7435250000000002},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":1.2628249999999999},"historical-provider-setting-intensive":{"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":7.44989}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":1.38945,"mean":0.43567666666666666,"median":0.20305499999999999,"min":0.131495,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"run_count":24,"token_priced_attempt_count":25,"total":10.45624},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":57.54673695867213,"highest":72.71863954731269,"medium":48.77530634137831,"none":48.68711526768556},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["end_turn","max_tokens"],"indexed_attempts":31,"output_token_observations":25,"total_output_tokens":356249},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-8","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":55.95804781595708,"score":55.95804781595708},"GB2-02":{"attempts":3,"playable":53.87668108059497,"score":53.87668108059497},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":31.561258303899752,"score":10.52041943463325},"GB2-04":{"attempts":3,"playable":50.92205157166277,"score":50.92205157166277},"GB2-05":{"attempts":3,"playable":39.75960415111708,"score":39.75960415111708},"GB2-06":{"attempts":3,"playable":71.07727948915263,"score":71.07727948915263},"GB2-07":{"attempts":3,"playable":65.63058838521492,"score":65.63058838521492},"GB2-08":{"attempts":3,"playable":65.60290621700545,"score":65.60290621700545}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.72326436156463,"score":68.72326436156463},"GB2-02":{"attempts":1,"playable":80.08011265613774,"score":80.08011265613774},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":69.16666469749526,"score":69.16666469749526},"GB2-05":{"attempts":1,"playable":48.272693336705764,"score":48.272693336705764},"GB2-06":{"attempts":1,"playable":84.06563801668298,"score":84.06563801668298},"GB2-07":{"attempts":1,"playable":76.79053067769553,"score":76.79053067769553},"GB2-08":{"attempts":1,"playable":81.93157308490703,"score":81.93157308490703}},"medium":{"GB2-01":{"attempts":1,"playable":42.05028340724878,"score":42.05028340724878},"GB2-02":{"attempts":1,"playable":41.7724945862077,"score":41.7724945862077},"GB2-03":{"attempts":1,"playable":31.561258303899752,"score":31.561258303899752},"GB2-04":{"attempts":1,"playable":42.1190097321142,"score":42.1190097321142},"GB2-05":{"attempts":1,"playable":48.65614536805991,"score":48.65614536805991},"GB2-06":{"attempts":1,"playable":81.1602700355153,"score":81.1602700355153},"GB2-07":{"attempts":1,"playable":68.79034221153495,"score":68.79034221153495},"GB2-08":{"attempts":1,"playable":34.09264708644591,"score":34.09264708644591}},"none":{"GB2-01":{"attempts":1,"playable":57.10059567905782,"score":57.10059567905782},"GB2-02":{"attempts":1,"playable":39.777435999439476,"score":39.777435999439476},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.48048028537886,"score":41.48048028537886},"GB2-05":{"attempts":1,"playable":22.349973748585565,"score":22.349973748585565},"GB2-06":{"attempts":1,"playable":48.0059304152596,"score":48.0059304152596},"GB2-07":{"attempts":1,"playable":51.31089226641426,"score":51.31089226641426},"GB2-08":{"attempts":1,"playable":80.78449847966341,"score":80.78449847966341}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-10-13T22:37:28Z","match_totals_all":{"draws":3114,"losses":4066,"wins":5688},"match_totals_tracks":{"highest":{"draws":564,"losses":870,"wins":2638},"medium":{"draws":1548,"losses":1617,"wins":1547},"none":{"draws":1002,"losses":1579,"wins":1503}},"model_slug":"claude-opus-4-8","overall":{"max":84.06563801668298,"mean":51.668447268167256,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.72326436156463,"GB2-02":80.08011265613774,"GB2-04":69.16666469749526,"GB2-05":48.272693336705764,"GB2-06":84.06563801668298,"GB2-07":76.79053067769553,"GB2-08":81.93157308490703},"per_game_all":{"GB2-01":55.95804781595708,"GB2-02":53.87668108059497,"GB2-04":50.92205157166277,"GB2-05":39.75960415111708,"GB2-06":71.07727948915263,"GB2-07":65.63058838521492,"GB2-08":65.60290621700545},"per_game_match_totals_all":{"GB2-01":{"draws":301,"losses":623,"wins":790},"GB2-02":{"draws":1096,"losses":239,"wins":343},"GB2-03":{"draws":191,"losses":275,"wins":70},"GB2-04":{"draws":1051,"losses":324,"wins":353},"GB2-05":{"draws":0,"losses":1054,"wins":760},"GB2-06":{"draws":96,"losses":451,"wins":1157},"GB2-07":{"draws":0,"losses":626,"wins":1190},"GB2-08":{"draws":379,"losses":474,"wins":1025}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":79,"losses":154,"wins":343},"GB2-02":{"draws":211,"losses":10,"wins":323},"GB2-04":{"draws":241,"losses":57,"wins":268},"GB2-05":{"draws":0,"losses":314,"wins":300},"GB2-06":{"draws":32,"losses":70,"wins":446},"GB2-07":{"draws":0,"losses":141,"wins":459},"GB2-08":{"draws":1,"losses":124,"wins":499}},"medium":{"GB2-01":{"draws":91,"losses":289,"wins":198},"GB2-02":{"draws":469,"losses":98,"wins":3},"GB2-03":{"draws":191,"losses":275,"wins":70},"GB2-04":{"draws":412,"losses":132,"wins":44},"GB2-05":{"draws":0,"losses":306,"wins":306},"GB2-06":{"draws":10,"losses":99,"wins":459},"GB2-07":{"draws":0,"losses":192,"wins":432},"GB2-08":{"draws":375,"losses":226,"wins":35}},"none":{"GB2-01":{"draws":131,"losses":180,"wins":249},"GB2-02":{"draws":416,"losses":131,"wins":17},"GB2-04":{"draws":398,"losses":135,"wins":41},"GB2-05":{"draws":0,"losses":434,"wins":154},"GB2-06":{"draws":54,"losses":282,"wins":252},"GB2-07":{"draws":0,"losses":293,"wins":299},"GB2-08":{"draws":3,"losses":124,"wins":491}}},"per_game_raw_elo_all":{"GB2-01":1542.9218230875695,"GB2-02":1522.5481570985814,"GB2-04":1489.247207598031,"GB2-05":1308.6455031492294,"GB2-06":1832.3534517857518,"GB2-07":1667.3801023354906,"GB2-08":1692.7982355656025},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1671.6471914059427,"GB2-02":1758.5072420237188,"GB2-04":1638.6144482279494,"GB2-05":1430.129097882008,"GB2-06":2069.036339294413,"GB2-07":1834.0884341426101,"GB2-08":1920.9981538480622},"medium":{"GB2-01":1406.0701406674104,"GB2-02":1412.3638809946701,"GB2-03":1276.3381286965537,"GB2-04":1417.0550621098455,"GB2-05":1434.9364254178336,"GB2-06":2007.862943702214,"GB2-07":1702.1325502637778,"GB2-08":1261.9918833161676},"none":{"GB2-01":1551.0481371893552,"GB2-02":1396.7733482773554,"GB2-04":1412.0721124562976,"GB2-05":1060.870986147847,"GB2-06":1420.161072360628,"GB2-07":1465.919322600084,"GB2-08":1895.4046695325778}},"per_game_tracks":{"highest":{"GB2-01":68.72326436156463,"GB2-02":80.08011265613774,"GB2-04":69.16666469749526,"GB2-05":48.272693336705764,"GB2-06":84.06563801668298,"GB2-07":76.79053067769553,"GB2-08":81.93157308490703},"medium":{"GB2-01":42.05028340724878,"GB2-02":41.7724945862077,"GB2-03":31.561258303899752,"GB2-04":42.1190097321142,"GB2-05":48.65614536805991,"GB2-06":81.1602700355153,"GB2-07":68.79034221153495,"GB2-08":34.09264708644591},"none":{"GB2-01":57.10059567905782,"GB2-02":39.777435999439476,"GB2-04":41.48048028537886,"GB2-05":22.349973748585565,"GB2-06":48.0059304152596,"GB2-07":51.31089226641426,"GB2-08":80.78449847966341}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.62880960389861,"medium":48.77530634137831,"none":42.60122585922487},"reasoning_agg":{"highest":{"max":84.06563801668298,"mean":63.62880960389861,"min":0.0},"medium":{"max":81.1602700355153,"mean":48.77530634137831,"min":31.561258303899752},"none":{"max":80.78449847966341,"mean":42.60122585922487,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.02758374467374}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:a48cab159a322be4","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":1.5865090123478316},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870414}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":1.5865090123478314},"historical-provider-setting-baseline-variant-1":{"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},"historical-provider-setting-baseline-variant-2":{"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":0.6972035991870417},"historical-provider-setting-intensive":{"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":2.1645493884651272}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":32,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.5094276945411561,"mean":0.1819473937669366,"median":0.18692147314407714,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"recorded_attempt_count":14,"run_count":32,"token_priced_attempt_count":32,"total":4.9824165},"codegen_output_tokens":{"attempt_count":32,"output_max":60921,"output_mean":18651.916666666668,"output_min":1790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":60921,"output_mean":31693.5,"output_min":21144,"run_count":8},"medium":{"attempt_count":10,"output_max":28586,"output_mean":21214.875,"output_min":16507,"run_count":8},"none":{"attempt_count":11,"output_max":4623,"output_mean":3047.375,"output_min":1790,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"all":52.35399939090772,"highest":63.29068327733995,"medium":57.28741237224011,"none":36.48390252314307},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":32,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"total_output_tokens":447646,"total_reasoning_output_tokens":288780,"total_visible_output_tokens":158866,"visible_token_observations":32},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":11,"first_pass_rate":0.6875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.1875},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":71.38127091135982,"score":71.38127091135982},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":48.83438652770303,"score":42.2039513668765},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":54.52857829889905,"score":50.481223637254004},"GB2-04":{"attempts":4,"playable":46.36719148483942,"score":46.36719148483942},"GB2-05":{"attempts":4,"playable":45.36441162411617,"score":45.36441162411617},"GB2-06":{"attempts":4,"playable":63.711001069004745,"score":63.711001069004745},"GB2-07":{"attempts":4,"playable":51.33649031294633,"score":51.33649031294633},"GB2-08":{"attempts":4,"playable":37.308664898393154,"score":37.308664898393154}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.61426215290578,"score":90.61426215290578},"GB2-02":{"attempts":1,"playable":62.35032369985962,"score":62.35032369985962},"GB2-03":{"attempts":1,"playable":69.78568219752599,"score":69.78568219752599},"GB2-04":{"attempts":1,"playable":43.055243162035055,"score":43.055243162035055},"GB2-05":{"attempts":1,"playable":52.705293319917516,"score":52.705293319917516},"GB2-06":{"attempts":1,"playable":76.30083194027264,"score":76.30083194027264},"GB2-07":{"attempts":1,"playable":52.20455642795334,"score":52.20455642795334},"GB2-08":{"attempts":1,"playable":59.30927331824966,"score":59.30927331824966}},"medium":{"GB2-01":{"attempts":1,"playable":73.57670939143314,"score":73.57670939143314},"GB2-02":{"attempts":1,"playable":44.370224918290276,"score":44.370224918290276},"GB2-03":{"attempts":1,"playable":69.51592472930088,"score":69.51592472930088},"GB2-04":{"attempts":1,"playable":53.52669916924585,"score":53.52669916924585},"GB2-05":{"attempts":1,"playable":67.48512564129713,"score":67.48512564129713},"GB2-06":{"attempts":1,"playable":73.6319360542391,"score":73.6319360542391},"GB2-07":{"attempts":1,"playable":56.97290715250018,"score":56.97290715250018},"GB2-08":{"attempts":1,"playable":19.219771921614296,"score":19.219771921614296}},"none":{"GB2-01":{"attempts":2,"playable":49.952841189740525,"score":49.952841189740525},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.782610964959176,"score":19.891305482479588},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":24.284127969870262,"score":12.142063984935131},"GB2-04":{"attempts":2,"playable":42.519632123237315,"score":42.519632123237315},"GB2-05":{"attempts":2,"playable":15.902815911133874,"score":15.902815911133874},"GB2-06":{"attempts":2,"playable":41.20023521250249,"score":41.20023521250249},"GB2-07":{"attempts":2,"playable":44.832007358385475,"score":44.832007358385475},"GB2-08":{"attempts":2,"playable":33.39694945531551,"score":33.39694945531551}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-10-15T06:15:37Z","match_totals_all":{"draws":4550,"losses":7163,"wins":6597},"match_totals_tracks":{"highest":{"draws":1038,"losses":1519,"wins":2595},"medium":{"draws":1227,"losses":1670,"wins":2137},"none":{"draws":2285,"losses":3974,"wins":1865}},"model_slug":"google-gemini-3-5-flash","overall":{"max":90.61426215290578,"mean":51.01927566309877,"min":12.142063984935131},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.61426215290578,"GB2-02":62.35032369985962,"GB2-03":69.78568219752599,"GB2-04":43.055243162035055,"GB2-05":52.705293319917516,"GB2-06":76.30083194027264,"GB2-07":52.20455642795334,"GB2-08":59.30927331824966},"per_game_all":{"GB2-01":71.38127091135982,"GB2-02":48.83438652770303,"GB2-03":54.52857829889905,"GB2-04":46.36719148483942,"GB2-05":45.36441162411617,"GB2-06":63.711001069004745,"GB2-07":51.33649031294633,"GB2-08":37.308664898393154},"per_game_match_totals_all":{"GB2-01":{"draws":266,"losses":687,"wins":1399},"GB2-02":{"draws":1309,"losses":281,"wins":202},"GB2-03":{"draws":296,"losses":747,"wins":787},"GB2-04":{"draws":1402,"losses":603,"wins":349},"GB2-05":{"draws":0,"losses":1535,"wins":971},"GB2-06":{"draws":58,"losses":1014,"wins":1318},"GB2-07":{"draws":0,"losses":1324,"wins":1262},"GB2-08":{"draws":1219,"losses":972,"wins":309}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":28,"losses":53,"wins":535},"GB2-02":{"draws":326,"losses":74,"wins":194},"GB2-03":{"draws":99,"losses":163,"wins":350},"GB2-04":{"draws":331,"losses":207,"wins":102},"GB2-05":{"draws":0,"losses":337,"wins":369},"GB2-06":{"draws":17,"losses":155,"wins":430},"GB2-07":{"draws":0,"losses":352,"wins":354},"GB2-08":{"draws":237,"losses":178,"wins":261}},"medium":{"GB2-01":{"draws":14,"losses":179,"wins":425},"GB2-02":{"draws":510,"losses":90,"wins":6},"GB2-03":{"draws":86,"losses":171,"wins":349},"GB2-04":{"draws":339,"losses":128,"wins":143},"GB2-05":{"draws":0,"losses":229,"wins":411},"GB2-06":{"draws":23,"losses":173,"wins":408},"GB2-07":{"draws":0,"losses":322,"wins":392},"GB2-08":{"draws":255,"losses":378,"wins":3}},"none":{"GB2-01":{"draws":224,"losses":455,"wins":439},"GB2-02":{"draws":473,"losses":117,"wins":2},"GB2-03":{"draws":111,"losses":413,"wins":88},"GB2-04":{"draws":732,"losses":268,"wins":104},"GB2-05":{"draws":0,"losses":969,"wins":191},"GB2-06":{"draws":18,"losses":686,"wins":480},"GB2-07":{"draws":0,"losses":650,"wins":516},"GB2-08":{"draws":727,"losses":416,"wins":45}}},"per_game_raw_elo_all":{"GB2-01":1742.1326819913036,"GB2-02":1468.124552561796,"GB2-03":1488.8404234770894,"GB2-04":1449.9958989091147,"GB2-05":1370.7116406610087,"GB2-06":1698.0303978648815,"GB2-07":1466.7135098329327,"GB2-08":1295.2850233516747},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2015.6290101939421,"GB2-02":1575.0864158568409,"GB2-03":1632.742833727587,"GB2-04":1424.3385083391597,"GB2-05":1485.8207770270135,"GB2-06":1911.4822521402216,"GB2-07":1477.2054712466686,"GB2-08":1534.2306622316364},"medium":{"GB2-01":1728.2165097133507,"GB2-02":1432.473232031423,"GB2-03":1629.613670658124,"GB2-04":1505.540189916037,"GB2-05":1689.254600799587,"GB2-06":1860.4049379146404,"GB2-07":1538.3329652344542,"GB2-08":1096.6960375227025},"none":{"GB2-01":1482.5525260666175,"GB2-02":1396.8140097971243,"GB2-03":1204.1647660455576,"GB2-04":1420.1089984721475,"GB2-05":937.0595441564253,"GB2-06":1322.2040035397827,"GB2-07":1384.602093017676,"GB2-08":1254.928370300685}},"per_game_tracks":{"highest":{"GB2-01":90.61426215290578,"GB2-02":62.35032369985962,"GB2-03":69.78568219752599,"GB2-04":43.055243162035055,"GB2-05":52.705293319917516,"GB2-06":76.30083194027264,"GB2-07":52.20455642795334,"GB2-08":59.30927331824966},"medium":{"GB2-01":73.57670939143314,"GB2-02":44.370224918290276,"GB2-03":69.51592472930088,"GB2-04":53.52669916924585,"GB2-05":67.48512564129713,"GB2-06":73.6319360542391,"GB2-07":56.97290715250018,"GB2-08":19.219771921614296},"none":{"GB2-01":49.952841189740525,"GB2-02":39.782610964959176,"GB2-03":24.284127969870262,"GB2-04":42.519632123237315,"GB2-05":15.902815911133874,"GB2-06":41.20023521250249,"GB2-07":44.832007358385475,"GB2-08":33.39694945531551}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.29068327733995,"medium":57.28741237224011,"none":32.47973133971624},"reasoning_agg":{"highest":{"max":90.61426215290578,"mean":63.29068327733995,"min":43.055243162035055},"medium":{"max":73.6319360542391,"mean":57.28741237224011,"min":19.219771921614296},"none":{"max":49.952841189740525,"mean":32.47973133971624,"min":12.142063984935131}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":30.810951937623713}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:881f6033db92eb7a","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":4.4173,"mean":1.10693125,"median":0.4176025,"min":0.12078,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"run_count":24,"token_priced_attempt_count":26,"total":26.566350000000003},"codegen_latency_ms":{"attempt_count":26,"max_ms":1288484,"mean_ms":282342.6666666667,"min_ms":29373,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1288484,"mean_ms":693731.5,"min_ms":464667,"run_count":8},"medium":{"attempt_count":9,"max_ms":158785,"mean_ms":120076.75,"min_ms":87418,"run_count":8},"none":{"attempt_count":8,"max_ms":37405,"mean_ms":33219.75,"min_ms":29373,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":144760,"output_mean":35491.166666666664,"output_min":2821,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":144760,"output_mean":89741.375,"output_min":66963,"run_count":8},"medium":{"attempt_count":9,"output_max":16870,"output_mean":13281.625,"output_min":10218,"run_count":8},"none":{"attempt_count":8,"output_max":3990,"output_mean":3450.5,"output_min":2821,"run_count":8}},"display_name":"GPT-5.5","economics":{"all":55.47338437638914,"highest":69.99175111829423,"medium":52.43497343396311,"none":42.395548520108896},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"total_output_tokens":851788},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":64.15025927770567,"score":64.15025927770567},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.36721744643859,"score":32.244811630959056},"GB2-03":{"attempts":3,"playable":42.70479996415182,"score":42.70479996415182},"GB2-04":{"attempts":3,"playable":39.474226708590244,"score":39.474226708590244},"GB2-05":{"attempts":3,"playable":68.55624020153151,"score":68.55624020153151},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.467765636322476,"score":36.97851042421498},"GB2-07":{"attempts":3,"playable":62.84220389141196,"score":62.84220389141196},"GB2-08":{"attempts":3,"playable":55.11257621494366,"score":55.11257621494366}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":78.88744538393281,"score":78.88744538393281},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":51.47869006855225,"score":51.47869006855225},"GB2-04":{"attempts":1,"playable":36.123793124362365,"score":36.123793124362365},"GB2-05":{"attempts":1,"playable":80.00586039212195,"score":80.00586039212195},"GB2-06":{"attempts":1,"playable":82.14350204705984,"score":82.14350204705984},"GB2-07":{"attempts":1,"playable":87.73324176499803,"score":87.73324176499803},"GB2-08":{"attempts":1,"playable":73.56972504703239,"score":73.56972504703239}},"medium":{"GB2-01":{"attempts":1,"playable":64.06188249918004,"score":64.06188249918004},"GB2-02":{"attempts":1,"playable":54.816924555723126,"score":54.816924555723126},"GB2-03":{"attempts":1,"playable":38.96081232957366,"score":38.96081232957366},"GB2-04":{"attempts":1,"playable":40.70525197146744,"score":40.70525197146744},"GB2-05":{"attempts":1,"playable":74.77879896587257,"score":74.77879896587257},"GB2-06":{"attempts":1,"playable":28.792029225585107,"score":28.792029225585107},"GB2-07":{"attempts":1,"playable":62.01522337286688,"score":62.01522337286688},"GB2-08":{"attempts":1,"playable":55.34886455143598,"score":55.34886455143598}},"none":{"GB2-01":{"attempts":1,"playable":49.50144995000416,"score":49.50144995000416},"GB2-02":{"attempts":1,"playable":41.91751033715405,"score":41.91751033715405},"GB2-03":{"attempts":1,"playable":37.67489749432954,"score":37.67489749432954},"GB2-04":{"attempts":1,"playable":41.59363502994095,"score":41.59363502994095},"GB2-05":{"attempts":1,"playable":50.88406124660001,"score":50.88406124660001},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.77814653637098,"score":38.77814653637098},"GB2-08":{"attempts":1,"playable":36.419139046362616,"score":36.419139046362616}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-10-14T17:58:58Z","match_totals_all":{"draws":4128,"losses":3789,"wins":4907},"match_totals_tracks":{"highest":{"draws":841,"losses":832,"wins":2381},"medium":{"draws":1511,"losses":1492,"wins":1685},"none":{"draws":1776,"losses":1465,"wins":841}},"model_slug":"gpt-5-5","overall":{"max":87.73324176499803,"mean":50.25795353918861,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":78.88744538393281,"GB2-03":51.47869006855225,"GB2-04":36.123793124362365,"GB2-05":80.00586039212195,"GB2-06":82.14350204705984,"GB2-07":87.73324176499803,"GB2-08":73.56972504703239},"per_game_all":{"GB2-01":64.15025927770567,"GB2-03":42.70479996415182,"GB2-04":39.474226708590244,"GB2-05":68.55624020153151,"GB2-07":62.84220389141196,"GB2-08":55.11257621494366},"per_game_match_totals_all":{"GB2-01":{"draws":881,"losses":204,"wins":651},"GB2-02":{"draws":829,"losses":163,"wins":120},"GB2-03":{"draws":519,"losses":700,"wins":399},"GB2-04":{"draws":1046,"losses":517,"wins":165},"GB2-05":{"draws":0,"losses":563,"wins":1183},"GB2-06":{"draws":47,"losses":504,"wins":615},"GB2-07":{"draws":0,"losses":679,"wins":1151},"GB2-08":{"draws":806,"losses":459,"wins":623}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":152,"losses":54,"wins":356},"GB2-03":{"draws":158,"losses":197,"wins":179},"GB2-04":{"draws":332,"losses":199,"wins":41},"GB2-05":{"draws":0,"losses":133,"wins":455},"GB2-06":{"draws":33,"losses":81,"wins":444},"GB2-07":{"draws":0,"losses":72,"wins":534},"GB2-08":{"draws":166,"losses":96,"wins":372}},"medium":{"GB2-01":{"draws":340,"losses":42,"wins":200},"GB2-02":{"draws":357,"losses":73,"wins":120},"GB2-03":{"draws":193,"losses":241,"wins":106},"GB2-04":{"draws":353,"losses":169,"wins":66},"GB2-05":{"draws":0,"losses":151,"wins":427},"GB2-06":{"draws":14,"losses":423,"wins":171},"GB2-07":{"draws":0,"losses":228,"wins":374},"GB2-08":{"draws":254,"losses":165,"wins":221}},"none":{"GB2-01":{"draws":389,"losses":108,"wins":95},"GB2-02":{"draws":472,"losses":90,"wins":0},"GB2-03":{"draws":168,"losses":262,"wins":114},"GB2-04":{"draws":361,"losses":149,"wins":58},"GB2-05":{"draws":0,"losses":279,"wins":301},"GB2-07":{"draws":0,"losses":379,"wins":243},"GB2-08":{"draws":386,"losses":198,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1632.245683037795,"GB2-03":1375.4975483290827,"GB2-04":1396.1535406682121,"GB2-05":1740.016424130742,"GB2-07":1671.9919536338791,"GB2-08":1507.4964472364538},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1797.7487130907384,"GB2-03":1451.8475929090023,"GB2-04":1369.5019749093196,"GB2-05":1938.4686571328716,"GB2-06":2028.163872338218,"GB2-07":2101.520488130208,"GB2-08":1751.371869524503},"medium":{"GB2-01":1621.4011329746177,"GB2-02":1513.44674944111,"GB2-03":1342.9741380989046,"GB2-04":1406.0024813727807,"GB2-05":1818.7005356528125,"GB2-06":1126.239698724502,"GB2-07":1605.4326004855789,"GB2-08":1485.6507701002058},"none":{"GB2-01":1477.5872030480289,"GB2-02":1413.4912564426043,"GB2-03":1331.6709139793409,"GB2-04":1412.9561657225356,"GB2-05":1462.8800796065418,"GB2-07":1309.0227722858504,"GB2-08":1285.4667020846528}},"per_game_tracks":{"highest":{"GB2-01":78.88744538393281,"GB2-03":51.47869006855225,"GB2-04":36.123793124362365,"GB2-05":80.00586039212195,"GB2-06":82.14350204705984,"GB2-07":87.73324176499803,"GB2-08":73.56972504703239},"medium":{"GB2-01":64.06188249918004,"GB2-02":54.816924555723126,"GB2-03":38.96081232957366,"GB2-04":40.70525197146744,"GB2-05":74.77879896587257,"GB2-06":28.792029225585107,"GB2-07":62.01522337286688,"GB2-08":55.34886455143598},"none":{"GB2-01":49.50144995000416,"GB2-02":41.91751033715405,"GB2-03":37.67489749432954,"GB2-04":41.59363502994095,"GB2-05":50.88406124660001,"GB2-07":38.77814653637098,"GB2-08":36.419139046362616}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":61.24278222850745,"medium":52.43497343396311,"none":37.09610495509529},"reasoning_agg":{"highest":{"max":87.73324176499803,"mean":61.24278222850745,"min":0.0},"medium":{"max":74.77879896587257,"mean":52.43497343396311,"min":28.792029225585107},"none":{"max":50.88406124660001,"mean":37.09610495509529,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":24.14667727341216}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:61da32d02ed7ac9c","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.957684},"historical-provider-setting-intensive":{"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":4.659586000000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.452750000000001},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":50.79155512763715,"highest":53.942167720847245,"medium":50.75042620114658,"none":47.6820714609176},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":1,"effective_max_output_tokens":[131072],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":30,"provider_post_attempts":30,"reasoning_token_observations":30,"reconciliation_get_attempt_observations":30,"reconciliation_get_attempts":142,"requested_max_output_token_observations":1,"requested_max_output_tokens":[131072],"total_output_tokens":994500,"total_reasoning_output_tokens":878493,"total_visible_output_tokens":116007,"visible_token_observations":30},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-02"],"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-02","GB2-06","GB2-08"],"infra_failures_excluded":3,"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04"],"performance_rejections":1}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":33.659442380532845,"score":33.659442380532845},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":45.580357392017014,"score":36.828601498624316},"GB2-03":{"attempts":3,"playable":51.22253262612484,"score":51.22253262612484},"GB2-04":{"attempts":3,"playable":48.97625195288786,"score":48.97625195288786},"GB2-05":{"attempts":3,"playable":68.26309391221632,"score":68.26309391221632},"GB2-06":{"attempts":3,"playable":40.496154386203656,"score":40.496154386203656},"GB2-07":{"attempts":3,"playable":63.35049037517937,"score":63.35049037517937},"GB2-08":{"attempts":3,"playable":54.784117995935276,"score":54.784117995935276}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":33.53796956050856,"score":33.53796956050856},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":52.51053536035614,"score":26.25526768017807},"GB2-03":{"attempts":1,"playable":58.27824618237586,"score":58.27824618237586},"GB2-04":{"attempts":1,"playable":66.43562487993297,"score":66.43562487993297},"GB2-05":{"attempts":1,"playable":46.83255542229182,"score":46.83255542229182},"GB2-06":{"attempts":1,"playable":51.610121002194575,"score":51.610121002194575},"GB2-07":{"attempts":1,"playable":78.54488189299026,"score":78.54488189299026},"GB2-08":{"attempts":1,"playable":43.787407466127824,"score":43.787407466127824}},"medium":{"GB2-01":{"attempts":1,"playable":42.3384356613993,"score":42.3384356613993},"GB2-02":{"attempts":1,"playable":43.27055023201369,"score":43.27055023201369},"GB2-03":{"attempts":1,"playable":56.99883279763065,"score":56.99883279763065},"GB2-04":{"attempts":1,"playable":38.23158350721224,"score":38.23158350721224},"GB2-05":{"attempts":1,"playable":67.24351136827728,"score":67.24351136827728},"GB2-06":{"attempts":1,"playable":50.734188944797765,"score":50.734188944797765},"GB2-07":{"attempts":1,"playable":39.54400996340699,"score":39.54400996340699},"GB2-08":{"attempts":1,"playable":67.64229713443474,"score":67.64229713443474}},"none":{"GB2-01":{"attempts":1,"playable":25.101921919690685,"score":25.101921919690685},"GB2-02":{"attempts":1,"playable":40.95998658368119,"score":40.95998658368119},"GB2-03":{"attempts":1,"playable":38.390518898368,"score":38.390518898368},"GB2-04":{"attempts":1,"playable":42.26154747151835,"score":42.26154747151835},"GB2-05":{"attempts":1,"playable":90.71321494607983,"score":90.71321494607983},"GB2-06":{"attempts":1,"playable":19.144153211618626,"score":19.144153211618626},"GB2-07":{"attempts":1,"playable":71.96257926914086,"score":71.96257926914086},"GB2-08":{"attempts":1,"playable":52.92264938724327,"score":52.92264938724327}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-14T17:24:33Z","match_totals_all":{"draws":4429,"losses":5585,"wins":5502},"match_totals_tracks":{"highest":{"draws":1335,"losses":1842,"wins":2065},"medium":{"draws":1488,"losses":1897,"wins":1805},"none":{"draws":1606,"losses":1846,"wins":1632}},"model_slug":"qwen-qwen3-8-max","overall":{"max":90.71321494607983,"mean":49.69758564096306,"min":19.144153211618626},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.53796956050856,"GB2-02":52.51053536035614,"GB2-03":58.27824618237586,"GB2-04":66.43562487993297,"GB2-05":46.83255542229182,"GB2-06":51.610121002194575,"GB2-07":78.54488189299026,"GB2-08":43.787407466127824},"per_game_all":{"GB2-01":33.659442380532845,"GB2-02":45.580357392017014,"GB2-03":51.22253262612484,"GB2-04":48.97625195288786,"GB2-05":68.26309391221632,"GB2-06":40.496154386203656,"GB2-07":63.35049037517937,"GB2-08":54.784117995935276},"per_game_match_totals_all":{"GB2-01":{"draws":511,"losses":1020,"wins":403},"GB2-02":{"draws":1388,"losses":291,"wins":107},"GB2-03":{"draws":452,"losses":759,"wins":669},"GB2-04":{"draws":1077,"losses":394,"wins":348},"GB2-05":{"draws":0,"losses":673,"wins":1348},"GB2-06":{"draws":160,"losses":1134,"wins":735},"GB2-07":{"draws":0,"losses":727,"wins":1192},"GB2-08":{"draws":841,"losses":587,"wins":700}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":123,"losses":345,"wins":148},"GB2-02":{"draws":438,"losses":73,"wins":84},"GB2-03":{"draws":56,"losses":266,"wins":305},"GB2-04":{"draws":252,"losses":91,"wins":262},"GB2-05":{"draws":0,"losses":381,"wins":337},"GB2-06":{"draws":66,"losses":320,"wins":315},"GB2-07":{"draws":0,"losses":149,"wins":493},"GB2-08":{"draws":400,"losses":217,"wins":121}},"medium":{"GB2-01":{"draws":236,"losses":286,"wins":168},"GB2-02":{"draws":500,"losses":105,"wins":7},"GB2-03":{"draws":153,"losses":224,"wins":247},"GB2-04":{"draws":416,"losses":162,"wins":28},"GB2-05":{"draws":0,"losses":234,"wins":420},"GB2-06":{"draws":56,"losses":334,"wins":318},"GB2-07":{"draws":0,"losses":375,"wins":259},"GB2-08":{"draws":127,"losses":177,"wins":358}},"none":{"GB2-01":{"draws":152,"losses":389,"wins":87},"GB2-02":{"draws":450,"losses":113,"wins":16},"GB2-03":{"draws":243,"losses":269,"wins":117},"GB2-04":{"draws":409,"losses":141,"wins":58},"GB2-05":{"draws":0,"losses":58,"wins":591},"GB2-06":{"draws":38,"losses":480,"wins":102},"GB2-07":{"draws":0,"losses":203,"wins":440},"GB2-08":{"draws":314,"losses":193,"wins":221}}},"per_game_raw_elo_all":{"GB2-01":1319.4161802745207,"GB2-02":1441.7832900558305,"GB2-03":1451.0945018621744,"GB2-04":1472.615161313409,"GB2-05":1805.9523842274439,"GB2-06":1304.6445325964658,"GB2-07":1645.844849849731,"GB2-08":1489.6789598704463},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1321.2165783034275,"GB2-02":1495.335993573763,"GB2-03":1513.6271149762285,"GB2-04":1613.2292042506592,"GB2-05":1412.053671887915,"GB2-06":1477.0510718543649,"GB2-07":1867.4576733245074,"GB2-08":1359.8522268305376},"medium":{"GB2-01":1408.8605312527436,"GB2-02":1423.9801401585992,"GB2-03":1501.685215624939,"GB2-04":1386.4507012347328,"GB2-05":1685.4575077768586,"GB2-06":1463.1275057621085,"GB2-07":1318.7054794993578,"GB2-08":1651.5887740394287},"none":{"GB2-01":1228.1714312673907,"GB2-02":1406.0337364351292,"GB2-03":1337.971174985356,"GB2-04":1418.1655784548357,"GB2-05":2320.345973017558,"GB2-06":973.7550201729238,"GB2-07":1751.3713967253284,"GB2-08":1457.5958787413726}},"per_game_tracks":{"highest":{"GB2-01":33.53796956050856,"GB2-02":52.51053536035614,"GB2-03":58.27824618237586,"GB2-04":66.43562487993297,"GB2-05":46.83255542229182,"GB2-06":51.610121002194575,"GB2-07":78.54488189299026,"GB2-08":43.787407466127824},"medium":{"GB2-01":42.3384356613993,"GB2-02":43.27055023201369,"GB2-03":56.99883279763065,"GB2-04":38.23158350721224,"GB2-05":67.24351136827728,"GB2-06":50.734188944797765,"GB2-07":39.54400996340699,"GB2-08":67.64229713443474},"none":{"GB2-01":25.101921919690685,"GB2-02":40.95998658368119,"GB2-03":38.390518898368,"GB2-04":42.26154747151835,"GB2-05":90.71321494607983,"GB2-06":19.144153211618626,"GB2-07":71.96257926914086,"GB2-08":52.92264938724327}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.66025926082499,"medium":50.75042620114658,"none":47.6820714609176},"reasoning_agg":{"highest":{"max":78.54488189299026,"mean":50.66025926082499,"min":26.25526768017807},"medium":{"max":67.64229713443474,"mean":50.75042620114658,"min":38.23158350721224},"none":{"max":90.71321494607983,"mean":47.6820714609176,"min":19.144153211618626}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":3.0683547402289832}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:4805358587e278d4","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":0.030688900000000005},"none":{"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":0.025451050000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.09391989999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.00625249375,"median":0.0043227375,"min":0.00169605,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":16,"boardgame-list-prices-2026-10-09":11},"run_count":24,"token_priced_attempt_count":27,"total":0.15005985000000002},"codegen_latency_ms":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":86701,"mean_ms":33803.25,"min_ms":21457,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":26534,"output_mean":10296.416666666666,"output_min":1575,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":26534,"output_mean":21543.25,"output_min":15583,"run_count":8},"medium":{"attempt_count":8,"output_max":6895,"output_mean":5735.5,"output_min":3866,"run_count":8},"none":{"attempt_count":11,"output_max":9509,"output_mean":3610.5,"output_min":1575,"run_count":8}},"display_name":"GPT-6 Luna","economics":{"all":48.80589386127944,"highest":57.555171667621714,"medium":44.1127319990593,"none":44.749777917157324},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"requested_max_output_token_observations":27,"requested_max_output_tokens":[65536,128000],"total_output_tokens":247114,"total_reasoning_output_tokens":163396,"total_visible_output_tokens":83718,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":38.722540951557725,"score":38.722540951557725},"GB2-02":{"attempts":3,"playable":50.51342414736848,"score":50.51342414736848},"GB2-03":{"attempts":3,"playable":48.66366056877991,"score":48.66366056877991},"GB2-04":{"attempts":3,"playable":53.06427280031872,"score":53.06427280031872},"GB2-05":{"attempts":3,"playable":47.02355622467987,"score":47.02355622467987},"GB2-06":{"attempts":3,"playable":64.13065498002176,"score":64.13065498002176},"GB2-07":{"attempts":3,"playable":41.789229811122944,"score":41.789229811122944},"GB2-08":{"attempts":3,"playable":46.53981140638615,"score":46.53981140638615}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.97348042191489,"score":29.97348042191489},"GB2-02":{"attempts":1,"playable":62.984388882988455,"score":62.984388882988455},"GB2-03":{"attempts":1,"playable":49.12012603987877,"score":49.12012603987877},"GB2-04":{"attempts":1,"playable":63.72930595327424,"score":63.72930595327424},"GB2-05":{"attempts":1,"playable":54.82982909315959,"score":54.82982909315959},"GB2-06":{"attempts":1,"playable":86.2733376490575,"score":86.2733376490575},"GB2-07":{"attempts":1,"playable":38.64092666347467,"score":38.64092666347467},"GB2-08":{"attempts":1,"playable":74.88997863722562,"score":74.88997863722562}},"medium":{"GB2-01":{"attempts":1,"playable":38.42050375820871,"score":38.42050375820871},"GB2-02":{"attempts":1,"playable":44.568601588963034,"score":44.568601588963034},"GB2-03":{"attempts":1,"playable":51.027162349442264,"score":51.027162349442264},"GB2-04":{"attempts":1,"playable":51.15438452546272,"score":51.15438452546272},"GB2-05":{"attempts":1,"playable":50.640550380919166,"score":50.640550380919166},"GB2-06":{"attempts":1,"playable":33.97485293483092,"score":33.97485293483092},"GB2-07":{"attempts":1,"playable":53.53391363189049,"score":53.53391363189049},"GB2-08":{"attempts":1,"playable":29.5818868227571,"score":29.5818868227571}},"none":{"GB2-01":{"attempts":1,"playable":47.773638674549574,"score":47.773638674549574},"GB2-02":{"attempts":1,"playable":43.98728197015397,"score":43.98728197015397},"GB2-03":{"attempts":1,"playable":45.843693317018705,"score":45.843693317018705},"GB2-04":{"attempts":1,"playable":44.3091279222192,"score":44.3091279222192},"GB2-05":{"attempts":1,"playable":35.60028919996085,"score":35.60028919996085},"GB2-06":{"attempts":1,"playable":72.14377435617686,"score":72.14377435617686},"GB2-07":{"attempts":1,"playable":33.19284913800368,"score":33.19284913800368},"GB2-08":{"attempts":1,"playable":35.147568759175726,"score":35.147568759175726}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-10-13T22:57:22Z","match_totals_all":{"draws":2957,"losses":4361,"wins":3764},"match_totals_tracks":{"highest":{"draws":547,"losses":1344,"wins":1803},"medium":{"draws":1180,"losses":1534,"wins":980},"none":{"draws":1230,"losses":1483,"wins":981}},"model_slug":"gpt-6-luna","overall":{"max":86.2733376490575,"mean":48.80589386127945,"min":29.5818868227571},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.97348042191489,"GB2-02":62.984388882988455,"GB2-03":49.12012603987877,"GB2-04":63.72930595327424,"GB2-05":54.82982909315959,"GB2-06":86.2733376490575,"GB2-07":38.64092666347467,"GB2-08":74.88997863722562},"per_game_all":{"GB2-01":38.722540951557725,"GB2-02":50.51342414736848,"GB2-03":48.66366056877991,"GB2-04":53.06427280031872,"GB2-05":47.02355622467987,"GB2-06":64.13065498002176,"GB2-07":41.789229811122944,"GB2-08":46.53981140638615},"per_game_match_totals_all":{"GB2-01":{"draws":433,"losses":658,"wins":313},"GB2-02":{"draws":967,"losses":174,"wins":155},"GB2-03":{"draws":194,"losses":635,"wins":509},"GB2-04":{"draws":771,"losses":262,"wins":311},"GB2-05":{"draws":0,"losses":772,"wins":680},"GB2-06":{"draws":70,"losses":468,"wins":830},"GB2-07":{"draws":0,"losses":859,"wins":563},"GB2-08":{"draws":522,"losses":533,"wins":403}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":332,"wins":135},"GB2-02":{"draws":252,"losses":39,"wins":141},"GB2-03":{"draws":22,"losses":231,"wins":193},"GB2-04":{"draws":212,"losses":62,"wins":174},"GB2-05":{"draws":0,"losses":220,"wins":264},"GB2-06":{"draws":25,"losses":49,"wins":382},"GB2-07":{"draws":0,"losses":302,"wins":172},"GB2-08":{"draws":35,"losses":109,"wins":342}},"medium":{"GB2-01":{"draws":176,"losses":205,"wins":87},"GB2-02":{"draws":360,"losses":65,"wins":7},"GB2-03":{"draws":89,"losses":189,"wins":168},"GB2-04":{"draws":267,"losses":91,"wins":90},"GB2-05":{"draws":0,"losses":240,"wins":244},"GB2-06":{"draws":24,"losses":300,"wins":132},"GB2-07":{"draws":0,"losses":229,"wins":245},"GB2-08":{"draws":264,"losses":215,"wins":7}},"none":{"GB2-01":{"draws":256,"losses":121,"wins":91},"GB2-02":{"draws":355,"losses":70,"wins":7},"GB2-03":{"draws":83,"losses":215,"wins":148},"GB2-04":{"draws":292,"losses":109,"wins":47},"GB2-05":{"draws":0,"losses":312,"wins":172},"GB2-06":{"draws":21,"losses":119,"wins":316},"GB2-07":{"draws":0,"losses":328,"wins":146},"GB2-08":{"draws":223,"losses":209,"wins":54}}},"per_game_raw_elo_all":{"GB2-01":1371.6864495149503,"GB2-02":1481.3478413411906,"GB2-03":1427.2302846433693,"GB2-04":1503.4294687730337,"GB2-05":1412.744216143987,"GB2-06":1718.6293830837033,"GB2-07":1346.0922682792584,"GB2-08":1421.3314506895692},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1283.440239948365,"GB2-02":1580.5221896610728,"GB2-03":1431.141203619718,"GB2-04":1589.228418313535,"GB2-05":1512.8290021702014,"GB2-06":2118.6188721253343,"GB2-07":1307.2840442981274,"GB2-08":1775.7535604062366},"medium":{"GB2-01":1370.5588281934845,"GB2-02":1434.003096842616,"GB2-03":1447.8633403332954,"GB2-04":1487.0003106802296,"GB2-05":1459.821971965261,"GB2-06":1204.927465489343,"GB2-07":1494.0790837461213,"GB2-08":1215.5822364858143},"none":{"GB2-01":1461.0602804030016,"GB2-02":1429.5182375198826,"GB2-03":1402.6863099770949,"GB2-04":1434.059677325336,"GB2-05":1265.5816742964987,"GB2-06":1832.3418116364328,"GB2-07":1236.9136767935265,"GB2-08":1272.6585551766566}},"per_game_tracks":{"highest":{"GB2-01":29.97348042191489,"GB2-02":62.984388882988455,"GB2-03":49.12012603987877,"GB2-04":63.72930595327424,"GB2-05":54.82982909315959,"GB2-06":86.2733376490575,"GB2-07":38.64092666347467,"GB2-08":74.88997863722562},"medium":{"GB2-01":38.42050375820871,"GB2-02":44.568601588963034,"GB2-03":51.027162349442264,"GB2-04":51.15438452546272,"GB2-05":50.640550380919166,"GB2-06":33.97485293483092,"GB2-07":53.53391363189049,"GB2-08":29.5818868227571},"none":{"GB2-01":47.773638674549574,"GB2-02":43.98728197015397,"GB2-03":45.843693317018705,"GB2-04":44.3091279222192,"GB2-05":35.60028919996085,"GB2-06":72.14377435617686,"GB2-07":33.19284913800368,"GB2-08":35.147568759175726}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.555171667621714,"medium":44.1127319990593,"none":44.749777917157324},"reasoning_agg":{"highest":{"max":86.2733376490575,"mean":57.555171667621714,"min":29.97348042191489},"medium":{"max":53.53391363189049,"mean":44.1127319990593,"min":29.5818868227571},"none":{"max":72.14377435617686,"mean":44.749777917157324,"min":33.19284913800368}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.442439668562415}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:f253398d34d2d321","codegen_cost_by_reasoning":{"highest":{"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":3.7157459999999998},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":2.3233296},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":3.7157459999999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.6877614000000001,"mean":0.27696257500000004,"median":0.2537256,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":6.6471018000000015},"codegen_latency_ms":{"attempt_count":35,"max_ms":754602,"mean_ms":294629.0833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":415982,"mean_ms":310768.0,"min_ms":108461,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":41670,"output_mean":16512.916666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":41670,"output_mean":28939.0,"output_min":14510,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":50.863311369990775,"highest":51.419779598529274,"medium":49.234927844804346,"none":51.99834362001389},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[262144],"finish_reason_observations":35,"finish_reasons":["length","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":10,"provider_post_attempts":13,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[262144],"total_output_tokens":396310,"total_reasoning_output_tokens":285325,"total_visible_output_tokens":110985,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":42.28990454892878,"score":42.28990454892878},"GB2-02":{"attempts":3,"playable":42.497415862731295,"score":42.497415862731295},"GB2-03":{"attempts":3,"playable":65.18884332851977,"score":65.18884332851977},"GB2-04":{"attempts":3,"playable":49.58394194850135,"score":49.58394194850135},"GB2-05":{"attempts":3,"playable":57.088232791959435,"score":57.088232791959435},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":50.83754506922229,"score":33.891696712814856},"GB2-07":{"attempts":3,"playable":48.4545237048454,"score":48.4545237048454},"GB2-08":{"attempts":3,"playable":50.94031740444942,"score":50.94031740444942}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.4049337234467,"score":6.4049337234467},"GB2-02":{"attempts":1,"playable":43.28928995530674,"score":43.28928995530674},"GB2-03":{"attempts":1,"playable":77.22914318556288,"score":77.22914318556288},"GB2-04":{"attempts":1,"playable":53.390749404314974,"score":53.390749404314974},"GB2-05":{"attempts":1,"playable":62.36468567876645,"score":62.36468567876645},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.56219612434326,"score":93.56219612434326},"GB2-08":{"attempts":1,"playable":23.697459117963955,"score":23.697459117963955}},"medium":{"GB2-01":{"attempts":1,"playable":68.6720885199358,"score":68.6720885199358},"GB2-02":{"attempts":1,"playable":41.2024267612772,"score":41.2024267612772},"GB2-03":{"attempts":1,"playable":66.69550770316529,"score":66.69550770316529},"GB2-04":{"attempts":1,"playable":48.79910125771219,"score":48.79910125771219},"GB2-05":{"attempts":1,"playable":52.48608296003704,"score":52.48608296003704},"GB2-06":{"attempts":1,"playable":54.38573883005792,"score":54.38573883005792},"GB2-07":{"attempts":1,"playable":25.08982639099122,"score":25.08982639099122},"GB2-08":{"attempts":1,"playable":36.54865033525812,"score":36.54865033525812}},"none":{"GB2-01":{"attempts":1,"playable":51.79269140340386,"score":51.79269140340386},"GB2-02":{"attempts":1,"playable":43.00053087160994,"score":43.00053087160994},"GB2-03":{"attempts":1,"playable":51.64187909683113,"score":51.64187909683113},"GB2-04":{"attempts":1,"playable":46.56197518347687,"score":46.56197518347687},"GB2-05":{"attempts":1,"playable":56.41392973707483,"score":56.41392973707483},"GB2-06":{"attempts":1,"playable":47.28935130838665,"score":47.28935130838665},"GB2-07":{"attempts":1,"playable":26.711548599201713,"score":26.711548599201713},"GB2-08":{"attempts":1,"playable":92.57484276012617,"score":92.57484276012617}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-10-15T06:55:39Z","match_totals_all":{"draws":4321,"losses":5728,"wins":5736},"match_totals_tracks":{"highest":{"draws":753,"losses":1228,"wins":1257},"medium":{"draws":1944,"losses":2239,"wins":2016},"none":{"draws":1624,"losses":2261,"wins":2463}},"model_slug":"moonshotai-kimi-k3","overall":{"max":93.56219612434326,"mean":48.74185953784379,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.4049337234467,"GB2-02":43.28928995530674,"GB2-03":77.22914318556288,"GB2-04":53.390749404314974,"GB2-05":62.36468567876645,"GB2-07":93.56219612434326,"GB2-08":23.697459117963955},"per_game_all":{"GB2-01":42.28990454892878,"GB2-02":42.497415862731295,"GB2-03":65.18884332851977,"GB2-04":49.58394194850135,"GB2-05":57.088232791959435,"GB2-07":48.4545237048454,"GB2-08":50.94031740444942},"per_game_match_totals_all":{"GB2-01":{"draws":602,"losses":829,"wins":618},"GB2-02":{"draws":1391,"losses":342,"wins":63},"GB2-03":{"draws":351,"losses":595,"wins":984},"GB2-04":{"draws":1113,"losses":474,"wins":410},"GB2-05":{"draws":0,"losses":959,"wins":1258},"GB2-06":{"draws":133,"losses":782,"wins":765},"GB2-07":{"draws":0,"losses":1139,"wins":853},"GB2-08":{"draws":731,"losses":608,"wins":785}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":437,"wins":23},"GB2-02":{"draws":307,"losses":97,"wins":28},"GB2-03":{"draws":31,"losses":96,"wins":319},"GB2-04":{"draws":227,"losses":101,"wins":120},"GB2-05":{"draws":0,"losses":184,"wins":300},"GB2-07":{"draws":0,"losses":28,"wins":446},"GB2-08":{"draws":180,"losses":285,"wins":21}},"medium":{"GB2-01":{"draws":131,"losses":197,"wins":404},"GB2-02":{"draws":519,"losses":123,"wins":18},"GB2-03":{"draws":148,"losses":189,"wins":373},"GB2-04":{"draws":529,"losses":137,"wins":113},"GB2-05":{"draws":0,"losses":403,"wins":459},"GB2-06":{"draws":66,"losses":364,"wins":414},"GB2-07":{"draws":0,"losses":560,"wins":192},"GB2-08":{"draws":551,"losses":266,"wins":43}},"none":{"GB2-01":{"draws":463,"losses":195,"wins":191},"GB2-02":{"draws":565,"losses":122,"wins":17},"GB2-03":{"draws":172,"losses":310,"wins":292},"GB2-04":{"draws":357,"losses":236,"wins":177},"GB2-05":{"draws":0,"losses":372,"wins":499},"GB2-06":{"draws":67,"losses":418,"wins":351},"GB2-07":{"draws":0,"losses":551,"wins":215},"GB2-08":{"draws":0,"losses":57,"wins":721}}},"per_game_raw_elo_all":{"GB2-01":1355.5467577745085,"GB2-02":1417.98032791728,"GB2-03":1593.6827348033455,"GB2-04":1474.895021311985,"GB2-05":1543.180848062418,"GB2-07":1543.997077546149,"GB2-08":1554.4349039719373},"per_game_raw_elo_tracks":{"highest":{"GB2-01":896.0136405602709,"GB2-02":1424.1250785301434,"GB2-03":1729.6725301946099,"GB2-04":1504.4720941766634,"GB2-05":1613.2603559606532,"GB2-07":2360.8414812321853,"GB2-08":1151.2006109625931},"medium":{"GB2-01":1671.0767841005784,"GB2-02":1407.925086803255,"GB2-03":1598.0854263987521,"GB2-04":1468.7446694179835,"GB2-05":1483.05141833077,"GB2-06":1521.6696497009984,"GB2-07":1123.6300728247743,"GB2-08":1286.7691406200859},"none":{"GB2-01":1499.549848662676,"GB2-02":1421.890818418441,"GB2-03":1453.2902478166745,"GB2-04":1451.468300341307,"GB2-05":1533.2307698958307,"GB2-06":1408.9638210643716,"GB2-07":1147.5196785814874,"GB2-08":2225.3349603331326}},"per_game_tracks":{"highest":{"GB2-01":6.4049337234467,"GB2-02":43.28928995530674,"GB2-03":77.22914318556288,"GB2-04":53.390749404314974,"GB2-05":62.36468567876645,"GB2-07":93.56219612434326,"GB2-08":23.697459117963955},"medium":{"GB2-01":68.6720885199358,"GB2-02":41.2024267612772,"GB2-03":66.69550770316529,"GB2-04":48.79910125771219,"GB2-05":52.48608296003704,"GB2-06":54.38573883005792,"GB2-07":25.08982639099122,"GB2-08":36.54865033525812},"none":{"GB2-01":51.79269140340386,"GB2-02":43.00053087160994,"GB2-03":51.64187909683113,"GB2-04":46.56197518347687,"GB2-05":56.41392973707483,"GB2-06":47.28935130838665,"GB2-07":26.711548599201713,"GB2-08":92.57484276012617}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.99230714871312,"medium":49.234927844804346,"none":51.99834362001389},"reasoning_agg":{"highest":{"max":93.56219612434326,"mean":44.99230714871312,"min":0.0},"medium":{"max":68.6720885199358,"mean":49.234927844804346,"min":25.08982639099122},"none":{"max":92.57484276012617,"mean":51.99834362001389,"min":26.711548599201713}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":7.006036471300774}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:b25498cf4a1e2d4f","codegen_cost_by_reasoning":{"highest":{"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":0.512955,"mean":0.43048093750000005,"median":0.4308725,"min":0.32672249999999997,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":9},"run_count":16,"token_priced_attempt_count":17,"total":6.887695000000001},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.266665,"mean":0.20888499999999996,"median":0.20905875000000002,"min":0.14104,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":8,"boardgame-list-prices-2026-10-09":8},"run_count":16,"token_priced_attempt_count":16,"total":3.3421600000000002},"none":{"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":0.9739299999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":1.4245200000000002},"historical-provider-setting-baseline":{"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":0.9739300000000001},"historical-provider-setting-intensive":{"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},"historical-thinking-budget-setting":{"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":4.09607}},"codegen_cost_usd":{"admitted_cell_count":39,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":41},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-10-09":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785000000002},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333333,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"all":49.86813333762436,"highest":49.73329834084729,"medium":52.18547373836192,"none":47.68562793366386},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":16,"requested_max_output_token_observations":16,"requested_max_output_tokens":[64000],"total_output_tokens":239955,"total_reasoning_output_tokens":171858,"total_visible_output_tokens":43839,"visible_token_observations":16},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-opus-4-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":46.22822002559676,"score":46.22822002559676},"GB2-02":{"attempts":5,"playable":43.79585610669529,"score":43.79585610669529},"GB2-03":{"attempts":4,"playable":47.260969030032975,"score":47.260969030032975},"GB2-04":{"attempts":5,"playable":43.86515973203431,"score":43.86515973203431},"GB2-05":{"attempts":5,"playable":47.120691130234626,"score":47.120691130234626},"GB2-06":{"attempts":5,"playable":47.27349533363127,"score":47.27349533363127},"GB2-07":{"attempts":5,"playable":45.925300455596805,"score":45.925300455596805},"GB2-08":{"attempts":5,"playable":67.24861808695641,"score":67.24861808695641}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":49.29503868226503,"score":49.29503868226503},"GB2-02":{"attempts":2,"playable":43.432140651016,"score":43.432140651016},"GB2-03":{"attempts":1,"playable":49.20225666121801,"score":49.20225666121801},"GB2-04":{"attempts":2,"playable":40.902415480879,"score":40.902415480879},"GB2-05":{"attempts":2,"playable":48.37888234660747,"score":48.37888234660747},"GB2-06":{"attempts":2,"playable":51.060915314144,"score":51.060915314144},"GB2-07":{"attempts":2,"playable":55.57211835350458,"score":55.57211835350458},"GB2-08":{"attempts":2,"playable":57.03368035407377,"score":57.03368035407377}},"medium":{"GB2-01":{"attempts":2,"playable":46.9567325101106,"score":46.9567325101106},"GB2-02":{"attempts":2,"playable":43.47852772193413,"score":43.47852772193413},"GB2-03":{"attempts":2,"playable":50.35602380276113,"score":50.35602380276113},"GB2-04":{"attempts":2,"playable":41.3192975716487,"score":41.3192975716487},"GB2-05":{"attempts":2,"playable":44.452057174865985,"score":44.452057174865985},"GB2-06":{"attempts":2,"playable":46.71785784375814,"score":46.71785784375814},"GB2-07":{"attempts":2,"playable":49.170284942639206,"score":49.170284942639206},"GB2-08":{"attempts":2,"playable":67.34167682159878,"score":67.34167682159878}},"none":{"GB2-01":{"attempts":1,"playable":42.43288888441468,"score":42.43288888441468},"GB2-02":{"attempts":1,"playable":44.47689994713574,"score":44.47689994713574},"GB2-03":{"attempts":1,"playable":42.22462662611978,"score":42.22462662611978},"GB2-04":{"attempts":1,"playable":49.373766143575246,"score":49.373766143575246},"GB2-05":{"attempts":1,"playable":48.53113386923041,"score":48.53113386923041},"GB2-06":{"attempts":1,"playable":44.041712842991664,"score":44.041712842991664},"GB2-07":{"attempts":1,"playable":33.03349807064664,"score":33.03349807064664},"GB2-08":{"attempts":1,"playable":77.37049708519667,"score":77.37049708519667}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-15T06:29:54Z","match_totals_all":{"draws":4672,"losses":6402,"wins":6154},"match_totals_tracks":{"highest":{"draws":1750,"losses":2419,"wins":2205},"medium":{"draws":1533,"losses":2240,"wins":2439},"none":{"draws":1389,"losses":1743,"wins":1510}},"model_slug":"claude-opus-4-5","overall":{"max":77.37049708519667,"mean":48.58978873759731,"min":33.03349807064664},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.81391631879376,"GB2-02":43.22967986642175,"GB2-03":49.20225666121801,"GB2-04":40.73267204170183,"GB2-05":51.84745951645585,"GB2-06":54.258861217884125,"GB2-07":49.2238317543594,"GB2-08":36.55770934994358},"per_game_all":{"GB2-01":58.37781171759315,"GB2-02":43.596721667069794,"GB2-03":46.75947602223565,"GB2-04":44.53819243814579,"GB2-05":48.95852323227951,"GB2-06":49.788540513447714,"GB2-07":42.50162987639269,"GB2-08":64.42417123383052},"per_game_match_totals_all":{"GB2-01":{"draws":612,"losses":610,"wins":931},"GB2-02":{"draws":1599,"losses":333,"wins":60},"GB2-03":{"draws":625,"losses":806,"wins":585},"GB2-04":{"draws":1198,"losses":485,"wins":238},"GB2-05":{"draws":0,"losses":1149,"wins":1165},"GB2-06":{"draws":150,"losses":1063,"wins":1047},"GB2-07":{"draws":0,"losses":1315,"wins":993},"GB2-08":{"draws":488,"losses":641,"wins":1135}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":99,"losses":181,"wins":453},"GB2-02":{"draws":573,"losses":116,"wins":15},"GB2-03":{"draws":149,"losses":319,"wins":280},"GB2-04":{"draws":435,"losses":252,"wins":96},"GB2-05":{"draws":0,"losses":420,"wins":454},"GB2-06":{"draws":64,"losses":362,"wins":408},"GB2-07":{"draws":0,"losses":431,"wins":411},"GB2-08":{"draws":430,"losses":338,"wins":88}},"medium":{"GB2-01":{"draws":224,"losses":242,"wins":368},"GB2-02":{"draws":578,"losses":121,"wins":19},"GB2-03":{"draws":255,"losses":274,"wins":197},"GB2-04":{"draws":407,"losses":121,"wins":48},"GB2-05":{"draws":0,"losses":434,"wins":418},"GB2-06":{"draws":61,"losses":391,"wins":398},"GB2-07":{"draws":0,"losses":477,"wins":381},"GB2-08":{"draws":8,"losses":180,"wins":610}},"none":{"GB2-01":{"draws":289,"losses":187,"wins":110},"GB2-02":{"draws":448,"losses":96,"wins":26},"GB2-03":{"draws":221,"losses":213,"wins":108},"GB2-04":{"draws":356,"losses":112,"wins":94},"GB2-05":{"draws":0,"losses":295,"wins":293},"GB2-06":{"draws":25,"losses":310,"wins":241},"GB2-07":{"draws":0,"losses":407,"wins":201},"GB2-08":{"draws":50,"losses":123,"wins":437}}},"per_game_raw_elo_all":{"GB2-01":1569.1447085615418,"GB2-02":1426.4978780832569,"GB2-03":1410.679570537125,"GB2-04":1435.7535549813567,"GB2-05":1438.7336147143126,"GB2-06":1448.8587348159754,"GB2-07":1354.8632600876674,"GB2-08":1658.3814999630868},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1718.961656205798,"GB2-02":1423.6640091281179,"GB2-03":1431.858309476602,"GB2-04":1406.2175726621315,"GB2-05":1474.9975443593587,"GB2-06":1519.6119367787912,"GB2-07":1439.7040681586018,"GB2-08":1286.860232316537},"medium":{"GB2-01":1578.6980108936762,"GB2-02":1422.533651473112,"GB2-03":1428.7978090165216,"GB2-04":1427.8535899024532,"GB2-05":1407.8340213621627,"GB2-06":1468.3786808079797,"GB2-07":1390.0807981266287,"GB2-08":1864.4222501458996},"none":{"GB2-01":1409.774458585151,"GB2-02":1433.2959736485407,"GB2-03":1371.3825931182519,"GB2-04":1473.189502379486,"GB2-05":1433.3692784214163,"GB2-06":1358.5855868611554,"GB2-07":1234.8049139777722,"GB2-08":1823.862017426824}},"per_game_tracks":{"highest":{"GB2-01":72.81391631879376,"GB2-02":43.22967986642175,"GB2-03":49.20225666121801,"GB2-04":40.73267204170183,"GB2-05":51.84745951645585,"GB2-06":54.258861217884125,"GB2-07":49.2238317543594,"GB2-08":36.55770934994358},"medium":{"GB2-01":59.88662994957098,"GB2-02":43.0835851876519,"GB2-03":48.85154477936919,"GB2-04":43.50813912916032,"GB2-05":46.49697631115229,"GB2-06":51.06504747946735,"GB2-07":45.24755980417205,"GB2-08":79.3443072663513},"none":{"GB2-01":42.43288888441468,"GB2-02":44.47689994713574,"GB2-03":42.22462662611978,"GB2-04":49.373766143575246,"GB2-05":48.53113386923041,"GB2-06":44.041712842991664,"GB2-07":33.03349807064664,"GB2-08":77.37049708519667}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.35968098046348,"medium":48.72405729866459,"none":47.68562793366386},"reasoning_agg":{"highest":{"max":57.03368035407377,"mean":49.35968098046348,"min":40.902415480879},"medium":{"max":67.34167682159878,"mean":48.72405729866459,"min":41.3192975716487},"none":{"max":77.37049708519667,"mean":47.68562793366386,"min":33.03349807064664}},"reasoning_labels":{"highest":"High effort + 32,000 thinking tokens","medium":"Medium effort + 16,000 thinking tokens","none":"Thinking field omitted"},"reasoning_settings":{"balanced":"medium","intensive":"high"},"score_diagnostics":{"reasoning_variance":1.6740530467996209}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:8583d72c67ca4ec4","codegen_cost_by_reasoning":{"highest":{"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":2.8079499999999995},"medium":{"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":0.52499},"none":{"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":0.49337000000000003}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.826309999999999},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":47.82154435903253,"highest":56.42105347252591,"medium":43.86738204675782,"none":43.176197557813836},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":322334,"total_reasoning_output_tokens":243107,"total_visible_output_tokens":79227,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":53.09809250789309,"score":53.09809250789309},"GB2-02":{"attempts":3,"playable":42.94175969974817,"score":42.94175969974817},"GB2-03":{"attempts":3,"playable":51.02936644959295,"score":51.02936644959295},"GB2-04":{"attempts":3,"playable":48.235649742601254,"score":48.235649742601254},"GB2-05":{"attempts":3,"playable":41.14841308619645,"score":41.14841308619645},"GB2-06":{"attempts":3,"playable":37.67141492670253,"score":37.67141492670253},"GB2-07":{"attempts":3,"playable":51.48971367636841,"score":51.48971367636841},"GB2-08":{"attempts":3,"playable":56.95794478315733,"score":56.95794478315733}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.01798231251271,"score":64.01798231251271},"GB2-02":{"attempts":1,"playable":41.90661616252166,"score":41.90661616252166},"GB2-03":{"attempts":1,"playable":57.10251894522522,"score":57.10251894522522},"GB2-04":{"attempts":1,"playable":55.5095186672599,"score":55.5095186672599},"GB2-05":{"attempts":1,"playable":55.84933586621808,"score":55.84933586621808},"GB2-06":{"attempts":1,"playable":28.056516418699708,"score":28.056516418699708},"GB2-07":{"attempts":1,"playable":67.75024237939125,"score":67.75024237939125},"GB2-08":{"attempts":1,"playable":81.1756970283788,"score":81.1756970283788}},"medium":{"GB2-01":{"attempts":1,"playable":46.77718549812911,"score":46.77718549812911},"GB2-02":{"attempts":1,"playable":44.206075222278635,"score":44.206075222278635},"GB2-03":{"attempts":1,"playable":41.83089485264183,"score":41.83089485264183},"GB2-04":{"attempts":1,"playable":45.67772315378228,"score":45.67772315378228},"GB2-05":{"attempts":1,"playable":43.89616971521909,"score":43.89616971521909},"GB2-06":{"attempts":1,"playable":38.04209942177484,"score":38.04209942177484},"GB2-07":{"attempts":1,"playable":50.67284847030405,"score":50.67284847030405},"GB2-08":{"attempts":1,"playable":39.83606003993275,"score":39.83606003993275}},"none":{"GB2-01":{"attempts":1,"playable":48.49910971303746,"score":48.49910971303746},"GB2-02":{"attempts":1,"playable":42.71258771444422,"score":42.71258771444422},"GB2-03":{"attempts":1,"playable":54.15468555091181,"score":54.15468555091181},"GB2-04":{"attempts":1,"playable":43.5197074067616,"score":43.5197074067616},"GB2-05":{"attempts":1,"playable":23.699733677152196,"score":23.699733677152196},"GB2-06":{"attempts":1,"playable":46.91562893963303,"score":46.91562893963303},"GB2-07":{"attempts":1,"playable":36.04605017940994,"score":36.04605017940994},"GB2-08":{"attempts":1,"playable":49.86207728116044,"score":49.86207728116044}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-10-13T22:53:55Z","match_totals_all":{"draws":4693,"losses":6904,"wins":5805},"match_totals_tracks":{"highest":{"draws":1178,"losses":1930,"wins":2478},"medium":{"draws":1830,"losses":2454,"wins":1652},"none":{"draws":1685,"losses":2520,"wins":1675}},"model_slug":"claude-sonnet-5","overall":{"max":81.1756970283788,"mean":47.82154435903252,"min":23.699733677152196},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.01798231251271,"GB2-02":41.90661616252166,"GB2-03":57.10251894522522,"GB2-04":55.5095186672599,"GB2-05":55.84933586621808,"GB2-06":28.056516418699708,"GB2-07":67.75024237939125,"GB2-08":81.1756970283788},"per_game_all":{"GB2-01":53.09809250789309,"GB2-02":42.94175969974817,"GB2-03":51.02936644959295,"GB2-04":48.235649742601254,"GB2-05":41.14841308619645,"GB2-06":37.67141492670253,"GB2-07":51.48971367636841,"GB2-08":56.95794478315733},"per_game_match_totals_all":{"GB2-01":{"draws":357,"losses":940,"wins":984},"GB2-02":{"draws":1636,"losses":322,"wins":36},"GB2-03":{"draws":606,"losses":836,"wins":736},"GB2-04":{"draws":1225,"losses":449,"wins":349},"GB2-05":{"draws":0,"losses":1313,"wins":925},"GB2-06":{"draws":102,"losses":1275,"wins":797},"GB2-07":{"draws":0,"losses":1125,"wins":1107},"GB2-08":{"draws":767,"losses":644,"wins":871}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":82,"losses":251,"wins":429},"GB2-02":{"draws":520,"losses":98,"wins":8},"GB2-03":{"draws":185,"losses":233,"wins":270},"GB2-04":{"draws":355,"losses":131,"wins":178},"GB2-05":{"draws":0,"losses":344,"wins":392},"GB2-06":{"draws":30,"losses":481,"wins":179},"GB2-07":{"draws":0,"losses":250,"wins":456},"GB2-08":{"draws":6,"losses":142,"wins":566}},"medium":{"GB2-01":{"draws":147,"losses":341,"wins":265},"GB2-02":{"draws":565,"losses":101,"wins":14},"GB2-03":{"draws":212,"losses":345,"wins":185},"GB2-04":{"draws":428,"losses":174,"wins":99},"GB2-05":{"draws":0,"losses":434,"wins":348},"GB2-06":{"draws":32,"losses":405,"wins":263},"GB2-07":{"draws":0,"losses":395,"wins":387},"GB2-08":{"draws":446,"losses":259,"wins":91}},"none":{"GB2-01":{"draws":128,"losses":348,"wins":290},"GB2-02":{"draws":551,"losses":123,"wins":14},"GB2-03":{"draws":209,"losses":258,"wins":281},"GB2-04":{"draws":442,"losses":144,"wins":72},"GB2-05":{"draws":0,"losses":535,"wins":185},"GB2-06":{"draws":40,"losses":389,"wins":355},"GB2-07":{"draws":0,"losses":480,"wins":264},"GB2-08":{"draws":315,"losses":243,"wins":214}}},"per_game_raw_elo_all":{"GB2-01":1513.4895448082996,"GB2-02":1421.4247562547973,"GB2-03":1448.7766310366412,"GB2-04":1464.600170302,"GB2-05":1328.350552259294,"GB2-06":1261.6120210208937,"GB2-07":1472.8846706899114,"GB2-08":1549.1737523745353},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1620.9423481036483,"GB2-02":1413.4065872577105,"GB2-03":1502.6464563175193,"GB2-04":1521.216525155471,"GB2-05":1525.928169070836,"GB2-06":1115.0093304205377,"GB2-07":1686.6334522299776,"GB2-08":1904.03779437462},"medium":{"GB2-01":1451.5277511920788,"GB2-02":1431.206864329595,"GB2-03":1367.9703981364971,"GB2-04":1444.6406722410088,"GB2-05":1374.95228014949,"GB2-06":1266.6898938292206,"GB2-07":1457.8857194196735,"GB2-08":1319.8045402906585},"none":{"GB2-01":1467.9985351291712,"GB2-02":1419.6608171770865,"GB2-03":1475.7130386559074,"GB2-04":1427.9433135095194,"GB2-05":1084.1712075575563,"GB2-06":1403.136838812923,"GB2-07":1274.1348404200835,"GB2-08":1423.6789224583274}},"per_game_tracks":{"highest":{"GB2-01":64.01798231251271,"GB2-02":41.90661616252166,"GB2-03":57.10251894522522,"GB2-04":55.5095186672599,"GB2-05":55.84933586621808,"GB2-06":28.056516418699708,"GB2-07":67.75024237939125,"GB2-08":81.1756970283788},"medium":{"GB2-01":46.77718549812911,"GB2-02":44.206075222278635,"GB2-03":41.83089485264183,"GB2-04":45.67772315378228,"GB2-05":43.89616971521909,"GB2-06":38.04209942177484,"GB2-07":50.67284847030405,"GB2-08":39.83606003993275},"none":{"GB2-01":48.49910971303746,"GB2-02":42.71258771444422,"GB2-03":54.15468555091181,"GB2-04":43.5197074067616,"GB2-05":23.699733677152196,"GB2-06":46.91562893963303,"GB2-07":36.04605017940994,"GB2-08":49.86207728116044}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.42105347252591,"medium":43.86738204675782,"none":43.176197557813836},"reasoning_agg":{"highest":{"max":81.1756970283788,"mean":56.42105347252591,"min":28.056516418699708},"medium":{"max":50.67284847030405,"mean":43.86738204675782,"min":38.04209942177484},"none":{"max":54.15468555091181,"mean":43.176197557813836,"min":23.699733677152196}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.244855914712076}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:3102bc1eaa5e56ef","codegen_cost_by_reasoning":{"highest":{"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":3.06723375},"medium":{"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":0.77569875},"none":{"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":0.6137425000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.7756987499999999},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675},"codegen_output_tokens":{"attempt_count":28,"output_max":28998,"output_mean":10500.666666666666,"output_min":2419,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":28998,"output_mean":23512.0,"output_min":18631,"run_count":8},"medium":{"attempt_count":9,"output_max":6917,"output_mean":4677.5,"output_min":3936,"run_count":8},"none":{"attempt_count":9,"output_max":6065,"output_mean":3312.5,"output_min":2419,"run_count":8}},"display_name":"GPT-5.6 Terra","economics":{"all":48.673504811681724,"highest":54.61404128888914,"medium":50.528282435041525,"none":41.94587294328041},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"total_output_tokens":252016,"total_reasoning_output_tokens":152800,"total_visible_output_tokens":99216,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-terra","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-05"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":68.72519341857831,"score":68.72519341857831},"GB2-02":{"attempts":3,"playable":49.83784549926915,"score":49.83784549926915},"GB2-03":{"attempts":3,"playable":35.11972143366492,"score":35.11972143366492},"GB2-04":{"attempts":3,"playable":43.86905321848045,"score":43.86905321848045},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.30804967454593,"score":37.538699783030616},"GB2-06":{"attempts":3,"playable":52.176214496822496,"score":52.176214496822496},"GB2-07":{"attempts":3,"playable":45.73823777396311,"score":45.73823777396311},"GB2-08":{"attempts":3,"playable":45.24826784099369,"score":45.24826784099369}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":72.6339261294873,"score":72.6339261294873},"GB2-02":{"attempts":1,"playable":58.84623066450606,"score":58.84623066450606},"GB2-03":{"attempts":1,"playable":38.6453008335583,"score":38.6453008335583},"GB2-04":{"attempts":1,"playable":42.854447842872176,"score":42.854447842872176},"GB2-05":{"attempts":1,"playable":55.710942462850255,"score":55.710942462850255},"GB2-06":{"attempts":1,"playable":80.05386022177917,"score":80.05386022177917},"GB2-07":{"attempts":1,"playable":44.333133552255525,"score":44.333133552255525},"GB2-08":{"attempts":1,"playable":43.83448860380437,"score":43.83448860380437}},"medium":{"GB2-01":{"attempts":1,"playable":78.365446654365,"score":78.365446654365},"GB2-02":{"attempts":1,"playable":46.13184987359883,"score":46.13184987359883},"GB2-03":{"attempts":1,"playable":32.81094203810552,"score":32.81094203810552},"GB2-04":{"attempts":1,"playable":42.936279993976434,"score":42.936279993976434},"GB2-05":{"attempts":1,"playable":56.90515688624159,"score":56.90515688624159},"GB2-06":{"attempts":1,"playable":38.96269920680077,"score":38.96269920680077},"GB2-07":{"attempts":1,"playable":62.29189008844291,"score":62.29189008844291},"GB2-08":{"attempts":1,"playable":45.821994738801145,"score":45.821994738801145}},"none":{"GB2-01":{"attempts":1,"playable":55.1762074718826,"score":55.1762074718826},"GB2-02":{"attempts":1,"playable":44.53545595970257,"score":44.53545595970257},"GB2-03":{"attempts":1,"playable":33.902921429330945,"score":33.902921429330945},"GB2-04":{"attempts":1,"playable":45.81643181859276,"score":45.81643181859276},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":37.51208406188754,"score":37.51208406188754},"GB2-07":{"attempts":1,"playable":30.5896896811909,"score":30.5896896811909},"GB2-08":{"attempts":1,"playable":46.08832018037556,"score":46.08832018037556}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-10-14T17:24:56Z","match_totals_all":{"draws":4548,"losses":5522,"wins":4834},"match_totals_tracks":{"highest":{"draws":1334,"losses":1766,"wins":2042},"medium":{"draws":1415,"losses":1983,"wins":1820},"none":{"draws":1799,"losses":1773,"wins":972}},"model_slug":"gpt-5-6-terra","overall":{"max":80.05386022177917,"mean":47.28165418310035,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.6339261294873,"GB2-02":58.84623066450606,"GB2-03":38.6453008335583,"GB2-04":42.854447842872176,"GB2-05":55.710942462850255,"GB2-06":80.05386022177917,"GB2-07":44.333133552255525,"GB2-08":43.83448860380437},"per_game_all":{"GB2-01":68.72519341857831,"GB2-02":49.83784549926915,"GB2-03":35.11972143366492,"GB2-04":43.86905321848045,"GB2-06":52.176214496822496,"GB2-07":45.73823777396311,"GB2-08":45.24826784099369},"per_game_match_totals_all":{"GB2-01":{"draws":314,"losses":506,"wins":1100},"GB2-02":{"draws":1340,"losses":274,"wins":208},"GB2-03":{"draws":759,"losses":825,"wins":250},"GB2-04":{"draws":1151,"losses":495,"wins":236},"GB2-05":{"draws":0,"losses":622,"wins":788},"GB2-06":{"draws":129,"losses":874,"wins":901},"GB2-07":{"draws":0,"losses":1176,"wins":876},"GB2-08":{"draws":855,"losses":750,"wins":475}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":90,"losses":148,"wins":380},"GB2-02":{"draws":321,"losses":86,"wins":163},"GB2-03":{"draws":218,"losses":275,"wins":121},"GB2-04":{"draws":404,"losses":131,"wins":57},"GB2-05":{"draws":0,"losses":318,"wins":402},"GB2-06":{"draws":53,"losses":110,"wins":439},"GB2-07":{"draws":0,"losses":418,"wins":306},"GB2-08":{"draws":248,"losses":280,"wins":174}},"medium":{"GB2-01":{"draws":5,"losses":154,"wins":461},"GB2-02":{"draws":497,"losses":96,"wins":35},"GB2-03":{"draws":287,"losses":271,"wins":54},"GB2-04":{"draws":335,"losses":218,"wins":109},"GB2-05":{"draws":0,"losses":304,"wins":386},"GB2-06":{"draws":74,"losses":394,"wins":218},"GB2-07":{"draws":0,"losses":270,"wins":374},"GB2-08":{"draws":217,"losses":276,"wins":183}},"none":{"GB2-01":{"draws":219,"losses":204,"wins":259},"GB2-02":{"draws":522,"losses":92,"wins":10},"GB2-03":{"draws":254,"losses":279,"wins":75},"GB2-04":{"draws":412,"losses":146,"wins":70},"GB2-06":{"draws":2,"losses":370,"wins":244},"GB2-07":{"draws":0,"losses":488,"wins":196},"GB2-08":{"draws":390,"losses":194,"wins":118}}},"per_game_raw_elo_all":{"GB2-01":1679.8269969511832,"GB2-02":1475.2054883290218,"GB2-03":1308.6845855267857,"GB2-04":1430.6349352978284,"GB2-06":1508.2489837922021,"GB2-07":1396.6252473683096,"GB2-08":1374.9222338870022},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1716.7999217511,"GB2-02":1545.825578352972,"GB2-03":1340.20811988067,"GB2-04":1422.7784591319285,"GB2-05":1524.1436771767653,"GB2-06":1985.4068376383943,"GB2-07":1378.68501943203,"GB2-08":1360.3342238632765},"medium":{"GB2-01":1790.445553170092,"GB2-02":1446.043365999252,"GB2-03":1287.9270514655218,"GB2-04":1423.4143673192932,"GB2-05":1539.6157898161953,"GB2-06":1280.7157615615854,"GB2-07":1609.2127143304222,"GB2-08":1380.8305986729517},"none":{"GB2-01":1532.2355159323579,"GB2-02":1433.7475206348413,"GB2-03":1297.9185852341652,"GB2-04":1445.7119794422633,"GB2-06":1258.6243521766264,"GB2-07":1201.978008342477,"GB2-08":1383.6018791247789}},"per_game_tracks":{"highest":{"GB2-01":72.6339261294873,"GB2-02":58.84623066450606,"GB2-03":38.6453008335583,"GB2-04":42.854447842872176,"GB2-05":55.710942462850255,"GB2-06":80.05386022177917,"GB2-07":44.333133552255525,"GB2-08":43.83448860380437},"medium":{"GB2-01":78.365446654365,"GB2-02":46.13184987359883,"GB2-03":32.81094203810552,"GB2-04":42.936279993976434,"GB2-05":56.90515688624159,"GB2-06":38.96269920680077,"GB2-07":62.29189008844291,"GB2-08":45.821994738801145},"none":{"GB2-01":55.1762074718826,"GB2-02":44.53545595970257,"GB2-03":33.902921429330945,"GB2-04":45.81643181859276,"GB2-06":37.51208406188754,"GB2-07":30.5896896811909,"GB2-08":46.08832018037556}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.61404128888914,"medium":50.528282435041525,"none":36.702638825370364},"reasoning_agg":{"highest":{"max":80.05386022177917,"mean":54.61404128888914,"min":38.6453008335583},"medium":{"max":78.365446654365,"mean":50.528282435041525,"min":32.81094203810552},"none":{"max":55.1762074718826,"mean":36.702638825370364,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.911402463518776}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:aa95c9efa1088490","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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":0.36704}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.6420659999999999},"historical-provider-setting-baseline":{"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":0.36704},"historical-provider-setting-intensive":{"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":2.5923719999999997}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.46894399999999997,"mean":0.15006158333333333,"median":0.080065,"min":0.035026,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"run_count":24,"token_priced_attempt_count":28,"total":3.6014779999999993},"codegen_latency_ms":{"attempt_count":28,"max_ms":255692,"mean_ms":76920.70833333333,"min_ms":12384,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":255692,"mean_ms":175619.75,"min_ms":52003,"run_count":8},"medium":{"attempt_count":8,"max_ms":58005,"mean_ms":37933.625,"min_ms":21700,"run_count":8},"none":{"attempt_count":9,"max_ms":20748,"mean_ms":17208.75,"min_ms":12384,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":36035,"output_mean":10826.541666666666,"output_min":1554,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":36035,"output_mean":24993.125,"output_min":6631,"run_count":8},"medium":{"attempt_count":8,"output_max":7812,"output_mean":5238.375,"output_min":2903,"run_count":8},"none":{"attempt_count":9,"output_max":3115,"output_mean":2248.125,"output_min":1554,"run_count":8}},"display_name":"Gemini 3.1 Pro Preview","economics":{"all":46.472520014804346,"highest":66.0844565897592,"medium":42.895053893013994,"none":30.438049561639847},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[65536],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"requested_max_output_token_observations":28,"requested_max_output_tokens":[65536],"total_output_tokens":259837,"total_reasoning_output_tokens":197903,"total_visible_output_tokens":61934,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-3.1-pro-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.24486218957529,"score":50.24486218957529},"GB2-02":{"attempts":3,"playable":43.48294887354232,"score":43.48294887354232},"GB2-03":{"attempts":3,"playable":54.28900423492525,"score":54.28900423492525},"GB2-04":{"attempts":3,"playable":56.681392213160734,"score":56.681392213160734},"GB2-05":{"attempts":3,"playable":39.46804653159105,"score":39.46804653159105},"GB2-06":{"attempts":3,"playable":20.932990864906042,"score":20.932990864906042},"GB2-07":{"attempts":3,"playable":56.479725085394904,"score":56.479725085394904},"GB2-08":{"attempts":3,"playable":50.201190125339174,"score":50.201190125339174}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.75345069479931,"score":74.75345069479931},"GB2-02":{"attempts":1,"playable":42.82371714689963,"score":42.82371714689963},"GB2-03":{"attempts":1,"playable":66.44351870301081,"score":66.44351870301081},"GB2-04":{"attempts":1,"playable":81.20346367106342,"score":81.20346367106342},"GB2-05":{"attempts":1,"playable":85.15635607540706,"score":85.15635607540706},"GB2-06":{"attempts":1,"playable":19.4264760779671,"score":19.4264760779671},"GB2-07":{"attempts":1,"playable":74.78132401480849,"score":74.78132401480849},"GB2-08":{"attempts":1,"playable":84.08734633411775,"score":84.08734633411775}},"medium":{"GB2-01":{"attempts":1,"playable":34.79173523551453,"score":34.79173523551453},"GB2-02":{"attempts":1,"playable":44.568601588963034,"score":44.568601588963034},"GB2-03":{"attempts":1,"playable":67.50881846286306,"score":67.50881846286306},"GB2-04":{"attempts":1,"playable":46.33265192192601,"score":46.33265192192601},"GB2-05":{"attempts":1,"playable":17.534074119250622,"score":17.534074119250622},"GB2-06":{"attempts":1,"playable":29.139305994368463,"score":29.139305994368463},"GB2-07":{"attempts":1,"playable":70.02713180027634,"score":70.02713180027634},"GB2-08":{"attempts":1,"playable":33.25811202094989,"score":33.25811202094989}},"none":{"GB2-01":{"attempts":1,"playable":41.18940063841202,"score":41.18940063841202},"GB2-02":{"attempts":1,"playable":43.0565278847643,"score":43.0565278847643},"GB2-03":{"attempts":1,"playable":28.91467553890189,"score":28.91467553890189},"GB2-04":{"attempts":1,"playable":42.50806104649276,"score":42.50806104649276},"GB2-05":{"attempts":1,"playable":15.713709400115475,"score":15.713709400115475},"GB2-06":{"attempts":1,"playable":14.233190522382563,"score":14.233190522382563},"GB2-07":{"attempts":1,"playable":24.630719441099906,"score":24.630719441099906},"GB2-08":{"attempts":1,"playable":33.25811202094989,"score":33.25811202094989}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-15T06:45:13Z","match_totals_all":{"draws":2763,"losses":4689,"wins":3630},"match_totals_tracks":{"highest":{"draws":485,"losses":1032,"wins":2177},"medium":{"draws":1134,"losses":1601,"wins":959},"none":{"draws":1144,"losses":2056,"wins":494}},"model_slug":"gemini-3-1-pro-preview","overall":{"max":85.15635607540706,"mean":46.47252001480435,"min":14.233190522382563},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.75345069479931,"GB2-02":42.82371714689963,"GB2-03":66.44351870301081,"GB2-04":81.20346367106342,"GB2-05":85.15635607540706,"GB2-06":19.4264760779671,"GB2-07":74.78132401480849,"GB2-08":84.08734633411775},"per_game_all":{"GB2-01":50.24486218957529,"GB2-02":43.48294887354232,"GB2-03":54.28900423492525,"GB2-04":56.681392213160734,"GB2-05":39.46804653159105,"GB2-06":20.932990864906042,"GB2-07":56.479725085394904,"GB2-08":50.201190125339174},"per_game_match_totals_all":{"GB2-01":{"draws":260,"losses":581,"wins":563},"GB2-02":{"draws":1048,"losses":225,"wins":23},"GB2-03":{"draws":251,"losses":525,"wins":562},"GB2-04":{"draws":624,"losses":285,"wins":435},"GB2-05":{"draws":0,"losses":882,"wins":570},"GB2-06":{"draws":25,"losses":1094,"wins":249},"GB2-07":{"draws":0,"losses":636,"wins":786},"GB2-08":{"draws":555,"losses":461,"wins":442}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":20,"losses":111,"wins":337},"GB2-02":{"draws":343,"losses":81,"wins":8},"GB2-03":{"draws":28,"losses":149,"wins":269},"GB2-04":{"draws":90,"losses":43,"wins":315},"GB2-05":{"draws":0,"losses":73,"wins":411},"GB2-06":{"draws":3,"losses":374,"wins":79},"GB2-07":{"draws":0,"losses":122,"wins":352},"GB2-08":{"draws":1,"losses":79,"wins":406}},"medium":{"GB2-01":{"draws":162,"losses":229,"wins":77},"GB2-02":{"draws":348,"losses":71,"wins":13},"GB2-03":{"draws":78,"losses":119,"wins":249},"GB2-04":{"draws":250,"losses":121,"wins":77},"GB2-05":{"draws":0,"losses":400,"wins":84},"GB2-06":{"draws":19,"losses":324,"wins":113},"GB2-07":{"draws":0,"losses":146,"wins":328},"GB2-08":{"draws":277,"losses":191,"wins":18}},"none":{"GB2-01":{"draws":78,"losses":241,"wins":149},"GB2-02":{"draws":357,"losses":73,"wins":2},"GB2-03":{"draws":145,"losses":257,"wins":44},"GB2-04":{"draws":284,"losses":121,"wins":43},"GB2-05":{"draws":0,"losses":409,"wins":75},"GB2-06":{"draws":3,"losses":396,"wins":57},"GB2-07":{"draws":0,"losses":368,"wins":106},"GB2-08":{"draws":277,"losses":191,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1491.5441485990902,"GB2-02":1425.6163560481818,"GB2-03":1484.4912536194927,"GB2-04":1547.812021377377,"GB2-05":1333.2626948939735,"GB2-06":998.5769665893937,"GB2-07":1545.3141389590146,"GB2-08":1492.8752519045959},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1742.8095883004505,"GB2-02":1420.521722454682,"GB2-03":1595.3650708650734,"GB2-04":1773.6533938860907,"GB2-05":2094.012078508322,"GB2-06":978.4895646716782,"GB2-07":1798.2681549311703,"GB2-08":1971.5922022669843},"medium":{"GB2-01":1334.1108723565362,"GB2-02":1434.003096842616,"GB2-03":1606.9677895025827,"GB2-04":1449.6979478659516,"GB2-05":971.4103005029103,"GB2-06":1131.532944619054,"GB2-07":1720.9515938589277,"GB2-08":1253.5167767234018},"none":{"GB2-01":1397.711985140284,"GB2-02":1422.3242488472476,"GB2-03":1251.1409004908223,"GB2-04":1420.084722380088,"GB2-05":934.3657056706884,"GB2-06":885.708390477449,"GB2-07":1116.722668086946,"GB2-08":1253.5167767234018}},"per_game_tracks":{"highest":{"GB2-01":74.75345069479931,"GB2-02":42.82371714689963,"GB2-03":66.44351870301081,"GB2-04":81.20346367106342,"GB2-05":85.15635607540706,"GB2-06":19.4264760779671,"GB2-07":74.78132401480849,"GB2-08":84.08734633411775},"medium":{"GB2-01":34.79173523551453,"GB2-02":44.568601588963034,"GB2-03":67.50881846286306,"GB2-04":46.33265192192601,"GB2-05":17.534074119250622,"GB2-06":29.139305994368463,"GB2-07":70.02713180027634,"GB2-08":33.25811202094989},"none":{"GB2-01":41.18940063841202,"GB2-02":43.0565278847643,"GB2-03":28.91467553890189,"GB2-04":42.50806104649276,"GB2-05":15.713709400115475,"GB2-06":14.233190522382563,"GB2-07":24.630719441099906,"GB2-08":33.25811202094989}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":66.0844565897592,"medium":42.895053893013994,"none":30.438049561639847},"reasoning_agg":{"highest":{"max":85.15635607540706,"mean":66.0844565897592,"min":19.4264760779671},"medium":{"max":70.02713180027634,"mean":42.895053893013994,"min":17.534074119250622},"none":{"max":43.0565278847643,"mean":30.438049561639847,"min":14.233190522382563}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":35.646407028119356}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:3f7b3092f4efde2e","codegen_cost_by_reasoning":{"highest":{"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":0.913572594249},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.9135725942490001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640004},"codegen_latency_ms":{"attempt_count":35,"max_ms":1560134,"mean_ms":432334.7916666667,"min_ms":52746,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1560134,"mean_ms":818090.375,"min_ms":426935,"run_count":8},"medium":{"attempt_count":12,"max_ms":673313,"mean_ms":392142.875,"min_ms":86869,"run_count":8},"none":{"attempt_count":12,"max_ms":170011,"mean_ms":86771.125,"min_ms":52746,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":74570,"output_mean":21422.416666666668,"output_min":2493,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":74570,"output_mean":43080.25,"output_min":21434,"run_count":8},"medium":{"attempt_count":12,"output_max":23131,"output_mean":16655.5,"output_min":5286,"run_count":8},"none":{"attempt_count":12,"output_max":8274,"output_mean":4531.5,"output_min":2493,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"all":47.494576263669536,"highest":49.647543391028975,"medium":54.05250316565751,"none":39.775718565336355},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":514138,"total_reasoning_output_tokens":410486,"total_visible_output_tokens":103652,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":39.37979588469351,"score":39.37979588469351},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.62158040794506,"score":28.41438693863004},"GB2-03":{"attempts":3,"playable":39.91058329601524,"score":39.91058329601524},"GB2-04":{"attempts":3,"playable":45.16660479888653,"score":45.16660479888653},"GB2-05":{"attempts":3,"playable":43.42310136855773,"score":43.42310136855773},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":64.05457514178416,"score":42.70305009452277},"GB2-07":{"attempts":3,"playable":67.21818264480606,"score":67.21818264480606},"GB2-08":{"attempts":3,"playable":49.869189589058145,"score":49.869189589058145}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":25.317999036314347,"score":25.317999036314347},"GB2-02":{"attempts":1,"playable":45.46191936603818,"score":45.46191936603818},"GB2-03":{"attempts":1,"playable":47.4802535926972,"score":47.4802535926972},"GB2-04":{"attempts":1,"playable":47.37007840089251,"score":47.37007840089251},"GB2-05":{"attempts":1,"playable":45.13148908259985,"score":45.13148908259985},"GB2-06":{"attempts":1,"playable":78.93405075167036,"score":78.93405075167036},"GB2-07":{"attempts":1,"playable":74.0121494304253,"score":74.0121494304253},"GB2-08":{"attempts":1,"playable":33.47240746759408,"score":33.47240746759408}},"medium":{"GB2-01":{"attempts":1,"playable":63.06659187715111,"score":63.06659187715111},"GB2-02":{"attempts":1,"playable":39.78124144985193,"score":39.78124144985193},"GB2-03":{"attempts":1,"playable":29.329813965176893,"score":29.329813965176893},"GB2-04":{"attempts":1,"playable":44.225346649633096,"score":44.225346649633096},"GB2-05":{"attempts":1,"playable":49.745253845654005,"score":49.745253845654005},"GB2-06":{"attempts":1,"playable":49.175099531897956,"score":49.175099531897956},"GB2-07":{"attempts":1,"playable":72.30106252568297,"score":72.30106252568297},"GB2-08":{"attempts":1,"playable":84.79561548021218,"score":84.79561548021218}},"none":{"GB2-01":{"attempts":1,"playable":29.754796740615063,"score":29.754796740615063},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.92168233017164,"score":42.92168233017164},"GB2-04":{"attempts":1,"playable":43.90438934613397,"score":43.90438934613397},"GB2-05":{"attempts":1,"playable":35.39256117741934,"score":35.39256117741934},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":55.341335978309914,"score":55.341335978309914},"GB2-08":{"attempts":1,"playable":31.33954581936816,"score":31.33954581936816}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-10-14T17:24:18Z","match_totals_all":{"draws":3821,"losses":5472,"wins":4875},"match_totals_tracks":{"highest":{"draws":1545,"losses":1907,"wins":1708},"medium":{"draws":1055,"losses":1923,"wins":2226},"none":{"draws":1221,"losses":1642,"wins":941}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":84.79561548021218,"mean":44.51061182689625,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":25.317999036314347,"GB2-02":45.46191936603818,"GB2-03":47.4802535926972,"GB2-04":47.37007840089251,"GB2-05":45.13148908259985,"GB2-06":78.93405075167036,"GB2-07":74.0121494304253,"GB2-08":33.47240746759408},"per_game_all":{"GB2-01":39.37979588469351,"GB2-03":39.91058329601524,"GB2-04":45.16660479888653,"GB2-05":43.42310136855773,"GB2-07":67.21818264480606,"GB2-08":49.869189589058145},"per_game_match_totals_all":{"GB2-01":{"draws":279,"losses":1006,"wins":629},"GB2-02":{"draws":903,"losses":236,"wins":49},"GB2-03":{"draws":628,"losses":865,"wins":431},"GB2-04":{"draws":1158,"losses":465,"wins":249},"GB2-05":{"draws":0,"losses":1137,"wins":921},"GB2-06":{"draws":49,"losses":486,"wins":773},"GB2-07":{"draws":0,"losses":706,"wins":1254},"GB2-08":{"draws":804,"losses":571,"wins":569}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":49,"losses":428,"wins":135},"GB2-02":{"draws":453,"losses":111,"wins":40},"GB2-03":{"draws":249,"losses":261,"wins":182},"GB2-04":{"draws":358,"losses":163,"wins":101},"GB2-05":{"draws":0,"losses":387,"wins":315},"GB2-06":{"draws":34,"losses":130,"wins":458},"GB2-07":{"draws":0,"losses":185,"wins":447},"GB2-08":{"draws":402,"losses":242,"wins":30}},"medium":{"GB2-01":{"draws":52,"losses":240,"wins":394},"GB2-02":{"draws":450,"losses":125,"wins":9},"GB2-03":{"draws":148,"losses":367,"wins":101},"GB2-04":{"draws":388,"losses":179,"wins":87},"GB2-05":{"draws":0,"losses":355,"wins":359},"GB2-06":{"draws":15,"losses":356,"wins":315},"GB2-07":{"draws":0,"losses":195,"wins":433},"GB2-08":{"draws":2,"losses":106,"wins":528}},"none":{"GB2-01":{"draws":178,"losses":338,"wins":100},"GB2-03":{"draws":231,"losses":237,"wins":148},"GB2-04":{"draws":412,"losses":123,"wins":61},"GB2-05":{"draws":0,"losses":395,"wins":247},"GB2-07":{"draws":0,"losses":326,"wins":374},"GB2-08":{"draws":400,"losses":223,"wins":11}}},"per_game_raw_elo_all":{"GB2-01":1374.284012626561,"GB2-03":1349.8150220145837,"GB2-04":1440.680938005901,"GB2-05":1367.3052788931184,"GB2-07":1686.3883544189905,"GB2-08":1492.8611259017616},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1230.7366179620453,"GB2-02":1440.886129849786,"GB2-03":1416.8679992505886,"GB2-04":1457.7064166079006,"GB2-05":1390.616518830716,"GB2-06":1963.0282125996341,"GB2-07":1785.1215337673148,"GB2-08":1255.6966458049349},"medium":{"GB2-01":1611.05572931117,"GB2-02":1396.803249161405,"GB2-03":1255.1595888182899,"GB2-04":1433.411096985039,"GB2-05":1448.5894256777617,"GB2-06":1438.5050461277926,"GB2-07":1756.8276982795844,"GB2-08":1989.0227302858464},"none":{"GB2-01":1281.0596906064675,"GB2-03":1377.4174779748728,"GB2-04":1430.9253004247632,"GB2-05":1262.7098921708773,"GB2-07":1517.2158312100726,"GB2-08":1233.8640016145036}},"per_game_tracks":{"highest":{"GB2-01":25.317999036314347,"GB2-02":45.46191936603818,"GB2-03":47.4802535926972,"GB2-04":47.37007840089251,"GB2-05":45.13148908259985,"GB2-06":78.93405075167036,"GB2-07":74.0121494304253,"GB2-08":33.47240746759408},"medium":{"GB2-01":63.06659187715111,"GB2-02":39.78124144985193,"GB2-03":29.329813965176893,"GB2-04":44.225346649633096,"GB2-05":49.745253845654005,"GB2-06":49.175099531897956,"GB2-07":72.30106252568297,"GB2-08":84.79561548021218},"none":{"GB2-01":29.754796740615063,"GB2-03":42.92168233017164,"GB2-04":43.90438934613397,"GB2-05":35.39256117741934,"GB2-07":55.341335978309914,"GB2-08":31.33954581936816}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.647543391028975,"medium":54.05250316565751,"none":29.831788924002264},"reasoning_agg":{"highest":{"max":78.93405075167036,"mean":49.647543391028975,"min":25.317999036314347},"medium":{"max":84.79561548021218,"mean":54.05250316565751,"min":29.329813965176893},"none":{"max":55.341335978309914,"mean":29.831788924002264,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.220714241655248}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:e81535a3e8cbf684","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666666,"recorded_attempt_count":37,"run_count":24,"total":0.5651094239}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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},"historical-provider-setting-balanced-variant-2":{"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},"historical-provider-setting-baseline-variant-1":{"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":0.3591713804},"historical-provider-setting-baseline-variant-2":{"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},"historical-provider-setting-intensive":{"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":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666666,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168000006},"codegen_latency_ms":{"attempt_count":32,"max_ms":882507,"mean_ms":240683.0,"min_ms":16088,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":882507,"mean_ms":333475.125,"min_ms":88401,"run_count":8},"medium":{"attempt_count":10,"max_ms":677392,"mean_ms":353638.875,"min_ms":112475,"run_count":8},"none":{"attempt_count":13,"max_ms":79329,"mean_ms":34935.0,"min_ms":16088,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":130069,"output_mean":34536.041666666664,"output_min":1442,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":130069,"output_mean":52728.5,"output_min":20107,"run_count":8},"medium":{"attempt_count":10,"output_max":83540,"output_mean":46751.875,"output_min":17329,"run_count":8},"none":{"attempt_count":13,"output_max":8574,"output_mean":4127.75,"output_min":1442,"run_count":8}},"display_name":"GLM-5.2","economics":{"all":43.86907114107802,"highest":43.66064658961648,"medium":48.08263613076984,"none":39.86393070284773},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":32,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"reconciliation_get_attempts":148,"total_output_tokens":828865,"total_reasoning_output_tokens":728689,"total_visible_output_tokens":100176,"visible_token_observations":32},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.2","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":16,"evaluated_cells":16,"first_pass_admitted":6,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":10,"repaired_rate":0.625},"baseline":{"admitted_plugins":24,"evaluated_cells":24,"first_pass_admitted":13,"first_pass_rate":0.5416666666666666,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":11,"repaired_rate":0.4583333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":40.94170526757969,"score":40.94170526757969},"GB2-02":{"attempts":6,"playable":50.37995399776117,"score":50.37995399776117},"GB2-03":{"attempts":6,"playable":36.17773217685343,"score":36.17773217685343},"GB2-04":{"attempts":6,"playable":48.090331104611266,"score":48.090331104611266},"GB2-05":{"attempts":6,"playable":48.63162054645711,"score":48.63162054645711},"GB2-06":{"attempts":6,"playable":55.823086553497234,"score":55.823086553497234},"GB2-07":{"attempts":6,"playable":39.416928613235505,"score":39.416928613235505},"GB2-08":{"attempts":6,"playable":35.80243338611205,"score":35.80243338611205}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":54.6978275536117,"score":54.6978275536117},"GB2-02":{"attempts":1,"playable":61.353382383562725,"score":61.353382383562725},"GB2-03":{"attempts":1,"playable":37.96649910095223,"score":37.96649910095223},"GB2-04":{"attempts":1,"playable":54.94896935877195,"score":54.94896935877195},"GB2-05":{"attempts":1,"playable":58.62413248603183,"score":58.62413248603183},"GB2-06":{"attempts":1,"playable":41.32404655250251,"score":41.32404655250251},"GB2-07":{"attempts":1,"playable":10.074602904287854,"score":10.074602904287854},"GB2-08":{"attempts":1,"playable":30.295712377211036,"score":30.295712377211036}},"medium":{"GB2-01":{"attempts":2,"playable":39.67497304532789,"score":39.67497304532789},"GB2-02":{"attempts":2,"playable":48.74398021474413,"score":48.74398021474413},"GB2-03":{"attempts":2,"playable":30.149317729619426,"score":30.149317729619426},"GB2-04":{"attempts":2,"playable":46.88857061810873,"score":46.88857061810873},"GB2-05":{"attempts":2,"playable":52.97347007024558,"score":52.97347007024558},"GB2-06":{"attempts":2,"playable":79.17714656231527,"score":79.17714656231527},"GB2-07":{"attempts":2,"playable":59.9772329403774,"score":59.9772329403774},"GB2-08":{"attempts":2,"playable":27.076397865420276,"score":27.076397865420276}},"none":{"GB2-01":{"attempts":3,"playable":28.452315203799483,"score":28.452315203799483},"GB2-02":{"attempts":3,"playable":41.042499394976666,"score":41.042499394976666},"GB2-03":{"attempts":3,"playable":40.417379699988665,"score":40.417379699988665},"GB2-04":{"attempts":3,"playable":42.433453336953114,"score":42.433453336953114},"GB2-05":{"attempts":3,"playable":34.297259083093905,"score":34.297259083093905},"GB2-06":{"attempts":3,"playable":46.96806654567393,"score":46.96806654567393},"GB2-07":{"attempts":3,"playable":48.198949995041254,"score":48.198949995041254},"GB2-08":{"attempts":3,"playable":50.03518991570485,"score":50.03518991570485}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-10-13T21:16:30Z","match_totals_all":{"draws":8862,"losses":11634,"wins":8090},"match_totals_tracks":{"highest":{"draws":1500,"losses":2122,"wins":1390},"medium":{"draws":3122,"losses":3400,"wins":2996},"none":{"draws":4240,"losses":6112,"wins":3704}},"model_slug":"z-ai-glm-5-2","overall":{"max":79.17714656231527,"mean":44.40797395576343,"min":10.074602904287854},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.6978275536117,"GB2-02":61.353382383562725,"GB2-03":37.96649910095223,"GB2-04":54.94896935877195,"GB2-05":58.62413248603183,"GB2-06":41.32404655250251,"GB2-07":10.074602904287854,"GB2-08":30.295712377211036},"per_game_all":{"GB2-01":41.12760202143473,"GB2-02":50.51178604526978,"GB2-03":35.82442631414753,"GB2-04":48.02149184679911,"GB2-05":47.377500421724,"GB2-06":54.480937523604375,"GB2-07":39.04478721852618,"GB2-08":34.56403773711844},"per_game_match_totals_all":{"GB2-01":{"draws":1000,"losses":1729,"wins":875},"GB2-02":{"draws":2483,"losses":538,"wins":313},"GB2-03":{"draws":1362,"losses":1507,"wins":503},"GB2-04":{"draws":1964,"losses":912,"wins":600},"GB2-05":{"draws":0,"losses":2059,"wins":1649},"GB2-06":{"draws":195,"losses":1417,"wins":1908},"GB2-07":{"draws":0,"losses":2103,"wins":1659},"GB2-08":{"draws":1858,"losses":1369,"wins":583}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":252,"losses":198,"wins":238},"GB2-02":{"draws":283,"losses":89,"wins":194},"GB2-03":{"draws":251,"losses":256,"wins":101},"GB2-04":{"draws":260,"losses":157,"wins":187},"GB2-05":{"draws":0,"losses":293,"wins":351},"GB2-06":{"draws":33,"losses":330,"wins":257},"GB2-07":{"draws":0,"losses":564,"wins":56},"GB2-08":{"draws":421,"losses":235,"wins":6}},"medium":{"GB2-01":{"draws":376,"losses":501,"wins":307},"GB2-02":{"draws":838,"losses":156,"wins":108},"GB2-03":{"draws":524,"losses":534,"wins":62},"GB2-04":{"draws":655,"losses":299,"wins":206},"GB2-05":{"draws":0,"losses":607,"wins":673},"GB2-06":{"draws":61,"losses":218,"wins":895},"GB2-07":{"draws":0,"losses":528,"wins":724},"GB2-08":{"draws":668,"losses":557,"wins":21}},"none":{"GB2-01":{"draws":372,"losses":1030,"wins":330},"GB2-02":{"draws":1362,"losses":293,"wins":11},"GB2-03":{"draws":587,"losses":717,"wins":340},"GB2-04":{"draws":1049,"losses":456,"wins":207},"GB2-05":{"draws":0,"losses":1159,"wins":625},"GB2-06":{"draws":101,"losses":869,"wins":756},"GB2-07":{"draws":0,"losses":1011,"wins":879},"GB2-08":{"draws":769,"losses":577,"wins":556}}},"per_game_raw_elo_all":{"GB2-01":1393.5667361696335,"GB2-02":1480.901024164407,"GB2-03":1314.2950270835825,"GB2-04":1462.8740019521786,"GB2-05":1407.3331545477038,"GB2-06":1548.1242670357642,"GB2-07":1276.4721627905867,"GB2-08":1279.914873523988},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1527.5878382373976,"GB2-02":1566.6336435377423,"GB2-03":1334.2413360530545,"GB2-04":1516.7647233191337,"GB2-05":1562.2227762045902,"GB2-06":1316.804818323151,"GB2-07":834.2389950487102,"GB2-08":1223.0445062625208},"medium":{"GB2-01":1382.1339329897673,"GB2-02":1466.3507660786474,"GB2-03":1262.4605013261448,"GB2-04":1453.9850621048731,"GB2-05":1489.2284734090945,"GB2-06":1976.1917897881967,"GB2-07":1580.9977350041481,"GB2-08":1187.7639187712728},"none":{"GB2-01":1270.9784372817353,"GB2-02":1409.7186628768313,"GB2-03":1346.1832438715483,"GB2-04":1417.8722204325295,"GB2-05":1170.5482140294257,"GB2-06":1351.376192995945,"GB2-07":1414.1797583189013,"GB2-08":1428.9361955381705}},"per_game_tracks":{"highest":{"GB2-01":54.6978275536117,"GB2-02":61.353382383562725,"GB2-03":37.96649910095223,"GB2-04":54.94896935877195,"GB2-05":58.62413248603183,"GB2-06":41.32404655250251,"GB2-07":10.074602904287854,"GB2-08":30.295712377211036},"medium":{"GB2-01":39.67497304532789,"GB2-02":48.74398021474413,"GB2-03":30.149317729619426,"GB2-04":46.88857061810873,"GB2-05":52.97347007024558,"GB2-06":79.17714656231527,"GB2-07":59.9772329403774,"GB2-08":27.076397865420276},"none":{"GB2-01":29.010005465364607,"GB2-02":41.437995537502474,"GB2-03":39.357462111870944,"GB2-04":42.22693556351663,"GB2-05":30.53489870889458,"GB2-06":42.94161945599534,"GB2-07":47.08252581091329,"GB2-08":46.320002968724005}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.66064658961648,"medium":48.08263613076984,"none":41.48063914690398},"reasoning_agg":{"highest":{"max":61.353382383562725,"mean":43.66064658961648,"min":10.074602904287854},"medium":{"max":79.17714656231527,"mean":48.08263613076984,"min":27.076397865420276},"none":{"max":50.03518991570485,"mean":41.48063914690398,"min":28.452315203799483}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.60199698386586}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:e630610a8ce59c4d","codegen_cost_by_reasoning":{"highest":{"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":1.1725616482799999},"medium":{"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":0.9884523218400001},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.37737643796},"codegen_latency_ms":{"attempt_count":31,"max_ms":1461124,"mean_ms":482100.7083333333,"min_ms":19301,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1461124,"mean_ms":902169.625,"min_ms":499972,"run_count":8},"medium":{"attempt_count":9,"max_ms":676490,"mean_ms":489467.75,"min_ms":326732,"run_count":8},"none":{"attempt_count":12,"max_ms":131002,"mean_ms":54664.75,"min_ms":19301,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":106197,"output_mean":33246.666666666664,"output_min":2345,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":106197,"output_mean":60744.125,"output_min":32963,"run_count":8},"medium":{"attempt_count":9,"output_max":42157,"output_mean":35085.125,"output_min":20989,"run_count":8},"none":{"attempt_count":12,"output_max":10866,"output_mean":3910.75,"output_min":2345,"run_count":8}},"display_name":"DeepSeek V4 Pro 0813","economics":{"all":47.58354842083107,"highest":56.220466329610964,"medium":46.832309311481424,"none":39.519208630300525},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":31,"finish_reasons":["stop"],"indexed_attempts":31,"output_token_observations":31,"provider_post_attempt_observations":31,"provider_post_attempts":31,"reasoning_token_observations":31,"reconciliation_get_attempt_observations":31,"reconciliation_get_attempts":150,"total_output_tokens":797920,"total_reasoning_output_tokens":686933,"total_visible_output_tokens":110987,"visible_token_observations":31},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-pro-0813","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.464488007775685,"score":43.464488007775685},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.276237601367114,"score":28.18415840091141},"GB2-03":{"attempts":3,"playable":48.57071795540717,"score":48.57071795540717},"GB2-04":{"attempts":3,"playable":40.88085036972145,"score":40.88085036972145},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":60.24055506642435,"score":40.1603700442829},"GB2-06":{"attempts":3,"playable":56.373029632353514,"score":56.373029632353514},"GB2-07":{"attempts":3,"playable":59.68968717677556,"score":59.68968717677556},"GB2-08":{"attempts":3,"playable":36.522517382953026,"score":36.522517382953026}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":44.40892925262469,"score":44.40892925262469},"GB2-02":{"attempts":1,"playable":44.53956867213121,"score":44.53956867213121},"GB2-03":{"attempts":1,"playable":65.31197675055986,"score":65.31197675055986},"GB2-04":{"attempts":1,"playable":44.48814724960762,"score":44.48814724960762},"GB2-05":{"attempts":1,"playable":75.64653896704814,"score":75.64653896704814},"GB2-06":{"attempts":1,"playable":68.51396450261925,"score":68.51396450261925},"GB2-07":{"attempts":1,"playable":79.85255894556767,"score":79.85255894556767},"GB2-08":{"attempts":1,"playable":27.002046296729237,"score":27.002046296729237}},"medium":{"GB2-01":{"attempts":1,"playable":51.31734296933465,"score":51.31734296933465},"GB2-02":{"attempts":1,"playable":40.01290653060302,"score":40.01290653060302},"GB2-03":{"attempts":1,"playable":43.460685114154316,"score":43.460685114154316},"GB2-04":{"attempts":1,"playable":33.132033330429664,"score":33.132033330429664},"GB2-05":{"attempts":1,"playable":44.834571165800554,"score":44.834571165800554},"GB2-06":{"attempts":1,"playable":39.062507071069064,"score":39.062507071069064},"GB2-07":{"attempts":1,"playable":74.35240802787297,"score":74.35240802787297},"GB2-08":{"attempts":1,"playable":48.48602028258709,"score":48.48602028258709}},"none":{"GB2-01":{"attempts":1,"playable":34.667191801367714,"score":34.667191801367714},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.93949200150734,"score":36.93949200150734},"GB2-04":{"attempts":1,"playable":45.02237052912705,"score":45.02237052912705},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.54261732337224,"score":61.54261732337224},"GB2-07":{"attempts":1,"playable":24.86409455688603,"score":24.86409455688603},"GB2-08":{"attempts":1,"playable":34.079485569542754,"score":34.079485569542754}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-10-15T06:26:40Z","match_totals_all":{"draws":3957,"losses":5441,"wins":4706},"match_totals_tracks":{"highest":{"draws":1290,"losses":1669,"wins":2179},"medium":{"draws":1399,"losses":2110,"wins":1725},"none":{"draws":1268,"losses":1662,"wins":802}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":79.85255894556767,"mean":44.23072737127259,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":41,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.40892925262469,"GB2-02":44.53956867213121,"GB2-03":65.31197675055986,"GB2-04":44.48814724960762,"GB2-05":75.64653896704814,"GB2-06":68.51396450261925,"GB2-07":79.85255894556767,"GB2-08":27.002046296729237},"per_game_all":{"GB2-01":43.464488007775685,"GB2-03":48.57071795540717,"GB2-04":40.88085036972145,"GB2-06":56.373029632353514,"GB2-07":59.68968717677556,"GB2-08":36.522517382953026},"per_game_match_totals_all":{"GB2-01":{"draws":555,"losses":804,"wins":583},"GB2-02":{"draws":913,"losses":252,"wins":39},"GB2-03":{"draws":398,"losses":849,"wins":667},"GB2-04":{"draws":1026,"losses":616,"wins":250},"GB2-05":{"draws":0,"losses":504,"wins":806},"GB2-06":{"draws":60,"losses":885,"wins":1005},"GB2-07":{"draws":0,"losses":785,"wins":1109},"GB2-08":{"draws":1005,"losses":746,"wins":247}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":327,"wins":282},"GB2-02":{"draws":490,"losses":103,"wins":21},"GB2-03":{"draws":46,"losses":222,"wins":346},"GB2-04":{"draws":343,"losses":209,"wins":120},"GB2-05":{"draws":0,"losses":169,"wins":481},"GB2-06":{"draws":21,"losses":213,"wins":436},"GB2-07":{"draws":0,"losses":137,"wins":489},"GB2-08":{"draws":371,"losses":289,"wins":4}},"medium":{"GB2-01":{"draws":394,"losses":151,"wins":149},"GB2-02":{"draws":423,"losses":149,"wins":18},"GB2-03":{"draws":81,"losses":370,"wins":235},"GB2-04":{"draws":229,"losses":278,"wins":85},"GB2-05":{"draws":0,"losses":335,"wins":325},"GB2-06":{"draws":32,"losses":396,"wins":238},"GB2-07":{"draws":0,"losses":180,"wins":466},"GB2-08":{"draws":240,"losses":251,"wins":209}},"none":{"GB2-01":{"draws":142,"losses":326,"wins":152},"GB2-03":{"draws":271,"losses":257,"wins":86},"GB2-04":{"draws":454,"losses":129,"wins":45},"GB2-06":{"draws":7,"losses":276,"wins":331},"GB2-07":{"draws":0,"losses":468,"wins":154},"GB2-08":{"draws":394,"losses":206,"wins":34}}},"per_game_raw_elo_all":{"GB2-01":1418.882302439664,"GB2-03":1430.1903939530173,"GB2-04":1406.6144769825387,"GB2-06":1562.8420559796407,"GB2-07":1601.678820995894,"GB2-08":1286.2700114863515},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1428.8233448278288,"GB2-02":1433.7792334059473,"GB2-03":1583.3237504022618,"GB2-04":1435.4451416550494,"GB2-05":1836.6032318571279,"GB2-06":1765.0850576431492,"GB2-07":1893.892178599828,"GB2-08":1188.078819953365},"medium":{"GB2-01":1494.9857169626237,"GB2-02":1398.6222383174659,"GB2-03":1382.080137457967,"GB2-04":1344.8214973799763,"GB2-05":1386.8602297907246,"GB2-06":1282.2377464243223,"GB2-07":1790.9019785166024,"GB2-08":1408.8727149380327},"none":{"GB2-01":1332.8378455285392,"GB2-03":1325.167293998823,"GB2-04":1439.5767919125904,"GB2-06":1641.2033638714508,"GB2-07":1120.2423058712516,"GB2-08":1261.858499567657}},"per_game_tracks":{"highest":{"GB2-01":44.40892925262469,"GB2-02":44.53956867213121,"GB2-03":65.31197675055986,"GB2-04":44.48814724960762,"GB2-05":75.64653896704814,"GB2-06":68.51396450261925,"GB2-07":79.85255894556767,"GB2-08":27.002046296729237},"medium":{"GB2-01":51.31734296933465,"GB2-02":40.01290653060302,"GB2-03":43.460685114154316,"GB2-04":33.132033330429664,"GB2-05":44.834571165800554,"GB2-06":39.062507071069064,"GB2-07":74.35240802787297,"GB2-08":48.48602028258709},"none":{"GB2-01":34.667191801367714,"GB2-03":36.93949200150734,"GB2-04":45.02237052912705,"GB2-06":61.54261732337224,"GB2-07":24.86409455688603,"GB2-08":34.079485569542754}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.220466329610964,"medium":46.832309311481424,"none":29.639406472725394},"reasoning_agg":{"highest":{"max":79.85255894556767,"mean":56.220466329610964,"min":27.002046296729237},"medium":{"max":74.35240802787297,"mean":46.832309311481424,"min":33.132033330429664},"none":{"max":61.54261732337224,"mean":29.639406472725394,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":26.58105985688557}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:0486b73521227988","codegen_cost_by_reasoning":{"highest":{"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":2.2561125},"medium":{"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":1.4205012499999998},"none":{"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":0.7793050000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.7793050000000001},"historical-provider-setting-intensive":{"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":2.2561125}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":31},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":3,"max":0.45464499999999997,"mean":0.18566328125000006,"median":0.17276625,"min":0.06945125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":12,"boardgame-list-prices-2026-10-09":19},"run_count":24,"token_priced_attempt_count":31,"total":4.45591875},"codegen_latency_ms":{"attempt_count":19,"max_ms":452838,"mean_ms":201000.75,"min_ms":115295,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":452838,"mean_ms":260996.125,"min_ms":140461,"run_count":8},"medium":{"attempt_count":9,"max_ms":181508,"mean_ms":141005.375,"min_ms":115295,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":43637,"output_mean":21815.875,"output_min":13286,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":43637,"output_mean":26965.5,"output_min":16148,"run_count":8},"medium":{"attempt_count":9,"output_max":19618,"output_mean":16666.25,"output_min":13286,"run_count":8}},"display_name":"GPT-5","economics":{"all":43.98320458258527,"highest":49.87958730163178,"medium":42.56765755789422,"none":41.830431578696725},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"total_output_tokens":349054},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"first_pass_admitted":4,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"performance_rejections":1},"GB2-05":{"admitted":1},"GB2-06":{"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-04","GB2-06"],"performance_rejections":2,"repaired_admitted":2,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":43.432951901191664,"score":43.432951901191664},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.006446979466034,"score":27.33763131964402},"GB2-03":{"attempts":3,"playable":27.678113664757507,"score":27.678113664757507},"GB2-04":{"attempts":2,"playable":42.26067634414268,"score":42.26067634414268},"GB2-05":{"attempts":3,"playable":61.209998474244884,"score":61.209998474244884},"GB2-06":{"attempts":2,"playable":60.85528770224882,"score":60.85528770224882},"GB2-07":{"attempts":3,"playable":52.7560030782563,"score":52.7560030782563},"GB2-08":{"attempts":3,"playable":34.83895579447599,"score":34.83895579447599}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":40.54200393056648,"score":40.54200393056648},"GB2-02":{"attempts":1,"playable":42.25054658396633,"score":42.25054658396633},"GB2-03":{"attempts":1,"playable":36.19396728663381,"score":36.19396728663381},"GB2-04":{"attempts":1,"playable":40.86370536734929,"score":40.86370536734929},"GB2-05":{"attempts":1,"playable":75.13722040668908,"score":75.13722040668908},"GB2-06":{"attempts":1,"playable":71.99508321911928,"score":71.99508321911928},"GB2-07":{"attempts":1,"playable":54.504112821148155,"score":54.504112821148155},"GB2-08":{"attempts":1,"playable":37.550058797581734,"score":37.550058797581734}},"medium":{"GB2-01":{"attempts":1,"playable":19.899991250987295,"score":19.899991250987295},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.121206475182767,"score":31.121206475182767},"GB2-04":{"attempts":1,"playable":43.65764732093608,"score":43.65764732093608},"GB2-05":{"attempts":1,"playable":60.73501507817214,"score":60.73501507817214},"GB2-06":{"attempts":1,"playable":49.715492185378366,"score":49.715492185378366},"GB2-07":{"attempts":1,"playable":62.47319537791681,"score":62.47319537791681},"GB2-08":{"attempts":1,"playable":30.371055216686127,"score":30.371055216686127}},"none":{"GB2-01":{"attempts":1,"playable":69.8568605220212,"score":69.8568605220212},"GB2-02":{"attempts":1,"playable":39.76234737496573,"score":39.76234737496573},"GB2-03":{"attempts":1,"playable":15.719167232455966,"score":15.719167232455966},"GB2-05":{"attempts":1,"playable":47.75775993787343,"score":47.75775993787343},"GB2-07":{"attempts":1,"playable":41.29070103570394,"score":41.29070103570394},"GB2-08":{"attempts":1,"playable":36.595753369160114,"score":36.595753369160114}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-10-15T06:44:43Z","match_totals_all":{"draws":3302,"losses":4862,"wins":3662},"match_totals_tracks":{"highest":{"draws":1440,"losses":1623,"wins":1543},"medium":{"draws":1009,"losses":1831,"wins":1264},"none":{"draws":853,"losses":1408,"wins":855}},"model_slug":"gpt-5","overall":{"max":75.13722040668908,"mean":42.98557308116199,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":40.54200393056648,"GB2-02":42.25054658396633,"GB2-03":36.19396728663381,"GB2-04":40.86370536734929,"GB2-05":75.13722040668908,"GB2-06":71.99508321911928,"GB2-07":54.504112821148155,"GB2-08":37.550058797581734},"per_game_all":{"GB2-01":43.432951901191664,"GB2-03":27.678113664757507,"GB2-05":61.209998474244884,"GB2-07":52.7560030782563,"GB2-08":34.83895579447599},"per_game_match_totals_all":{"GB2-01":{"draws":227,"losses":839,"wins":594},"GB2-02":{"draws":799,"losses":222,"wins":23},"GB2-03":{"draws":464,"losses":892,"wins":176},"GB2-04":{"draws":726,"losses":301,"wins":125},"GB2-05":{"draws":0,"losses":669,"wins":1019},"GB2-06":{"draws":49,"losses":441,"wins":672},"GB2-07":{"draws":0,"losses":840,"wins":922},"GB2-08":{"draws":1037,"losses":658,"wins":131}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":86,"losses":301,"wins":193},"GB2-02":{"draws":423,"losses":107,"wins":18},"GB2-03":{"draws":177,"losses":256,"wins":91},"GB2-04":{"draws":390,"losses":141,"wins":35},"GB2-05":{"draws":0,"losses":161,"wins":419},"GB2-06":{"draws":19,"losses":156,"wins":393},"GB2-07":{"draws":0,"losses":282,"wins":326},"GB2-08":{"draws":345,"losses":219,"wins":68}},"medium":{"GB2-01":{"draws":77,"losses":411,"wins":86},"GB2-03":{"draws":211,"losses":261,"wins":54},"GB2-04":{"draws":336,"losses":160,"wins":90},"GB2-05":{"draws":0,"losses":237,"wins":353},"GB2-06":{"draws":30,"losses":285,"wins":279},"GB2-07":{"draws":0,"losses":231,"wins":379},"GB2-08":{"draws":355,"losses":246,"wins":23}},"none":{"GB2-01":{"draws":64,"losses":127,"wins":315},"GB2-02":{"draws":376,"losses":115,"wins":5},"GB2-03":{"draws":76,"losses":375,"wins":31},"GB2-05":{"draws":0,"losses":271,"wins":247},"GB2-07":{"draws":0,"losses":327,"wins":217},"GB2-08":{"draws":337,"losses":193,"wins":40}}},"per_game_raw_elo_all":{"GB2-01":1412.612538853811,"GB2-03":1230.2632373046702,"GB2-05":1613.4497669261484,"GB2-07":1486.2788755049803,"GB2-08":1269.301351146578},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1391.402985797586,"GB2-02":1416.0777980678804,"GB2-03":1318.5402629343282,"GB2-04":1407.2450104261595,"GB2-05":1826.013975877041,"GB2-06":1829.553362121167,"GB2-07":1506.4679864781879,"GB2-08":1296.832312580219},"medium":{"GB2-01":1162.0272385360452,"GB2-03":1272.2138372025838,"GB2-04":1429.0129528364569,"GB2-05":1590.664502213498,"GB2-06":1447.0174504665697,"GB2-07":1611.696356634669,"GB2-08":1223.828976925681},"none":{"GB2-01":1684.4073922278014,"GB2-02":1396.6547843211138,"GB2-03":1100.0356117770987,"GB2-05":1423.670822687906,"GB2-07":1340.672283402084,"GB2-08":1287.2427639338346}},"per_game_tracks":{"highest":{"GB2-01":40.54200393056648,"GB2-02":42.25054658396633,"GB2-03":36.19396728663381,"GB2-04":40.86370536734929,"GB2-05":75.13722040668908,"GB2-06":71.99508321911928,"GB2-07":54.504112821148155,"GB2-08":37.550058797581734},"medium":{"GB2-01":19.899991250987295,"GB2-03":31.121206475182767,"GB2-04":43.65764732093608,"GB2-05":60.73501507817214,"GB2-06":49.715492185378366,"GB2-07":62.47319537791681,"GB2-08":30.371055216686127},"none":{"GB2-01":69.8568605220212,"GB2-02":39.76234737496573,"GB2-03":15.719167232455966,"GB2-05":47.75775993787343,"GB2-07":41.29070103570394,"GB2-08":36.595753369160114}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":49.87958730163178,"medium":37.246700363157444,"none":41.830431578696725},"reasoning_agg":{"highest":{"max":75.13722040668908,"mean":49.87958730163178,"min":36.19396728663381},"medium":{"max":62.47319537791681,"mean":37.246700363157444,"min":0.0},"none":{"max":69.8568605220212,"mean":41.830431578696725,"min":15.719167232455966}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":12.632886938474336}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:0f2b44abb61ff1a1","codegen_cost_by_reasoning":{"highest":{"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":0.24666659999999996},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399885000000007},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":41.79355050089158,"highest":55.830500004703374,"medium":43.32650618765281,"none":26.223645310318535},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":238178,"total_reasoning_output_tokens":167062,"total_visible_output_tokens":71116,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":51.25640077746193,"score":51.25640077746193},"GB2-02":{"attempts":3,"playable":43.6071991458788,"score":43.6071991458788},"GB2-03":{"attempts":3,"playable":38.65149813562926,"score":38.65149813562926},"GB2-04":{"attempts":3,"playable":42.52020930613339,"score":42.52020930613339},"GB2-05":{"attempts":3,"playable":40.51769529632679,"score":40.51769529632679},"GB2-06":{"attempts":3,"playable":53.00201027352559,"score":53.00201027352559},"GB2-07":{"attempts":3,"playable":39.08480137400609,"score":39.08480137400609},"GB2-08":{"attempts":3,"playable":25.70858969817078,"score":25.70858969817078}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.97794576654384,"score":81.97794576654384},"GB2-02":{"attempts":1,"playable":44.56656253819403,"score":44.56656253819403},"GB2-03":{"attempts":1,"playable":42.15762155433653,"score":42.15762155433653},"GB2-04":{"attempts":1,"playable":38.08758468823469,"score":38.08758468823469},"GB2-05":{"attempts":1,"playable":52.2256319845447,"score":52.2256319845447},"GB2-06":{"attempts":1,"playable":82.29165315050798,"score":82.29165315050798},"GB2-07":{"attempts":1,"playable":72.36056407368862,"score":72.36056407368862},"GB2-08":{"attempts":1,"playable":32.97643628157664,"score":32.97643628157664}},"medium":{"GB2-01":{"attempts":1,"playable":47.18693863391379,"score":47.18693863391379},"GB2-02":{"attempts":1,"playable":43.69038923684135,"score":43.69038923684135},"GB2-03":{"attempts":1,"playable":43.99305104556608,"score":43.99305104556608},"GB2-04":{"attempts":1,"playable":48.82188019095235,"score":48.82188019095235},"GB2-05":{"attempts":1,"playable":44.02700568636855,"score":44.02700568636855},"GB2-06":{"attempts":1,"playable":57.533900493630995,"score":57.533900493630995},"GB2-07":{"attempts":1,"playable":28.739723152398216,"score":28.739723152398216},"GB2-08":{"attempts":1,"playable":32.6191610615512,"score":32.6191610615512}},"none":{"GB2-01":{"attempts":1,"playable":24.604317931928154,"score":24.604317931928154},"GB2-02":{"attempts":1,"playable":42.564645662601016,"score":42.564645662601016},"GB2-03":{"attempts":1,"playable":29.80382180698518,"score":29.80382180698518},"GB2-04":{"attempts":1,"playable":40.65116303921313,"score":40.65116303921313},"GB2-05":{"attempts":1,"playable":25.300448218067125,"score":25.300448218067125},"GB2-06":{"attempts":1,"playable":19.180477176437776,"score":19.180477176437776},"GB2-07":{"attempts":1,"playable":16.154116895931438,"score":16.154116895931438},"GB2-08":{"attempts":1,"playable":11.530171751384485,"score":11.530171751384485}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-10-13T22:57:21Z","match_totals_all":{"draws":5248,"losses":7235,"wins":4402},"match_totals_tracks":{"highest":{"draws":1792,"losses":1631,"wins":2210},"medium":{"draws":1837,"losses":2360,"wins":1571},"none":{"draws":1619,"losses":3244,"wins":621}},"model_slug":"gpt-5-6-luna","overall":{"max":82.29165315050798,"mean":41.79355050089158,"min":11.530171751384485},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.97794576654384,"GB2-02":44.56656253819403,"GB2-03":42.15762155433653,"GB2-04":38.08758468823469,"GB2-05":52.2256319845447,"GB2-06":82.29165315050798,"GB2-07":72.36056407368862,"GB2-08":32.97643628157664},"per_game_all":{"GB2-01":51.25640077746193,"GB2-02":43.6071991458788,"GB2-03":38.65149813562926,"GB2-04":42.52020930613339,"GB2-05":40.51769529632679,"GB2-06":53.00201027352559,"GB2-07":39.08480137400609,"GB2-08":25.70858969817078},"per_game_match_totals_all":{"GB2-01":{"draws":251,"losses":966,"wins":932},"GB2-02":{"draws":1598,"losses":290,"wins":56},"GB2-03":{"draws":926,"losses":900,"wins":343},"GB2-04":{"draws":1289,"losses":497,"wins":202},"GB2-05":{"draws":0,"losses":1290,"wins":963},"GB2-06":{"draws":142,"losses":953,"wins":1049},"GB2-07":{"draws":0,"losses":1300,"wins":798},"GB2-08":{"draws":1042,"losses":1039,"wins":59}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":145,"wins":544},"GB2-02":{"draws":501,"losses":91,"wins":36},"GB2-03":{"draws":331,"losses":287,"wins":134},"GB2-04":{"draws":399,"losses":203,"wins":58},"GB2-05":{"draws":0,"losses":384,"wins":422},"GB2-06":{"draws":74,"losses":93,"wins":516},"GB2-07":{"draws":0,"losses":207,"wins":495},"GB2-08":{"draws":486,"losses":221,"wins":5}},"medium":{"GB2-01":{"draws":102,"losses":372,"wins":295},"GB2-02":{"draws":563,"losses":109,"wins":14},"GB2-03":{"draws":257,"losses":300,"wins":180},"GB2-04":{"draws":455,"losses":125,"wins":84},"GB2-05":{"draws":0,"losses":382,"wins":347},"GB2-06":{"draws":30,"losses":321,"wins":420},"GB2-07":{"draws":0,"losses":497,"wins":199},"GB2-08":{"draws":430,"losses":254,"wins":32}},"none":{"GB2-01":{"draws":148,"losses":449,"wins":93},"GB2-02":{"draws":534,"losses":90,"wins":6},"GB2-03":{"draws":338,"losses":313,"wins":29},"GB2-04":{"draws":435,"losses":169,"wins":60},"GB2-05":{"draws":0,"losses":524,"wins":194},"GB2-06":{"draws":38,"losses":539,"wins":113},"GB2-07":{"draws":0,"losses":596,"wins":104},"GB2-08":{"draws":126,"losses":564,"wins":22}}},"per_game_raw_elo_all":{"GB2-01":1507.1385818755928,"GB2-02":1426.5756803818474,"GB2-03":1339.0672136410747,"GB2-04":1419.9337135815001,"GB2-05":1322.4456091924242,"GB2-06":1526.3283957396968,"GB2-07":1302.2784716742842,"GB2-08":1158.937244676076},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1843.750490573871,"GB2-02":1433.987374773062,"GB2-03":1370.8021022140329,"GB2-04":1385.3022684985513,"GB2-05":1479.7643876452812,"GB2-06":2031.2547068372157,"GB2-07":1757.7913851603553,"GB2-08":1250.6473671385113},"medium":{"GB2-01":1455.4483580542194,"GB2-02":1427.2254508728429,"GB2-03":1386.6833806580244,"GB2-04":1468.9207725810768,"GB2-05":1376.6161193630765,"GB2-06":1573.3648142714899,"GB2-07":1176.4158113551412,"GB2-08":1247.0006346456425},"none":{"GB2-01":1222.216896998688,"GB2-02":1418.5142154996374,"GB2-03":1259.7161580511668,"GB2-04":1405.578099664872,"GB2-05":1110.9563205689146,"GB2-06":974.3656661103846,"GB2-07":972.628218507356,"GB2-08":979.1637322440739}},"per_game_tracks":{"highest":{"GB2-01":81.97794576654384,"GB2-02":44.56656253819403,"GB2-03":42.15762155433653,"GB2-04":38.08758468823469,"GB2-05":52.2256319845447,"GB2-06":82.29165315050798,"GB2-07":72.36056407368862,"GB2-08":32.97643628157664},"medium":{"GB2-01":47.18693863391379,"GB2-02":43.69038923684135,"GB2-03":43.99305104556608,"GB2-04":48.82188019095235,"GB2-05":44.02700568636855,"GB2-06":57.533900493630995,"GB2-07":28.739723152398216,"GB2-08":32.6191610615512},"none":{"GB2-01":24.604317931928154,"GB2-02":42.564645662601016,"GB2-03":29.80382180698518,"GB2-04":40.65116303921313,"GB2-05":25.300448218067125,"GB2-06":19.180477176437776,"GB2-07":16.154116895931438,"GB2-08":11.530171751384485}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.830500004703374,"medium":43.32650618765281,"none":26.223645310318535},"reasoning_agg":{"highest":{"max":82.29165315050798,"mean":55.830500004703374,"min":32.97643628157664},"medium":{"max":57.533900493630995,"mean":43.32650618765281,"min":28.739723152398216},"none":{"max":42.564645662601016,"mean":26.223645310318535,"min":11.530171751384485}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.60685469438484}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:e111031353bc7327","codegen_cost_by_reasoning":{"highest":{"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":0.0773785,"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},"medium":{"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},"none":{"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":0.34510199999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.345102},"historical-provider-setting-intensive":{"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":0.0773785,"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_cost_usd":{"admitted_cell_count":33,"cell_count":24,"cost_basis_counts":{"estimated":32,"local_standard_estimate":26},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":15,"max":0.1097735,"mean":0.06116525,"median":0.054719000000000004,"min":0.030172,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":58},"recorded_attempt_count":32,"run_count":48,"token_priced_attempt_count":26,"total":3.6636299999999995},"codegen_latency_ms":{"attempt_count":26,"max_ms":79649,"mean_ms":37254.041666666664,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":10,"max_ms":74310,"mean_ms":41174.25,"min_ms":21597,"run_count":8}},"codegen_output_tokens":{"attempt_count":58,"output_max":15813,"output_mean":7191.916666666667,"output_min":1943,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":10,"output_max":6022,"output_mean":2920.75,"output_min":1943,"run_count":8}},"display_name":"o3","economics":{"all":46.09070415097665,"highest":46.67855439624913,"medium":46.41068538544434,"none":42.44527960472948},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[100000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":82,"output_token_observations":58,"provider_post_attempt_observations":10,"provider_post_attempts":10,"reasoning_token_observations":10,"reconciliation_get_attempt_observations":10,"requested_max_output_token_observations":10,"requested_max_output_tokens":[100000],"total_output_tokens":345212,"total_reasoning_output_tokens":5824,"total_visible_output_tokens":17542,"visible_token_observations":10},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"o3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":19,"evaluated_cells":32,"failed_game_aliases":["GB2-01","GB2-03","GB2-04","GB2-08"],"first_pass_admitted":19,"first_pass_rate":0.6785714285714286,"game_attempts":{"GB2-01":{"admitted":3,"model_code_failures":1},"GB2-02":{"performance_rejections":4},"GB2-03":{"admitted":1,"model_code_failures":3},"GB2-04":{"model_code_failures":4},"GB2-05":{"admitted":4},"GB2-06":{"admitted":4},"GB2-07":{"admitted":4},"GB2-08":{"admitted":3,"model_code_failures":1}},"model_code_failure_rate":0.32142857142857145,"model_code_failures":9,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-02"],"performance_rejections":4}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":46.54811273745827,"score":41.48414089292492},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.82371714689963,"score":21.411858573449816},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.43719124298299,"score":17.121533722376764},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.51950681524062,"score":28.34633787682708},"GB2-05":{"attempts":6,"playable":48.47020875490484,"score":48.47020875490484},"GB2-06":{"attempts":6,"playable":45.967588991042966,"score":45.967588991042966},"GB2-07":{"attempts":6,"playable":47.004890507485506,"score":47.004890507485506},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":42.46271976399169,"score":38.42518944945501}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":60.76766213440027,"score":45.5757466008002},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":36.67970842511426,"score":9.169927106278566},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":48.80908854042169,"score":48.80908854042169},"GB2-06":{"attempts":4,"playable":42.30294676679012,"score":42.30294676679012},"GB2-07":{"attempts":4,"playable":43.06155673632825,"score":43.06155673632825},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":48.450363774440255,"score":36.33777283083019}},"medium":{"GB2-01":{"attempts":1,"playable":40.13642766663945,"score":40.13642766663945},"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":40.61739231293471,"score":40.61739231293471},"GB2-05":{"attempts":1,"playable":45.75153596738895,"score":45.75153596738895},"GB2-06":{"attempts":1,"playable":47.59247498856193,"score":47.59247498856193},"GB2-07":{"attempts":1,"playable":58.89658576206831,"score":58.89658576206831},"GB2-08":{"attempts":1,"playable":45.46969561507267,"score":45.46969561507267}},"none":{"GB2-01":{"attempts":1,"playable":38.7402484113351,"score":38.7402484113351},"GB2-02":{"attempts":1,"playable":42.82371714689963,"score":42.82371714689963},"GB2-03":{"attempts":1,"playable":42.194674060851725,"score":42.194674060851725},"GB2-04":{"attempts":1,"playable":44.42162131754653,"score":44.42162131754653},"GB2-05":{"attempts":1,"playable":50.850001756903886,"score":50.850001756903886},"GB2-06":{"attempts":1,"playable":48.007345217776844,"score":48.007345217776844},"GB2-07":{"attempts":1,"playable":39.05652902405997,"score":39.05652902405997},"GB2-08":{"attempts":1,"playable":33.468099902462164,"score":33.468099902462164}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-10-15T06:38:16Z","match_totals_all":{"draws":3365,"losses":10312,"wins":8502},"match_totals_tracks":{"highest":{"draws":1464,"losses":7122,"wins":6241},"medium":{"draws":864,"losses":1523,"wins":1271},"none":{"draws":1037,"losses":1667,"wins":990}},"model_slug":"o3","overall":{"max":58.89658576206831,"mean":36.47762352800658,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.76766213440027,"GB2-03":36.67970842511426,"GB2-05":48.80908854042168,"GB2-06":42.30294676679012,"GB2-07":43.06155673632825,"GB2-08":48.450363774440255},"per_game_all":{"GB2-01":46.54811273745827,"GB2-05":48.47020875490484,"GB2-06":45.967588991042966,"GB2-07":47.004890507485506,"GB2-08":42.46271976399169},"per_game_match_totals_all":{"GB2-01":{"draws":369,"losses":1373,"wins":1498},"GB2-02":{"draws":349,"losses":78,"wins":5},"GB2-03":{"draws":339,"losses":560,"wins":271},"GB2-04":{"draws":645,"losses":271,"wins":110},"GB2-05":{"draws":0,"losses":2128,"wins":2125},"GB2-06":{"draws":109,"losses":2350,"wins":1778},"GB2-07":{"draws":0,"losses":2401,"wins":1915},"GB2-08":{"draws":1554,"losses":1151,"wins":800}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":222,"losses":810,"wins":1166},"GB2-03":{"draws":216,"losses":349,"wins":159},"GB2-05":{"draws":0,"losses":1563,"wins":1590},"GB2-06":{"draws":56,"losses":1802,"wins":1313},"GB2-07":{"draws":0,"losses":1849,"wins":1379},"GB2-08":{"draws":970,"losses":749,"wins":634}},"medium":{"GB2-01":{"draws":108,"losses":291,"wins":175},"GB2-04":{"draws":406,"losses":136,"wins":36},"GB2-05":{"draws":0,"losses":326,"wins":290},"GB2-06":{"draws":45,"losses":305,"wins":260},"GB2-07":{"draws":0,"losses":252,"wins":362},"GB2-08":{"draws":305,"losses":213,"wins":148}},"none":{"GB2-01":{"draws":39,"losses":272,"wins":157},"GB2-02":{"draws":349,"losses":78,"wins":5},"GB2-03":{"draws":123,"losses":211,"wins":112},"GB2-04":{"draws":239,"losses":135,"wins":74},"GB2-05":{"draws":0,"losses":239,"wins":245},"GB2-06":{"draws":8,"losses":243,"wins":205},"GB2-07":{"draws":0,"losses":300,"wins":174},"GB2-08":{"draws":279,"losses":189,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1450.518865919413,"GB2-05":1432.5540530154346,"GB2-06":1388.9503975397447,"GB2-07":1412.5629606933464,"GB2-08":1357.2929615500495},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1590.3984237716465,"GB2-03":1322.8621300374828,"GB2-05":1436.7645408756473,"GB2-06":1332.9715769946872,"GB2-07":1361.5738703078748,"GB2-08":1439.0516444366192},"medium":{"GB2-01":1387.4392157898142,"GB2-04":1405.313072359592,"GB2-05":1398.4453679569608,"GB2-06":1413.6964025315485,"GB2-07":1563.5685471234256,"GB2-08":1377.1743863483832},"none":{"GB2-01":1373.7189581967784,"GB2-02":1420.521722454682,"GB2-03":1371.123111778785,"GB2-04":1434.9303449237595,"GB2-05":1462.4522502136952,"GB2-06":1420.1832130929981,"GB2-07":1312.5464646487385,"GB2-08":1255.652853865146}},"per_game_tracks":{"highest":{"GB2-01":60.76766213440027,"GB2-03":36.67970842511426,"GB2-05":48.80908854042168,"GB2-06":42.30294676679012,"GB2-07":43.06155673632825,"GB2-08":48.450363774440255},"medium":{"GB2-01":40.13642766663945,"GB2-04":40.61739231293471,"GB2-05":45.75153596738895,"GB2-06":47.59247498856193,"GB2-07":58.89658576206831,"GB2-08":45.46969561507267},"none":{"GB2-01":38.7402484113351,"GB2-02":42.82371714689963,"GB2-03":42.194674060851725,"GB2-04":44.42162131754653,"GB2-05":50.850001756903886,"GB2-06":48.007345217776844,"GB2-07":39.05652902405997,"GB2-08":33.468099902462164}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.179576940207006,"medium":34.808014039083254,"none":42.44527960472948},"reasoning_agg":{"highest":{"max":48.80908854042169,"mean":32.179576940207006,"min":0.0},"medium":{"max":58.89658576206831,"mean":34.808014039083254,"min":0.0},"none":{"max":50.850001756903886,"mean":42.44527960472948,"min":33.468099902462164}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.265702664522472}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:417d288b9594825c","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":0.42810400000000004},"none":{"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":0.167609}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.167609},"historical-provider-setting-intensive":{"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":0.40577}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":39.36398889607862,"highest":41.69899650817971,"medium":45.81351792875488,"none":29.80340469159085},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":157,"total_output_tokens":288440,"total_reasoning_output_tokens":204471,"total_visible_output_tokens":83969,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":36.997545767070285,"score":36.997545767070285},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.35224564641277,"score":26.901497097608512},"GB2-03":{"attempts":3,"playable":44.04729983486451,"score":44.04729983486451},"GB2-04":{"attempts":3,"playable":40.94003193165142,"score":40.94003193165142},"GB2-05":{"attempts":3,"playable":37.88569408604695,"score":37.88569408604695},"GB2-06":{"attempts":3,"playable":17.64320840139258,"score":17.64320840139258},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":36.82706949280856,"score":24.551379661872375},"GB2-08":{"attempts":3,"playable":58.67015335544596,"score":58.67015335544596}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.95793287756534,"score":39.95793287756534},"GB2-02":{"attempts":1,"playable":40.950317712641336,"score":40.950317712641336},"GB2-03":{"attempts":1,"playable":43.329562285943524,"score":43.329562285943524},"GB2-04":{"attempts":1,"playable":39.36592265565716,"score":39.36592265565716},"GB2-05":{"attempts":1,"playable":49.82293953250482,"score":49.82293953250482},"GB2-06":{"attempts":1,"playable":20.19467236862593,"score":20.19467236862593},"GB2-07":{"attempts":1,"playable":44.89985296678005,"score":44.89985296678005},"GB2-08":{"attempts":1,"playable":55.0707716657195,"score":55.0707716657195}},"medium":{"GB2-01":{"attempts":1,"playable":49.05223910007238,"score":49.05223910007238},"GB2-02":{"attempts":1,"playable":39.75417358018421,"score":39.75417358018421},"GB2-03":{"attempts":1,"playable":41.441748516944585,"score":41.441748516944585},"GB2-04":{"attempts":1,"playable":41.051909903790786,"score":41.051909903790786},"GB2-05":{"attempts":1,"playable":47.607909478079584,"score":47.607909478079584},"GB2-06":{"attempts":1,"playable":14.246948560346425,"score":14.246948560346425},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":87.53969636186618,"score":87.53969636186618}},"none":{"GB2-01":{"attempts":1,"playable":21.98246532357312,"score":21.98246532357312},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":47.37058870170542,"score":47.37058870170542},"GB2-04":{"attempts":1,"playable":42.40226323550631,"score":42.40226323550631},"GB2-05":{"attempts":1,"playable":16.226233247556443,"score":16.226233247556443},"GB2-06":{"attempts":1,"playable":18.48800427520538,"score":18.48800427520538},"GB2-07":{"attempts":1,"playable":28.754286018837078,"score":28.754286018837078},"GB2-08":{"attempts":1,"playable":33.39999203875222,"score":33.39999203875222}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-10-15T06:41:24Z","match_totals_all":{"draws":3973,"losses":6460,"wins":3507},"match_totals_tracks":{"highest":{"draws":1701,"losses":2180,"wins":1309},"medium":{"draws":1091,"losses":1789,"wins":1458},"none":{"draws":1181,"losses":2491,"wins":740}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":87.53969636186618,"mean":35.954601266994075,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.95793287756534,"GB2-02":40.950317712641336,"GB2-03":43.329562285943524,"GB2-04":39.36592265565716,"GB2-05":49.82293953250482,"GB2-06":20.19467236862593,"GB2-07":44.89985296678005,"GB2-08":55.0707716657195},"per_game_all":{"GB2-01":36.997545767070285,"GB2-03":44.04729983486451,"GB2-04":40.94003193165142,"GB2-05":37.88569408604695,"GB2-06":17.64320840139258,"GB2-08":58.67015335544596},"per_game_match_totals_all":{"GB2-01":{"draws":528,"losses":889,"wins":455},"GB2-02":{"draws":918,"losses":230,"wins":14},"GB2-03":{"draws":503,"losses":918,"wins":545},"GB2-04":{"draws":1251,"losses":431,"wins":128},"GB2-05":{"draws":0,"losses":1205,"wins":803},"GB2-06":{"draws":9,"losses":1491,"wins":316},"GB2-07":{"draws":0,"losses":846,"wins":496},"GB2-08":{"draws":764,"losses":450,"wins":750}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":277,"losses":225,"wins":126},"GB2-02":{"draws":467,"losses":106,"wins":5},"GB2-03":{"draws":207,"losses":297,"wins":172},"GB2-04":{"draws":399,"losses":156,"wins":39},"GB2-05":{"draws":0,"losses":363,"wins":355},"GB2-06":{"draws":2,"losses":482,"wins":122},"GB2-07":{"draws":0,"losses":399,"wins":309},"GB2-08":{"draws":349,"losses":152,"wins":181}},"medium":{"GB2-01":{"draws":93,"losses":265,"wins":270},"GB2-02":{"draws":451,"losses":124,"wins":9},"GB2-03":{"draws":139,"losses":323,"wins":156},"GB2-04":{"draws":405,"losses":156,"wins":51},"GB2-05":{"draws":0,"losses":317,"wins":339},"GB2-06":{"draws":1,"losses":518,"wins":85},"GB2-08":{"draws":2,"losses":86,"wins":548}},"none":{"GB2-01":{"draws":158,"losses":399,"wins":59},"GB2-03":{"draws":157,"losses":298,"wins":217},"GB2-04":{"draws":447,"losses":119,"wins":38},"GB2-05":{"draws":0,"losses":525,"wins":109},"GB2-06":{"draws":6,"losses":491,"wins":109},"GB2-07":{"draws":0,"losses":447,"wins":187},"GB2-08":{"draws":413,"losses":212,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1349.537777464254,"GB2-03":1387.1523796321533,"GB2-04":1407.8120513961933,"GB2-05":1272.1229627328905,"GB2-06":946.6212830452658,"GB2-08":1599.536967687008},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1385.691812146259,"GB2-02":1405.9582595541367,"GB2-03":1380.9460888508565,"GB2-04":1395.4553432770979,"GB2-05":1449.5635716609718,"GB2-06":991.2444254625834,"GB2-07":1385.7481146294508,"GB2-08":1482.3755401794729},"medium":{"GB2-01":1473.2892209791266,"GB2-02":1396.5905514001663,"GB2-03":1364.5949459392732,"GB2-04":1408.719519361122,"GB2-05":1421.7905976584539,"GB2-06":885.9749742858238,"GB2-08":2061.2750517857685},"none":{"GB2-01":1189.6322992673763,"GB2-03":1415.9161041063298,"GB2-04":1419.2612915503605,"GB2-05":945.0147188792463,"GB2-06":962.64444938739,"GB2-07":1176.6197989577977,"GB2-08":1254.9603110957828}},"per_game_tracks":{"highest":{"GB2-01":39.95793287756534,"GB2-02":40.950317712641336,"GB2-03":43.329562285943524,"GB2-04":39.36592265565716,"GB2-05":49.82293953250482,"GB2-06":20.19467236862593,"GB2-07":44.89985296678005,"GB2-08":55.0707716657195},"medium":{"GB2-01":49.05223910007238,"GB2-02":39.75417358018421,"GB2-03":41.441748516944585,"GB2-04":41.051909903790786,"GB2-05":47.607909478079584,"GB2-06":14.246948560346425,"GB2-08":87.53969636186618},"none":{"GB2-01":21.98246532357312,"GB2-03":47.37058870170542,"GB2-04":42.40226323550631,"GB2-05":16.226233247556443,"GB2-06":18.48800427520538,"GB2-07":28.754286018837078,"GB2-08":33.39999203875222}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.69899650817971,"medium":40.086828187660515,"none":26.077979105141992},"reasoning_agg":{"highest":{"max":55.0707716657195,"mean":41.69899650817971,"min":20.19467236862593},"medium":{"max":87.53969636186618,"mean":40.086828187660515,"min":0.0},"none":{"max":47.37058870170542,"mean":26.077979105141992,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":15.621017403037719}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:46d75de3b4280668","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":0.35846965000000003},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.3521656,"mean":0.08720021666666666,"median":0.0402421875,"min":0.00651321,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":38,"run_count":24,"total":2.0928052},"codegen_latency_ms":{"attempt_count":38,"max_ms":2128037,"mean_ms":537328.375,"min_ms":33625,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":2128037,"mean_ms":1259891.875,"min_ms":809012,"run_count":8},"medium":{"attempt_count":13,"max_ms":394009,"mean_ms":249918.25,"min_ms":106640,"run_count":8},"none":{"attempt_count":14,"max_ms":139550,"mean_ms":102175.0,"min_ms":33625,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":142524,"output_mean":33293.458333333336,"output_min":2177,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":142524,"output_mean":77872.0,"output_min":45409,"run_count":8},"medium":{"attempt_count":13,"output_max":24263,"output_mean":15845.5,"output_min":6781,"run_count":8},"none":{"attempt_count":14,"output_max":9194,"output_mean":6162.875,"output_min":2177,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"all":45.56198422767833,"highest":59.42955706074539,"medium":46.50779466129585,"none":35.143826257953286},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[131072],"finish_reason_observations":38,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":41,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"reconciliation_get_attempts":53,"requested_max_output_token_observations":27,"requested_max_output_tokens":[131072],"total_output_tokens":799043,"total_reasoning_output_tokens":636129,"total_visible_output_tokens":162914,"visible_token_observations":38},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-27b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.5,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":50.629480204671005,"score":50.629480204671005},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.35794453779071,"score":28.23862969186047},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":45.55115925400891,"score":30.367439502672607},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.60156335888671,"score":37.06770890592447},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.05087420370238,"score":39.36724946913492},"GB2-06":{"attempts":3,"playable":40.494488250685656,"score":40.494488250685656},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.16717374109558,"score":32.77811582739705},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":45.87787446831797,"score":15.292624822772657}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.65252112649355,"score":74.65252112649355},"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":71.06221138040671,"score":71.06221138040671},"GB2-05":{"attempts":1,"playable":58.87482319555104,"score":58.87482319555104},"GB2-06":{"attempts":1,"playable":28.91154004281422,"score":28.91154004281422},"GB2-07":{"attempts":1,"playable":77.1983721508889,"score":77.1983721508889},"GB2-08":{"attempts":1,"playable":45.87787446831797,"score":45.87787446831797}},"medium":{"GB2-01":{"attempts":1,"playable":52.8556597549126,"score":52.8556597549126},"GB2-02":{"attempts":1,"playable":42.24147881033311,"score":42.24147881033311},"GB2-03":{"attempts":1,"playable":48.10642753651848,"score":48.10642753651848},"GB2-04":{"attempts":1,"playable":40.1409153373667,"score":40.1409153373667},"GB2-05":{"attempts":1,"playable":59.22692521185372,"score":59.22692521185372},"GB2-06":{"attempts":1,"playable":61.847180646784054,"score":61.847180646784054},"GB2-07":{"attempts":1,"playable":21.13597533130227,"score":21.13597533130227},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":24.380259732606834,"score":24.380259732606834},"GB2-02":{"attempts":1,"playable":42.4744102652483,"score":42.4744102652483},"GB2-03":{"attempts":1,"playable":42.99589097149933,"score":42.99589097149933},"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":30.724744062458694,"score":30.724744062458694},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.8-27b","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:10Z","match_totals_all":{"draws":1968,"losses":3636,"wins":3322},"match_totals_tracks":{"highest":{"draws":466,"losses":1416,"wins":2034},"medium":{"draws":918,"losses":1304,"wins":986},"none":{"draws":584,"losses":916,"wins":302}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":77.1983721508889,"mean":34.27946708438985,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":46,"overall_ranking_status":"partial","per_game":{"GB2-01":74.65252112649355,"GB2-04":71.06221138040671,"GB2-05":58.87482319555104,"GB2-06":28.91154004281422,"GB2-07":77.1983721508889,"GB2-08":45.87787446831797},"per_game_all":{"GB2-01":50.629480204671005,"GB2-06":40.494488250685656},"per_game_match_totals_all":{"GB2-01":{"draws":250,"losses":639,"wins":669},"GB2-02":{"draws":692,"losses":163,"wins":9},"GB2-03":{"draws":255,"losses":388,"wins":249},"GB2-04":{"draws":469,"losses":230,"wins":359},"GB2-05":{"draws":0,"losses":494,"wins":708},"GB2-06":{"draws":63,"losses":911,"wins":560},"GB2-07":{"draws":0,"losses":541,"wins":571},"GB2-08":{"draws":239,"losses":270,"wins":197}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":173,"wins":434},"GB2-04":{"draws":184,"losses":99,"wins":327},"GB2-05":{"draws":0,"losses":295,"wins":423},"GB2-06":{"draws":28,"losses":422,"wins":172},"GB2-07":{"draws":0,"losses":157,"wins":481},"GB2-08":{"draws":239,"losses":270,"wins":197}},"medium":{"GB2-01":{"draws":104,"losses":173,"wins":191},"GB2-02":{"draws":346,"losses":82,"wins":4},"GB2-03":{"draws":161,"losses":166,"wins":119},"GB2-04":{"draws":285,"losses":131,"wins":32},"GB2-05":{"draws":0,"losses":199,"wins":285},"GB2-06":{"draws":22,"losses":169,"wins":265},"GB2-07":{"draws":0,"losses":384,"wins":90}},"none":{"GB2-01":{"draws":131,"losses":293,"wins":44},"GB2-02":{"draws":346,"losses":81,"wins":5},"GB2-03":{"draws":94,"losses":222,"wins":130},"GB2-06":{"draws":13,"losses":320,"wins":123}}},"per_game_raw_elo_all":{"GB2-01":1490.2774594389446,"GB2-06":1310.0539581469127},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1741.5420725737424,"GB2-04":1657.0688691349635,"GB2-05":1565.558027986117,"GB2-06":1128.0619124679213,"GB2-07":1841.654745758921,"GB2-08":1381.4115302728635},"medium":{"GB2-01":1509.7766995790191,"GB2-02":1416.0074179354133,"GB2-03":1422.308893317096,"GB2-04":1401.5684898674713,"GB2-05":1570.2606580604838,"GB2-06":1646.4579239990076,"GB2-07":1061.6357674271105},"none":{"GB2-01":1219.513606164072,"GB2-02":1417.8145634089035,"GB2-03":1378.059587236347,"GB2-06":1155.642037973809}},"per_game_tracks":{"highest":{"GB2-01":74.65252112649355,"GB2-04":71.06221138040671,"GB2-05":58.87482319555104,"GB2-06":28.91154004281422,"GB2-07":77.1983721508889,"GB2-08":45.87787446831797},"medium":{"GB2-01":52.8556597549126,"GB2-02":42.24147881033311,"GB2-03":48.10642753651848,"GB2-04":40.1409153373667,"GB2-05":59.22692521185372,"GB2-06":61.847180646784054,"GB2-07":21.13597533130227},"none":{"GB2-01":24.380259732606834,"GB2-02":42.4744102652483,"GB2-03":42.99589097149933,"GB2-06":30.724744062458694}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.57216779555904,"medium":40.694320328633864,"none":17.571913128976643},"reasoning_agg":{"highest":{"max":77.1983721508889,"mean":44.57216779555904,"min":0.0},"medium":{"max":61.847180646784054,"mean":40.694320328633864,"min":0.0},"none":{"max":42.99589097149933,"mean":17.571913128976643,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.000254666582396}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:bc29f998e211af2f","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.008042989573333334,"mean":0.0037891845841666666,"median":0.0032265161666666666,"min":0.002126702,"recorded_attempt_count":36,"run_count":24,"total":0.09094043001999999},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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},"historical-provider-setting-balanced-variant-2":{"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":0.050973330659999996},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.0584754711}},"codegen_cost_usd":{"admitted_cell_count":36,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749804000003},"codegen_latency_ms":{"attempt_count":35,"max_ms":2156476,"mean_ms":402937.5,"min_ms":36579,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":2156476,"mean_ms":830597.625,"min_ms":100447,"run_count":8},"medium":{"attempt_count":12,"max_ms":572210,"mean_ms":258473.0,"min_ms":66883,"run_count":8},"none":{"attempt_count":10,"max_ms":286097,"mean_ms":119741.875,"min_ms":36579,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":54472,"output_mean":14159.166666666666,"output_min":1979,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":47250,"output_mean":26393.0,"output_min":7308,"run_count":8},"medium":{"attempt_count":12,"output_max":54472,"output_mean":12951.25,"output_min":5048,"run_count":8},"none":{"attempt_count":10,"output_max":4856,"output_mean":3133.25,"output_min":1979,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":37.59238955456222,"highest":41.59582799178746,"medium":37.182163938066445,"none":35.49884045035951},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":339820,"total_reasoning_output_tokens":258096,"total_visible_output_tokens":81724,"visible_token_observations":35},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":22,"evaluated_cells":22,"first_pass_admitted":15,"first_pass_rate":0.6818181818181818,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":3},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":3},"GB2-08":{"admitted":3}},"infra_excluded_game_aliases":["GB2-03","GB2-04"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.3181818181818182},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-05"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":24.98280636159957,"score":24.98280636159957},"GB2-02":{"attempts":5,"playable":41.751574336222575,"score":41.751574336222575},"GB2-03":{"attempts":4,"playable":37.89131565111919,"score":37.89131565111919},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.49585612870429,"score":27.66390408580286},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.63832085675427,"score":23.758880571169513},"GB2-06":{"attempts":5,"playable":55.004506626132326,"score":55.004506626132326},"GB2-07":{"attempts":5,"playable":28.524122131747443,"score":28.524122131747443},"GB2-08":{"attempts":5,"playable":33.51443604516551,"score":33.51443604516551}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.978176288674941,"score":15.978176288674941},"GB2-02":{"attempts":1,"playable":43.08135922380174,"score":43.08135922380174},"GB2-03":{"attempts":1,"playable":34.51189419495256,"score":34.51189419495256},"GB2-04":{"attempts":1,"playable":42.68232296008115,"score":42.68232296008115},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":81.93050131891336,"score":81.93050131891336},"GB2-07":{"attempts":1,"playable":39.864654185202276,"score":39.864654185202276},"GB2-08":{"attempts":1,"playable":33.121887770886204,"score":33.121887770886204}},"medium":{"GB2-01":{"attempts":3,"playable":38.42354942422301,"score":38.42354942422301},"GB2-02":{"attempts":3,"playable":39.91618412794167,"score":39.91618412794167},"GB2-03":{"attempts":2,"playable":43.72614449237642,"score":43.72614449237642},"GB2-04":{"attempts":2,"playable":40.30938929732743,"score":40.30938929732743},"GB2-05":{"attempts":3,"playable":26.20272050304057,"score":26.20272050304057},"GB2-06":{"attempts":3,"playable":26.080010987923064,"score":26.080010987923064},"GB2-07":{"attempts":3,"playable":25.859550831358195,"score":25.859550831358195},"GB2-08":{"attempts":3,"playable":39.094408667657795,"score":39.094408667657795}},"none":{"GB2-01":{"attempts":1,"playable":20.546693371900755,"score":20.546693371900755},"GB2-02":{"attempts":1,"playable":42.257179656924315,"score":42.257179656924315},"GB2-03":{"attempts":1,"playable":35.43590826602859,"score":35.43590826602859},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":45.07392121046797,"score":45.07392121046797},"GB2-06":{"attempts":1,"playable":57.00300757156055,"score":57.00300757156055},"GB2-07":{"attempts":1,"playable":19.84816137868185,"score":19.84816137868185},"GB2-08":{"attempts":1,"playable":28.327011696952535,"score":28.327011696952535}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-10-13T22:40:34Z","match_totals_all":{"draws":6444,"losses":10741,"wins":4759},"match_totals_tracks":{"highest":{"draws":1593,"losses":1814,"wins":991},"medium":{"draws":3701,"losses":6667,"wins":2734},"none":{"draws":1150,"losses":2260,"wins":1034}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":81.93050131891336,"mean":34.13644322611987,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.978176288674941,"GB2-02":43.08135922380174,"GB2-03":34.51189419495256,"GB2-04":42.68232296008115,"GB2-06":81.93050131891336,"GB2-07":39.864654185202276,"GB2-08":33.121887770886204},"per_game_all":{"GB2-01":24.62429249226736,"GB2-02":41.92139006267095,"GB2-03":37.89131565111919,"GB2-06":56.98731511917978,"GB2-07":29.402086603232704,"GB2-08":34.72793739890333},"per_game_match_totals_all":{"GB2-01":{"draws":512,"losses":1871,"wins":641},"GB2-02":{"draws":2222,"losses":561,"wins":51},"GB2-03":{"draws":790,"losses":1050,"wins":500},"GB2-04":{"draws":1211,"losses":498,"wins":145},"GB2-05":{"draws":0,"losses":1644,"wins":886},"GB2-06":{"draws":83,"losses":1688,"wins":1343},"GB2-07":{"draws":0,"losses":2238,"wins":864},"GB2-08":{"draws":1626,"losses":1191,"wins":329}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":145,"losses":442,"wins":25},"GB2-02":{"draws":442,"losses":98,"wins":26},"GB2-03":{"draws":210,"losses":297,"wins":101},"GB2-04":{"draws":380,"losses":195,"wins":83},"GB2-06":{"draws":42,"losses":102,"wins":458},"GB2-07":{"draws":0,"losses":438,"wins":262},"GB2-08":{"draws":374,"losses":242,"wins":36}},"medium":{"GB2-01":{"draws":219,"losses":1018,"wins":563},"GB2-02":{"draws":1278,"losses":348,"wins":20},"GB2-03":{"draws":377,"losses":457,"wins":288},"GB2-04":{"draws":831,"losses":303,"wins":62},"GB2-05":{"draws":0,"losses":1312,"wins":568},"GB2-06":{"draws":20,"losses":1288,"wins":512},"GB2-07":{"draws":0,"losses":1297,"wins":483},"GB2-08":{"draws":976,"losses":644,"wins":238}},"none":{"GB2-01":{"draws":148,"losses":411,"wins":53},"GB2-02":{"draws":502,"losses":115,"wins":5},"GB2-03":{"draws":203,"losses":296,"wins":111},"GB2-05":{"draws":0,"losses":332,"wins":318},"GB2-06":{"draws":21,"losses":298,"wins":373},"GB2-07":{"draws":0,"losses":503,"wins":119},"GB2-08":{"draws":276,"losses":305,"wins":55}}},"per_game_raw_elo_all":{"GB2-01":1207.7396144477564,"GB2-02":1413.4338680739831,"GB2-03":1333.191910478172,"GB2-06":1583.542225066349,"GB2-07":1172.9128905244079,"GB2-08":1268.8662844607009},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1104.3995482720518,"GB2-02":1422.516424902125,"GB2-03":1303.4419050007268,"GB2-04":1421.4403143897869,"GB2-06":2023.7354117779114,"GB2-07":1322.7492230928606,"GB2-08":1252.1296722135464},"medium":{"GB2-01":1348.0327037696375,"GB2-02":1401.6558997713282,"GB2-03":1384.3710951330281,"GB2-04":1402.8517718190164,"GB2-05":1178.5005059772748,"GB2-06":1162.3349206042276,"GB2-07":1155.9833138439155,"GB2-08":1352.1507131041317},"none":{"GB2-01":1170.7865913015803,"GB2-02":1416.1292795484962,"GB2-03":1311.7627313007615,"GB2-05":1389.8886247899811,"GB2-06":1564.556342816908,"GB2-07":1040.0061346364475,"GB2-08":1202.3184680644245}},"per_game_tracks":{"highest":{"GB2-01":15.978176288674941,"GB2-02":43.08135922380174,"GB2-03":34.51189419495256,"GB2-04":42.68232296008115,"GB2-06":81.93050131891336,"GB2-07":39.864654185202276,"GB2-08":33.121887770886204},"medium":{"GB2-01":37.34800781622639,"GB2-02":40.42563130728679,"GB2-03":43.72614449237642,"GB2-04":40.30938929732743,"GB2-05":32.39134514956389,"GB2-06":32.02843646706543,"GB2-07":28.49344424581399,"GB2-08":42.73491272887123},"none":{"GB2-01":20.546693371900755,"GB2-02":42.257179656924315,"GB2-03":35.43590826602859,"GB2-05":45.07392121046797,"GB2-06":57.00300757156055,"GB2-07":19.84816137868185,"GB2-08":28.327011696952535}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.396349492814025,"medium":34.951494791481025,"none":31.06148539406457},"reasoning_agg":{"highest":{"max":81.93050131891336,"mean":36.396349492814025,"min":0.0},"medium":{"max":43.72614449237642,"mean":34.951494791481025,"min":25.859550831358195},"none":{"max":57.00300757156055,"mean":31.06148539406457,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.334864098749456}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:f78f5f2f111ce853","codegen_cost_by_reasoning":{"highest":{"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":0.9722945000000001},"medium":{"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":0.6081093},"none":{"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":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.2715711},"historical-provider-setting-intensive":{"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":0.9722945000000001}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519749},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":37.609884305335356,"highest":38.56550816180745,"medium":31.472811601471097,"none":42.79133315272753},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":132,"finish_reasons":["stop"],"indexed_attempts":132,"output_token_observations":132,"reasoning_token_observations":89,"total_output_tokens":604751,"total_reasoning_output_tokens":229572,"total_visible_output_tokens":177334,"visible_token_observations":89},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.5-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":14,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.0625,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375},"intensive":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":13,"first_pass_rate":0.8125,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.0625}},"headline_games_all":{"GB2-01":{"attempts":6,"failed_attempts":1,"playable":38.1102346518309,"score":32.3049607448152},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":43.371734972319,"score":28.50238825971448},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":47.13937584311534,"score":38.27088735214096},"GB2-04":{"attempts":6,"playable":43.31342543056021,"score":43.31342543056021},"GB2-05":{"attempts":6,"playable":15.007926650120595,"score":15.007926650120595},"GB2-06":{"attempts":6,"playable":37.938862170133994,"score":37.938862170133994},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.55064952504604,"score":39.10840856058889},"GB2-08":{"attempts":6,"playable":33.446865199556804,"score":33.446865199556804}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":34.83164344209421,"score":17.415821721047106},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":45.31042120878015,"score":22.655210604390074},"GB2-03":{"attempts":2,"playable":47.969675817808685,"score":47.969675817808685},"GB2-04":{"attempts":2,"playable":40.194628217886006,"score":40.194628217886006},"GB2-05":{"attempts":2,"playable":18.813476131753553,"score":18.813476131753553},"GB2-06":{"attempts":2,"playable":43.03168786465784,"score":43.03168786465784},"GB2-07":{"attempts":2,"playable":45.01639096877774,"score":45.01639096877774},"GB2-08":{"attempts":2,"playable":33.356141642701395,"score":33.356141642701395}},"medium":{"GB2-01":{"attempts":2,"playable":41.61480579064591,"score":41.61480579064591},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.905659066846994,"score":21.952829533423497},"GB2-03":{"attempts":2,"playable":40.23752076569107,"score":40.23752076569107},"GB2-04":{"attempts":2,"playable":42.599844110809904,"score":42.599844110809904},"GB2-05":{"attempts":2,"playable":15.369151689676425,"score":15.369151689676425},"GB2-06":{"attempts":2,"playable":13.885309721919729,"score":13.885309721919729},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.653445786742857,"score":10.326722893371429},"GB2-08":{"attempts":2,"playable":33.51675587943592,"score":33.51675587943592}},"none":{"GB2-01":{"attempts":2,"playable":37.88425472275257,"score":37.88425472275257},"GB2-02":{"attempts":2,"playable":40.899124641329855,"score":40.899124641329855},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":53.21093094584627,"score":26.605465472923136},"GB2-04":{"attempts":2,"playable":47.14580396298469,"score":47.14580396298469},"GB2-05":{"attempts":2,"playable":10.841152128931814,"score":10.841152128931814},"GB2-06":{"attempts":2,"playable":56.89958892382441,"score":56.89958892382441},"GB2-07":{"attempts":2,"playable":61.982111819617515,"score":61.982111819617515},"GB2-08":{"attempts":2,"playable":33.4676980765331,"score":33.4676980765331}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-15T06:33:40Z","match_totals_all":{"draws":9238,"losses":15256,"wins":7450},"match_totals_tracks":{"highest":{"draws":2344,"losses":4769,"wins":2648},"medium":{"draws":3367,"losses":5485,"wins":1651},"none":{"draws":3527,"losses":5002,"wins":3151}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":61.982111819617515,"mean":33.48671554595389,"min":10.326722893371429},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":48,"overall_ranking_status":"ranked","per_game":{"GB2-01":34.83164344209421,"GB2-02":45.31042120878015,"GB2-03":47.969675817808685,"GB2-04":40.194628217886006,"GB2-05":18.813476131753553,"GB2-06":43.03168786465784,"GB2-07":45.01639096877774,"GB2-08":33.356141642701395},"per_game_all":{"GB2-01":38.1102346518309,"GB2-02":43.371734972319,"GB2-03":47.13937584311534,"GB2-04":43.31342543056021,"GB2-05":15.007926650120595,"GB2-06":37.938862170133994,"GB2-07":42.55064952504604,"GB2-08":33.446865199556804},"per_game_match_totals_all":{"GB2-01":{"draws":757,"losses":2058,"wins":1157},"GB2-02":{"draws":2297,"losses":432,"wins":60},"GB2-03":{"draws":968,"losses":1565,"wins":1204},"GB2-04":{"draws":2684,"losses":1056,"wins":535},"GB2-05":{"draws":0,"losses":3869,"wins":771},"GB2-06":{"draws":88,"losses":2832,"wins":1736},"GB2-07":{"draws":0,"losses":2111,"wins":1828},"GB2-08":{"draws":2444,"losses":1333,"wins":159}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":160,"losses":391,"wins":181},"GB2-02":{"draws":519,"losses":122,"wins":49},"GB2-03":{"draws":255,"losses":654,"wins":567},"GB2-04":{"draws":871,"losses":405,"wins":144},"GB2-05":{"draws":0,"losses":1213,"wins":319},"GB2-06":{"draws":60,"losses":838,"wins":644},"GB2-07":{"draws":0,"losses":884,"wins":713},"GB2-08":{"draws":479,"losses":262,"wins":31}},"medium":{"GB2-01":{"draws":290,"losses":843,"wins":533},"GB2-02":{"draws":638,"losses":94,"wins":5},"GB2-03":{"draws":534,"losses":598,"wins":309},"GB2-04":{"draws":923,"losses":274,"wins":112},"GB2-05":{"draws":0,"losses":1288,"wins":264},"GB2-06":{"draws":10,"losses":1266,"wins":204},"GB2-07":{"draws":0,"losses":594,"wins":160},"GB2-08":{"draws":972,"losses":528,"wins":64}},"none":{"GB2-01":{"draws":307,"losses":824,"wins":443},"GB2-02":{"draws":1140,"losses":216,"wins":6},"GB2-03":{"draws":179,"losses":313,"wins":328},"GB2-04":{"draws":890,"losses":377,"wins":279},"GB2-05":{"draws":0,"losses":1368,"wins":188},"GB2-06":{"draws":18,"losses":728,"wins":888},"GB2-07":{"draws":0,"losses":633,"wins":955},"GB2-08":{"draws":993,"losses":543,"wins":64}}},"per_game_raw_elo_all":{"GB2-01":1367.0582999998903,"GB2-02":1424.7170165475727,"GB2-03":1414.6311016119346,"GB2-04":1426.2279483034145,"GB2-05":914.222112702853,"GB2-06":1265.416972617212,"GB2-07":1351.1394238265184,"GB2-08":1255.4368139022529},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1334.5184459797126,"GB2-02":1439.7194270252126,"GB2-03":1422.5272338557947,"GB2-04":1401.9188410392544,"GB2-05":996.26052215179,"GB2-06":1353.886136331842,"GB2-07":1387.1917954388377,"GB2-08":1254.5142867085124},"medium":{"GB2-01":1401.8387712143108,"GB2-02":1428.8880617185036,"GB2-03":1354.1240191682568,"GB2-04":1420.7890257596343,"GB2-05":927.0905722806588,"GB2-06":878.9180861404927,"GB2-07":1053.6268377705228,"GB2-08":1256.1474182167558},"none":{"GB2-01":1364.817682805648,"GB2-02":1405.5435608990017,"GB2-03":1467.2420518117526,"GB2-04":1455.9759781113548,"GB2-05":819.3152436761102,"GB2-06":1563.446695379301,"GB2-07":1612.5996382701946,"GB2-08":1255.6487367814907}},"per_game_tracks":{"highest":{"GB2-01":34.83164344209421,"GB2-02":45.31042120878015,"GB2-03":47.969675817808685,"GB2-04":40.194628217886006,"GB2-05":18.813476131753553,"GB2-06":43.03168786465784,"GB2-07":45.01639096877774,"GB2-08":33.356141642701395},"medium":{"GB2-01":41.61480579064591,"GB2-02":43.905659066846994,"GB2-03":40.23752076569107,"GB2-04":42.599844110809904,"GB2-05":15.369151689676425,"GB2-06":13.885309721919729,"GB2-07":20.653445786742857,"GB2-08":33.51675587943592},"none":{"GB2-01":37.88425472275257,"GB2-02":40.899124641329855,"GB2-03":53.21093094584627,"GB2-04":47.14580396298469,"GB2-05":10.841152128931814,"GB2-06":56.89958892382441,"GB2-07":61.982111819617515,"GB2-08":33.4676980765331}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.556629121127806,"medium":27.437867548121734,"none":39.465649968612134},"reasoning_agg":{"highest":{"max":47.969675817808685,"mean":33.556629121127806,"min":17.415821721047106},"medium":{"max":42.599844110809904,"mean":27.437867548121734,"min":10.326722893371429},"none":{"max":61.982111819617515,"mean":39.465649968612134,"min":10.841152128931814}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":12.0277824204904}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:ac228f4ce33a4444","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":19,"cell_count":24,"cost_basis_counts":{"provider_reported":42},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":42},"recorded_attempt_count":42,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":42,"max_ms":537122,"mean_ms":137533.5,"min_ms":13879,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":537122,"mean_ms":335588.75,"min_ms":221492,"run_count":8},"medium":{"attempt_count":11,"max_ms":84351,"mean_ms":41299.125,"min_ms":13879,"run_count":8},"none":{"attempt_count":16,"max_ms":68645,"mean_ms":35712.625,"min_ms":19448,"run_count":8}},"codegen_output_tokens":{"attempt_count":42,"output_max":39424,"output_mean":14219.625,"output_min":2263,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":39424,"output_mean":32529.75,"output_min":24807,"run_count":8},"medium":{"attempt_count":11,"output_max":9849,"output_mean":5340.25,"output_min":2263,"run_count":8},"none":{"attempt_count":16,"output_max":8167,"output_mean":4788.875,"output_min":2672,"run_count":8}},"display_name":"Space Bunny Alpha","economics":{"all":40.415596089655104,"highest":47.773371829627926,"medium":40.971458831241364,"none":37.760251968555174},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":42,"effective_max_output_tokens":[262144],"finish_reason_observations":42,"finish_reasons":["stop"],"indexed_attempts":42,"output_token_observations":42,"provider_post_attempt_observations":42,"provider_post_attempts":42,"reasoning_token_observations":42,"reconciliation_get_attempt_observations":42,"requested_max_output_token_observations":42,"requested_max_output_tokens":[262144],"total_output_tokens":341271,"total_visible_output_tokens":341271,"visible_token_observations":42},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"stealth/space-bunny-alpha","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-08"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-06"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":56.383964828464755,"score":37.58930988564317},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.183117318948405,"score":28.12207821263227},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":41.364628701323504,"score":27.57641913421567},"GB2-04":{"attempts":3,"playable":41.19232732307699,"score":41.19232732307699},"GB2-05":{"attempts":3,"playable":34.14681675438819,"score":34.14681675438819},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":49.353894068985795,"score":32.90259604599053},"GB2-07":{"attempts":3,"playable":45.90764419150014,"score":45.90764419150014},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":28.845189982723635,"score":19.23012665514909}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.93451066466446,"score":63.93451066466446},"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":38.7866730807556,"score":38.7866730807556},"GB2-05":{"attempts":1,"playable":45.406713782694574,"score":45.406713782694574},"GB2-06":{"attempts":1,"playable":40.336955748131025,"score":40.336955748131025},"GB2-07":{"attempts":1,"playable":74.58299269512445,"score":74.58299269512445},"GB2-08":{"attempts":1,"playable":23.592385006397414,"score":23.592385006397414}},"medium":{"GB2-01":{"attempts":1,"playable":48.83341899226506,"score":48.83341899226506},"GB2-02":{"attempts":1,"playable":42.707293595846515,"score":42.707293595846515},"GB2-03":{"attempts":1,"playable":45.95715860201683,"score":45.95715860201683},"GB2-04":{"attempts":1,"playable":41.494011759920376,"score":41.494011759920376},"GB2-05":{"attempts":1,"playable":13.09109284174289,"score":13.09109284174289},"GB2-06":{"attempts":1,"playable":58.370832389840565,"score":58.370832389840565},"GB2-07":{"attempts":1,"playable":36.346403637057314,"score":36.346403637057314},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.65894104205029,"score":41.65894104205029},"GB2-03":{"attempts":1,"playable":36.772098800630175,"score":36.772098800630175},"GB2-04":{"attempts":1,"playable":43.29629712855498,"score":43.29629712855498},"GB2-05":{"attempts":1,"playable":43.942643638727105,"score":43.942643638727105},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.793536242318638,"score":26.793536242318638},"GB2-08":{"attempts":1,"playable":34.097994959049856,"score":34.097994959049856}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-13T23:03:06Z","match_totals_all":{"draws":2507,"losses":3966,"wins":2321},"match_totals_tracks":{"highest":{"draws":635,"losses":1181,"wins":1000},"medium":{"draws":837,"losses":1534,"wins":837},"none":{"draws":1035,"losses":1251,"wins":484}},"model_slug":"stealth-space-bunny-alpha","overall":{"max":74.58299269512445,"mean":33.333414775324506,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.93451066466446,"GB2-04":38.7866730807556,"GB2-05":45.406713782694574,"GB2-06":40.336955748131025,"GB2-07":74.58299269512445,"GB2-08":23.592385006397414},"per_game_all":{"GB2-04":41.19232732307699,"GB2-05":34.14681675438819,"GB2-07":45.90764419150014},"per_game_match_totals_all":{"GB2-01":{"draws":223,"losses":305,"wins":408},"GB2-02":{"draws":689,"losses":166,"wins":9},"GB2-03":{"draws":212,"losses":446,"wins":234},"GB2-04":{"draws":873,"losses":370,"wins":101},"GB2-05":{"draws":0,"losses":959,"wins":493},"GB2-06":{"draws":14,"losses":473,"wins":425},"GB2-07":{"draws":0,"losses":794,"wins":628},"GB2-08":{"draws":496,"losses":453,"wins":23}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":141,"losses":102,"wins":225},"GB2-04":{"draws":271,"losses":144,"wins":33},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":8,"losses":279,"wins":169},"GB2-07":{"draws":0,"losses":123,"wins":351},"GB2-08":{"draws":215,"losses":268,"wins":3}},"medium":{"GB2-01":{"draws":82,"losses":203,"wins":183},"GB2-02":{"draws":348,"losses":79,"wins":5},"GB2-03":{"draws":96,"losses":208,"wins":142},"GB2-04":{"draws":305,"losses":115,"wins":28},"GB2-05":{"draws":0,"losses":422,"wins":62},"GB2-06":{"draws":6,"losses":194,"wins":256},"GB2-07":{"draws":0,"losses":313,"wins":161}},"none":{"GB2-02":{"draws":341,"losses":87,"wins":4},"GB2-03":{"draws":116,"losses":238,"wins":92},"GB2-04":{"draws":297,"losses":111,"wins":40},"GB2-05":{"draws":0,"losses":272,"wins":212},"GB2-07":{"draws":0,"losses":358,"wins":116},"GB2-08":{"draws":281,"losses":185,"wins":20}}},"per_game_raw_elo_all":{"GB2-04":1409.7513394325586,"GB2-05":1215.4165298244968,"GB2-07":1407.1866204005498},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1620.0706612514805,"GB2-04":1390.8661521765669,"GB2-05":1394.0939966722483,"GB2-06":1301.6974872751948,"GB2-07":1794.8507592540393,"GB2-08":1149.9893605628301},"medium":{"GB2-01":1471.1960511426253,"GB2-02":1419.6197961664582,"GB2-03":1403.668215090791,"GB2-04":1412.1778549706899,"GB2-05":876.6121633322336,"GB2-06":1587.3311774900449,"GB2-07":1278.0013368070736},"none":{"GB2-02":1411.4806097375767,"GB2-03":1323.682432044279,"GB2-04":1426.2100111504192,"GB2-05":1375.5434294690087,"GB2-07":1148.7077651405361,"GB2-08":1262.046078302914}},"per_game_tracks":{"highest":{"GB2-01":63.93451066466446,"GB2-04":38.7866730807556,"GB2-05":45.406713782694574,"GB2-06":40.336955748131025,"GB2-07":74.58299269512445,"GB2-08":23.592385006397414},"medium":{"GB2-01":48.83341899226506,"GB2-02":42.707293595846515,"GB2-03":45.95715860201683,"GB2-04":41.494011759920376,"GB2-05":13.09109284174289,"GB2-06":58.370832389840565,"GB2-07":36.346403637057314},"none":{"GB2-02":41.65894104205029,"GB2-03":36.772098800630175,"GB2-04":43.29629712855498,"GB2-05":43.942643638727105,"GB2-07":26.793536242318638,"GB2-08":34.097994959049856}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.83002887222094,"medium":35.85002647733619,"none":28.320188976416386},"reasoning_agg":{"highest":{"max":74.58299269512445,"mean":35.83002887222094,"min":0.0},"medium":{"max":58.370832389840565,"mean":35.85002647733619,"min":0.0},"none":{"max":43.942643638727105,"mean":28.320188976416386,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":7.5298375009198075}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:bafcffdaa4610350","codegen_cost_by_reasoning":{"highest":{"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":0.38761484999999996},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373185999999998},"codegen_latency_ms":{"attempt_count":43,"max_ms":599272,"mean_ms":125847.07142857143,"min_ms":18961,"run_count":28},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":599272,"mean_ms":283663.1,"min_ms":69866,"run_count":10},"medium":{"attempt_count":15,"max_ms":68712,"mean_ms":42566.11111111111,"min_ms":22862,"run_count":9},"none":{"attempt_count":14,"max_ms":63236,"mean_ms":33776.88888888889,"min_ms":18961,"run_count":9}},"codegen_output_tokens":{"attempt_count":43,"output_max":49133,"output_mean":11683.67857142857,"output_min":894,"run_count":28},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":49133,"output_mean":28182.1,"output_min":11882,"run_count":10},"medium":{"attempt_count":15,"output_max":4066,"output_mean":2679.6666666666665,"output_min":1736,"run_count":9},"none":{"attempt_count":14,"output_max":5147,"output_mean":2356.1111111111113,"output_min":894,"run_count":9}},"display_name":"Inkling Small","economics":{"all":34.24621269397148,"highest":39.16678416446703,"medium":32.13391032040533,"none":31.437943597042054},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":43,"finish_reasons":["stop"],"indexed_attempts":43,"output_token_observations":43,"provider_post_attempt_observations":43,"provider_post_attempts":43,"reasoning_token_observations":43,"reconciliation_get_attempt_observations":43,"reconciliation_get_attempts":203,"total_output_tokens":327143,"total_reasoning_output_tokens":261125,"total_visible_output_tokens":66018,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling-small","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.4444444444444444},"baseline":{"admitted_plugins":8,"evaluated_cells":9,"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.3333333333333333},"intensive":{"admitted_plugins":8,"evaluated_cells":10,"failed_game_aliases":["GB2-04"],"first_pass_admitted":6,"first_pass_rate":0.6666666666666666,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1,"performance_rejections":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.1111111111111111,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-06"],"performance_rejections":1,"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":21.656403004797625,"score":21.656403004797625},"GB2-02":{"attempts":3,"playable":41.98811996831373,"score":41.98811996831373},"GB2-03":{"attempts":3,"playable":47.19400180116167,"score":47.19400180116167},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":45.10598661641392,"score":37.90741574751981},"GB2-05":{"attempts":3,"playable":18.226460467277544,"score":18.226460467277544},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.917328074869364,"score":23.98375828157737},"GB2-07":{"attempts":3,"playable":35.38492351297926,"score":35.38492351297926},"GB2-08":{"attempts":3,"playable":34.496478105958666,"score":34.496478105958666}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.9757366194435,"score":32.9757366194435},"GB2-02":{"attempts":1,"playable":42.18006169262212,"score":42.18006169262212},"GB2-03":{"attempts":1,"playable":46.85759203265854,"score":46.85759203265854},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.19142521336464,"score":21.59571260668232},"GB2-05":{"attempts":1,"playable":40.58304517802721,"score":40.58304517802721},"GB2-06":{"attempts":1,"playable":54.15056546485613,"score":54.15056546485613},"GB2-07":{"attempts":1,"playable":18.934943067474368,"score":18.934943067474368},"GB2-08":{"attempts":1,"playable":34.46090404728977,"score":34.46090404728977}},"medium":{"GB2-01":{"attempts":1,"playable":9.534249274008635,"score":9.534249274008635},"GB2-02":{"attempts":1,"playable":41.8361817988177,"score":41.8361817988177},"GB2-03":{"attempts":1,"playable":40.14798382243654,"score":40.14798382243654},"GB2-04":{"attempts":1,"playable":46.60682009330942,"score":46.60682009330942},"GB2-05":{"attempts":1,"playable":9.537918709575207,"score":9.537918709575207},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":18.32741945850136,"score":9.16370972925068},"GB2-07":{"attempts":1,"playable":55.21638184742195,"score":55.21638184742195},"GB2-08":{"attempts":1,"playable":35.86432755917181,"score":35.86432755917181}},"none":{"GB2-01":{"attempts":1,"playable":22.459223120940727,"score":22.459223120940727},"GB2-02":{"attempts":1,"playable":41.9481164135014,"score":41.9481164135014},"GB2-03":{"attempts":1,"playable":54.57642954838992,"score":54.57642954838992},"GB2-04":{"attempts":1,"playable":45.51971454256769,"score":45.51971454256769},"GB2-05":{"attempts":1,"playable":4.558417514230206,"score":4.558417514230206},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.273999301250594,"score":8.636999650625297},"GB2-07":{"attempts":1,"playable":32.003445624041454,"score":32.003445624041454},"GB2-08":{"attempts":1,"playable":33.16420271141441,"score":33.16420271141441}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-15T06:06:26Z","match_totals_all":{"draws":5049,"losses":7714,"wins":2821},"match_totals_tracks":{"highest":{"draws":1696,"losses":2378,"wins":1217},"medium":{"draws":1598,"losses":2753,"wins":883},"none":{"draws":1755,"losses":2583,"wins":721}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":55.21638184742195,"mean":32.60469511119821,"min":4.558417514230206},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":50,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.9757366194435,"GB2-02":42.18006169262212,"GB2-03":46.85759203265854,"GB2-04":43.19142521336464,"GB2-05":40.58304517802721,"GB2-06":54.15056546485613,"GB2-07":18.934943067474368,"GB2-08":34.46090404728977},"per_game_all":{"GB2-01":21.656403004797625,"GB2-02":41.98811996831373,"GB2-03":47.19400180116167,"GB2-04":45.10598661641392,"GB2-05":18.226460467277544,"GB2-06":29.917328074869364,"GB2-07":35.38492351297926,"GB2-08":34.496478105958666},"per_game_match_totals_all":{"GB2-01":{"draws":356,"losses":1287,"wins":232},"GB2-02":{"draws":1523,"losses":298,"wins":3},"GB2-03":{"draws":626,"losses":711,"wins":568},"GB2-04":{"draws":1252,"losses":487,"wins":243},"GB2-05":{"draws":0,"losses":1585,"wins":384},"GB2-06":{"draws":24,"losses":1345,"wins":587},"GB2-07":{"draws":0,"losses":1284,"wins":711},"GB2-08":{"draws":1268,"losses":717,"wins":93}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":186,"losses":318,"wins":114},"GB2-02":{"draws":525,"losses":111,"wins":0},"GB2-03":{"draws":138,"losses":290,"wins":224},"GB2-04":{"draws":406,"losses":182,"wins":75},"GB2-05":{"draws":0,"losses":385,"wins":292},"GB2-06":{"draws":19,"losses":323,"wins":366},"GB2-07":{"draws":0,"losses":518,"wins":118},"GB2-08":{"draws":422,"losses":251,"wins":28}},"medium":{"GB2-01":{"draws":81,"losses":531,"wins":18},"GB2-02":{"draws":494,"losses":86,"wins":0},"GB2-03":{"draws":192,"losses":285,"wins":152},"GB2-04":{"draws":398,"losses":167,"wins":105},"GB2-05":{"draws":0,"losses":582,"wins":64},"GB2-06":{"draws":3,"losses":507,"wins":113},"GB2-07":{"draws":0,"losses":338,"wins":387},"GB2-08":{"draws":430,"losses":257,"wins":44}},"none":{"GB2-01":{"draws":89,"losses":438,"wins":100},"GB2-02":{"draws":504,"losses":101,"wins":3},"GB2-03":{"draws":296,"losses":136,"wins":192},"GB2-04":{"draws":448,"losses":138,"wins":63},"GB2-05":{"draws":0,"losses":618,"wins":28},"GB2-06":{"draws":2,"losses":515,"wins":108},"GB2-07":{"draws":0,"losses":428,"wins":206},"GB2-08":{"draws":416,"losses":209,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1164.31838299801,"GB2-02":1414.0396151909656,"GB2-03":1414.7774362976918,"GB2-04":1440.2101932173725,"GB2-05":907.2402142117513,"GB2-06":1139.8006555456602,"GB2-07":1253.6122100860553,"GB2-08":1266.0549170786232},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1315.3741854791617,"GB2-02":1415.5306596499445,"GB2-03":1411.46671218226,"GB2-04":1425.3959759713032,"GB2-05":1332.3193316413137,"GB2-06":1517.8570486813849,"GB2-07":1024.143659374752,"GB2-08":1265.720699991161},"medium":{"GB2-01":981.8587513514066,"GB2-02":1412.8590804862106,"GB2-03":1353.3454158338136,"GB2-04":1451.8144832915204,"GB2-05":785.8740623999518,"GB2-06":959.901084160031,"GB2-07":1515.608167380841,"GB2-08":1279.8833878507885},"none":{"GB2-01":1195.7222121634625,"GB2-02":1413.7291054367415,"GB2-03":1479.5201808770023,"GB2-04":1443.4201203892933,"GB2-05":603.5272485939884,"GB2-06":941.6438337955649,"GB2-07":1221.0848035025729,"GB2-08":1252.5606633939199}},"per_game_tracks":{"highest":{"GB2-01":32.9757366194435,"GB2-02":42.18006169262212,"GB2-03":46.85759203265854,"GB2-04":43.19142521336464,"GB2-05":40.58304517802721,"GB2-06":54.15056546485613,"GB2-07":18.934943067474368,"GB2-08":34.46090404728977},"medium":{"GB2-01":9.534249274008635,"GB2-02":41.8361817988177,"GB2-03":40.14798382243654,"GB2-04":46.60682009330942,"GB2-05":9.537918709575207,"GB2-06":18.32741945850136,"GB2-07":55.21638184742195,"GB2-08":35.86432755917181},"none":{"GB2-01":22.459223120940727,"GB2-02":41.9481164135014,"GB2-03":54.57642954838992,"GB2-04":45.51971454256769,"GB2-05":4.558417514230206,"GB2-06":17.273999301250594,"GB2-07":32.003445624041454,"GB2-08":33.16420271141441}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":36.46732008863175,"medium":30.988446604248992,"none":30.35831864071389},"reasoning_agg":{"highest":{"max":54.15056546485613,"mean":36.46732008863175,"min":18.934943067474368},"medium":{"max":55.21638184742195,"mean":30.988446604248992,"min":9.16370972925068},"none":{"max":54.57642954838992,"mean":30.35831864071389,"min":4.558417514230206}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.109001447917862}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:77cc296015f7d9bb","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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":0.058501660000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":34.96969582236659,"highest":41.084023781855116,"medium":31.584574387076444,"none":32.049909861586265},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"visible_token_observations":34},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-glimmer-30b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":30.308955020951597,"score":30.308955020951597},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.733299746202306,"score":28.488866497468205},"GB2-03":{"attempts":3,"playable":39.88247239755023,"score":39.88247239755023},"GB2-04":{"attempts":3,"playable":45.8006113826609,"score":45.8006113826609},"GB2-05":{"attempts":3,"playable":23.035738044619308,"score":23.035738044619308},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.643096444111773,"score":5.881032148037257},"GB2-07":{"attempts":3,"playable":37.189345092974456,"score":37.189345092974456},"GB2-08":{"attempts":3,"playable":33.60105299544304,"score":33.60105299544304}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":30.983768741281764,"score":30.983768741281764},"GB2-02":{"attempts":1,"playable":42.7052485497491,"score":42.7052485497491},"GB2-03":{"attempts":1,"playable":37.67116258039527,"score":37.67116258039527},"GB2-04":{"attempts":1,"playable":48.73552925015593,"score":48.73552925015593},"GB2-05":{"attempts":1,"playable":46.673094048105426,"score":46.673094048105426},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":47.16625287736929,"score":47.16625287736929},"GB2-08":{"attempts":1,"playable":33.653110425929036,"score":33.653110425929036}},"medium":{"GB2-01":{"attempts":1,"playable":22.896491785202784,"score":22.896491785202784},"GB2-02":{"attempts":1,"playable":42.761350942655504,"score":42.761350942655504},"GB2-03":{"attempts":1,"playable":38.9033887691057,"score":38.9033887691057},"GB2-04":{"attempts":1,"playable":44.923846345547915,"score":44.923846345547915},"GB2-05":{"attempts":1,"playable":15.352345757188553,"score":15.352345757188553},"GB2-06":{"attempts":1,"playable":17.643096444111773,"score":17.643096444111773},"GB2-07":{"attempts":1,"playable":36.6159463878844,"score":36.6159463878844},"GB2-08":{"attempts":1,"playable":33.58012866491494,"score":33.58012866491494}},"none":{"GB2-01":{"attempts":1,"playable":37.04660453637024,"score":37.04660453637024},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":43.07286584314972,"score":43.07286584314972},"GB2-04":{"attempts":1,"playable":43.742458552278876,"score":43.742458552278876},"GB2-05":{"attempts":1,"playable":7.081774328563944,"score":7.081774328563944},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":27.78583601366967,"score":27.78583601366967},"GB2-08":{"attempts":1,"playable":33.56991989548515,"score":33.56991989548515}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-10-13T22:51:01Z","match_totals_all":{"draws":4526,"losses":6274,"wins":2431},"match_totals_tracks":{"highest":{"draws":1672,"losses":1783,"wins":1046},"medium":{"draws":1644,"losses":2528,"wins":762},"none":{"draws":1210,"losses":1963,"wins":623}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":48.73552925015593,"mean":30.523509197463124,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":30.983768741281764,"GB2-02":42.7052485497491,"GB2-03":37.67116258039527,"GB2-04":48.73552925015593,"GB2-05":46.673094048105426,"GB2-07":47.16625287736929,"GB2-08":33.653110425929036},"per_game_all":{"GB2-01":30.308955020951597,"GB2-03":39.88247239755023,"GB2-04":45.8006113826609,"GB2-05":23.035738044619308,"GB2-07":37.189345092974456,"GB2-08":33.60105299544304},"per_game_match_totals_all":{"GB2-01":{"draws":451,"losses":1060,"wins":356},"GB2-02":{"draws":996,"losses":158,"wins":8},"GB2-03":{"draws":614,"losses":815,"wins":425},"GB2-04":{"draws":1256,"losses":423,"wins":231},"GB2-05":{"draws":0,"losses":1507,"wins":481},"GB2-06":{"draws":3,"losses":508,"wins":109},"GB2-07":{"draws":0,"losses":1185,"wins":737},"GB2-08":{"draws":1206,"losses":618,"wins":84}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":182,"losses":326,"wins":107},"GB2-02":{"draws":491,"losses":81,"wins":6},"GB2-03":{"draws":223,"losses":277,"wins":118},"GB2-04":{"draws":380,"losses":156,"wins":122},"GB2-05":{"draws":0,"losses":387,"wins":333},"GB2-07":{"draws":0,"losses":348,"wins":328},"GB2-08":{"draws":396,"losses":208,"wins":32}},"medium":{"GB2-01":{"draws":134,"losses":404,"wins":78},"GB2-02":{"draws":505,"losses":77,"wins":2},"GB2-03":{"draws":176,"losses":293,"wins":149},"GB2-04":{"draws":423,"losses":119,"wins":60},"GB2-05":{"draws":0,"losses":531,"wins":103},"GB2-06":{"draws":3,"losses":508,"wins":109},"GB2-07":{"draws":0,"losses":389,"wins":235},"GB2-08":{"draws":403,"losses":207,"wins":26}},"none":{"GB2-01":{"draws":135,"losses":330,"wins":171},"GB2-03":{"draws":215,"losses":245,"wins":158},"GB2-04":{"draws":453,"losses":148,"wins":49},"GB2-05":{"draws":0,"losses":589,"wins":45},"GB2-07":{"draws":0,"losses":448,"wins":174},"GB2-08":{"draws":407,"losses":203,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1284.1564450095545,"GB2-03":1350.9448597885635,"GB2-04":1445.5795802365192,"GB2-05":1015.1091282485203,"GB2-07":1286.1364378880046,"GB2-08":1257.0039825700126},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1294.336121163577,"GB2-02":1419.6039501065045,"GB2-03":1331.6379616588795,"GB2-04":1468.2532293455622,"GB2-05":1410.0490392528498,"GB2-07":1413.9956778933652,"GB2-08":1257.5328023984364},"medium":{"GB2-01":1201.2397262071272,"GB2-02":1420.0386196522961,"GB2-03":1342.4710472355337,"GB2-04":1438.8150990257723,"GB2-05":926.7447579539746,"GB2-06":948.0947574327216,"GB2-07":1281.4639824654523,"GB2-08":1256.7914357523268},"none":{"GB2-01":1356.8934876579594,"GB2-03":1378.7255704712775,"GB2-04":1429.6704123382237,"GB2-05":708.5335875387362,"GB2-07":1162.9496533051965,"GB2-08":1256.6877095592747}},"per_game_tracks":{"highest":{"GB2-01":30.983768741281764,"GB2-02":42.7052485497491,"GB2-03":37.67116258039527,"GB2-04":48.73552925015593,"GB2-05":46.673094048105426,"GB2-07":47.16625287736929,"GB2-08":33.653110425929036},"medium":{"GB2-01":22.896491785202784,"GB2-02":42.761350942655504,"GB2-03":38.9033887691057,"GB2-04":44.923846345547915,"GB2-05":15.352345757188553,"GB2-06":17.643096444111773,"GB2-07":36.6159463878844,"GB2-08":33.58012866491494},"none":{"GB2-01":37.04660453637024,"GB2-03":43.07286584314972,"GB2-04":43.742458552278876,"GB2-05":7.081774328563944,"GB2-07":27.78583601366967,"GB2-08":33.56991989548515}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.948520809123224,"medium":31.584574387076444,"none":24.0374323961897},"reasoning_agg":{"highest":{"max":48.73552925015593,"mean":35.948520809123224,"min":0.0},"medium":{"max":44.923846345547915,"mean":31.584574387076444,"min":15.352345757188553},"none":{"max":43.742458552278876,"mean":24.0374323961897,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":11.911088412933523}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:62cf2f5dff5e8c28","codegen_cost_by_reasoning":{"highest":{"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":0.059539762},"medium":{"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":0.009085673},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.059539761999999996}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.015120192000000001,"mean":0.0032700552500000003,"median":0.0013951725,"min":0.00046744,"recorded_attempt_count":33,"run_count":24,"total":0.078481326},"codegen_latency_ms":{"attempt_count":33,"max_ms":1105859,"mean_ms":161415.45833333334,"min_ms":22661,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1105859,"mean_ms":300420.375,"min_ms":56038,"run_count":8},"medium":{"attempt_count":10,"max_ms":291211,"mean_ms":111417.625,"min_ms":22661,"run_count":8},"none":{"attempt_count":12,"max_ms":151123,"mean_ms":72408.375,"min_ms":26216,"run_count":8}},"codegen_output_tokens":{"attempt_count":33,"output_max":63626,"output_mean":9305.125,"output_min":1487,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":63626,"output_mean":22255.875,"output_min":2344,"run_count":8},"medium":{"attempt_count":10,"output_max":5420,"output_mean":3175.75,"output_min":2107,"run_count":8},"none":{"attempt_count":12,"output_max":4178,"output_mean":2483.75,"output_min":1487,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":34.40245728094722,"highest":39.49778172727559,"medium":31.430306327762075,"none":32.74286159088178},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":33,"finish_reasons":["stop"],"indexed_attempts":33,"output_token_observations":33,"provider_post_attempt_observations":33,"provider_post_attempts":33,"reasoning_token_observations":33,"reconciliation_get_attempt_observations":33,"reconciliation_get_attempts":158,"total_output_tokens":223323,"total_reasoning_output_tokens":139050,"total_visible_output_tokens":87482,"visible_token_observations":33},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"openai/gpt-oss-120b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":39.11790217328851,"score":26.078601448859008},"GB2-02":{"attempts":3,"playable":43.46015819951123,"score":43.46015819951123},"GB2-03":{"attempts":3,"playable":39.37679610493118,"score":39.37679610493118},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.223866676639176,"score":27.482577784426116},"GB2-05":{"attempts":3,"playable":30.22789939711274,"score":30.22789939711274},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":23.83184767212636,"score":15.887898448084242},"GB2-07":{"attempts":3,"playable":27.568181121561143,"score":27.568181121561143},"GB2-08":{"attempts":3,"playable":31.379251581619826,"score":31.379251581619826}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.699360504737875,"score":44.699360504737875},"GB2-03":{"attempts":1,"playable":45.44635205412105,"score":45.44635205412105},"GB2-04":{"attempts":1,"playable":43.10542795456368,"score":43.10542795456368},"GB2-05":{"attempts":1,"playable":59.23590436676645,"score":59.23590436676645},"GB2-06":{"attempts":1,"playable":21.939650298524583,"score":21.939650298524583},"GB2-07":{"attempts":1,"playable":32.87879025900604,"score":32.87879025900604},"GB2-08":{"attempts":1,"playable":29.178986653209442,"score":29.178986653209442}},"medium":{"GB2-01":{"attempts":1,"playable":36.7457673905092,"score":36.7457673905092},"GB2-02":{"attempts":1,"playable":42.46933011201489,"score":42.46933011201489},"GB2-03":{"attempts":1,"playable":35.92537078411879,"score":35.92537078411879},"GB2-04":{"attempts":1,"playable":39.342305398714664,"score":39.342305398714664},"GB2-05":{"attempts":1,"playable":15.513537310237849,"score":15.513537310237849},"GB2-06":{"attempts":1,"playable":25.72404504572814,"score":25.72404504572814},"GB2-07":{"attempts":1,"playable":21.120818904037307,"score":21.120818904037307},"GB2-08":{"attempts":1,"playable":34.60127567673579,"score":34.60127567673579}},"none":{"GB2-01":{"attempts":1,"playable":41.49003695606782,"score":41.49003695606782},"GB2-02":{"attempts":1,"playable":43.21178398178092,"score":43.21178398178092},"GB2-03":{"attempts":1,"playable":36.75866547655372,"score":36.75866547655372},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.934256514333928,"score":15.934256514333928},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.704934201640082,"score":28.704934201640082},"GB2-08":{"attempts":1,"playable":30.35749241491424,"score":30.35749241491424}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-10-15T06:42:03Z","match_totals_all":{"draws":4250,"losses":6454,"wins":2382},"match_totals_tracks":{"highest":{"draws":1434,"losses":1912,"wins":964},"medium":{"draws":1641,"losses":2605,"wins":758},"none":{"draws":1175,"losses":1937,"wins":660}},"model_slug":"openai-gpt-oss-120b","overall":{"max":59.23590436676645,"mean":30.182670510763188,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-02":44.699360504737875,"GB2-03":45.44635205412105,"GB2-04":43.10542795456368,"GB2-05":59.23590436676645,"GB2-06":21.939650298524583,"GB2-07":32.87879025900604,"GB2-08":29.178986653209442},"per_game_all":{"GB2-02":43.46015819951123,"GB2-03":39.37679610493118,"GB2-05":30.22789939711274,"GB2-07":27.568181121561143,"GB2-08":31.379251581619826},"per_game_match_totals_all":{"GB2-01":{"draws":239,"losses":702,"wins":403},"GB2-02":{"draws":1441,"losses":252,"wins":21},"GB2-03":{"draws":538,"losses":850,"wins":440},"GB2-04":{"draws":850,"losses":326,"wins":92},"GB2-05":{"draws":0,"losses":1346,"wins":566},"GB2-06":{"draws":14,"losses":910,"wins":284},"GB2-07":{"draws":0,"losses":1349,"wins":523},"GB2-08":{"draws":1168,"losses":719,"wins":53}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":458,"losses":98,"wins":16},"GB2-03":{"draws":185,"losses":243,"wins":182},"GB2-04":{"draws":400,"losses":135,"wins":59},"GB2-05":{"draws":0,"losses":289,"wins":355},"GB2-06":{"draws":3,"losses":469,"wins":132},"GB2-07":{"draws":0,"losses":414,"wins":212},"GB2-08":{"draws":388,"losses":264,"wins":8}},"medium":{"GB2-01":{"draws":122,"losses":341,"wins":177},"GB2-02":{"draws":484,"losses":82,"wins":4},"GB2-03":{"draws":189,"losses":301,"wins":120},"GB2-04":{"draws":450,"losses":191,"wins":33},"GB2-05":{"draws":0,"losses":530,"wins":104},"GB2-06":{"draws":11,"losses":441,"wins":152},"GB2-07":{"draws":0,"losses":493,"wins":131},"GB2-08":{"draws":385,"losses":226,"wins":37}},"none":{"GB2-01":{"draws":117,"losses":361,"wins":226},"GB2-02":{"draws":499,"losses":72,"wins":1},"GB2-03":{"draws":164,"losses":306,"wins":138},"GB2-05":{"draws":0,"losses":527,"wins":107},"GB2-07":{"draws":0,"losses":442,"wins":180},"GB2-08":{"draws":395,"losses":229,"wins":8}}},"per_game_raw_elo_all":{"GB2-02":1425.4373102364461,"GB2-03":1346.3185363109808,"GB2-05":1146.502495780331,"GB2-07":1156.6894574035143,"GB2-08":1234.05775290831},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1435.0111909155714,"GB2-03":1399.2488496351343,"GB2-04":1424.7282515881104,"GB2-05":1570.3808673011695,"GB2-06":1019.6206533508753,"GB2-07":1232.754181996012,"GB2-08":1211.344975246072},"medium":{"GB2-01":1353.8809611878955,"GB2-02":1417.775166945671,"GB2-03":1316.143563493279,"GB2-04":1395.2685811925908,"GB2-05":930.1560581220575,"GB2-06":1079.1519688798453,"GB2-07":1061.3858696657053,"GB2-08":1267.1404799114266},"none":{"GB2-01":1400.6346654249833,"GB2-02":1423.5255728480959,"GB2-03":1323.5631958045287,"GB2-05":938.9705619177662,"GB2-07":1175.928320548826,"GB2-08":1223.687803567431}},"per_game_tracks":{"highest":{"GB2-02":44.699360504737875,"GB2-03":45.44635205412105,"GB2-04":43.10542795456368,"GB2-05":59.23590436676645,"GB2-06":21.939650298524583,"GB2-07":32.87879025900604,"GB2-08":29.178986653209442},"medium":{"GB2-01":36.7457673905092,"GB2-02":42.46933011201489,"GB2-03":35.92537078411879,"GB2-04":39.342305398714664,"GB2-05":15.513537310237849,"GB2-06":25.72404504572814,"GB2-07":21.120818904037307,"GB2-08":34.60127567673579},"none":{"GB2-01":41.49003695606782,"GB2-02":43.21178398178092,"GB2-03":36.75866547655372,"GB2-05":15.934256514333928,"GB2-07":28.704934201640082,"GB2-08":30.35749241491424}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.56055901136614,"medium":31.430306327762075,"none":24.557146193161334},"reasoning_agg":{"highest":{"max":59.23590436676645,"mean":34.56055901136614,"min":0.0},"medium":{"max":42.46933011201489,"mean":31.430306327762075,"min":15.513537310237849},"none":{"max":43.21178398178092,"mean":24.557146193161334,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.003412818204804}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:7bf75f6ebf97c516","codegen_cost_by_reasoning":{"highest":{"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":0.50472065},"medium":{"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":0.31772779999999995},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.31772779999999995},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":0.50472065}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.13485595000000003,"mean":0.03294963020833334,"median":0.02851355,"min":0.0111232,"recorded_attempt_count":70,"run_count":34,"total":1.21164085},"codegen_latency_ms":{"attempt_count":56,"max_ms":622714,"mean_ms":85345.36,"min_ms":23604,"run_count":25},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":35,"max_ms":622714,"mean_ms":94544.1875,"min_ms":23604,"run_count":16},"medium":{"attempt_count":21,"max_ms":124322,"mean_ms":68991.88888888889,"min_ms":25332,"run_count":9}},"codegen_output_tokens":{"attempt_count":56,"output_max":17712,"output_mean":7782.6,"output_min":2728,"run_count":25},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":35,"output_max":17712,"output_mean":7793.4375,"output_min":2728,"run_count":16},"medium":{"attempt_count":21,"output_max":13873,"output_mean":7763.333333333333,"output_min":4525,"run_count":9}},"display_name":"Nemotron 3 Ultra 550B A55B","economics":{"all":38.38977795180257,"highest":34.25353492429692,"medium":39.38845659388538,"none":34.97989008068024},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":56,"finish_reasons":["error","length","stop"],"indexed_attempts":56,"output_token_observations":56,"total_output_tokens":194565},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3-ultra-550b-a55b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":7,"failed_game_aliases":["GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-05"],"infra_failures_excluded":2,"model_code_failure_rate":0.2857142857142857,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.7142857142857143},"baseline":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-02","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222},"intensive":{"admitted_plugins":9,"evaluated_cells":14,"failed_game_aliases":["GB2-01","GB2-03","GB2-07"],"first_pass_admitted":2,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.35714285714285715,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.419598004710046,"score":41.1128661524477},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.994120609309306,"score":27.329413739539536},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":30.731020792135144,"score":10.24367359737838},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.7612156438654,"score":27.8408104292436},"GB2-05":{"attempts":3,"playable":45.414863768384436,"score":45.414863768384436},"GB2-06":{"attempts":3,"playable":35.502759420925166,"score":35.502759420925166},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.371650339246768,"score":4.040724692665056},"GB2-08":{"attempts":4,"playable":34.2469764297725,"score":34.2469764297725}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.840391113574064,"score":12.920195556787032},"GB2-02":{"attempts":2,"playable":40.88210770019616,"score":40.88210770019616},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":40.930929849227695,"score":40.930929849227695},"GB2-05":{"attempts":2,"playable":30.095241090888436,"score":30.095241090888436},"GB2-06":{"attempts":1,"playable":33.57933881905365,"score":33.57933881905365},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":34.193200972841524,"score":34.193200972841524}},"medium":{"GB2-01":{"attempts":1,"playable":55.367530090772235,"score":55.367530090772235},"GB2-02":{"attempts":1,"playable":41.10613351842246,"score":41.10613351842246},"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":57.475927504546895,"score":57.475927504546895},"GB2-07":{"attempts":1,"playable":9.501047477496801,"score":9.501047477496801},"GB2-08":{"attempts":1,"playable":33.49164437818853,"score":33.49164437818853}},"none":{"GB2-01":{"attempts":1,"playable":55.05087280978383,"score":55.05087280978383},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":30.731020792135144,"score":30.731020792135144},"GB2-04":{"attempts":1,"playable":42.5915014385031,"score":42.5915014385031},"GB2-05":{"attempts":1,"playable":60.73448644588044,"score":60.73448644588044},"GB2-06":{"attempts":1,"playable":15.453011939174962,"score":15.453011939174962},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":5.242253200996736,"score":2.621126600498368},"GB2-08":{"attempts":1,"playable":35.056083938287465,"score":35.056083938287465}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-10-15T06:51:18Z","match_totals_all":{"draws":4211,"losses":5632,"wins":2312},"match_totals_tracks":{"highest":{"draws":2147,"losses":2285,"wins":759},"medium":{"draws":969,"losses":1310,"wins":681},"none":{"draws":1095,"losses":2037,"wins":872}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":60.73448644588044,"mean":27.496500532310833,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":53,"overall_ranking_status":"partial","per_game":{"GB2-01":25.840391113574064,"GB2-02":40.88210770019616,"GB2-04":40.930929849227695,"GB2-05":30.095241090888436,"GB2-06":33.57933881905365,"GB2-08":34.193200972841524},"per_game_all":{"GB2-01":45.419598004710046,"GB2-06":35.502759420925166,"GB2-08":34.2469764297725},"per_game_match_totals_all":{"GB2-01":{"draws":332,"losses":781,"wins":603},"GB2-02":{"draws":1300,"losses":306,"wins":16},"GB2-03":{"draws":225,"losses":252,"wins":47},"GB2-04":{"draws":814,"losses":254,"wins":66},"GB2-05":{"draws":0,"losses":1014,"wins":752},"GB2-06":{"draws":64,"losses":1066,"wins":591},"GB2-07":{"draws":0,"losses":1087,"wins":99},"GB2-08":{"draws":1476,"losses":872,"wins":138}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":123,"losses":354,"wins":93},"GB2-02":{"draws":841,"losses":209,"wins":14},"GB2-04":{"draws":411,"losses":134,"wins":27},"GB2-05":{"draws":0,"losses":785,"wins":389},"GB2-06":{"draws":35,"losses":365,"wins":171},"GB2-08":{"draws":737,"losses":438,"wins":65}},"medium":{"GB2-01":{"draws":117,"losses":206,"wins":257},"GB2-02":{"draws":459,"losses":97,"wins":2},"GB2-06":{"draws":24,"losses":239,"wins":323},"GB2-07":{"draws":0,"losses":541,"wins":63},"GB2-08":{"draws":369,"losses":227,"wins":36}},"none":{"GB2-01":{"draws":92,"losses":221,"wins":253},"GB2-03":{"draws":225,"losses":252,"wins":47},"GB2-04":{"draws":403,"losses":120,"wins":39},"GB2-05":{"draws":0,"losses":229,"wins":363},"GB2-06":{"draws":5,"losses":462,"wins":97},"GB2-07":{"draws":0,"losses":546,"wins":36},"GB2-08":{"draws":370,"losses":207,"wins":37}}},"per_game_raw_elo_all":{"GB2-01":1434.0010192593902,"GB2-06":1226.7173826039368,"GB2-08":1263.545855517588},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1236.8889689295902,"GB2-02":1405.4123495083968,"GB2-04":1407.7718498769007,"GB2-05":1178.9086076142805,"GB2-06":1198.9319546051586,"GB2-08":1263.0101282933679},"medium":{"GB2-01":1534.0972617510238,"GB2-02":1407.1741425539014,"GB2-06":1572.4010446266834,"GB2-07":818.3351652045661,"GB2-08":1255.892201095899},"none":{"GB2-01":1531.0168270975569,"GB2-03":1268.5365001948508,"GB2-04":1420.733916211565,"GB2-05":1590.657269987275,"GB2-06":908.8191485799686,"GB2-07":668.9707133493545,"GB2-08":1271.735237163497}},"per_game_tracks":{"highest":{"GB2-01":25.840391113574064,"GB2-02":40.88210770019616,"GB2-04":40.930929849227695,"GB2-05":30.095241090888436,"GB2-06":33.57933881905365,"GB2-08":34.193200972841524},"medium":{"GB2-01":55.367530090772235,"GB2-02":41.10613351842246,"GB2-06":57.475927504546895,"GB2-07":9.501047477496801,"GB2-08":33.49164437818853},"none":{"GB2-01":55.05087280978383,"GB2-03":30.731020792135144,"GB2-04":42.5915014385031,"GB2-05":60.73448644588044,"GB2-06":15.453011939174962,"GB2-07":5.242253200996736,"GB2-08":35.056083938287465}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.075126748624314,"medium":28.134611852775272,"none":30.279762995532913},"reasoning_agg":{"highest":{"max":40.930929849227695,"mean":24.075126748624314,"min":0.0},"medium":{"max":57.475927504546895,"mean":28.134611852775272,"min":0.0},"none":{"max":60.73448644588044,"mean":30.279762995532913,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.204636246908599}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:05dc2b52c65a627c","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":0.24908164},"none":{"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":0.5884539500000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":4.906380560000001}},"codegen_cost_usd":{"admitted_cell_count":32,"cell_count":24,"cost_basis_counts":{"provider_reported":112},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.261503015,"mean":0.09751241583333332,"median":0.042993304999999996,"min":0.01737051,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":112,"run_count":46,"total":5.7439161499999996},"codegen_latency_ms":{"attempt_count":112,"max_ms":712912,"mean_ms":234938.63043478262,"min_ms":16322,"run_count":46},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":60,"max_ms":712912,"mean_ms":442344.0909090909,"min_ms":125659,"run_count":22},"medium":{"attempt_count":13,"max_ms":52676,"mean_ms":32623.625,"min_ms":16322,"run_count":8},"none":{"attempt_count":39,"max_ms":118093,"mean_ms":50913.625,"min_ms":20774,"run_count":16}},"codegen_output_tokens":{"attempt_count":112,"output_max":80000,"output_mean":26608.978260869564,"output_min":1372,"run_count":46},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":60,"output_max":80000,"output_mean":50498.318181818184,"output_min":12059,"run_count":22},"medium":{"attempt_count":13,"output_max":9117,"output_mean":4863.875,"output_min":2632,"run_count":8},"none":{"attempt_count":39,"output_max":11313,"output_mean":4633.6875,"output_min":1372,"run_count":16}},"display_name":"Inkling","economics":{"all":31.33796404224155,"highest":39.19213363428479,"medium":25.379384894800385,"none":37.49819228244357},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":20,"effective_max_output_tokens":[262144],"finish_reason_observations":112,"finish_reasons":["length","stop"],"indexed_attempts":112,"output_token_observations":112,"provider_post_attempt_observations":20,"provider_post_attempts":23,"reasoning_token_observations":85,"reconciliation_get_attempt_observations":20,"reconciliation_get_attempts":33,"requested_max_output_token_observations":20,"requested_max_output_tokens":[262144],"total_output_tokens":1224013,"total_reasoning_output_tokens":793927,"total_visible_output_tokens":126602,"visible_token_observations":82},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"thinkingmachines","provider_model":"thinkingmachines/inkling","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-06","GB2-07","GB2-08"],"first_pass_admitted":7,"first_pass_rate":0.4375,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":1,"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125},"intensive":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":2,"infra_failures_excluded":1},"GB2-03":{"admitted":2,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"model_code_failures":1},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-07","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.3125}},"headline_games_all":{"GB2-01":{"attempts":5,"playable":24.75079617445121,"score":24.75079617445121},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":43.058126559755976,"score":21.38853791258677},"GB2-03":{"attempts":5,"playable":44.030408039983826,"score":44.030408039983826},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":42.49239053370218,"score":34.85843956395124},"GB2-05":{"attempts":5,"playable":18.832846667547624,"score":18.832846667547624},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":34.5041765307271,"score":21.30586311338337},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.417166307037363,"score":19.64401603315958},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":57.79965541138464,"score":26.366907080376887}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":38.816090609251454,"score":38.816090609251454},"GB2-02":{"attempts":2,"playable":42.214974356008675,"score":42.214974356008675},"GB2-03":{"attempts":2,"playable":47.671710595262084,"score":47.671710595262084},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":45.80370581850568,"score":22.90185290925284},"GB2-05":{"attempts":2,"playable":15.81049254803779,"score":15.81049254803779},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":52.15553829100356,"score":26.07776914550178},"GB2-07":{"attempts":2,"playable":28.46242519671702,"score":28.46242519671702},"GB2-08":{"attempts":2,"playable":42.60213165949203,"score":42.60213165949203}},"medium":{"GB2-01":{"attempts":1,"playable":17.12525138519513,"score":17.12525138519513},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.42345530092635,"score":36.42345530092635},"GB2-04":{"attempts":1,"playable":41.15584698047724,"score":41.15584698047724},"GB2-05":{"attempts":1,"playable":14.098934532956322,"score":14.098934532956322},"GB2-06":{"attempts":1,"playable":24.322649088118915,"score":24.322649088118915},"GB2-07":{"attempts":1,"playable":19.15017208112837,"score":19.15017208112837},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":18.31104652890705,"score":18.31104652890705},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.901278763503285,"score":21.950639381751643},"GB2-03":{"attempts":2,"playable":47.99605822376304,"score":47.99605822376304},"GB2-04":{"attempts":2,"playable":40.51761880212363,"score":40.51761880212363},"GB2-05":{"attempts":2,"playable":26.589112921648756,"score":26.589112921648756},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.034342213058828,"score":13.517171106529414},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":22.63890164326669,"score":11.319450821633344},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.99717916327725,"score":36.498589581638626}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-10-15T06:55:39Z","match_totals_all":{"draws":5266,"losses":9794,"wins":3972},"match_totals_tracks":{"highest":{"draws":2687,"losses":4514,"wins":2017},"medium":{"draws":624,"losses":1811,"wins":341},"none":{"draws":1955,"losses":3469,"wins":1614}},"model_slug":"thinkingmachines-inkling","overall":{"max":47.99605822376304,"mean":26.397226823180063,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":38.816090609251454,"GB2-02":42.214974356008675,"GB2-03":47.671710595262084,"GB2-04":45.80370581850568,"GB2-05":15.81049254803779,"GB2-06":52.15553829100356,"GB2-07":28.46242519671702,"GB2-08":42.60213165949203},"per_game_all":{"GB2-01":24.75079617445121,"GB2-03":44.030408039983826,"GB2-04":42.49239053370218,"GB2-05":18.832846667547624,"GB2-06":34.5041765307271,"GB2-07":23.417166307037363},"per_game_match_totals_all":{"GB2-01":{"draws":777,"losses":1703,"wins":356},"GB2-02":{"draws":1403,"losses":256,"wins":21},"GB2-03":{"draws":915,"losses":1097,"wins":746},"GB2-04":{"draws":1539,"losses":614,"wins":241},"GB2-05":{"draws":0,"losses":2544,"wins":686},"GB2-06":{"draws":47,"losses":1192,"wins":691},"GB2-07":{"draws":0,"losses":1735,"wins":569},"GB2-08":{"draws":585,"losses":653,"wins":662}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":362,"losses":582,"wins":248},"GB2-02":{"draws":926,"losses":179,"wins":13},"GB2-03":{"draws":316,"losses":522,"wins":398},"GB2-04":{"draws":499,"losses":178,"wins":103},"GB2-05":{"draws":0,"losses":1280,"wins":270},"GB2-06":{"draws":25,"losses":403,"wins":422},"GB2-07":{"draws":0,"losses":888,"wins":338},"GB2-08":{"draws":559,"losses":482,"wins":225}},"medium":{"GB2-01":{"draws":54,"losses":365,"wins":49},"GB2-03":{"draws":271,"losses":162,"wins":13},"GB2-04":{"draws":296,"losses":121,"wins":31},"GB2-05":{"draws":0,"losses":417,"wins":67},"GB2-06":{"draws":3,"losses":353,"wins":100},"GB2-07":{"draws":0,"losses":393,"wins":81}},"none":{"GB2-01":{"draws":361,"losses":756,"wins":59},"GB2-02":{"draws":477,"losses":77,"wins":8},"GB2-03":{"draws":328,"losses":413,"wins":335},"GB2-04":{"draws":744,"losses":315,"wins":107},"GB2-05":{"draws":0,"losses":847,"wins":349},"GB2-06":{"draws":19,"losses":436,"wins":169},"GB2-07":{"draws":0,"losses":454,"wins":150},"GB2-08":{"draws":26,"losses":171,"wins":437}}},"per_game_raw_elo_all":{"GB2-01":1209.5801626239456,"GB2-03":1387.6197281057885,"GB2-04":1419.8600248202656,"GB2-05":988.3226935530389,"GB2-06":1214.1527280482696,"GB2-07":1095.4508752073702},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1369.262589764273,"GB2-02":1415.8016770687836,"GB2-03":1418.5312625620777,"GB2-04":1445.613696783723,"GB2-05":936.1839637081274,"GB2-06":1485.7566303338874,"GB2-07":1172.5147243459892,"GB2-08":1353.388785441529},"medium":{"GB2-01":1122.1653939522162,"GB2-03":1320.5840724190828,"GB2-04":1409.533229379178,"GB2-05":899.5174413058886,"GB2-06":1057.3536734337813,"GB2-07":1027.9241328911246},"none":{"GB2-01":1137.312504155348,"GB2-02":1428.8542397849637,"GB2-03":1423.7438493362051,"GB2-04":1404.4331482978955,"GB2-05":1129.2666756451008,"GB2-06":1099.3478803771404,"GB2-07":1085.9137683849972,"GB2-08":1741.0531253765662}},"per_game_tracks":{"highest":{"GB2-01":38.816090609251454,"GB2-02":42.214974356008675,"GB2-03":47.671710595262084,"GB2-04":45.80370581850568,"GB2-05":15.81049254803779,"GB2-06":52.15553829100356,"GB2-07":28.46242519671702,"GB2-08":42.60213165949203},"medium":{"GB2-01":17.12525138519513,"GB2-03":36.42345530092635,"GB2-04":41.15584698047724,"GB2-05":14.098934532956322,"GB2-06":24.322649088118915,"GB2-07":19.15017208112837},"none":{"GB2-01":18.31104652890705,"GB2-02":43.901278763503285,"GB2-03":47.99605822376304,"GB2-04":40.51761880212363,"GB2-05":26.589112921648756,"GB2-06":27.034342213058828,"GB2-07":22.63890164326669,"GB2-08":72.99717916327725}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.069680877440454,"medium":19.03453867110029,"none":27.087460920999444},"reasoning_agg":{"highest":{"max":47.671710595262084,"mean":33.069680877440454,"min":15.81049254803779},"medium":{"max":41.15584698047724,"mean":19.03453867110029,"min":0.0},"none":{"max":47.99605822376304,"mean":27.087460920999444,"min":11.319450821633344}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":14.035142206340165}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:c772c6115b8fc654","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":46},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.11219570000000001,"mean":0.030692482499999996,"median":0.01928415,"min":0.00650197,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":46,"run_count":24,"total":0.73661958},"codegen_latency_ms":{"attempt_count":46,"max_ms":511905,"mean_ms":147013.95833333334,"min_ms":23584,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":20,"max_ms":511905,"mean_ms":284845.75,"min_ms":132388,"run_count":8},"medium":{"attempt_count":13,"max_ms":348782,"mean_ms":92838.875,"min_ms":39705,"run_count":8},"none":{"attempt_count":13,"max_ms":194018,"mean_ms":63357.25,"min_ms":23584,"run_count":8}},"codegen_output_tokens":{"attempt_count":46,"output_max":93362,"output_mean":24067.583333333332,"output_min":4359,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":20,"output_max":93362,"output_mean":49316.75,"output_min":16213,"run_count":8},"medium":{"attempt_count":13,"output_max":33638,"output_mean":12726.0,"output_min":7627,"run_count":8},"none":{"attempt_count":13,"output_max":17245,"output_mean":10160.0,"output_min":4359,"run_count":8}},"display_name":"Step 3.7 Flash","economics":{"all":31.769267028534056,"highest":27.914177360390976,"medium":35.086656938431624,"none":40.90076286235185},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[230400],"finish_reason_observations":46,"finish_reasons":["stop"],"indexed_attempts":46,"output_token_observations":46,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[230400],"total_output_tokens":577622,"total_visible_output_tokens":183088,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-3.7-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-05","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":17.532990392923292,"score":17.532990392923292},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.6383413309806,"score":14.546113776993534},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":35.66249492369823,"score":23.774996615798823},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":39.689626857956206,"score":13.229875619318735},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":45.1368093864228,"score":30.091206257615198},"GB2-06":{"attempts":3,"playable":42.20608943506394,"score":42.20608943506394},"GB2-07":{"attempts":3,"playable":35.568721257614946,"score":35.568721257614946},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.322712770335144,"score":21.54847518022343}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.590538978329137,"score":9.590538978329137},"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":39.004703564950226,"score":39.004703564950226},"GB2-06":{"attempts":1,"playable":32.09267229972095,"score":32.09267229972095},"GB2-07":{"attempts":1,"playable":24.870012443643382,"score":24.870012443643382},"GB2-08":{"attempts":1,"playable":34.01295951531119,"score":34.01295951531119}},"medium":{"GB2-01":{"attempts":1,"playable":10.355834775492651,"score":10.355834775492651},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":33.740560429080546,"score":33.740560429080546},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":51.26891520789536,"score":51.26891520789536},"GB2-06":{"attempts":1,"playable":45.05051122562779,"score":45.05051122562779},"GB2-07":{"attempts":1,"playable":39.47165396713429,"score":39.47165396713429},"GB2-08":{"attempts":1,"playable":30.632466025359093,"score":30.632466025359093}},"none":{"GB2-01":{"attempts":1,"playable":32.65259742494809,"score":32.65259742494809},"GB2-02":{"attempts":1,"playable":43.6383413309806,"score":43.6383413309806},"GB2-03":{"attempts":1,"playable":37.58442941831591,"score":37.58442941831591},"GB2-04":{"attempts":1,"playable":39.689626857956206,"score":39.689626857956206},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.47508477984305,"score":49.47508477984305},"GB2-07":{"attempts":1,"playable":42.36449736206718,"score":42.36449736206718},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-10-15T06:07:17Z","match_totals_all":{"draws":1841,"losses":4742,"wins":1958},"match_totals_tracks":{"highest":{"draws":471,"losses":1896,"wins":636},"medium":{"draws":478,"losses":1631,"wins":705},"none":{"draws":892,"losses":1215,"wins":617}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":51.26891520789536,"mean":24.812308566943987,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.590538978329137,"GB2-05":39.004703564950226,"GB2-06":32.09267229972095,"GB2-07":24.870012443643382,"GB2-08":34.01295951531119},"per_game_all":{"GB2-01":17.532990392923292,"GB2-06":42.20608943506394,"GB2-07":35.568721257614946},"per_game_match_totals_all":{"GB2-01":{"draws":190,"losses":1160,"wins":156},"GB2-02":{"draws":348,"losses":75,"wins":9},"GB2-03":{"draws":267,"losses":468,"wins":157},"GB2-04":{"draws":289,"losses":131,"wins":28},"GB2-05":{"draws":0,"losses":588,"wins":494},"GB2-06":{"draws":57,"losses":867,"wins":574},"GB2-07":{"draws":0,"losses":1038,"wins":517},"GB2-08":{"draws":690,"losses":415,"wins":23}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":494,"wins":40},"GB2-05":{"draws":0,"losses":351,"wins":247},"GB2-06":{"draws":15,"losses":387,"wins":184},"GB2-07":{"draws":0,"losses":456,"wins":151},"GB2-08":{"draws":420,"losses":208,"wins":14}},"medium":{"GB2-01":{"draws":66,"losses":390,"wins":12},"GB2-03":{"draws":130,"losses":244,"wins":72},"GB2-05":{"draws":0,"losses":237,"wins":247},"GB2-06":{"draws":12,"losses":255,"wins":189},"GB2-07":{"draws":0,"losses":298,"wins":176},"GB2-08":{"draws":270,"losses":207,"wins":9}},"none":{"GB2-01":{"draws":88,"losses":276,"wins":104},"GB2-02":{"draws":348,"losses":75,"wins":9},"GB2-03":{"draws":137,"losses":224,"wins":85},"GB2-04":{"draws":289,"losses":131,"wins":28},"GB2-06":{"draws":30,"losses":225,"wins":201},"GB2-07":{"draws":0,"losses":284,"wins":190}}},"per_game_raw_elo_all":{"GB2-01":1098.5590716735603,"GB2-06":1331.2663511598491,"GB2-07":1264.0795069842738},"per_game_raw_elo_tracks":{"highest":{"GB2-01":983.176143842516,"GB2-05":1311.5809245837943,"GB2-06":1176.395756146061,"GB2-07":1120.3313278289986,"GB2-08":1261.1841722059798},"medium":{"GB2-01":1000.5028036865888,"GB2-03":1296.4403126744292,"GB2-05":1467.7167642295944,"GB2-06":1374.1755679297532,"GB2-07":1317.7921854333715,"GB2-08":1226.5463666826672},"none":{"GB2-01":1311.9982674915757,"GB2-02":1426.823328178995,"GB2-03":1330.8725187370317,"GB2-04":1398.0122920670037,"GB2-06":1443.2277294037335,"GB2-07":1354.1150076904514}},"per_game_tracks":{"highest":{"GB2-01":9.590538978329137,"GB2-05":39.004703564950226,"GB2-06":32.09267229972095,"GB2-07":24.870012443643382,"GB2-08":34.01295951531119},"medium":{"GB2-01":10.355834775492651,"GB2-03":33.740560429080546,"GB2-05":51.26891520789536,"GB2-06":45.05051122562779,"GB2-07":39.47165396713429,"GB2-08":30.632466025359093},"none":{"GB2-01":32.65259742494809,"GB2-02":43.6383413309806,"GB2-03":37.58442941831591,"GB2-04":39.689626857956206,"GB2-06":49.47508477984305,"GB2-07":42.36449736206718}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.44636085024436,"medium":26.314992703823716,"none":30.675572146763884},"reasoning_agg":{"highest":{"max":39.004703564950226,"mean":17.44636085024436,"min":0.0},"medium":{"max":51.26891520789536,"mean":26.314992703823716,"min":0.0},"none":{"max":49.47508477984305,"mean":30.675572146763884,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":13.229211296519523}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:5306429c9898abc6","codegen_cost_by_reasoning":{"highest":{"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":0.01057822},"medium":{"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},"none":{"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":0.007612509999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.01012224},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.02831297},"codegen_latency_ms":{"attempt_count":37,"max_ms":49328,"mean_ms":21505.916666666668,"min_ms":9355,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":47445,"mean_ms":22491.5,"min_ms":13295,"run_count":8},"medium":{"attempt_count":12,"max_ms":49328,"mean_ms":23044.25,"min_ms":13295,"run_count":8},"none":{"attempt_count":14,"max_ms":24913,"mean_ms":18982.0,"min_ms":9355,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":11394,"output_mean":4854.291666666667,"output_min":1030,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":11185,"output_mean":6150.25,"output_min":2902,"run_count":8},"medium":{"attempt_count":12,"output_max":11394,"output_mean":5469.5,"output_min":3022,"run_count":8},"none":{"attempt_count":14,"output_max":4416,"output_mean":2943.125,"output_min":1030,"run_count":8}},"display_name":"Mercury 2.5 Preview","economics":{"all":34.26219365997945,"highest":27.895057393486912,"medium":27.293734064958645,"none":38.71592247888755},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inception","provider_model":"inception/mercury-2.5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":27.654593069648364,"score":9.218197689882787},"GB2-02":{"attempts":3,"playable":42.491381053348,"score":42.491381053348},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.334728564950815,"score":15.111576188316938},"GB2-04":{"attempts":3,"playable":41.262024178851554,"score":41.262024178851554},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":27.924869824316016,"score":18.616579882877343},"GB2-06":{"attempts":3,"playable":19.0331757477388,"score":19.0331757477388},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.443426391495446,"score":8.295617594330297},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":31.313352069536993,"score":20.875568046357994}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.654593069648364,"score":27.654593069648364},"GB2-02":{"attempts":1,"playable":42.415667821457404,"score":42.415667821457404},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.1244797864432,"score":40.1244797864432},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":14.973090935149536,"score":14.973090935149536},"GB2-07":{"attempts":1,"playable":14.148550339227176,"score":14.148550339227176},"GB2-08":{"attempts":1,"playable":28.0539624089958,"score":28.0539624089958}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.90863075444862,"score":42.90863075444862},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.012111161179234,"score":40.012111161179234},"GB2-05":{"attempts":1,"playable":16.37993895890505,"score":16.37993895890505},"GB2-06":{"attempts":1,"playable":19.15067934137708,"score":19.15067934137708},"GB2-07":{"attempts":1,"playable":10.738302443763716,"score":10.738302443763716},"GB2-08":{"attempts":1,"playable":34.572741730078185,"score":34.572741730078185}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.14984458413797,"score":42.14984458413797},"GB2-03":{"attempts":1,"playable":45.334728564950815,"score":45.334728564950815},"GB2-04":{"attempts":1,"playable":43.64948158893223,"score":43.64948158893223},"GB2-05":{"attempts":1,"playable":39.46980068972698,"score":39.46980068972698},"GB2-06":{"attempts":1,"playable":22.97575696668978,"score":22.97575696668978},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"inception/mercury-2.5-preview","is_recent_addition":false,"last_measured_at":"2026-10-15T06:51:01Z","match_totals_all":{"draws":3986,"losses":5313,"wins":1321},"match_totals_tracks":{"highest":{"draws":1481,"losses":1958,"wins":313},"medium":{"draws":1352,"losses":1996,"wins":346},"none":{"draws":1153,"losses":1359,"wins":662}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":45.334728564950815,"mean":21.863015047712963,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.654593069648364,"GB2-02":42.415667821457404,"GB2-04":40.1244797864432,"GB2-06":14.973090935149536,"GB2-07":14.148550339227176,"GB2-08":28.0539624089958},"per_game_all":{"GB2-02":42.491381053348,"GB2-04":41.262024178851554,"GB2-06":19.0331757477388},"per_game_match_totals_all":{"GB2-01":{"draws":155,"losses":369,"wins":102},"GB2-02":{"draws":1501,"losses":279,"wins":2},"GB2-03":{"draws":185,"losses":310,"wins":205},"GB2-04":{"draws":1326,"losses":397,"wins":89},"GB2-05":{"draws":0,"losses":910,"wins":402},"GB2-06":{"draws":14,"losses":1459,"wins":339},"GB2-07":{"draws":0,"losses":1131,"wins":149},"GB2-08":{"draws":805,"losses":458,"wins":33}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":155,"losses":369,"wins":102},"GB2-02":{"draws":503,"losses":93,"wins":2},"GB2-04":{"draws":452,"losses":150,"wins":22},"GB2-06":{"draws":4,"losses":512,"wins":88},"GB2-07":{"draws":0,"losses":563,"wins":87},"GB2-08":{"draws":367,"losses":271,"wins":12}},"medium":{"GB2-02":{"draws":493,"losses":75,"wins":0},"GB2-04":{"draws":415,"losses":146,"wins":33},"GB2-05":{"draws":0,"losses":535,"wins":117},"GB2-06":{"draws":6,"losses":485,"wins":113},"GB2-07":{"draws":0,"losses":568,"wins":62},"GB2-08":{"draws":438,"losses":187,"wins":21}},"none":{"GB2-02":{"draws":505,"losses":111,"wins":0},"GB2-03":{"draws":185,"losses":310,"wins":205},"GB2-04":{"draws":459,"losses":101,"wins":34},"GB2-05":{"draws":0,"losses":375,"wins":285},"GB2-06":{"draws":4,"losses":462,"wins":138}}},"per_game_raw_elo_all":{"GB2-02":1417.944782075662,"GB2-04":1410.3144228846465,"GB2-06":969.9537695305357},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1257.7543478754828,"GB2-02":1417.3589722408683,"GB2-04":1401.4391438354899,"GB2-06":899.8481741309525,"GB2-07":931.7274176062131,"GB2-08":1199.4050839122647},"medium":{"GB2-02":1421.1793205694296,"GB2-04":1400.5544809178068,"GB2-05":948.1733487900146,"GB2-06":973.8647646276173,"GB2-07":851.836527436389,"GB2-08":1266.8519417518676},"none":{"GB2-02":1415.296053416688,"GB2-03":1398.283426886964,"GB2-04":1428.9496439006423,"GB2-05":1317.7260594403172,"GB2-06":1036.1483698330373}},"per_game_tracks":{"highest":{"GB2-01":27.654593069648364,"GB2-02":42.415667821457404,"GB2-04":40.1244797864432,"GB2-06":14.973090935149536,"GB2-07":14.148550339227176,"GB2-08":28.0539624089958},"medium":{"GB2-02":42.90863075444862,"GB2-04":40.012111161179234,"GB2-05":16.37993895890505,"GB2-06":19.15067934137708,"GB2-07":10.738302443763716,"GB2-08":34.572741730078185},"none":{"GB2-02":42.14984458413797,"GB2-03":45.334728564950815,"GB2-04":43.64948158893223,"GB2-05":39.46980068972698,"GB2-06":22.97575696668978}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.921293045115185,"medium":20.470300548718985,"none":24.19745154930472},"reasoning_agg":{"highest":{"max":42.415667821457404,"mean":20.921293045115185,"min":0.0},"medium":{"max":42.90863075444862,"mean":20.470300548718985,"min":0.0},"none":{"max":45.334728564950815,"mean":24.19745154930472,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":3.727151000585735}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:f8b6c8a1e8419df3","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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":0.08108400000000002},"none":{"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":0.04706874999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.08108399999999999},"historical-provider-setting-baseline":{"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":0.04706874999999999},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.34809299999999993},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":15.588383508763018,"highest":27.615168450689644,"medium":26.93024798172736,"none":17.89813221904284},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"total_output_tokens":150003},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.1-flash-lite","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5},"baseline":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.375,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":24.232085166334386,"score":16.154723444222924},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.76395762336313,"score":14.254652541121045},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":43.51771894880092,"score":29.011812632533946},"GB2-05":{"attempts":3,"playable":10.916053086329384,"score":10.916053086329384},"GB2-06":{"attempts":3,"playable":21.973839173055016,"score":21.973839173055016},"GB2-07":{"attempts":3,"playable":13.875258266904659,"score":13.875258266904659},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":35.294486903262836,"score":23.529657935508556}},"headline_games_tracks":{"highest":{"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":42.69597165659207,"score":42.69597165659207},"GB2-05":{"attempts":1,"playable":9.96368510380721,"score":9.96368510380721},"GB2-06":{"attempts":1,"playable":18.806016935678727,"score":18.806016935678727},"GB2-07":{"attempts":1,"playable":33.3794824895676,"score":33.3794824895676},"GB2-08":{"attempts":1,"playable":33.23068606780264,"score":33.23068606780264}},"medium":{"GB2-01":{"attempts":1,"playable":34.68671809500689,"score":34.68671809500689},"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":44.339466241009774,"score":44.339466241009774},"GB2-05":{"attempts":1,"playable":16.240620009597773,"score":16.240620009597773},"GB2-06":{"attempts":1,"playable":23.278627543509973,"score":23.278627543509973},"GB2-07":{"attempts":1,"playable":5.677768262516722,"score":5.677768262516722},"GB2-08":{"attempts":1,"playable":37.358287738723035,"score":37.358287738723035}},"none":{"GB2-01":{"attempts":1,"playable":13.777452237661885,"score":13.777452237661885},"GB2-02":{"attempts":1,"playable":42.76395762336313,"score":42.76395762336313},"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":6.543854145583172,"score":6.543854145583172},"GB2-06":{"attempts":1,"playable":23.836873039976357,"score":23.836873039976357},"GB2-07":{"attempts":1,"playable":2.5685240486296568,"score":2.5685240486296568},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-15T05:59:04Z","match_totals_all":{"draws":2261,"losses":5904,"wins":1280},"match_totals_tracks":{"highest":{"draws":797,"losses":1739,"wins":453},"medium":{"draws":890,"losses":2158,"wins":584},"none":{"draws":574,"losses":2007,"wins":243}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":44.339466241009774,"mean":16.21449963495944,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":57,"overall_ranking_status":"partial","per_game":{"GB2-04":42.69597165659207,"GB2-05":9.96368510380721,"GB2-06":18.806016935678727,"GB2-07":33.3794824895676,"GB2-08":33.23068606780264},"per_game_all":{"GB2-05":10.916053086329384,"GB2-06":21.973839173055016,"GB2-07":13.875258266904659},"per_game_match_totals_all":{"GB2-01":{"draws":399,"losses":663,"wins":102},"GB2-02":{"draws":452,"losses":84,"wins":6},"GB2-04":{"draws":803,"losses":243,"wins":98},"GB2-05":{"draws":0,"losses":1529,"wins":245},"GB2-06":{"draws":10,"losses":1318,"wins":411},"GB2-07":{"draws":0,"losses":1531,"wins":253},"GB2-08":{"draws":597,"losses":536,"wins":165}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":420,"losses":120,"wins":34},"GB2-05":{"draws":0,"losses":522,"wins":76},"GB2-06":{"draws":0,"losses":450,"wins":119},"GB2-07":{"draws":0,"losses":415,"wins":199},"GB2-08":{"draws":377,"losses":232,"wins":25}},"medium":{"GB2-01":{"draws":284,"losses":233,"wins":73},"GB2-04":{"draws":383,"losses":123,"wins":64},"GB2-05":{"draws":0,"losses":482,"wins":120},"GB2-06":{"draws":3,"losses":457,"wins":148},"GB2-07":{"draws":0,"losses":559,"wins":39},"GB2-08":{"draws":220,"losses":304,"wins":140}},"none":{"GB2-01":{"draws":115,"losses":430,"wins":29},"GB2-02":{"draws":452,"losses":84,"wins":6},"GB2-05":{"draws":0,"losses":525,"wins":49},"GB2-06":{"draws":7,"losses":411,"wins":144},"GB2-07":{"draws":0,"losses":557,"wins":15}}},"per_game_raw_elo_all":{"GB2-05":810.7000944146067,"GB2-06":1019.5762735314362,"GB2-07":812.6202392986028},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1421.546452396237,"GB2-05":797.7964964402153,"GB2-06":968.048673894182,"GB2-07":1239.3790229959327,"GB2-08":1253.2376006128534},"medium":{"GB2-01":1333.0375444100528,"GB2-04":1434.2945078665123,"GB2-05":945.3110352382996,"GB2-06":1040.942081692602,"GB2-07":687.9222286857057,"GB2-08":1294.9059480258586},"none":{"GB2-01":1067.6012091357711,"GB2-02":1420.0588136376907,"GB2-05":688.9927515653053,"GB2-06":1049.7380650075245,"GB2-07":510.55946621416956}},"per_game_tracks":{"highest":{"GB2-04":42.69597165659207,"GB2-05":9.96368510380721,"GB2-06":18.806016935678727,"GB2-07":33.3794824895676,"GB2-08":33.23068606780264},"medium":{"GB2-01":34.68671809500689,"GB2-04":44.339466241009774,"GB2-05":16.240620009597773,"GB2-06":23.278627543509973,"GB2-07":5.677768262516722,"GB2-08":37.358287738723035},"none":{"GB2-01":13.777452237661885,"GB2-02":42.76395762336313,"GB2-05":6.543854145583172,"GB2-06":23.836873039976357,"GB2-07":2.5685240486296568}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.25948028168103,"medium":20.197685986295518,"none":11.186332636901774},"reasoning_agg":{"highest":{"max":42.69597165659207,"mean":17.25948028168103,"min":0.0},"medium":{"max":44.339466241009774,"mean":20.197685986295518,"min":0.0},"none":{"max":42.76395762336313,"mean":11.186332636901774,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":9.011353349393744}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:8ed9f35f2f7d99b2","codegen_cost_by_reasoning":{"highest":{"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":0.13069024999999998},"medium":{"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},"none":{"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":0.01215665}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":6,"cell_count":24,"cost_basis_counts":{"provider_reported":49},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":17,"max":0.02342595,"mean":0.008376991666666668,"median":0.0080226,"min":0.00063975,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":48},"recorded_attempt_count":49,"run_count":24,"total":0.2010478},"codegen_latency_ms":{"attempt_count":48,"max_ms":1854161,"mean_ms":628655.8260869565,"min_ms":24176,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":1854161,"mean_ms":1241203.5,"min_ms":669527,"run_count":8},"medium":{"attempt_count":14,"max_ms":912503,"mean_ms":578415.5714285715,"min_ms":208280,"run_count":7},"none":{"attempt_count":16,"max_ms":108436,"mean_ms":60068.375,"min_ms":24176,"run_count":8}},"codegen_output_tokens":{"attempt_count":49,"output_max":112315,"output_mean":38073.333333333336,"output_min":1354,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":112315,"output_mean":77461.75,"output_min":52895,"run_count":8},"medium":{"attempt_count":15,"output_max":54994,"output_mean":32804.625,"output_min":3815,"run_count":8},"none":{"attempt_count":16,"output_max":7089,"output_mean":3953.625,"output_min":1354,"run_count":8}},"display_name":"Solar Mini 4","economics":{"highest":37.15044077752244,"medium":19.993469468116626,"none":40.592076508410386},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":49,"effective_max_output_tokens":[131072],"finish_reason_observations":48,"finish_reasons":["stop"],"indexed_attempts":49,"output_token_observations":49,"provider_post_attempt_observations":49,"provider_post_attempts":51,"reasoning_token_observations":49,"reconciliation_get_attempt_observations":49,"requested_max_output_token_observations":49,"requested_max_output_tokens":[131072],"total_output_tokens":913760,"total_reasoning_output_tokens":808441,"total_visible_output_tokens":105319,"visible_token_observations":49},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"upstage","provider_model":"upstage/solar-mini4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":2,"evaluated_cells":7,"failed_game_aliases":["GB2-03","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.14285714285714285,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-02"],"infra_failures_excluded":1,"model_code_failure_rate":0.7142857142857143,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.14285714285714285},"baseline":{"admitted_plugins":1,"evaluated_cells":8,"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,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.875,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":2,"playable":19.622542952082743,"score":6.540847650694247},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.592076508410386,"score":13.530692169470129},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.871537219550895,"score":15.623845739850298},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.77009004666788,"score":17.18006003111192},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":33.40400100383117,"score":11.134667001277057},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"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":46.871537219550895,"score":46.871537219550895},"GB2-06":{"attempts":1,"playable":31.17578410918525,"score":31.17578410918525},"GB2-07":{"attempts":1,"playable":33.40400100383117,"score":33.40400100383117},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":19.622542952082743,"score":19.622542952082743},"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":20.36439598415051,"score":20.36439598415051},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"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":40.592076508410386,"score":40.592076508410386},"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}}},"id":"upstage/solar-mini4","is_recent_addition":false,"last_measured_at":"2026-10-12T22:38:55Z","match_totals_all":{"draws":406,"losses":1730,"wins":650},"match_totals_tracks":{"highest":{"draws":7,"losses":906,"wins":501},"medium":{"draws":84,"losses":710,"wins":130},"none":{"draws":315,"losses":114,"wins":19}},"model_slug":"upstage-solar-mini4","overall":{"max":46.871537219550895,"mean":8.239281567718512,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":58,"overall_ranking_status":"partial","per_game":{"GB2-05":46.871537219550895,"GB2-06":31.17578410918525,"GB2-07":33.40400100383117},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":341,"wins":48},"GB2-04":{"draws":315,"losses":114,"wins":19},"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":12,"losses":690,"wins":210},"GB2-07":{"draws":0,"losses":327,"wins":147}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":258,"wins":226},"GB2-06":{"draws":7,"losses":321,"wins":128},"GB2-07":{"draws":0,"losses":327,"wins":147}},"medium":{"GB2-01":{"draws":79,"losses":341,"wins":48},"GB2-06":{"draws":5,"losses":369,"wins":82}},"none":{"GB2-04":{"draws":315,"losses":114,"wins":19}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1412.5435996032684,"GB2-06":1162.4884191432325,"GB2-07":1239.702549757927},"medium":{"GB2-01":1158.2133231753928,"GB2-06":994.0388879769692},"none":{"GB2-04":1405.1143663647663}},"per_game_tracks":{"highest":{"GB2-05":46.871537219550895,"GB2-06":31.17578410918525,"GB2-07":33.40400100383117},"medium":{"GB2-01":19.622542952082743,"GB2-06":20.36439598415051},"none":{"GB2-04":40.592076508410386}},"provider_color":"#805CFB","provider_company":"Upstage","provider_key":"upstage","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":13.931415291570914,"medium":5.7124198480333215,"none":5.074009563551298},"reasoning_agg":{"highest":{"max":46.871537219550895,"mean":13.931415291570914,"min":0.0},"medium":{"max":20.36439598415051,"mean":5.7124198480333215,"min":0.0},"none":{"max":40.592076508410386,"mean":5.074009563551298,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.857405728019616}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:cad88ef1dc140c69","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.01810518},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":1,"cell_count":24,"cost_basis_counts":{"provider_reported":56},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":23,"max":0.01113168,"mean":0.00448752,"median":0.002935335,"min":0.00164236,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":37},"recorded_attempt_count":56,"run_count":24,"total":0.10770047999999999},"codegen_latency_ms":{"attempt_count":56,"max_ms":643052,"mean_ms":207186.875,"min_ms":45308,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":18,"max_ms":643052,"mean_ms":466285.75,"min_ms":257629,"run_count":8},"medium":{"attempt_count":19,"max_ms":129121,"mean_ms":76432.5,"min_ms":45308,"run_count":8},"none":{"attempt_count":19,"max_ms":136274,"mean_ms":78842.375,"min_ms":49515,"run_count":8}},"codegen_output_tokens":{"attempt_count":56,"output_max":39360,"output_mean":13818.666666666666,"output_min":3954,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":39360,"output_mean":29587.25,"output_min":21705,"run_count":8},"medium":{"attempt_count":19,"output_max":7321,"output_mean":5310.0,"output_min":3954,"run_count":8},"none":{"attempt_count":19,"output_max":9484,"output_mean":6558.75,"output_min":4755,"run_count":8}},"display_name":"Granite 4.2 8B","economics":{"medium":38.899569524957755},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":37,"effective_max_output_tokens":[117964],"finish_reason_observations":56,"finish_reasons":["stop"],"indexed_attempts":56,"output_token_observations":56,"provider_post_attempt_observations":56,"provider_post_attempts":56,"reasoning_token_observations":56,"reconciliation_get_attempt_observations":56,"reconciliation_get_attempts":88,"requested_max_output_token_observations":37,"requested_max_output_tokens":[117964],"total_output_tokens":331648,"total_reasoning_output_tokens":194609,"total_visible_output_tokens":137039,"visible_token_observations":56},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"ibm","provider_model":"ibm-granite/granite-4.2-8b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.875,"model_code_failures":7,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}},"intensive":{"admitted_plugins":0,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":1.0,"model_code_failures":8,"official_qualification":{"fixed_coverage_complete":false,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"under_tested","grouped_stable":false,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-02":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":38.899569524957755,"score":12.966523174985918},"GB2-05":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-06":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-07":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-08":{"attempts":3,"failed_attempts":3,"score":0.0}},"headline_games_tracks":{"highest":{"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}},"medium":{"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":38.899569524957755,"score":38.899569524957755},"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}},"none":{"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}}},"id":"ibm-granite/granite-4.2-8b","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:01Z","match_totals_all":{"draws":286,"losses":136,"wins":26},"match_totals_tracks":{"medium":{"draws":286,"losses":136,"wins":26}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":38.899569524957755,"mean":1.6208153968732397,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"overall_official_rank":59,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-04":{"draws":286,"losses":136,"wins":26}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":286,"losses":136,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1391.762022294602}},"per_game_tracks":{"medium":{"GB2-04":38.899569524957755}},"provider_color":"#0F62FE","provider_company":"IBM","provider_key":"ibm","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":0.0,"medium":4.862446190619719,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":38.899569524957755,"mean":4.862446190619719,"min":0.0},"none":{"max":0.0,"mean":0.0,"min":0.0}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Non-thinking"},"reasoning_settings":{"balanced":"low"},"score_diagnostics":{"reasoning_variance":4.862446190619719}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:279ed8e1938a92c1","codegen_cost_by_reasoning":{"none":{"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":0.2454376}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998}},"codegen_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":0.2454376},"codegen_latency_ms":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":9,"max_ms":206060,"mean_ms":152052.0,"min_ms":81370,"run_count":8}},"codegen_output_tokens":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":9,"output_max":9255,"output_mean":7213.75,"output_min":4888,"run_count":8}},"display_name":"Pareto 26.10 Preview","economics":{"none":89.75925665520103},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":9,"effective_max_output_tokens":[131072],"finish_reason_observations":9,"finish_reasons":["stop"],"indexed_attempts":9,"output_token_observations":9,"provider_post_attempt_observations":9,"provider_post_attempts":9,"reasoning_token_observations":9,"reconciliation_get_attempt_observations":9,"requested_max_output_token_observations":9,"requested_max_output_tokens":[131072],"total_output_tokens":57710,"total_visible_output_tokens":57710,"visible_token_observations":9},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"unbiased","provider_model":"unbiased/pareto-26.10-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":74.33444641198543,"score":74.33444641198543},"GB2-02":{"attempts":1,"playable":91.35739397946848,"score":91.35739397946848},"GB2-03":{"attempts":1,"playable":94.04169854588783,"score":94.04169854588783},"GB2-04":{"attempts":1,"playable":86.01523868985326,"score":86.01523868985326},"GB2-05":{"attempts":1,"playable":94.83440428010096,"score":94.83440428010096},"GB2-06":{"attempts":1,"playable":87.54531673206525,"score":87.54531673206525},"GB2-07":{"attempts":1,"playable":95.80671523735789,"score":95.80671523735789},"GB2-08":{"attempts":1,"playable":94.13883936488912,"score":94.13883936488912}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":74.33444641198543,"score":74.33444641198543},"GB2-02":{"attempts":1,"playable":91.35739397946848,"score":91.35739397946848},"GB2-03":{"attempts":1,"playable":94.04169854588783,"score":94.04169854588783},"GB2-04":{"attempts":1,"playable":86.01523868985326,"score":86.01523868985326},"GB2-05":{"attempts":1,"playable":94.83440428010096,"score":94.83440428010096},"GB2-06":{"attempts":1,"playable":87.54531673206525,"score":87.54531673206525},"GB2-07":{"attempts":1,"playable":95.80671523735789,"score":95.80671523735789},"GB2-08":{"attempts":1,"playable":94.13883936488912,"score":94.13883936488912}}},"id":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-10-13T22:57:19Z","match_totals_all":{"draws":128,"losses":313,"wins":3253},"match_totals_tracks":{"none":{"draws":128,"losses":313,"wins":3253}},"model_slug":"unbiased-pareto-26-10-preview","overall":{"max":95.80671523735789,"mean":89.75925665520103,"min":74.33444641198543},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":117,"wins":339},"GB2-02":{"draws":35,"losses":20,"wins":377},"GB2-03":{"draws":5,"losses":25,"wins":416},"GB2-04":{"draws":39,"losses":46,"wins":363},"GB2-05":{"draws":0,"losses":23,"wins":461},"GB2-06":{"draws":37,"losses":37,"wins":382},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":28,"wins":458}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":12,"losses":117,"wins":339},"GB2-02":{"draws":35,"losses":20,"wins":377},"GB2-03":{"draws":5,"losses":25,"wins":416},"GB2-04":{"draws":39,"losses":46,"wins":363},"GB2-05":{"draws":0,"losses":23,"wins":461},"GB2-06":{"draws":37,"losses":37,"wins":382},"GB2-07":{"draws":0,"losses":17,"wins":457},"GB2-08":{"draws":0,"losses":28,"wins":458}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1737.5674662645843,"GB2-02":1967.7146188190113,"GB2-03":2151.9994389253416,"GB2-04":1846.959223183505,"GB2-05":2545.18427873966,"GB2-06":2148.963313742678,"GB2-07":2500.7174373426883,"GB2-08":2291.937019771423}},"per_game_tracks":{"none":{"GB2-01":74.33444641198543,"GB2-02":91.35739397946848,"GB2-03":94.04169854588783,"GB2-04":86.01523868985326,"GB2-05":94.83440428010096,"GB2-06":87.54531673206525,"GB2-07":95.80671523735789,"GB2-08":94.13883936488912}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":89.75925665520103},"reasoning_agg":{"none":{"max":95.80671523735789,"mean":89.75925665520103,"min":74.33444641198543}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:ba0e7b91d293d49e","codegen_cost_by_reasoning":{"medium":{"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":0.45532711499999995},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.057513089999999996}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.158732805,"mean":0.032052512812499996,"median":0.0201057,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":19,"run_count":16,"total":0.512840205},"codegen_latency_ms":{"attempt_count":19,"max_ms":3172586,"mean_ms":488857.125,"min_ms":33029,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":9,"max_ms":3172586,"mean_ms":924271.75,"min_ms":388744,"run_count":8},"none":{"attempt_count":10,"max_ms":84396,"mean_ms":53442.5,"min_ms":33029,"run_count":8}},"codegen_output_tokens":{"attempt_count":19,"output_max":171951,"output_mean":32110.125,"output_min":2214,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":9,"output_max":171951,"output_mean":60792.125,"output_min":28781,"run_count":8},"none":{"attempt_count":10,"output_max":6088,"output_mean":3428.125,"output_min":2214,"run_count":8}},"display_name":"MiMo-V2.6-Pro","economics":{"medium":73.31215265967204,"none":50.940267654212086},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":19,"effective_max_output_tokens":[131072],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":19,"output_token_observations":19,"provider_post_attempt_observations":19,"provider_post_attempts":20,"reasoning_token_observations":19,"reconciliation_get_attempt_observations":19,"requested_max_output_token_observations":19,"requested_max_output_tokens":[131072],"total_output_tokens":513762,"total_reasoning_output_tokens":447944,"total_visible_output_tokens":65818,"visible_token_observations":19},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":47.017792345518814,"score":47.017792345518814},"GB2-02":{"attempts":2,"playable":60.839895099609606,"score":60.839895099609606},"GB2-03":{"attempts":2,"playable":65.49105740773737,"score":65.49105740773737},"GB2-04":{"attempts":2,"playable":50.643539704347745,"score":50.643539704347745},"GB2-05":{"attempts":2,"playable":65.18333159696937,"score":65.18333159696937},"GB2-06":{"attempts":2,"playable":56.98513660043638,"score":56.98513660043638},"GB2-07":{"attempts":2,"playable":66.56653038555282,"score":66.56653038555282},"GB2-08":{"attempts":2,"playable":84.2823981153644,"score":84.2823981153644}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.23001096984008,"score":54.23001096984008},"GB2-02":{"attempts":1,"playable":80.7202850209492,"score":80.7202850209492},"GB2-03":{"attempts":1,"playable":85.81993686331167,"score":85.81993686331167},"GB2-04":{"attempts":1,"playable":46.44498437678018,"score":46.44498437678018},"GB2-05":{"attempts":1,"playable":84.95994941124415,"score":84.95994941124415},"GB2-06":{"attempts":1,"playable":57.65294621136401,"score":57.65294621136401},"GB2-07":{"attempts":1,"playable":89.94610223945115,"score":89.94610223945115},"GB2-08":{"attempts":1,"playable":86.72300618443583,"score":86.72300618443583}},"none":{"GB2-01":{"attempts":1,"playable":39.805573721197554,"score":39.805573721197554},"GB2-02":{"attempts":1,"playable":40.95950517827001,"score":40.95950517827001},"GB2-03":{"attempts":1,"playable":45.16217795216307,"score":45.16217795216307},"GB2-04":{"attempts":1,"playable":54.842095031915306,"score":54.842095031915306},"GB2-05":{"attempts":1,"playable":45.406713782694574,"score":45.406713782694574},"GB2-06":{"attempts":1,"playable":56.31732698950874,"score":56.31732698950874},"GB2-07":{"attempts":1,"playable":43.18695853165451,"score":43.18695853165451},"GB2-08":{"attempts":1,"playable":81.84179004629296,"score":81.84179004629296}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:48Z","match_totals_all":{"draws":1294,"losses":2216,"wins":3878},"match_totals_tracks":{"medium":{"draws":341,"losses":835,"wins":2518},"none":{"draws":953,"losses":1381,"wins":1360}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":89.94610223945115,"mean":62.126210156942065,"min":39.805573721197554},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":280,"losses":365,"wins":291},"GB2-02":{"draws":407,"losses":143,"wins":314},"GB2-03":{"draws":95,"losses":281,"wins":516},"GB2-04":{"draws":459,"losses":224,"wins":213},"GB2-05":{"draws":0,"losses":339,"wins":629},"GB2-06":{"draws":53,"losses":381,"wins":478},"GB2-07":{"draws":0,"losses":326,"wins":622},"GB2-08":{"draws":0,"losses":157,"wins":815}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":71,"losses":183,"wins":214},"GB2-02":{"draws":76,"losses":48,"wins":308},"GB2-03":{"draws":2,"losses":68,"wins":376},"GB2-04":{"draws":163,"losses":164,"wins":121},"GB2-05":{"draws":0,"losses":74,"wins":410},"GB2-06":{"draws":29,"losses":186,"wins":241},"GB2-07":{"draws":0,"losses":46,"wins":428},"GB2-08":{"draws":0,"losses":66,"wins":420}},"none":{"GB2-01":{"draws":209,"losses":182,"wins":77},"GB2-02":{"draws":331,"losses":95,"wins":6},"GB2-03":{"draws":93,"losses":213,"wins":140},"GB2-04":{"draws":296,"losses":60,"wins":92},"GB2-05":{"draws":0,"losses":265,"wins":219},"GB2-06":{"draws":24,"losses":195,"wins":237},"GB2-07":{"draws":0,"losses":280,"wins":194},"GB2-08":{"draws":0,"losses":91,"wins":395}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1523.052427782989,"GB2-02":1767.1635955352988,"GB2-03":1885.1720378161647,"GB2-04":1450.5651616490488,"GB2-05":2087.2035550705473,"GB2-06":1575.3453553124195,"GB2-07":2185.294317341084,"GB2-08":2038.8905524925487},"none":{"GB2-01":1384.198795233665,"GB2-02":1406.0299785878242,"GB2-03":1396.791223405974,"GB2-04":1515.9178446860271,"GB2-05":1394.0939966722483,"GB2-06":1553.2361593558105,"GB2-07":1364.388930001521,"GB2-08":1918.9637988908282}},"per_game_tracks":{"medium":{"GB2-01":54.23001096984008,"GB2-02":80.7202850209492,"GB2-03":85.81993686331167,"GB2-04":46.44498437678018,"GB2-05":84.95994941124415,"GB2-06":57.65294621136401,"GB2-07":89.94610223945115,"GB2-08":86.72300618443583},"none":{"GB2-01":39.805573721197554,"GB2-02":40.95950517827001,"GB2-03":45.16217795216307,"GB2-04":54.842095031915306,"GB2-05":45.406713782694574,"GB2-06":56.31732698950874,"GB2-07":43.18695853165451,"GB2-08":81.84179004629296}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":73.31215265967204,"none":50.940267654212086},"reasoning_agg":{"medium":{"max":89.94610223945115,"mean":73.31215265967204,"min":46.44498437678018},"none":{"max":81.84179004629296,"mean":50.940267654212086,"min":39.805573721197554}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":22.37188500545995}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:d6acf4ab074f64d1","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.183419,"mean":0.183419,"median":0.183419,"min":0.183419,"recorded_attempt_count":1,"run_count":1,"total":0.183419}},"codegen_cost_usd":{"admitted_cell_count":2,"cell_count":3,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1898863,"mean":0.1851245,"median":0.183419,"min":0.1820682,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":5,"run_count":3,"total":0.5553735},"codegen_latency_ms":{"attempt_count":4,"max_ms":724394,"mean_ms":700552.5,"min_ms":676711,"run_count":2},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":2,"max_ms":724394,"mean_ms":724394.0,"min_ms":724394,"run_count":1},"none":{"attempt_count":2,"max_ms":676711,"mean_ms":676711.0,"min_ms":676711,"run_count":1}},"codegen_output_tokens":{"attempt_count":5,"output_max":64000,"output_mean":62025.0,"output_min":59586,"run_count":3},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":1,"output_max":64000,"output_mean":64000.0,"output_min":64000,"run_count":1},"medium":{"attempt_count":2,"output_max":59586,"output_mean":59586.0,"output_min":59586,"run_count":1},"none":{"attempt_count":2,"output_max":62489,"output_mean":62489.0,"output_min":62489,"run_count":1}},"display_name":"Step 5 Preview","economics":{"medium":83.01348641254609,"none":35.35744234499034},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":5,"effective_max_output_tokens":[64000],"finish_reason_observations":4,"finish_reasons":["stop"],"indexed_attempts":5,"output_token_observations":5,"provider_post_attempt_observations":5,"provider_post_attempts":5,"reasoning_token_observations":5,"reconciliation_get_attempt_observations":5,"requested_max_output_token_observations":5,"requested_max_output_tokens":[64000],"total_output_tokens":186075,"total_reasoning_output_tokens":53683,"total_visible_output_tokens":132392,"visible_token_observations":5},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":64000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"stepfun","provider_model":"stepfun/step-5-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}},"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-08":{"attempts":2,"playable":59.185464378768216,"score":59.185464378768216}},"headline_games_tracks":{"medium":{"GB2-08":{"attempts":1,"playable":83.01348641254609,"score":83.01348641254609}},"none":{"GB2-08":{"attempts":1,"playable":35.35744234499034,"score":35.35744234499034}}},"id":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-10-13T23:00:32Z","match_totals_all":{"draws":277,"losses":266,"wins":429},"match_totals_tracks":{"medium":{"draws":2,"losses":84,"wins":400},"none":{"draws":275,"losses":182,"wins":29}},"model_slug":"stepfun-step-5-preview","overall":{"max":83.01348641254609,"mean":59.185464378768216,"min":35.35744234499034},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":277,"losses":266,"wins":429}},"per_game_match_totals_tracks":{"medium":{"GB2-08":{"draws":2,"losses":84,"wins":400}},"none":{"GB2-08":{"draws":275,"losses":182,"wins":29}}},"per_game_raw_elo_tracks":{"medium":{"GB2-08":1945.9548324962466},"none":{"GB2-08":1274.7756595684953}},"per_game_tracks":{"medium":{"GB2-08":83.01348641254609},"none":{"GB2-08":35.35744234499034}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":83.01348641254609,"none":35.35744234499034},"reasoning_agg":{"medium":{"max":83.01348641254609,"mean":83.01348641254609,"min":83.01348641254609},"none":{"max":35.35744234499034,"mean":35.35744234499034,"min":35.35744234499034}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":47.65604406755575}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:1634fd786aeaa347","codegen_cost_by_reasoning":{"medium":{"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":0.14258062000000002},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.14258062000000002},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02304638,"mean":0.01037612625,"median":0.0072198,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"recorded_attempt_count":23,"run_count":16,"total":0.16601802},"codegen_latency_ms":{"attempt_count":23,"max_ms":1374551,"mean_ms":491530.125,"min_ms":35032,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1374551,"mean_ms":925316.625,"min_ms":428464,"run_count":8},"none":{"attempt_count":12,"max_ms":114099,"mean_ms":57743.625,"min_ms":35032,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":78655,"output_mean":31302.375,"output_min":3072,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":78655,"output_mean":57997.125,"output_min":33074,"run_count":8},"none":{"attempt_count":12,"output_max":6869,"output_mean":4607.625,"output_min":3072,"run_count":8}},"display_name":"MiMo-V2.6-Flash","economics":{"medium":60.263759388883905,"none":46.07408754113957},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[131072],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[131072],"total_output_tokens":500838,"total_reasoning_output_tokens":411817,"total_visible_output_tokens":89021,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":60.921999754977456,"score":60.921999754977456},"GB2-02":{"attempts":2,"playable":54.482662579863955,"score":54.482662579863955},"GB2-03":{"attempts":2,"playable":52.674337894753194,"score":52.674337894753194},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":58.29527697564496,"score":29.14763848782248},"GB2-05":{"attempts":2,"playable":56.923013603356765,"score":56.923013603356765},"GB2-06":{"attempts":2,"playable":59.7703917836742,"score":59.7703917836742},"GB2-07":{"attempts":2,"playable":62.227438916134425,"score":62.227438916134425},"GB2-08":{"attempts":2,"playable":26.166860928941652,"score":26.166860928941652}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":53.70151094438849,"score":53.70151094438849},"GB2-02":{"attempts":1,"playable":66.95682571299996,"score":66.95682571299996},"GB2-03":{"attempts":1,"playable":64.30148957733782,"score":64.30148957733782},"GB2-04":{"attempts":1,"playable":58.29527697564496,"score":58.29527697564496},"GB2-05":{"attempts":1,"playable":60.48243455121046,"score":60.48243455121046},"GB2-06":{"attempts":1,"playable":66.94130045267329,"score":66.94130045267329},"GB2-07":{"attempts":1,"playable":83.7406737739015,"score":83.7406737739015},"GB2-08":{"attempts":1,"playable":27.690563122914792,"score":27.690563122914792}},"none":{"GB2-01":{"attempts":1,"playable":68.14248856556642,"score":68.14248856556642},"GB2-02":{"attempts":1,"playable":42.00849944672796,"score":42.00849944672796},"GB2-03":{"attempts":1,"playable":41.04718621216857,"score":41.04718621216857},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":53.36359265550307,"score":53.36359265550307},"GB2-06":{"attempts":1,"playable":52.59948311467512,"score":52.59948311467512},"GB2-07":{"attempts":1,"playable":40.71420405836734,"score":40.71420405836734},"GB2-08":{"attempts":1,"playable":24.643158734968512,"score":24.643158734968512}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-14T17:24:56Z","match_totals_all":{"draws":1425,"losses":2603,"wins":2912},"match_totals_tracks":{"medium":{"draws":558,"losses":1236,"wins":1900},"none":{"draws":867,"losses":1367,"wins":1012}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":83.7406737739015,"mean":50.28929299369051,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":165,"losses":291,"wins":480},"GB2-02":{"draws":515,"losses":146,"wins":203},"GB2-03":{"draws":169,"losses":366,"wins":357},"GB2-04":{"draws":51,"losses":167,"wins":230},"GB2-05":{"draws":0,"losses":420,"wins":548},"GB2-06":{"draws":46,"losses":357,"wins":509},"GB2-07":{"draws":0,"losses":369,"wins":579},"GB2-08":{"draws":479,"losses":487,"wins":6}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":211,"wins":237},"GB2-02":{"draws":189,"losses":53,"wins":190},"GB2-03":{"draws":30,"losses":158,"wins":258},"GB2-04":{"draws":51,"losses":167,"wins":230},"GB2-05":{"draws":0,"losses":193,"wins":291},"GB2-06":{"draws":16,"losses":147,"wins":293},"GB2-07":{"draws":0,"losses":77,"wins":397},"GB2-08":{"draws":252,"losses":230,"wins":4}},"none":{"GB2-01":{"draws":145,"losses":80,"wins":243},"GB2-02":{"draws":326,"losses":93,"wins":13},"GB2-03":{"draws":139,"losses":208,"wins":99},"GB2-05":{"draws":0,"losses":227,"wins":257},"GB2-06":{"draws":30,"losses":210,"wins":216},"GB2-07":{"draws":0,"losses":292,"wins":182},"GB2-08":{"draws":227,"losses":257,"wins":2}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1517.9392729797335,"GB2-02":1615.8199185353449,"GB2-03":1572.7968127512622,"GB2-04":1543.627514429262,"GB2-05":1587.2156495782647,"GB2-06":1736.4984181270656,"GB2-07":1983.2997287413896,"GB2-08":1195.511188994022},"none":{"GB2-01":1665.2011598556505,"GB2-02":1414.19827218165,"GB2-03":1361.1689932301854,"GB2-05":1494.1544837085542,"GB2-06":1492.8639201817207,"GB2-07":1333.4377178490117,"GB2-08":1161.9848596697861}},"per_game_tracks":{"medium":{"GB2-01":53.70151094438849,"GB2-02":66.95682571299996,"GB2-03":64.30148957733782,"GB2-04":58.29527697564496,"GB2-05":60.48243455121046,"GB2-06":66.94130045267329,"GB2-07":83.7406737739015,"GB2-08":27.690563122914792},"none":{"GB2-01":68.14248856556642,"GB2-02":42.00849944672796,"GB2-03":41.04718621216857,"GB2-05":53.36359265550307,"GB2-06":52.59948311467512,"GB2-07":40.71420405836734,"GB2-08":24.643158734968512}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":60.263759388883905,"none":40.31482659849712},"reasoning_agg":{"medium":{"max":83.7406737739015,"mean":60.263759388883905,"min":27.690563122914792},"none":{"max":68.14248856556642,"mean":40.31482659849712,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":19.948932790386785}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:a78fcb9a5f009aff","codegen_cost_by_reasoning":{"medium":{"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":0.30150960000000004},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.027488630000000003}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899823000000006},"codegen_latency_ms":{"attempt_count":22,"max_ms":1377805,"mean_ms":526774.25,"min_ms":30630,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1377805,"mean_ms":998592.5,"min_ms":680734,"run_count":8},"none":{"attempt_count":11,"max_ms":104368,"mean_ms":54956.0,"min_ms":30630,"run_count":8}},"codegen_output_tokens":{"attempt_count":22,"output_max":125053,"output_mean":40030.0625,"output_min":2070,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":125053,"output_mean":76276.375,"output_min":52513,"run_count":8},"none":{"attempt_count":11,"output_max":7265,"output_mean":3783.75,"output_min":2070,"run_count":8}},"display_name":"Qwen3.8 Flash","economics":{"medium":60.9920757821213,"none":34.9165293687167},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":22,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":22,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"reconciliation_get_attempts":100,"total_output_tokens":640481,"total_reasoning_output_tokens":544948,"total_visible_output_tokens":95533,"visible_token_observations":22},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.998111526572345,"score":42.998111526572345},"GB2-02":{"attempts":2,"playable":50.21599557114878,"score":50.21599557114878},"GB2-03":{"attempts":2,"playable":57.04586363743972,"score":57.04586363743972},"GB2-04":{"attempts":2,"playable":42.96892869183892,"score":42.96892869183892},"GB2-05":{"attempts":2,"playable":44.91995839551188,"score":44.91995839551188},"GB2-06":{"attempts":2,"playable":67.16798408977617,"score":67.16798408977617},"GB2-07":{"attempts":2,"playable":42.4368465341463,"score":42.4368465341463},"GB2-08":{"attempts":2,"playable":35.88073215691793,"score":35.88073215691793}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":51.335748181833665,"score":51.335748181833665},"GB2-02":{"attempts":1,"playable":57.26634105066082,"score":57.26634105066082},"GB2-03":{"attempts":1,"playable":67.16634695254893,"score":67.16634695254893},"GB2-04":{"attempts":1,"playable":45.43743637182478,"score":45.43743637182478},"GB2-05":{"attempts":1,"playable":72.60385456024665,"score":72.60385456024665},"GB2-06":{"attempts":1,"playable":79.48842679144681,"score":79.48842679144681},"GB2-07":{"attempts":1,"playable":75.01557107915292,"score":75.01557107915292},"GB2-08":{"attempts":1,"playable":39.62288126925586,"score":39.62288126925586}},"none":{"GB2-01":{"attempts":1,"playable":34.66047487131102,"score":34.66047487131102},"GB2-02":{"attempts":1,"playable":43.165650091636735,"score":43.165650091636735},"GB2-03":{"attempts":1,"playable":46.925380322330504,"score":46.925380322330504},"GB2-04":{"attempts":1,"playable":40.50042101185306,"score":40.50042101185306},"GB2-05":{"attempts":1,"playable":17.23606223077711,"score":17.23606223077711},"GB2-06":{"attempts":1,"playable":54.847541388105526,"score":54.847541388105526},"GB2-07":{"attempts":1,"playable":9.858121989139674,"score":9.858121989139674},"GB2-08":{"attempts":1,"playable":32.13858304457999,"score":32.13858304457999}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-14T17:54:41Z","match_totals_all":{"draws":3271,"losses":3832,"wins":3141},"match_totals_tracks":{"medium":{"draws":1600,"losses":1328,"wins":2212},"none":{"draws":1671,"losses":2504,"wins":929}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":79.48842679144681,"mean":47.954302575419,"min":9.858121989139674},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":416,"losses":555,"wins":373},"GB2-02":{"draws":835,"losses":185,"wins":172},"GB2-03":{"draws":325,"losses":427,"wins":474},"GB2-04":{"draws":785,"losses":290,"wins":139},"GB2-05":{"draws":0,"losses":718,"wins":582},"GB2-06":{"draws":90,"losses":422,"wins":794},"GB2-07":{"draws":0,"losses":752,"wins":516},"GB2-08":{"draws":820,"losses":483,"wins":91}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":253,"losses":232,"wins":223},"GB2-02":{"draws":341,"losses":92,"wins":159},"GB2-03":{"draws":142,"losses":157,"wins":303},"GB2-04":{"draws":364,"losses":143,"wins":99},"GB2-05":{"draws":0,"losses":191,"wins":463},"GB2-06":{"draws":74,"losses":106,"wins":436},"GB2-07":{"draws":0,"losses":177,"wins":461},"GB2-08":{"draws":426,"losses":230,"wins":68}},"none":{"GB2-01":{"draws":163,"losses":323,"wins":150},"GB2-02":{"draws":494,"losses":93,"wins":13},"GB2-03":{"draws":183,"losses":270,"wins":171},"GB2-04":{"draws":421,"losses":147,"wins":40},"GB2-05":{"draws":0,"losses":527,"wins":119},"GB2-06":{"draws":16,"losses":316,"wins":358},"GB2-07":{"draws":0,"losses":575,"wins":55},"GB2-08":{"draws":394,"losses":253,"wins":23}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1495.1623456396428,"GB2-02":1532.9950980487545,"GB2-03":1603.2081795532629,"GB2-04":1442.7844700561252,"GB2-05":1776.549021269311,"GB2-06":1974.0670464266423,"GB2-07":1802.3299921726807,"GB2-08":1317.6596597211292},"none":{"GB2-01":1332.7691407990421,"GB2-02":1423.1686627689146,"GB2-03":1412.0543589789831,"GB2-04":1404.394725957357,"GB2-05":965.4883526098827,"GB2-06":1529.1750739346962,"GB2-07":828.316454941568,"GB2-08":1242.0815961216988}},"per_game_tracks":{"medium":{"GB2-01":51.335748181833665,"GB2-02":57.26634105066082,"GB2-03":67.16634695254893,"GB2-04":45.43743637182478,"GB2-05":72.60385456024665,"GB2-06":79.48842679144681,"GB2-07":75.01557107915292,"GB2-08":39.62288126925586},"none":{"GB2-01":34.66047487131102,"GB2-02":43.165650091636735,"GB2-03":46.925380322330504,"GB2-04":40.50042101185306,"GB2-05":17.23606223077711,"GB2-06":54.847541388105526,"GB2-07":9.858121989139674,"GB2-08":32.13858304457999}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":60.9920757821213,"none":34.9165293687167},"reasoning_agg":{"medium":{"max":79.48842679144681,"mean":60.9920757821213,"min":39.62288126925586},"none":{"max":54.847541388105526,"mean":34.9165293687167,"min":9.858121989139674}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":26.075546413404595}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:8588f7e459b09704","codegen_cost_by_reasoning":{"highest":{"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},"none":{"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":0.16924833000000003}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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":1.5289414000000001}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.33846634,"mean":0.10613685812499998,"median":0.05239252,"min":0.01134557,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.69818973},"codegen_latency_ms":{"attempt_count":23,"max_ms":2372746,"mean_ms":755436.1875,"min_ms":27078,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":2372746,"mean_ms":1420193.375,"min_ms":412995,"run_count":8},"none":{"attempt_count":13,"max_ms":165291,"mean_ms":90679.0,"min_ms":27078,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":159550,"output_mean":46908.8125,"output_min":3069,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":159550,"output_mean":88125.0,"output_min":32501,"run_count":8},"none":{"attempt_count":13,"output_max":9287,"output_mean":5692.625,"output_min":3069,"run_count":8}},"display_name":"Mistral Large 4","economics":{"highest":57.892542404711925,"none":40.84754994743407},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[262144],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[262144],"total_output_tokens":750541,"total_reasoning_output_tokens":655796,"total_visible_output_tokens":94745,"visible_token_observations":23},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":262144,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-large-4-0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":47.09464443615136,"score":47.09464443615136},"GB2-02":{"attempts":2,"playable":54.27175501903388,"score":54.27175501903388},"GB2-03":{"attempts":2,"playable":37.24103838613979,"score":37.24103838613979},"GB2-04":{"attempts":2,"playable":52.13906587054657,"score":52.13906587054657},"GB2-05":{"attempts":2,"playable":56.8154573838041,"score":56.8154573838041},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":80.2907506875607,"score":40.14537534378035},"GB2-07":{"attempts":2,"playable":44.819393096330536,"score":44.819393096330536},"GB2-08":{"attempts":2,"playable":42.00986489908032,"score":42.00986489908032}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":34.36418983626872,"score":34.36418983626872},"GB2-02":{"attempts":1,"playable":65.37059502096302,"score":65.37059502096302},"GB2-03":{"attempts":1,"playable":43.79543531856587,"score":43.79543531856587},"GB2-04":{"attempts":1,"playable":65.71727468495449,"score":65.71727468495449},"GB2-05":{"attempts":1,"playable":50.01222255140794,"score":50.01222255140794},"GB2-06":{"attempts":1,"playable":80.2907506875607,"score":80.2907506875607},"GB2-07":{"attempts":1,"playable":79.7497734986751,"score":79.7497734986751},"GB2-08":{"attempts":1,"playable":43.84009763929952,"score":43.84009763929952}},"none":{"GB2-01":{"attempts":1,"playable":59.825099036034004,"score":59.825099036034004},"GB2-02":{"attempts":1,"playable":43.17291501710474,"score":43.17291501710474},"GB2-03":{"attempts":1,"playable":30.68664145371372,"score":30.68664145371372},"GB2-04":{"attempts":1,"playable":38.560857056138644,"score":38.560857056138644},"GB2-05":{"attempts":1,"playable":63.618692216200266,"score":63.618692216200266},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.88901269398598,"score":9.88901269398598},"GB2-08":{"attempts":1,"playable":40.17963215886112,"score":40.17963215886112}}},"id":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-10-15T06:55:22Z","match_totals_all":{"draws":2054,"losses":2527,"wins":2351},"match_totals_tracks":{"highest":{"draws":918,"losses":1141,"wins":1635},"none":{"draws":1136,"losses":1386,"wins":716}},"model_slug":"mistralai-mistral-large-4-0","overall":{"max":80.2907506875607,"mean":46.81707430435837,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":34.36418983626872,"GB2-02":65.37059502096302,"GB2-03":43.79543531856587,"GB2-04":65.71727468495449,"GB2-05":50.01222255140794,"GB2-06":80.2907506875607,"GB2-07":79.7497734986751,"GB2-08":43.84009763929952},"per_game_match_totals_all":{"GB2-01":{"draws":120,"losses":444,"wins":372},"GB2-02":{"draws":589,"losses":111,"wins":164},"GB2-03":{"draws":319,"losses":428,"wins":145},"GB2-04":{"draws":477,"losses":201,"wins":218},"GB2-05":{"draws":0,"losses":421,"wins":547},"GB2-06":{"draws":34,"losses":73,"wins":349},"GB2-07":{"draws":0,"losses":531,"wins":417},"GB2-08":{"draws":515,"losses":318,"wins":139}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":301,"wins":145},"GB2-02":{"draws":233,"losses":38,"wins":161},"GB2-03":{"draws":167,"losses":182,"wins":97},"GB2-04":{"draws":206,"losses":56,"wins":186},"GB2-05":{"draws":0,"losses":243,"wins":241},"GB2-06":{"draws":34,"losses":73,"wins":349},"GB2-07":{"draws":0,"losses":97,"wins":377},"GB2-08":{"draws":256,"losses":151,"wins":79}},"none":{"GB2-01":{"draws":98,"losses":143,"wins":227},"GB2-02":{"draws":356,"losses":73,"wins":3},"GB2-03":{"draws":152,"losses":246,"wins":48},"GB2-04":{"draws":271,"losses":145,"wins":32},"GB2-05":{"draws":0,"losses":178,"wins":306},"GB2-07":{"draws":0,"losses":434,"wins":40},"GB2-08":{"draws":259,"losses":167,"wins":60}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1329.733676799675,"GB2-02":1601.446080063768,"GB2-03":1384.9748025119168,"GB2-04":1606.7566642531872,"GB2-05":1451.9374292823388,"GB2-06":1990.183789337923,"GB2-07":1891.7596916392235,"GB2-08":1360.3916566151302},"none":{"GB2-01":1578.081058971144,"GB2-02":1423.2248704314998,"GB2-03":1268.1169905449037,"GB2-04":1389.072068275135,"GB2-05":1631.101450701966,"GB2-07":829.1673660176565,"GB2-08":1323.2634564946932}},"per_game_tracks":{"highest":{"GB2-01":34.36418983626872,"GB2-02":65.37059502096302,"GB2-03":43.79543531856587,"GB2-04":65.71727468495449,"GB2-05":50.01222255140794,"GB2-06":80.2907506875607,"GB2-07":79.7497734986751,"GB2-08":43.84009763929952},"none":{"GB2-01":59.825099036034004,"GB2-02":43.17291501710474,"GB2-03":30.68664145371372,"GB2-04":38.560857056138644,"GB2-05":63.618692216200266,"GB2-07":9.88901269398598,"GB2-08":40.17963215886112}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.892542404711925,"none":35.74160620400481},"reasoning_agg":{"highest":{"max":80.2907506875607,"mean":57.892542404711925,"min":34.36418983626872},"none":{"max":63.618692216200266,"mean":35.74160620400481,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":22.150936200707115}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:8e6f19a50c9cfbcd","codegen_cost_by_reasoning":{"none":{"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":0.4575640000000001}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"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_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":0.4575640000000001},"codegen_latency_ms":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":11,"max_ms":57255,"mean_ms":36267.375,"min_ms":22935,"run_count":8}},"codegen_output_tokens":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":11,"output_max":7568,"output_mean":4433.625,"output_min":2259,"run_count":8}},"display_name":"GPT-4.1","economics":{"none":41.868615462324165},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":11,"finish_reasons":["stop"],"indexed_attempts":11,"output_token_observations":11,"total_output_tokens":35469},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":60.848907283242404,"score":60.848907283242404},"GB2-02":{"attempts":1,"playable":42.55385244160608,"score":42.55385244160608},"GB2-03":{"attempts":1,"playable":41.064056823011654,"score":41.064056823011654},"GB2-04":{"attempts":1,"playable":37.5857002970769,"score":37.5857002970769},"GB2-05":{"attempts":1,"playable":13.304237011308523,"score":13.304237011308523},"GB2-06":{"attempts":1,"playable":50.31092999743644,"score":50.31092999743644},"GB2-07":{"attempts":1,"playable":47.9830554402282,"score":47.9830554402282},"GB2-08":{"attempts":1,"playable":41.29818440468312,"score":41.29818440468312}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":60.848907283242404,"score":60.848907283242404},"GB2-02":{"attempts":1,"playable":42.55385244160608,"score":42.55385244160608},"GB2-03":{"attempts":1,"playable":41.064056823011654,"score":41.064056823011654},"GB2-04":{"attempts":1,"playable":37.5857002970769,"score":37.5857002970769},"GB2-05":{"attempts":1,"playable":13.304237011308523,"score":13.304237011308523},"GB2-06":{"attempts":1,"playable":50.31092999743644,"score":50.31092999743644},"GB2-07":{"attempts":1,"playable":47.9830554402282,"score":47.9830554402282},"GB2-08":{"attempts":1,"playable":41.29818440468312,"score":41.29818440468312}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-10-14T17:26:42Z","match_totals_all":{"draws":1462,"losses":1993,"wins":1262},"match_totals_tracks":{"none":{"draws":1462,"losses":1993,"wins":1262}},"model_slug":"gpt-4-1","overall":{"max":60.848907283242404,"mean":41.868615462324165,"min":13.304237011308523},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":214,"wins":333},"GB2-02":{"draws":482,"losses":91,"wins":5},"GB2-03":{"draws":137,"losses":261,"wins":150},"GB2-04":{"draws":382,"losses":167,"wins":29},"GB2-05":{"draws":0,"losses":498,"wins":100},"GB2-06":{"draws":35,"losses":269,"wins":286},"GB2-07":{"draws":0,"losses":312,"wins":286},"GB2-08":{"draws":382,"losses":181,"wins":73}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":44,"losses":214,"wins":333},"GB2-02":{"draws":482,"losses":91,"wins":5},"GB2-03":{"draws":137,"losses":261,"wins":150},"GB2-04":{"draws":382,"losses":167,"wins":29},"GB2-05":{"draws":0,"losses":498,"wins":100},"GB2-06":{"draws":35,"losses":269,"wins":286},"GB2-07":{"draws":0,"losses":312,"wins":286},"GB2-08":{"draws":382,"losses":181,"wins":73}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1588.3884922891166,"GB2-02":1418.4305408309122,"GB2-03":1361.3155584771343,"GB2-04":1381.2894152944316,"GB2-05":881.5394635182919,"GB2-06":1456.4235305048232,"GB2-07":1424.1896031801728,"GB2-08":1334.5475509914045}},"per_game_tracks":{"none":{"GB2-01":60.848907283242404,"GB2-02":42.55385244160608,"GB2-03":41.064056823011654,"GB2-04":37.5857002970769,"GB2-05":13.304237011308523,"GB2-06":50.31092999743644,"GB2-07":47.9830554402282,"GB2-08":41.29818440468312}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":41.868615462324165},"reasoning_agg":{"none":{"max":60.848907283242404,"mean":41.868615462324165,"min":13.304237011308523}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:ca5706e1289410bb","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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_cost_usd":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":47.36451342546491},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":18,"finish_reasons":["length","stop"],"indexed_attempts":18,"output_token_observations":18,"total_output_tokens":308283},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k2.7-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":7,"failed_game_aliases":["GB2-06"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03"],"infra_failures_excluded":1,"model_code_failure_rate":0.14285714285714285,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":6,"repaired_rate":0.8571428571428571}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":38.68067838158645,"score":38.68067838158645},"GB2-02":{"attempts":1,"playable":42.36877101638822,"score":42.36877101638822},"GB2-04":{"attempts":1,"playable":39.42861390543466,"score":39.42861390543466},"GB2-05":{"attempts":1,"playable":52.17248886582673,"score":52.17248886582673},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.35564553797386,"score":43.35564553797386},"GB2-08":{"attempts":1,"playable":68.18088284557948,"score":68.18088284557948}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":38.68067838158645,"score":38.68067838158645},"GB2-02":{"attempts":1,"playable":42.36877101638822,"score":42.36877101638822},"GB2-04":{"attempts":1,"playable":39.42861390543466,"score":39.42861390543466},"GB2-05":{"attempts":1,"playable":52.17248886582673,"score":52.17248886582673},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.35564553797386,"score":43.35564553797386},"GB2-08":{"attempts":1,"playable":68.18088284557948,"score":68.18088284557948}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-10-14T17:55:01Z","match_totals_all":{"draws":899,"losses":1434,"wins":1278},"match_totals_tracks":{"medium":{"draws":899,"losses":1434,"wins":1278}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":68.18088284557948,"mean":40.598154364684206,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":13,"losses":345,"wins":237},"GB2-02":{"draws":451,"losses":115,"wins":20},"GB2-04":{"draws":371,"losses":165,"wins":48},"GB2-05":{"draws":0,"losses":293,"wins":315},"GB2-07":{"draws":0,"losses":341,"wins":273},"GB2-08":{"draws":64,"losses":175,"wins":385}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":13,"losses":345,"wins":237},"GB2-02":{"draws":451,"losses":115,"wins":20},"GB2-04":{"draws":371,"losses":165,"wins":48},"GB2-05":{"draws":0,"losses":293,"wins":315},"GB2-07":{"draws":0,"losses":341,"wins":273},"GB2-08":{"draws":64,"losses":175,"wins":385}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1373.130750436223,"GB2-02":1416.995181533216,"GB2-04":1395.950957759717,"GB2-05":1479.0941142223414,"GB2-07":1366.494263983981,"GB2-08":1660.0376286811088}},"per_game_tracks":{"medium":{"GB2-01":38.68067838158645,"GB2-02":42.36877101638822,"GB2-04":39.42861390543466,"GB2-05":52.17248886582673,"GB2-07":43.35564553797386,"GB2-08":68.18088284557948}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.598154364684206},"reasoning_agg":{"medium":{"max":68.18088284557948,"mean":40.598154364684206,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:2b64bf35e39106cc","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965},"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":2.0151682500000003},"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":1.503294825,"median":1.503294825,"min":1.503294825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":3.00658965}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":22},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":1.503294825,"mean":0.2156185632352941,"median":0.169101,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":22},"recorded_attempt_count":2,"run_count":18,"token_priced_attempt_count":22,"total":5.1688104},"codegen_latency_ms":{"attempt_count":22,"max_ms":1819696,"mean_ms":244013.16666666666,"min_ms":11548,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1819696,"mean_ms":1344520.5,"min_ms":869345,"run_count":2},"medium":{"attempt_count":9,"max_ms":308347,"mean_ms":195019.75,"min_ms":115259,"run_count":8},"none":{"attempt_count":10,"max_ms":30363,"mean_ms":17879.75,"min_ms":11548,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":383888,"output_mean":60889.444444444445,"output_min":1571,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":383888,"output_mean":319916.0,"output_min":255944,"run_count":2},"medium":{"attempt_count":9,"output_max":69661,"output_mean":54514.75,"output_min":36373,"run_count":8},"none":{"attempt_count":10,"output_max":4247,"output_mean":2507.5,"output_min":1571,"run_count":8}},"display_name":"GPT-5.4 Mini","economics":{"medium":48.88724352541986,"none":30.41270042022714},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":21,"finish_reasons":["incomplete","stop"],"indexed_attempts":24,"output_token_observations":24,"reasoning_token_observations":2,"total_output_tokens":1096010,"total_reasoning_output_tokens":255888,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-mini","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":51.31061182124415,"score":51.31061182124415},"GB2-02":{"attempts":2,"playable":41.7193805355057,"score":41.7193805355057},"GB2-03":{"attempts":2,"playable":44.79301970716246,"score":44.79301970716246},"GB2-04":{"attempts":2,"playable":44.88106868846697,"score":44.88106868846697},"GB2-05":{"attempts":2,"playable":29.474145768420694,"score":29.474145768420694},"GB2-06":{"attempts":2,"playable":39.03612667031182,"score":39.03612667031182},"GB2-07":{"attempts":2,"playable":26.952306389793087,"score":26.952306389793087},"GB2-08":{"attempts":2,"playable":39.0331162016831,"score":39.0331162016831}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":69.91144599022908,"score":69.91144599022908},"GB2-02":{"attempts":1,"playable":41.774697297640806,"score":41.774697297640806},"GB2-03":{"attempts":1,"playable":45.857763144591665,"score":45.857763144591665},"GB2-04":{"attempts":1,"playable":46.27252407936975,"score":46.27252407936975},"GB2-05":{"attempts":1,"playable":47.47933934999746,"score":47.47933934999746},"GB2-06":{"attempts":1,"playable":47.98713690526481,"score":47.98713690526481},"GB2-07":{"attempts":1,"playable":47.76753090430773,"score":47.76753090430773},"GB2-08":{"attempts":1,"playable":44.04751053195751,"score":44.04751053195751}},"none":{"GB2-01":{"attempts":1,"playable":32.70977765225922,"score":32.70977765225922},"GB2-02":{"attempts":1,"playable":41.66406377337059,"score":41.66406377337059},"GB2-03":{"attempts":1,"playable":43.72827626973324,"score":43.72827626973324},"GB2-04":{"attempts":1,"playable":43.48961329756418,"score":43.48961329756418},"GB2-05":{"attempts":1,"playable":11.46895218684393,"score":11.46895218684393},"GB2-06":{"attempts":1,"playable":30.085116435358835,"score":30.085116435358835},"GB2-07":{"attempts":1,"playable":6.1370818752784375,"score":6.1370818752784375},"GB2-08":{"attempts":1,"playable":34.018721871408694,"score":34.018721871408694}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-10-14T17:24:50Z","match_totals_all":{"draws":3168,"losses":4016,"wins":2145},"match_totals_tracks":{"medium":{"draws":1330,"losses":1752,"wins":1635},"none":{"draws":1838,"losses":2264,"wins":510}},"model_slug":"gpt-5-4-mini","overall":{"max":69.91144599022908,"mean":39.6499719728235,"min":6.1370818752784375},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":224,"losses":448,"wins":474},"GB2-02":{"draws":911,"losses":188,"wins":11},"GB2-03":{"draws":641,"losses":297,"wins":147},"GB2-04":{"draws":713,"losses":271,"wins":162},"GB2-05":{"draws":0,"losses":810,"wins":382},"GB2-06":{"draws":75,"losses":650,"wins":439},"GB2-07":{"draws":0,"losses":889,"wins":337},"GB2-08":{"draws":604,"losses":463,"wins":193}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":34,"losses":161,"wins":375},"GB2-02":{"draws":452,"losses":98,"wins":10},"GB2-03":{"draws":214,"losses":203,"wins":132},"GB2-04":{"draws":363,"losses":122,"wins":83},"GB2-05":{"draws":0,"losses":308,"wins":296},"GB2-06":{"draws":53,"losses":273,"wins":266},"GB2-07":{"draws":0,"losses":328,"wins":298},"GB2-08":{"draws":214,"losses":259,"wins":175}},"none":{"GB2-01":{"draws":190,"losses":287,"wins":99},"GB2-02":{"draws":459,"losses":90,"wins":1},"GB2-03":{"draws":427,"losses":94,"wins":15},"GB2-04":{"draws":350,"losses":149,"wins":79},"GB2-05":{"draws":0,"losses":502,"wins":86},"GB2-06":{"draws":22,"losses":377,"wins":173},"GB2-07":{"draws":0,"losses":561,"wins":39},"GB2-08":{"draws":390,"losses":204,"wins":18}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1685.0280814783393,"GB2-02":1412.381010407928,"GB2-03":1402.8080594077435,"GB2-04":1449.2337392169127,"GB2-05":1420.1770260154117,"GB2-06":1419.8669788843997,"GB2-07":1421.4985737904642,"GB2-08":1362.516910168056},"none":{"GB2-01":1312.5966287638826,"GB2-02":1411.5204660769461,"GB2-03":1384.3941113146475,"GB2-04":1427.7098973403984,"GB2-05":837.4250436566115,"GB2-06":1145.9249458608992,"GB2-07":706.6862126976207,"GB2-08":1261.2425895869171}},"per_game_tracks":{"medium":{"GB2-01":69.91144599022908,"GB2-02":41.774697297640806,"GB2-03":45.857763144591665,"GB2-04":46.27252407936975,"GB2-05":47.47933934999746,"GB2-06":47.98713690526481,"GB2-07":47.76753090430773,"GB2-08":44.04751053195751},"none":{"GB2-01":32.70977765225922,"GB2-02":41.66406377337059,"GB2-03":43.72827626973324,"GB2-04":43.48961329756418,"GB2-05":11.46895218684393,"GB2-06":30.085116435358835,"GB2-07":6.1370818752784375,"GB2-08":34.018721871408694}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":48.88724352541986,"none":30.41270042022714},"reasoning_agg":{"medium":{"max":69.91144599022908,"mean":48.88724352541986,"min":41.774697297640806},"none":{"max":43.72827626973324,"mean":30.41270042022714,"min":6.1370818752784375}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":18.474543105192723}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:023fe3dc3324481d","codegen_cost_by_reasoning":{"medium":{"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":1.0777302951999999},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":1.0777302951999999},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2996388,"mean":0.08320818615,"median":0.048126608099999996,"min":0.0057139812,"recorded_attempt_count":28,"run_count":16,"total":1.3313309783999998},"codegen_latency_ms":{"attempt_count":28,"max_ms":2144825,"mean_ms":691475.625,"min_ms":43161,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":2144825,"mean_ms":1159734.625,"min_ms":304276,"run_count":8},"none":{"attempt_count":11,"max_ms":886851,"mean_ms":223216.625,"min_ms":43161,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":131072,"output_mean":41065.3125,"output_min":2846,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":71259.5,"output_min":16045,"run_count":8},"none":{"attempt_count":11,"output_max":42691,"output_mean":10871.125,"output_min":2846,"run_count":8}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":47.08221260561021,"none":35.40300689525171},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["error","length","stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":657045},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":6,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-02","GB2-03"],"infra_failures_excluded":2,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":6,"repaired_rate":1.0},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":53.37506767904169,"score":53.37506767904169},"GB2-02":{"attempts":1,"playable":39.77711179479568,"score":39.77711179479568},"GB2-03":{"attempts":1,"playable":34.188758000787594,"score":34.188758000787594},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":48.332301366041484,"score":24.166150683020742},"GB2-05":{"attempts":2,"playable":22.514955813724747,"score":22.514955813724747},"GB2-06":{"attempts":2,"playable":52.91403190814275,"score":52.91403190814275},"GB2-07":{"attempts":2,"playable":45.21479466381896,"score":45.21479466381896},"GB2-08":{"attempts":2,"playable":29.989226304671067,"score":29.989226304671067}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":71.26763413710049,"score":71.26763413710049},"GB2-04":{"attempts":1,"playable":48.332301366041484,"score":48.332301366041484},"GB2-05":{"attempts":1,"playable":24.374677418915006,"score":24.374677418915006},"GB2-06":{"attempts":1,"playable":68.82102163249591,"score":68.82102163249591},"GB2-07":{"attempts":1,"playable":41.34202075649036,"score":41.34202075649036},"GB2-08":{"attempts":1,"playable":28.35562032261799,"score":28.35562032261799}},"none":{"GB2-01":{"attempts":1,"playable":35.4825012209829,"score":35.4825012209829},"GB2-02":{"attempts":1,"playable":39.77711179479568,"score":39.77711179479568},"GB2-03":{"attempts":1,"playable":34.188758000787594,"score":34.188758000787594},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":20.655234208534484,"score":20.655234208534484},"GB2-06":{"attempts":1,"playable":37.00704218378959,"score":37.00704218378959},"GB2-07":{"attempts":1,"playable":49.08756857114755,"score":49.08756857114755},"GB2-08":{"attempts":1,"playable":31.622832286724144,"score":31.622832286724144}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-13T22:51:06Z","match_totals_all":{"draws":1874,"losses":3659,"wins":2347},"match_totals_tracks":{"medium":{"draws":762,"losses":1621,"wins":1437},"none":{"draws":1112,"losses":2038,"wins":910}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":71.26763413710049,"mean":39.02992181947773,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":251,"losses":511,"wins":598},"GB2-02":{"draws":395,"losses":136,"wins":27},"GB2-03":{"draws":220,"losses":248,"wins":74},"GB2-04":{"draws":294,"losses":148,"wins":130},"GB2-05":{"draws":0,"losses":904,"wins":314},"GB2-06":{"draws":22,"losses":552,"wins":624},"GB2-07":{"draws":0,"losses":680,"wins":564},"GB2-08":{"draws":692,"losses":480,"wins":16}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":93,"losses":207,"wins":458},"GB2-04":{"draws":294,"losses":148,"wins":130},"GB2-05":{"draws":0,"losses":445,"wins":171},"GB2-06":{"draws":16,"losses":189,"wins":405},"GB2-07":{"draws":0,"losses":363,"wins":269},"GB2-08":{"draws":359,"losses":269,"wins":4}},"none":{"GB2-01":{"draws":158,"losses":304,"wins":140},"GB2-02":{"draws":395,"losses":136,"wins":27},"GB2-03":{"draws":220,"losses":248,"wins":74},"GB2-05":{"draws":0,"losses":459,"wins":143},"GB2-06":{"draws":6,"losses":363,"wins":219},"GB2-07":{"draws":0,"losses":317,"wins":295},"GB2-08":{"draws":333,"losses":211,"wins":12}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1700.6473691744552,"GB2-04":1465.1371306941924,"GB2-05":1095.573175061923,"GB2-06":1770.7070102076254,"GB2-07":1341.3156577272855,"GB2-08":1202.623119440429},"none":{"GB2-01":1341.1421793475458,"GB2-02":1396.770800844954,"GB2-03":1300.515203233649,"GB2-05":1030.6006088524587,"GB2-06":1250.9447269562825,"GB2-07":1437.9981341387129,"GB2-08":1236.7833399228143}},"per_game_tracks":{"medium":{"GB2-01":71.26763413710049,"GB2-04":48.332301366041484,"GB2-05":24.374677418915006,"GB2-06":68.82102163249591,"GB2-07":41.34202075649036,"GB2-08":28.35562032261799},"none":{"GB2-01":35.4825012209829,"GB2-02":39.77711179479568,"GB2-03":34.188758000787594,"GB2-05":20.655234208534484,"GB2-06":37.00704218378959,"GB2-07":49.08756857114755,"GB2-08":31.622832286724144}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":47.08221260561021,"none":30.977631033345244},"reasoning_agg":{"medium":{"max":71.26763413710049,"mean":47.08221260561021,"min":24.374677418915006},"none":{"max":49.08756857114755,"mean":30.977631033345244,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.104581572264966}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:7528e8434c2eda2e","codegen_cost_by_reasoning":{"medium":{"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":0.7288237500000001},"none":{"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":0.18239875}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.72882375},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.12185499999999999,"mean":0.05695140625,"median":0.036751875,"min":0.015285,"recorded_attempt_count":24,"run_count":16,"total":0.9112225},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":45.16125545813015,"none":41.296915735580846},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"total_output_tokens":178317},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-max","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.75},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.875,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.878571819927096,"score":42.878571819927096},"GB2-02":{"attempts":2,"playable":45.219102074765956,"score":45.219102074765956},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":30.56787156293219,"score":15.283935781466095},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.68644335333745,"score":21.843221676668726},"GB2-05":{"attempts":2,"playable":38.34734933438354,"score":38.34734933438354},"GB2-06":{"attempts":2,"playable":37.48476480180349,"score":37.48476480180349},"GB2-07":{"attempts":2,"playable":69.02502693802467,"score":69.02502693802467},"GB2-08":{"attempts":2,"playable":32.52162675094892,"score":32.52162675094892}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":17.928108226844188,"score":17.928108226844188},"GB2-02":{"attempts":1,"playable":44.12068985108434,"score":44.12068985108434},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.68644335333745,"score":43.68644335333745},"GB2-05":{"attempts":1,"playable":40.53747592815602,"score":40.53747592815602},"GB2-06":{"attempts":1,"playable":58.90837876422969,"score":58.90837876422969},"GB2-07":{"attempts":1,"playable":77.12254152892164,"score":77.12254152892164},"GB2-08":{"attempts":1,"playable":33.82515055433771,"score":33.82515055433771}},"none":{"GB2-01":{"attempts":1,"playable":67.82903541301,"score":67.82903541301},"GB2-02":{"attempts":1,"playable":46.31751429844758,"score":46.31751429844758},"GB2-03":{"attempts":1,"playable":30.56787156293219,"score":30.56787156293219},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":36.15722274061106,"score":36.15722274061106},"GB2-06":{"attempts":1,"playable":16.061150839377298,"score":16.061150839377298},"GB2-07":{"attempts":1,"playable":60.92751234712769,"score":60.92751234712769},"GB2-08":{"attempts":1,"playable":31.218102947560123,"score":31.218102947560123}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-10-13T23:00:16Z","match_totals_all":{"draws":2525,"losses":3427,"wins":2374},"match_totals_tracks":{"medium":{"draws":1334,"losses":1623,"wins":1267},"none":{"draws":1191,"losses":1804,"wins":1107}},"model_slug":"qwen-qwen3-7-max","overall":{"max":77.12254152892164,"mean":37.82544989724856,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":278,"losses":526,"wins":356},"GB2-02":{"draws":853,"losses":193,"wins":84},"GB2-03":{"draws":247,"losses":251,"wins":38},"GB2-04":{"draws":333,"losses":162,"wins":97},"GB2-05":{"draws":0,"losses":750,"wins":506},"GB2-06":{"draws":64,"losses":686,"wins":428},"GB2-07":{"draws":0,"losses":367,"wins":815},"GB2-08":{"draws":750,"losses":492,"wins":50}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":108,"losses":414,"wins":62},"GB2-02":{"draws":453,"losses":95,"wins":26},"GB2-04":{"draws":333,"losses":162,"wins":97},"GB2-05":{"draws":0,"losses":364,"wins":266},"GB2-06":{"draws":60,"losses":214,"wins":322},"GB2-07":{"draws":0,"losses":134,"wins":462},"GB2-08":{"draws":380,"losses":240,"wins":32}},"none":{"GB2-01":{"draws":170,"losses":112,"wins":294},"GB2-02":{"draws":400,"losses":98,"wins":58},"GB2-03":{"draws":247,"losses":251,"wins":38},"GB2-05":{"draws":0,"losses":386,"wins":240},"GB2-06":{"draws":4,"losses":472,"wins":106},"GB2-07":{"draws":0,"losses":233,"wins":353},"GB2-08":{"draws":370,"losses":252,"wins":18}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1134.117759493411,"GB2-02":1430.5479659567886,"GB2-04":1429.2361973776997,"GB2-05":1331.725001678669,"GB2-06":1596.3546967723237,"GB2-07":1840.2396693287435,"GB2-08":1259.2793103461913},"none":{"GB2-01":1661.7464563818735,"GB2-02":1447.4722475279164,"GB2-03":1266.992997222227,"GB2-05":1273.2414331128602,"GB2-06":919.9823485538259,"GB2-07":1590.681686482521,"GB2-08":1232.61039966563}},"per_game_tracks":{"medium":{"GB2-01":17.928108226844188,"GB2-02":44.12068985108434,"GB2-04":43.68644335333745,"GB2-05":40.53747592815602,"GB2-06":58.90837876422969,"GB2-07":77.12254152892164,"GB2-08":33.82515055433771},"none":{"GB2-01":67.82903541301,"GB2-02":46.31751429844758,"GB2-03":30.56787156293219,"GB2-05":36.15722274061106,"GB2-06":16.061150839377298,"GB2-07":60.92751234712769,"GB2-08":31.218102947560123}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.51609852586388,"none":36.13480126863324},"reasoning_agg":{"medium":{"max":77.12254152892164,"mean":39.51609852586388,"min":0.0},"none":{"max":67.82903541301,"mean":36.13480126863324,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":3.381297257230642}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:996839815f24af4e","codegen_cost_by_reasoning":{"medium":{"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":0.4852846}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.4852846}},"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":0.4852846},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":35.2126643662463},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":17,"finish_reasons":["stop"],"indexed_attempts":17,"output_token_observations":17,"total_output_tokens":179458},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-build-0.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":8,"repaired_rate":1.0}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":38.253648520055016,"score":38.253648520055016},"GB2-02":{"attempts":1,"playable":43.89448055096423,"score":43.89448055096423},"GB2-03":{"attempts":1,"playable":30.62258467172971,"score":30.62258467172971},"GB2-04":{"attempts":1,"playable":41.00169440293084,"score":41.00169440293084},"GB2-05":{"attempts":1,"playable":49.917567566672446,"score":49.917567566672446},"GB2-06":{"attempts":1,"playable":31.728565884502206,"score":31.728565884502206},"GB2-07":{"attempts":1,"playable":12.78344141643851,"score":12.78344141643851},"GB2-08":{"attempts":1,"playable":33.49933191667748,"score":33.49933191667748}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":38.253648520055016,"score":38.253648520055016},"GB2-02":{"attempts":1,"playable":43.89448055096423,"score":43.89448055096423},"GB2-03":{"attempts":1,"playable":30.62258467172971,"score":30.62258467172971},"GB2-04":{"attempts":1,"playable":41.00169440293084,"score":41.00169440293084},"GB2-05":{"attempts":1,"playable":49.917567566672446,"score":49.917567566672446},"GB2-06":{"attempts":1,"playable":31.728565884502206,"score":31.728565884502206},"GB2-07":{"attempts":1,"playable":12.78344141643851,"score":12.78344141643851},"GB2-08":{"attempts":1,"playable":33.49933191667748,"score":33.49933191667748}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-10-13T11:42:16Z","match_totals_all":{"draws":1576,"losses":2261,"wins":923},"match_totals_tracks":{"medium":{"draws":1576,"losses":2261,"wins":923}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":49.917567566672446,"mean":35.2126643662463,"min":12.78344141643851},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":115,"losses":302,"wins":173},"GB2-02":{"draws":468,"losses":80,"wins":12},"GB2-03":{"draws":164,"losses":294,"wins":80},"GB2-04":{"draws":427,"losses":128,"wins":31},"GB2-05":{"draws":0,"losses":305,"wins":307},"GB2-06":{"draws":4,"losses":405,"wins":205},"GB2-07":{"draws":0,"losses":529,"wins":89},"GB2-08":{"draws":398,"losses":218,"wins":26}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":115,"losses":302,"wins":173},"GB2-02":{"draws":468,"losses":80,"wins":12},"GB2-03":{"draws":164,"losses":294,"wins":80},"GB2-04":{"draws":427,"losses":128,"wins":31},"GB2-05":{"draws":0,"losses":305,"wins":307},"GB2-06":{"draws":4,"losses":405,"wins":205},"GB2-07":{"draws":0,"losses":529,"wins":89},"GB2-08":{"draws":398,"losses":218,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1368.9068686172975,"GB2-02":1428.801747577118,"GB2-03":1267.5110144352664,"GB2-04":1408.3262379217372,"GB2-05":1450.750269509251,"GB2-06":1170.8743049787022,"GB2-07":901.5700700131282,"GB2-08":1255.9703439929665}},"per_game_tracks":{"medium":{"GB2-01":38.253648520055016,"GB2-02":43.89448055096423,"GB2-03":30.62258467172971,"GB2-04":41.00169440293084,"GB2-05":49.917567566672446,"GB2-06":31.728565884502206,"GB2-07":12.78344141643851,"GB2-08":33.49933191667748}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.2126643662463},"reasoning_agg":{"medium":{"max":49.917567566672446,"mean":35.2126643662463,"min":12.78344141643851}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:b57bb69ec0ce5eaa","codegen_cost_by_reasoning":{"medium":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"recorded_attempt_count":1,"run_count":1,"total":0.0},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":1,"cell_count":2,"cost_basis_counts":{"provider_reported":3},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":2},"recorded_attempt_count":3,"run_count":2,"total":0.0},"codegen_latency_ms":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":2,"max_ms":81836,"mean_ms":81836.0,"min_ms":81836,"run_count":1}},"codegen_output_tokens":{"attempt_count":3,"output_max":32768,"output_mean":19502.5,"output_min":6237,"run_count":2},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":1,"output_max":32768,"output_mean":32768.0,"output_min":32768,"run_count":1},"none":{"attempt_count":2,"output_max":6237,"output_mean":6237.0,"output_min":6237,"run_count":1}},"display_name":"Ling 3.1 Flash","economics":{"none":34.51786408853646},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":3,"effective_max_output_tokens":[32768],"finish_reason_observations":2,"finish_reasons":["stop"],"indexed_attempts":3,"output_token_observations":3,"provider_post_attempt_observations":3,"provider_post_attempts":4,"reasoning_token_observations":3,"reconciliation_get_attempt_observations":3,"requested_max_output_token_observations":3,"requested_max_output_tokens":[32768],"total_output_tokens":39005,"total_reasoning_output_tokens":30791,"total_visible_output_tokens":8214,"visible_token_observations":3},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":1,"evaluated_cells":1,"first_pass_admitted":1,"first_pass_rate":1.0,"game_attempts":{"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-08":{"attempts":1,"playable":34.51786408853646,"score":34.51786408853646}},"headline_games_tracks":{"none":{"GB2-08":{"attempts":1,"playable":34.51786408853646,"score":34.51786408853646}}},"id":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-13T22:57:25Z","match_totals_all":{"draws":287,"losses":180,"wins":19},"match_totals_tracks":{"none":{"draws":287,"losses":180,"wins":19}},"model_slug":"inclusionai-ling-3-1-flash","overall":{"max":34.51786408853646,"mean":34.51786408853646,"min":34.51786408853646},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-08":{"draws":287,"losses":180,"wins":19}},"per_game_match_totals_tracks":{"none":{"GB2-08":{"draws":287,"losses":180,"wins":19}}},"per_game_raw_elo_tracks":{"none":{"GB2-08":1266.296918467592}},"per_game_tracks":{"none":{"GB2-08":34.51786408853646}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":34.51786408853646},"reasoning_agg":{"none":{"max":34.51786408853646,"mean":34.51786408853646,"min":34.51786408853646}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:c6ab2531e1444a25","codegen_cost_by_reasoning":{"medium":{"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":0.04917796},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.04917796},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094182},"codegen_latency_ms":{"attempt_count":68,"max_ms":490920,"mean_ms":122427.25,"min_ms":29915,"run_count":28},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":35,"max_ms":490920,"mean_ms":129686.92857142857,"min_ms":29915,"run_count":14},"none":{"attempt_count":33,"max_ms":199208,"mean_ms":115167.57142857143,"min_ms":46525,"run_count":14}},"codegen_output_tokens":{"attempt_count":68,"output_max":42038,"output_mean":8274.82142857143,"output_min":1701,"run_count":28},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":35,"output_max":42038,"output_mean":9630.357142857143,"output_min":1701,"run_count":14},"none":{"attempt_count":33,"output_max":12644,"output_mean":6919.285714285715,"output_min":2544,"run_count":14}},"display_name":"Laguna S 2.1","economics":{"medium":34.443145684595294,"none":39.915608942723246},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":68,"finish_reasons":["length","stop"],"indexed_attempts":72,"output_token_observations":68,"reasoning_token_observations":45,"total_output_tokens":231695,"total_reasoning_output_tokens":57724,"total_visible_output_tokens":117243,"visible_token_observations":43},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"poolside","provider_model":"poolside/laguna-s-2.1","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":11,"evaluated_cells":13,"failed_game_aliases":["GB2-01"],"first_pass_admitted":7,"first_pass_rate":0.5833333333333334,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":2},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"infra_failures_excluded":1,"performance_rejections":1},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.08333333333333333,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"performance_rejected_game_aliases":["GB2-07"],"performance_rejections":1,"repaired_admitted":4,"repaired_rate":0.3333333333333333},"baseline":{"admitted_plugins":12,"evaluated_cells":14,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":7,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"infra_failures_excluded":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"model_code_failure_rate":0.14285714285714285,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.35714285714285715}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":45.84654822060314,"score":35.5100721751233},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.959134105551335,"score":31.716069852237663},"GB2-03":{"attempts":4,"playable":39.49367462268843,"score":39.49367462268843},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":37.845076116769846,"score":18.922538058384923},"GB2-05":{"attempts":4,"playable":37.918916494363316,"score":37.918916494363316},"GB2-06":{"attempts":2,"playable":20.179884955933826,"score":20.179884955933826},"GB2-07":{"attempts":2,"playable":45.10947686026366,"score":45.10947686026366},"GB2-08":{"attempts":4,"playable":33.38020630795809,"score":33.38020630795809}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":41.34590418191937,"score":20.672952090959686},"GB2-02":{"attempts":2,"playable":42.94601119784798,"score":42.94601119784798},"GB2-03":{"attempts":2,"playable":38.64007559789331,"score":38.64007559789331},"GB2-04":{"attempts":1,"playable":37.845076116769846,"score":37.845076116769846},"GB2-05":{"attempts":2,"playable":26.911035832666116,"score":26.911035832666116},"GB2-06":{"attempts":1,"playable":19.997138369083007,"score":19.997138369083007},"GB2-08":{"attempts":2,"playable":33.41677849598742,"score":33.41677849598742}},"none":{"GB2-01":{"attempts":2,"playable":50.34719225928691,"score":50.34719225928691},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.97225701325469,"score":20.486128506627345},"GB2-03":{"attempts":2,"playable":40.34727364748356,"score":40.34727364748356},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.92679715606051,"score":48.92679715606051},"GB2-06":{"attempts":1,"playable":20.362631542784644,"score":20.362631542784644},"GB2-07":{"attempts":2,"playable":45.10947686026366,"score":45.10947686026366},"GB2-08":{"attempts":2,"playable":33.34363411992875,"score":33.34363411992875}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-10-14T17:55:12Z","match_totals_all":{"draws":5310,"losses":7170,"wins":3440},"match_totals_tracks":{"medium":{"draws":3348,"losses":3807,"wins":1348},"none":{"draws":1962,"losses":3363,"wins":2092}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":50.34719225928691,"mean":31.927629288006315,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":327,"losses":925,"wins":744},"GB2-02":{"draws":1694,"losses":325,"wins":23},"GB2-03":{"draws":1051,"losses":1262,"wins":586},"GB2-04":{"draws":445,"losses":223,"wins":66},"GB2-05":{"draws":0,"losses":1716,"wins":1083},"GB2-06":{"draws":32,"losses":1050,"wins":284},"GB2-07":{"draws":0,"losses":692,"wins":536},"GB2-08":{"draws":1761,"losses":977,"wins":118}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":132,"losses":423,"wins":263},"GB2-02":{"draws":1238,"losses":210,"wins":2},"GB2-03":{"draws":547,"losses":692,"wins":309},"GB2-04":{"draws":445,"losses":223,"wins":66},"GB2-05":{"draws":0,"losses":1122,"wins":485},"GB2-06":{"draws":15,"losses":603,"wins":156},"GB2-08":{"draws":971,"losses":534,"wins":67}},"none":{"GB2-01":{"draws":195,"losses":502,"wins":481},"GB2-02":{"draws":456,"losses":115,"wins":21},"GB2-03":{"draws":504,"losses":570,"wins":277},"GB2-05":{"draws":0,"losses":594,"wins":598},"GB2-06":{"draws":17,"losses":447,"wins":128},"GB2-07":{"draws":0,"losses":692,"wins":536},"GB2-08":{"draws":790,"losses":443,"wins":51}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1399.2339940656689,"GB2-02":1421.4685855579028,"GB2-03":1339.8459625998682,"GB2-04":1383.3652820179684,"GB2-05":1115.7263008222935,"GB2-06":987.981667362477,"GB2-08":1255.1308098077218},"none":{"GB2-01":1486.1445873969888,"GB2-02":1406.1295162615754,"GB2-03":1354.8032252902556,"GB2-05":1453.6745199488041,"GB2-06":994.0098784798145,"GB2-07":1388.0149704564506,"GB2-08":1254.387042457423}},"per_game_tracks":{"medium":{"GB2-01":41.34590418191937,"GB2-02":42.94601119784798,"GB2-03":38.64007559789331,"GB2-04":37.845076116769846,"GB2-05":26.911035832666116,"GB2-06":19.997138369083007,"GB2-08":33.41677849598742},"none":{"GB2-01":50.34719225928691,"GB2-02":40.97225701325469,"GB2-03":40.34727364748356,"GB2-05":48.92679715606051,"GB2-06":20.362631542784644,"GB2-07":45.10947686026366,"GB2-08":33.34363411992875}},"provider_color":"#4137FF","provider_company":"Poolside","provider_key":"poolside","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.4898668144582,"none":32.36539176155443},"reasoning_agg":{"medium":{"max":42.94601119784798,"mean":31.4898668144582,"min":19.997138369083007},"none":{"max":50.34719225928691,"mean":32.36539176155443,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.8755249470962276}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:1e3168587010809f","codegen_cost_by_reasoning":{"highest":{"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},"none":{"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":0.010139173999999999}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"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},"historical-provider-setting-intensive":{"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_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725613},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":41.92102944161344,"none":41.228311279947924},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"total_output_tokens":130744},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"tencent","provider_model":"tencent/hy3-preview","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-06","GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":9,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.5555555555555556,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1,"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.2222222222222222,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":71.88123931740179,"score":71.88123931740179},"GB2-02":{"attempts":2,"playable":38.128931584719325,"score":38.128931584719325},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":32.358214802939486,"score":16.179107401469743},"GB2-04":{"attempts":2,"playable":45.708918136733324,"score":45.708918136733324},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":38.28069210105063,"score":22.933524390648767},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.444169946860058,"score":8.222084973430029},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":26.320699937365156,"score":13.160349968682578},"GB2-08":{"attempts":2,"playable":38.84721340200342,"score":38.84721340200342}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":64.65696943177932,"score":64.65696943177932},"GB2-02":{"attempts":1,"playable":38.987988867897904,"score":38.987988867897904},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.63977103192549,"score":42.63977103192549},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":61.388670841607464,"score":30.694335420803732},"GB2-06":{"attempts":1,"playable":16.444169946860058,"score":16.444169946860058},"GB2-07":{"attempts":1,"playable":26.320699937365156,"score":26.320699937365156},"GB2-08":{"attempts":1,"playable":43.00893603385874,"score":43.00893603385874}},"none":{"GB2-01":{"attempts":1,"playable":79.10550920302428,"score":79.10550920302428},"GB2-02":{"attempts":1,"playable":37.26987430154075,"score":37.26987430154075},"GB2-03":{"attempts":1,"playable":32.358214802939486,"score":32.358214802939486},"GB2-04":{"attempts":1,"playable":48.77806524154116,"score":48.77806524154116},"GB2-05":{"attempts":1,"playable":15.1727133604938,"score":15.1727133604938},"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":34.6854907701481,"score":34.6854907701481}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-10-15T06:45:05Z","match_totals_all":{"draws":2517,"losses":3181,"wins":1908},"match_totals_tracks":{"highest":{"draws":1118,"losses":1826,"wins":1154},"none":{"draws":1399,"losses":1355,"wins":754}},"model_slug":"tencent-hy3-preview","overall":{"max":79.10550920302428,"mean":31.88267114688612,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":64.65696943177932,"GB2-02":38.987988867897904,"GB2-04":42.63977103192549,"GB2-05":61.388670841607464,"GB2-06":16.444169946860058,"GB2-07":26.320699937365156,"GB2-08":43.00893603385874},"per_game_match_totals_all":{"GB2-01":{"draws":194,"losses":251,"wins":713},"GB2-02":{"draws":825,"losses":260,"wins":7},"GB2-03":{"draws":147,"losses":307,"wins":106},"GB2-04":{"draws":764,"losses":228,"wins":132},"GB2-05":{"draws":0,"losses":731,"wins":467},"GB2-06":{"draws":2,"losses":467,"wins":103},"GB2-07":{"draws":0,"losses":448,"wins":166},"GB2-08":{"draws":585,"losses":489,"wins":214}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":99,"losses":168,"wins":311},"GB2-02":{"draws":412,"losses":127,"wins":7},"GB2-04":{"draws":423,"losses":112,"wins":33},"GB2-05":{"draws":0,"losses":239,"wins":353},"GB2-06":{"draws":2,"losses":467,"wins":103},"GB2-07":{"draws":0,"losses":448,"wins":166},"GB2-08":{"draws":182,"losses":265,"wins":181}},"none":{"GB2-01":{"draws":95,"losses":83,"wins":402},"GB2-02":{"draws":413,"losses":133,"wins":0},"GB2-03":{"draws":147,"losses":307,"wins":106},"GB2-04":{"draws":341,"losses":116,"wins":99},"GB2-05":{"draws":0,"losses":492,"wins":114},"GB2-08":{"draws":403,"losses":224,"wins":33}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.6437257161201,"GB2-02":1390.554702958117,"GB2-04":1421.1093796022976,"GB2-05":1599.6537758081072,"GB2-06":926.9050355510012,"GB2-07":1141.83087278216,"GB2-08":1351.9028400620823},"none":{"GB2-01":1800.8355927071025,"GB2-02":1376.8987689172,"GB2-03":1283.7488484505698,"GB2-04":1468.5820462648003,"GB2-05":922.9201446883784,"GB2-08":1267.9918777940563}},"per_game_tracks":{"highest":{"GB2-01":64.65696943177932,"GB2-02":38.987988867897904,"GB2-04":42.63977103192549,"GB2-05":61.388670841607464,"GB2-06":16.444169946860058,"GB2-07":26.320699937365156,"GB2-08":43.00893603385874},"none":{"GB2-01":79.10550920302428,"GB2-02":37.26987430154075,"GB2-03":32.358214802939486,"GB2-04":48.77806524154116,"GB2-05":15.1727133604938,"GB2-08":34.6854907701481}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.8441088338113,"none":30.921233459960945},"reasoning_agg":{"highest":{"max":64.65696943177932,"mean":32.8441088338113,"min":0.0},"none":{"max":79.10550920302428,"mean":30.921233459960945,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":1.9228753738503528}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:2aacde13c82c4c44","codegen_cost_by_reasoning":{"highest":{"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},"medium":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.03062629,"mean":0.020124273158333334,"median":0.017895481666666668,"min":0.012095886733333333,"recorded_attempt_count":52,"run_count":24,"total":0.486187507},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.005169185000000001,"mean":0.002871050658333333,"median":0.0023354879666666667,"min":0.00169122,"recorded_attempt_count":37,"run_count":24,"total":0.0689052158}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"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":0.27207317540000003},"historical-provider-setting-balanced-variant-2":{"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},"historical-provider-setting-baseline-variant-1":{"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},"historical-provider-setting-baseline-variant-2":{"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":0.030685472800000002},"historical-provider-setting-intensive":{"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":0.19736108440000003}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0597184625,"mean":0.015888486455555555,"median":0.014928570933333333,"min":0.00169122,"recorded_attempt_count":108,"run_count":56,"total":0.7524538072},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":35.516719462735935,"highest":37.13230085282357,"medium":31.62468159754825,"none":35.17706151726432},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["length","stop"],"indexed_attempts":32,"output_token_observations":32,"total_output_tokens":734523},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":15,"evaluated_cells":16,"failed_game_aliases":["GB2-08"],"first_pass_admitted":1,"first_pass_rate":0.0625,"game_attempts":{"GB2-01":{"admitted":2,"infra_failures_excluded":1},"GB2-02":{"admitted":3},"GB2-03":{"infra_failures_excluded":3},"GB2-04":{"admitted":3},"GB2-05":{"admitted":2},"GB2-06":{"admitted":1,"infra_failures_excluded":2},"GB2-07":{"admitted":2,"infra_failures_excluded":1},"GB2-08":{"admitted":2,"infra_failures_excluded":1,"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-01","GB2-03","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":8,"model_code_failure_rate":0.0625,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":14,"repaired_rate":0.875},"baseline":{"admitted_plugins":17,"evaluated_cells":23,"failed_game_aliases":["GB2-02","GB2-03","GB2-07","GB2-08"],"first_pass_admitted":12,"first_pass_rate":0.5217391304347826,"game_attempts":{"GB2-01":{"admitted":3},"GB2-02":{"admitted":1,"model_code_failures":2},"GB2-03":{"admitted":1,"model_code_failures":2},"GB2-04":{"admitted":2,"infra_failures_excluded":1},"GB2-05":{"admitted":3},"GB2-06":{"admitted":3},"GB2-07":{"admitted":2,"model_code_failures":1},"GB2-08":{"admitted":2,"model_code_failures":1}},"infra_excluded_game_aliases":["GB2-04"],"infra_failures_excluded":1,"model_code_failure_rate":0.2608695652173913,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.21739130434782608},"intensive":{"admitted_plugins":5,"evaluated_cells":5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"infra_failures_excluded":1},"GB2-04":{"admitted":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"admitted":1},"GB2-07":{"infra_failures_excluded":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-03","GB2-05","GB2-07"],"infra_failures_excluded":3,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":1.0}},"headline_games_all":{"GB2-01":{"attempts":6,"playable":31.300780069928255,"score":31.300780069928255},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.51634136659086,"score":33.43812512784103},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.02017954706449,"score":14.673393182354829},"GB2-04":{"attempts":6,"playable":40.0104214845617,"score":40.0104214845617},"GB2-05":{"attempts":5,"playable":26.565782383785628,"score":26.565782383785628},"GB2-06":{"attempts":5,"playable":34.558737077090086,"score":34.558737077090086},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":26.41198090311795,"score":22.77977183962521},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":31.024951067219007,"score":24.216637465834225}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":21.951599253996644,"score":21.951599253996644},"GB2-02":{"attempts":1,"playable":43.92071891359098,"score":43.92071891359098},"GB2-04":{"attempts":1,"playable":39.7060214555361,"score":39.7060214555361},"GB2-06":{"attempts":1,"playable":48.283133851800144,"score":48.283133851800144},"GB2-08":{"attempts":1,"playable":31.80003078919399,"score":31.80003078919399}},"medium":{"GB2-01":{"attempts":2,"playable":29.342165543525493,"score":29.342165543525493},"GB2-02":{"attempts":3,"playable":42.776332111807385,"score":42.776332111807385},"GB2-04":{"attempts":3,"playable":38.308446175760366,"score":38.308446175760366},"GB2-05":{"attempts":2,"playable":25.186058800421666,"score":25.186058800421666},"GB2-06":{"attempts":1,"playable":21.872879423496883,"score":21.872879423496883},"GB2-07":{"attempts":2,"playable":31.030707425279445,"score":31.030707425279445},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.896750740360154,"score":21.931167160240104}},"none":{"GB2-01":{"attempts":3,"playable":42.60857541226263,"score":42.60857541226263},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":40.85197307437419,"score":13.617324358124732},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":44.02017954706449,"score":14.673393182354829},"GB2-04":{"attempts":2,"playable":42.016796822388606,"score":42.016796822388606},"GB2-05":{"attempts":3,"playable":27.94550596714959,"score":27.94550596714959},"GB2-06":{"attempts":3,"playable":33.52019795597324,"score":33.52019795597324},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":21.793254380956455,"score":14.52883625397097},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":28.37807167210287,"score":18.91871444806858}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-10-13T22:26:58Z","match_totals_all":{"draws":7070,"losses":10403,"wins":3987},"match_totals_tracks":{"highest":{"draws":1489,"losses":1046,"wins":327},"medium":{"draws":3185,"losses":4184,"wins":1455},"none":{"draws":2396,"losses":5173,"wins":2205}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":48.283133851800144,"mean":31.058311379073945,"min":13.617324358124732},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-01":21.951599253996644,"GB2-02":43.92071891359098,"GB2-04":39.7060214555361,"GB2-06":48.283133851800144,"GB2-08":31.80003078919399},"per_game_all":{"GB2-01":30.756658809479205,"GB2-02":42.50281835398631,"GB2-04":40.0104214845617,"GB2-06":33.28874759843347,"GB2-08":31.024951067219007},"per_game_match_totals_all":{"GB2-01":{"draws":722,"losses":1848,"wins":878},"GB2-02":{"draws":2214,"losses":460,"wins":64},"GB2-03":{"draws":204,"losses":207,"wins":125},"GB2-04":{"draws":2208,"losses":935,"wins":263},"GB2-05":{"draws":0,"losses":2058,"wins":892},"GB2-06":{"draws":85,"losses":1840,"wins":959},"GB2-07":{"draws":0,"losses":1753,"wins":651},"GB2-08":{"draws":1637,"losses":1302,"wins":155}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":257,"losses":295,"wins":6},"GB2-02":{"draws":441,"losses":86,"wins":15},"GB2-04":{"draws":365,"losses":155,"wins":44},"GB2-06":{"draws":36,"losses":297,"wins":253},"GB2-08":{"draws":390,"losses":213,"wins":9}},"medium":{"GB2-01":{"draws":146,"losses":721,"wins":293},"GB2-02":{"draws":1347,"losses":272,"wins":43},"GB2-04":{"draws":1105,"losses":497,"wins":110},"GB2-05":{"draws":0,"losses":859,"wins":363},"GB2-06":{"draws":29,"losses":443,"wins":128},"GB2-07":{"draws":0,"losses":830,"wins":380},"GB2-08":{"draws":558,"losses":562,"wins":138}},"none":{"GB2-01":{"draws":319,"losses":832,"wins":579},"GB2-02":{"draws":426,"losses":102,"wins":6},"GB2-03":{"draws":204,"losses":207,"wins":125},"GB2-04":{"draws":738,"losses":283,"wins":109},"GB2-05":{"draws":0,"losses":1199,"wins":529},"GB2-06":{"draws":20,"losses":1100,"wins":578},"GB2-07":{"draws":0,"losses":923,"wins":271},"GB2-08":{"draws":689,"losses":527,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1286.5900444689935,"GB2-02":1418.0095664632197,"GB2-04":1400.4620664939303,"GB2-06":1194.3897236347664,"GB2-08":1227.7957102634211},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1189.2352787289565,"GB2-02":1429.0043416168128,"GB2-04":1398.141654197544,"GB2-06":1424.5016937680682,"GB2-08":1238.6060432307697},"medium":{"GB2-01":1276.098020200337,"GB2-02":1419.834003023807,"GB2-04":1386.9877299853797,"GB2-05":1106.521745626173,"GB2-06":1018.5481210080736,"GB2-07":1202.466370052713,"GB2-08":1242.6531906846983},"none":{"GB2-01":1394.4368344776872,"GB2-02":1405.1903547490388,"GB2-03":1386.9179223795811,"GB2-04":1416.2568152988667,"GB2-05":1205.5068754945928,"GB2-06":1140.119356128157,"GB2-07":1053.4176753798154,"GB2-08":1202.1278968747956}},"per_game_tracks":{"highest":{"GB2-01":21.951599253996644,"GB2-02":43.92071891359098,"GB2-04":39.7060214555361,"GB2-06":48.283133851800144,"GB2-08":31.80003078919399},"medium":{"GB2-01":29.342165543525493,"GB2-02":42.73576307399375,"GB2-04":38.308446175760366,"GB2-05":25.186058800421666,"GB2-06":21.872879423496883,"GB2-07":31.030707425279445,"GB2-08":32.896750740360154},"none":{"GB2-01":40.976211630915486,"GB2-02":40.85197307437419,"GB2-03":44.02017954706449,"GB2-04":42.016796822388606,"GB2-05":33.6697754903091,"GB2-06":29.710229520003374,"GB2-07":21.793254380956455,"GB2-08":28.37807167210287}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.13230085282357,"medium":30.063965234361625,"none":25.97866805003665},"reasoning_agg":{"highest":{"max":48.283133851800144,"mean":37.13230085282357,"min":21.951599253996644},"medium":{"max":42.776332111807385,"mean":30.063965234361625,"min":21.872879423496883},"none":{"max":42.60857541226263,"mean":25.97866805003665,"min":13.617324358124732}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.15363280278692}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:264b96442a17a515","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999},"medium":{"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},"none":{"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":0.14744575000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","max":0.26962149999999996,"mean":0.26962149999999996,"median":0.26962149999999996,"min":0.26962149999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":2,"run_count":2,"token_priced_attempt_count":3,"total":0.5392429999999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":17,"cost_basis_counts":{"estimated":2,"local_standard_estimate":55},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":8,"max":0.26962149999999996,"mean":0.03182758529411764,"median":0.01676735,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":2,"boardgame-list-prices-2026-10-09":55},"recorded_attempt_count":2,"run_count":34,"token_priced_attempt_count":55,"total":1.0821379},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":43.350878593330904,"none":34.96582268329322},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["incomplete","stop"],"indexed_attempts":57,"output_token_observations":57,"reasoning_token_observations":2,"total_output_tokens":752982,"total_reasoning_output_tokens":128000,"visible_token_observations":2},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-03","GB2-04"],"first_pass_admitted":5,"first_pass_rate":0.3125,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"model_code_failures":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375},"baseline":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-03","GB2-04","GB2-07"],"first_pass_admitted":5,"first_pass_rate":0.3125,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":2},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"model_code_failures":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":1,"model_code_failures":1},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.4375}},"headline_games_all":{"GB2-01":{"attempts":4,"playable":31.707880605401336,"score":31.707880605401336},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.53648335281071,"score":30.40158920076245},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":35.330674035111166,"score":8.832668508777791},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":53.117449063704925,"score":13.279362265926231},"GB2-05":{"attempts":4,"playable":29.4836942047392,"score":29.4836942047392},"GB2-06":{"attempts":4,"playable":50.28464670631534,"score":50.28464670631534},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":26.925511610708877,"score":22.069567331579048},"GB2-08":{"attempts":4,"playable":50.94617643880092,"score":50.94617643880092}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":15.959619700984568,"score":15.959619700984568},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.53957660819305,"score":20.269788304096526},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":53.117449063704925,"score":26.558724531852462},"GB2-05":{"attempts":2,"playable":50.58762671213809,"score":50.58762671213809},"GB2-06":{"attempts":2,"playable":58.90470679566916,"score":58.90470679566916},"GB2-07":{"attempts":2,"playable":34.42724610489844,"score":34.42724610489844},"GB2-08":{"attempts":2,"playable":49.91992516772809,"score":49.91992516772809}},"none":{"GB2-01":{"attempts":2,"playable":47.4561415098181,"score":47.4561415098181},"GB2-02":{"attempts":2,"playable":40.533390097428374,"score":40.533390097428374},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":35.330674035111166,"score":17.665337017555583},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.379761697340314,"score":8.379761697340314},"GB2-06":{"attempts":2,"playable":41.66458661696152,"score":41.66458661696152},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":19.423777116519318,"score":9.711888558259659},"GB2-08":{"attempts":2,"playable":51.97242770987374,"score":51.97242770987374}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-10-14T17:55:01Z","match_totals_all":{"draws":2994,"losses":6980,"wins":4140},"match_totals_tracks":{"medium":{"draws":1248,"losses":3399,"wins":2459},"none":{"draws":1746,"losses":3581,"wins":1681}},"model_slug":"gpt-5-4-nano","overall":{"max":58.90470679566916,"mean":29.62569815778779,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":442,"losses":1328,"wins":506},"GB2-02":{"draws":1332,"losses":329,"wins":15},"GB2-03":{"draws":172,"losses":275,"wins":101},"GB2-04":{"draws":288,"losses":125,"wins":165},"GB2-05":{"draws":0,"losses":1641,"wins":743},"GB2-06":{"draws":58,"losses":1111,"wins":1143},"GB2-07":{"draws":0,"losses":1287,"wins":563},"GB2-08":{"draws":702,"losses":884,"wins":904}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":179,"losses":849,"wins":104},"GB2-02":{"draws":440,"losses":104,"wins":2},"GB2-04":{"draws":288,"losses":125,"wins":165},"GB2-05":{"draws":0,"losses":587,"wins":619},"GB2-06":{"draws":54,"losses":456,"wins":658},"GB2-07":{"draws":0,"losses":795,"wins":433},"GB2-08":{"draws":287,"losses":483,"wins":478}},"none":{"GB2-01":{"draws":263,"losses":479,"wins":402},"GB2-02":{"draws":892,"losses":225,"wins":13},"GB2-03":{"draws":172,"losses":275,"wins":101},"GB2-05":{"draws":0,"losses":1054,"wins":124},"GB2-06":{"draws":4,"losses":655,"wins":485},"GB2-07":{"draws":0,"losses":492,"wins":130},"GB2-08":{"draws":415,"losses":401,"wins":426}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1054.7831617086133,"GB2-02":1402.7484712601495,"GB2-04":1502.3272112042787,"GB2-05":1504.2316610859054,"GB2-06":1598.0339831718834,"GB2-07":1183.8047388607465,"GB2-08":1477.1782390422204},"none":{"GB2-01":1457.9418205447887,"GB2-02":1402.69550005589,"GB2-03":1310.818515347658,"GB2-05":751.4446541278162,"GB2-06":1330.6209648750287,"GB2-07":1032.692044139437,"GB2-08":1485.654044056478}},"per_game_tracks":{"medium":{"GB2-01":15.959619700984568,"GB2-02":40.53957660819305,"GB2-04":53.117449063704925,"GB2-05":50.58762671213809,"GB2-06":58.90470679566916,"GB2-07":34.42724610489844,"GB2-08":49.91992516772809},"none":{"GB2-01":47.4561415098181,"GB2-02":40.533390097428374,"GB2-03":35.330674035111166,"GB2-05":8.379761697340314,"GB2-06":41.66458661696152,"GB2-07":19.423777116519318,"GB2-08":51.97242770987374}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.07845466467092,"none":27.17294165090466},"reasoning_agg":{"medium":{"max":58.90470679566916,"mean":32.07845466467092,"min":0.0},"none":{"max":51.97242770987374,"mean":27.17294165090466,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":4.90551301376626}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:b01aa117506268d3","codegen_cost_by_reasoning":{"medium":{"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":0.030739789999999996},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.014924670000000001}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0061656,"mean":0.0028540287500000002,"median":0.00232709,"min":0.0011068,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":25},"recorded_attempt_count":25,"run_count":16,"total":0.04566446},"codegen_latency_ms":{"attempt_count":25,"max_ms":425398,"mean_ms":137358.0,"min_ms":22859,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":14,"max_ms":425398,"mean_ms":207893.5,"min_ms":65353,"run_count":8},"none":{"attempt_count":11,"max_ms":256957,"mean_ms":66822.5,"min_ms":22859,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":12120,"output_mean":4888.4375,"output_min":1108,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":14,"output_max":12120,"output_mean":7438.375,"output_min":3314,"run_count":8},"none":{"attempt_count":11,"output_max":4877,"output_mean":2338.5,"output_min":1108,"run_count":8}},"display_name":"Gemma 4 31B","economics":{"medium":38.26683818844134,"none":27.363814833991313},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[16384],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":26,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[16384],"total_output_tokens":78215,"total_reasoning_output_tokens":27437,"total_visible_output_tokens":50778,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":16384,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemma-4-31b-it","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":5,"first_pass_rate":0.625,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":21.247297396143118,"score":10.623648698071559},"GB2-02":{"attempts":2,"playable":41.949316615554366,"score":41.949316615554366},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":44.47942426900786,"score":22.23971213450393},"GB2-04":{"attempts":2,"playable":44.92692634412568,"score":44.92692634412568},"GB2-05":{"attempts":2,"playable":44.344955546634594,"score":44.344955546634594},"GB2-06":{"attempts":2,"playable":22.591531120730775,"score":22.591531120730775},"GB2-07":{"attempts":2,"playable":14.647185194011715,"score":14.647185194011715},"GB2-08":{"attempts":2,"playable":33.83552160210668,"score":33.83552160210668}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":21.247297396143118,"score":21.247297396143118},"GB2-02":{"attempts":1,"playable":43.40565267198956,"score":43.40565267198956},"GB2-03":{"attempts":1,"playable":44.47942426900786,"score":44.47942426900786},"GB2-04":{"attempts":1,"playable":43.40886831147119,"score":43.40886831147119},"GB2-05":{"attempts":1,"playable":72.57203747186148,"score":72.57203747186148},"GB2-06":{"attempts":1,"playable":28.228677408732228,"score":28.228677408732228},"GB2-07":{"attempts":1,"playable":18.484812110708994,"score":18.484812110708994},"GB2-08":{"attempts":1,"playable":34.30793586761629,"score":34.30793586761629}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":40.492980559119175,"score":40.492980559119175},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":46.44498437678018,"score":46.44498437678018},"GB2-05":{"attempts":1,"playable":16.117873621407707,"score":16.117873621407707},"GB2-06":{"attempts":1,"playable":16.95438483272932,"score":16.95438483272932},"GB2-07":{"attempts":1,"playable":10.809558277314437,"score":10.809558277314437},"GB2-08":{"attempts":1,"playable":33.36310733659707,"score":33.36310733659707}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:40Z","match_totals_all":{"draws":2053,"losses":3371,"wins":1050},"match_totals_tracks":{"medium":{"draws":1163,"losses":1756,"wins":775},"none":{"draws":890,"losses":1615,"wins":275}},"model_slug":"google-gemma-4-31b-it","overall":{"max":72.57203747186148,"mean":29.394849656967413,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":314,"wins":36},"GB2-02":{"draws":677,"losses":174,"wins":13},"GB2-03":{"draws":101,"losses":212,"wins":133},"GB2-04":{"draws":571,"losses":219,"wins":106},"GB2-05":{"draws":0,"losses":542,"wins":426},"GB2-06":{"draws":37,"losses":705,"wins":170},"GB2-07":{"draws":0,"losses":826,"wins":122},"GB2-08":{"draws":549,"losses":379,"wins":44}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":118,"losses":314,"wins":36},"GB2-02":{"draws":344,"losses":78,"wins":10},"GB2-03":{"draws":101,"losses":212,"wins":133},"GB2-04":{"draws":292,"losses":113,"wins":43},"GB2-05":{"draws":0,"losses":135,"wins":349},"GB2-06":{"draws":35,"losses":320,"wins":101},"GB2-07":{"draws":0,"losses":396,"wins":78},"GB2-08":{"draws":273,"losses":188,"wins":25}},"none":{"GB2-02":{"draws":333,"losses":96,"wins":3},"GB2-04":{"draws":279,"losses":106,"wins":63},"GB2-05":{"draws":0,"losses":407,"wins":77},"GB2-06":{"draws":2,"losses":385,"wins":69},"GB2-07":{"draws":0,"losses":430,"wins":44},"GB2-08":{"draws":276,"losses":191,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1180.0814113224606,"GB2-02":1425.0248837880517,"GB2-03":1390.8881779651126,"GB2-04":1427.083522901607,"GB2-05":1775.9585148950814,"GB2-06":1117.6406213873374,"GB2-07":1016.1493141851975,"GB2-08":1264.1725505652194},"none":{"GB2-02":1402.3838998497758,"GB2-04":1450.5651616490488,"GB2-05":942.7783975251537,"GB2-06":936.0071190759296,"GB2-07":853.6784709013722,"GB2-08":1254.5851456329806}},"per_game_tracks":{"medium":{"GB2-01":21.247297396143118,"GB2-02":43.40565267198956,"GB2-03":44.47942426900786,"GB2-04":43.40886831147119,"GB2-05":72.57203747186148,"GB2-06":28.228677408732228,"GB2-07":18.484812110708994,"GB2-08":34.30793586761629},"none":{"GB2-02":40.492980559119175,"GB2-04":46.44498437678018,"GB2-05":16.117873621407707,"GB2-06":16.95438483272932,"GB2-07":10.809558277314437,"GB2-08":33.36310733659707}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.26683818844134,"none":20.522861125493485},"reasoning_agg":{"medium":{"max":72.57203747186148,"mean":38.26683818844134,"min":18.484812110708994},"none":{"max":46.44498437678018,"mean":20.522861125493485,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":17.743977062947856}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:6b5ca8216d334a6a","codegen_cost_by_reasoning":{"medium":{"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":1.3863592560000002},"none":{"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":0.214047204}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":26,"cell_count":16,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.103943664,"mean":0.050012701874999996,"median":0.041983026,"min":0.006392298,"recorded_attempt_count":108,"run_count":32,"total":1.6004064599999999},"codegen_latency_ms":{"attempt_count":87,"max_ms":1635062,"mean_ms":598630.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":49,"max_ms":1635062,"mean_ms":1021590.9375,"min_ms":525940,"run_count":16},"none":{"attempt_count":38,"max_ms":457140,"mean_ms":175670.5625,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":110598,"output_mean":38325.9375,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":59,"output_max":110598,"output_mean":68392.8125,"output_min":16796,"run_count":16},"none":{"attempt_count":38,"output_max":22812,"output_mean":8259.0625,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":36.17821502760831,"none":35.15474168855758},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":87,"finish_reasons":["length","stop","unknown"],"indexed_attempts":109,"output_token_observations":109,"reasoning_token_observations":57,"total_output_tokens":1226430,"total_reasoning_output_tokens":474156,"total_visible_output_tokens":133629,"visible_token_observations":44},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meituan","provider_model":"meituan/longcat-2.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":12,"evaluated_cells":16,"failed_game_aliases":["GB2-01","GB2-02","GB2-03"],"first_pass_admitted":9,"first_pass_rate":0.5625,"game_attempts":{"GB2-01":{"model_code_failures":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":1,"model_code_failures":1},"GB2-04":{"admitted":2},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.25,"model_code_failures":4,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.1875},"baseline":{"admitted_plugins":14,"evaluated_cells":16,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":8,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"admitted":2},"GB2-06":{"admitted":2},"GB2-07":{"admitted":2},"GB2-08":{"admitted":2}},"model_code_failure_rate":0.125,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":6,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":4,"failed_attempts":2,"playable":41.79650899288879,"score":20.898254496444395},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":42.16589077801038,"score":21.08294538900519},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":38.293349475480724,"score":27.841924751661104},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.06896225022104,"score":29.47036427363257},"GB2-05":{"attempts":4,"playable":22.99979534179502,"score":22.99979534179502},"GB2-06":{"attempts":4,"playable":31.138121004806848,"score":31.138121004806848},"GB2-07":{"attempts":4,"playable":35.58645193666563,"score":35.58645193666563},"GB2-08":{"attempts":4,"playable":35.09189406743536,"score":35.09189406743536}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.9132044269218,"score":21.9566022134609},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":41.80569889527846,"score":20.90284944763923},"GB2-04":{"attempts":2,"playable":35.74353259408819,"score":35.74353259408819},"GB2-05":{"attempts":2,"playable":34.582852494522484,"score":34.582852494522484},"GB2-06":{"attempts":2,"playable":24.502722140548823,"score":24.502722140548823},"GB2-07":{"attempts":2,"playable":37.14510352220532,"score":37.14510352220532},"GB2-08":{"attempts":2,"playable":35.55439111969309,"score":35.55439111969309}},"none":{"GB2-01":{"attempts":2,"playable":41.79650899288879,"score":41.79650899288879},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.418577129098956,"score":20.209288564549478},"GB2-03":{"attempts":2,"playable":34.78100005568298,"score":34.78100005568298},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":46.394391906353896,"score":23.197195953176948},"GB2-05":{"attempts":2,"playable":11.416738189067555,"score":11.416738189067555},"GB2-06":{"attempts":2,"playable":37.77351986906487,"score":37.77351986906487},"GB2-07":{"attempts":2,"playable":34.02780035112595,"score":34.02780035112595},"GB2-08":{"attempts":2,"playable":34.62939701517763,"score":34.62939701517763}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-10-14T17:59:48Z","match_totals_all":{"draws":4593,"losses":8997,"wins":3784},"match_totals_tracks":{"medium":{"draws":2255,"losses":4745,"wins":2058},"none":{"draws":2338,"losses":4252,"wins":1726}},"model_slug":"meituan-longcat-2-0","overall":{"max":41.79650899288879,"mean":28.013718907680765,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":314,"losses":539,"wins":367},"GB2-02":{"draws":1067,"losses":200,"wins":5},"GB2-03":{"draws":627,"losses":837,"wins":358},"GB2-04":{"draws":1128,"losses":632,"wins":223},"GB2-05":{"draws":0,"losses":2043,"wins":745},"GB2-06":{"draws":144,"losses":1789,"wins":769},"GB2-07":{"draws":0,"losses":1789,"wins":973},"GB2-08":{"draws":1313,"losses":1168,"wins":344}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":592,"losses":94,"wins":4},"GB2-03":{"draws":275,"losses":303,"wins":164},"GB2-04":{"draws":799,"losses":492,"wins":126},"GB2-05":{"draws":0,"losses":1025,"wins":569},"GB2-06":{"draws":68,"losses":1085,"wins":361},"GB2-07":{"draws":0,"losses":987,"wins":551},"GB2-08":{"draws":521,"losses":759,"wins":283}},"none":{"GB2-01":{"draws":314,"losses":539,"wins":367},"GB2-02":{"draws":475,"losses":106,"wins":1},"GB2-03":{"draws":352,"losses":534,"wins":194},"GB2-04":{"draws":329,"losses":140,"wins":97},"GB2-05":{"draws":0,"losses":1018,"wins":176},"GB2-06":{"draws":76,"losses":704,"wins":408},"GB2-07":{"draws":0,"losses":802,"wins":422},"GB2-08":{"draws":792,"losses":409,"wins":61}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1428.9463213830836,"GB2-03":1367.7519438412296,"GB2-04":1366.3126451923235,"GB2-05":1218.4825500720622,"GB2-06":1059.7554420148967,"GB2-07":1253.4382630396208,"GB2-08":1266.9780169070382},"none":{"GB2-01":1403.594088390987,"GB2-02":1401.8015690735149,"GB2-03":1304.0828722988076,"GB2-04":1450.1745894865694,"GB2-05":833.1975980578679,"GB2-06":1263.6092792700642,"GB2-07":1246.2692747144652,"GB2-08":1267.423166604106}},"per_game_tracks":{"medium":{"GB2-02":43.9132044269218,"GB2-03":41.80569889527846,"GB2-04":35.74353259408819,"GB2-05":34.582852494522484,"GB2-06":24.502722140548823,"GB2-07":37.14510352220532,"GB2-08":35.55439111969309},"none":{"GB2-01":41.79650899288879,"GB2-02":40.418577129098956,"GB2-03":34.78100005568298,"GB2-04":46.394391906353896,"GB2-05":11.416738189067555,"GB2-06":37.77351986906487,"GB2-07":34.02780035112595,"GB2-08":34.62939701517763}},"provider_color":"#29E154","provider_company":"Meituan","provider_key":"meituan","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.29850669151976,"none":29.72893112384177},"reasoning_agg":{"medium":{"max":37.14510352220532,"mean":26.29850669151976,"min":0.0},"none":{"max":41.79650899288879,"mean":29.72893112384177,"min":11.416738189067555}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":3.430424432322013}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:eb4b745f99eebdb9","codegen_cost_by_reasoning":{"medium":{"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":0.5845103400000001},"none":{"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":0.20304798000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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":0.20304798000000002}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":27.848757180791413,"none":40.33226093148046},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"total_output_tokens":596080},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":7,"repaired_rate":0.875},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":38.76088564610376,"score":38.76088564610376},"GB2-02":{"attempts":2,"playable":39.68050588089713,"score":39.68050588089713},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":40.43227719046391,"score":20.216138595231953},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.081338597518794,"score":20.540669298759397},"GB2-05":{"attempts":2,"playable":15.450634217854216,"score":15.450634217854216},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.51946440751578,"score":8.75973220375789},"GB2-07":{"attempts":2,"playable":32.52419682873078,"score":32.52419682873078},"GB2-08":{"attempts":2,"playable":42.53467025587621,"score":42.53467025587621}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":19.812945610444416,"score":19.812945610444416},"GB2-02":{"attempts":1,"playable":39.16537940045146,"score":39.16537940045146},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.081338597518794,"score":41.081338597518794},"GB2-05":{"attempts":1,"playable":1.916705010888433,"score":1.916705010888433},"GB2-06":{"attempts":1,"playable":17.51946440751578,"score":17.51946440751578},"GB2-07":{"attempts":1,"playable":41.4562323983508,"score":41.4562323983508},"GB2-08":{"attempts":1,"playable":33.989234840370216,"score":33.989234840370216}},"none":{"GB2-01":{"attempts":1,"playable":57.7088256817631,"score":57.7088256817631},"GB2-02":{"attempts":1,"playable":40.195632361342795,"score":40.195632361342795},"GB2-03":{"attempts":1,"playable":40.43227719046391,"score":40.43227719046391},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.98456342482,"score":28.98456342482},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.592161259110764,"score":23.592161259110764},"GB2-08":{"attempts":1,"playable":51.080105671382206,"score":51.080105671382206}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-10-14T17:55:06Z","match_totals_all":{"draws":1984,"losses":4103,"wins":1691},"match_totals_tracks":{"medium":{"draws":1262,"losses":2344,"wins":590},"none":{"draws":722,"losses":1759,"wins":1101}},"model_slug":"minimax-minimax-m3","overall":{"max":57.7088256817631,"mean":27.30842911590142,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":136,"losses":652,"wins":412},"GB2-02":{"draws":888,"losses":227,"wins":5},"GB2-03":{"draws":136,"losses":270,"wins":154},"GB2-04":{"draws":393,"losses":143,"wins":46},"GB2-05":{"draws":0,"losses":1013,"wins":213},"GB2-06":{"draws":5,"losses":474,"wins":117},"GB2-07":{"draws":0,"losses":811,"wins":419},"GB2-08":{"draws":426,"losses":513,"wins":325}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":32,"losses":448,"wins":112},"GB2-02":{"draws":436,"losses":115,"wins":1},"GB2-04":{"draws":393,"losses":143,"wins":46},"GB2-05":{"draws":0,"losses":597,"wins":11},"GB2-06":{"draws":5,"losses":474,"wins":117},"GB2-07":{"draws":0,"losses":353,"wins":269},"GB2-08":{"draws":396,"losses":214,"wins":34}},"none":{"GB2-01":{"draws":104,"losses":204,"wins":300},"GB2-02":{"draws":452,"losses":112,"wins":4},"GB2-03":{"draws":136,"losses":270,"wins":154},"GB2-05":{"draws":0,"losses":416,"wins":202},"GB2-07":{"draws":0,"losses":458,"wins":150},"GB2-08":{"draws":30,"losses":299,"wins":291}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1160.8343880432978,"GB2-02":1391.9548471639846,"GB2-04":1408.9499553103951,"GB2-05":416.6295285908236,"GB2-06":945.9407372293821,"GB2-07":1342.7471265773795,"GB2-08":1260.9436400932432},"none":{"GB2-01":1557.0384800334375,"GB2-02":1400.05521224371,"GB2-03":1355.8215557182307,"GB2-05":1169.4830103054305,"GB2-07":1100.8375550454023,"GB2-08":1437.0016127969375}},"per_game_tracks":{"medium":{"GB2-01":19.812945610444416,"GB2-02":39.16537940045146,"GB2-04":41.081338597518794,"GB2-05":1.916705010888433,"GB2-06":17.51946440751578,"GB2-07":41.4562323983508,"GB2-08":33.989234840370216},"none":{"GB2-01":57.7088256817631,"GB2-02":40.195632361342795,"GB2-03":40.43227719046391,"GB2-05":28.98456342482,"GB2-07":23.592161259110764,"GB2-08":51.080105671382206}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.367662533192487,"none":30.249195698610347},"reasoning_agg":{"medium":{"max":41.4562323983508,"mean":24.367662533192487,"min":0.0},"none":{"max":57.7088256817631,"mean":30.249195698610347,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":5.88153316541786}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:58ee641433c53262","codegen_cost_by_reasoning":{"highest":{"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":1.3975426639832813},"none":{"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":0.5409853360167187}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"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":0.5409853360167187},"historical-provider-setting-intensive":{"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":1.3975426639832813}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.27741402547937455,"mean":0.12115799999999999,"median":0.10979066017348882,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":16,"token_priced_attempt_count":25,"total":1.938528},"codegen_output_tokens":{"attempt_count":25,"output_max":39199,"output_mean":13770.375,"output_min":1490,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":39199,"output_mean":24874.75,"output_min":14259,"run_count":8},"none":{"attempt_count":12,"output_max":5186,"output_mean":2666.0,"output_min":1490,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":33.67655142746384,"none":26.52176286308391},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[209715],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":34,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[209715],"total_output_tokens":220326,"total_visible_output_tokens":220326,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":209715,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"mistral","provider_model":"mistralai/mistral-medium-3-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-07"],"first_pass_admitted":4,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.5}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":11.889197636057522,"score":5.944598818028761},"GB2-02":{"attempts":2,"playable":42.74039725183472,"score":42.74039725183472},"GB2-03":{"attempts":2,"playable":37.16364847953977,"score":37.16364847953977},"GB2-04":{"attempts":2,"playable":36.019988279766324,"score":36.019988279766324},"GB2-05":{"attempts":2,"playable":25.383634673574207,"score":25.383634673574207},"GB2-06":{"attempts":2,"playable":22.588477084149766,"score":22.588477084149766},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":12.860028797665068,"score":6.430014398832534},"GB2-08":{"attempts":2,"playable":34.423341031191036,"score":34.423341031191036}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.839085585535564,"score":44.839085585535564},"GB2-03":{"attempts":1,"playable":38.75847279473334,"score":38.75847279473334},"GB2-04":{"attempts":1,"playable":39.139847277950906,"score":39.139847277950906},"GB2-05":{"attempts":1,"playable":38.55024180767929,"score":38.55024180767929},"GB2-06":{"attempts":1,"playable":26.905258816068116,"score":26.905258816068116},"GB2-07":{"attempts":1,"playable":12.860028797665068,"score":12.860028797665068},"GB2-08":{"attempts":1,"playable":34.68292491261459,"score":34.68292491261459}},"none":{"GB2-01":{"attempts":1,"playable":11.889197636057522,"score":11.889197636057522},"GB2-02":{"attempts":1,"playable":40.64170891813389,"score":40.64170891813389},"GB2-03":{"attempts":1,"playable":35.5688241643462,"score":35.5688241643462},"GB2-04":{"attempts":1,"playable":32.900129281581734,"score":32.900129281581734},"GB2-05":{"attempts":1,"playable":12.217027539469118,"score":12.217027539469118},"GB2-06":{"attempts":1,"playable":18.27169535223141,"score":18.27169535223141},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":34.163757149767484,"score":34.163757149767484}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-15T06:41:19Z","match_totals_all":{"draws":2919,"losses":4643,"wins":1218},"match_totals_tracks":{"highest":{"draws":1538,"losses":2191,"wins":755},"none":{"draws":1381,"losses":2452,"wins":463}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":44.839085585535564,"mean":26.33676250211464,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-02":44.839085585535564,"GB2-03":38.75847279473334,"GB2-04":39.139847277950906,"GB2-05":38.55024180767929,"GB2-06":26.905258816068116,"GB2-07":12.860028797665068,"GB2-08":34.68292491261459},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":509,"wins":40},"GB2-02":{"draws":982,"losses":216,"wins":28},"GB2-03":{"draws":352,"losses":610,"wins":280},"GB2-04":{"draws":698,"losses":410,"wins":92},"GB2-05":{"draws":0,"losses":938,"wins":358},"GB2-06":{"draws":27,"losses":919,"wins":264},"GB2-07":{"draws":0,"losses":576,"wins":78},"GB2-08":{"draws":795,"losses":465,"wins":78}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":505,"losses":104,"wins":27},"GB2-03":{"draws":187,"losses":287,"wins":140},"GB2-04":{"draws":413,"losses":159,"wins":36},"GB2-05":{"draws":0,"losses":385,"wins":277},"GB2-06":{"draws":24,"losses":427,"wins":155},"GB2-07":{"draws":0,"losses":576,"wins":78},"GB2-08":{"draws":409,"losses":253,"wins":42}},"none":{"GB2-01":{"draws":65,"losses":509,"wins":40},"GB2-02":{"draws":477,"losses":112,"wins":1},"GB2-03":{"draws":165,"losses":323,"wins":140},"GB2-04":{"draws":285,"losses":251,"wins":56},"GB2-05":{"draws":0,"losses":553,"wins":81},"GB2-06":{"draws":3,"losses":492,"wins":109},"GB2-08":{"draws":386,"losses":212,"wins":36}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1436.0881592397375,"GB2-03":1341.200785417578,"GB2-04":1393.6663728178387,"GB2-05":1305.5468574354384,"GB2-06":1097.3648273989172,"GB2-07":903.3196114246525,"GB2-08":1267.96594170732},"none":{"GB2-01":1032.3939519759795,"GB2-02":1403.547243156956,"GB2-03":1312.9541195646611,"GB2-04":1342.8713797537873,"GB2-05":855.8905058919541,"GB2-06":958.9467872883766,"GB2-08":1262.7123973609598}},"per_game_tracks":{"highest":{"GB2-02":44.839085585535564,"GB2-03":38.75847279473334,"GB2-04":39.139847277950906,"GB2-05":38.55024180767929,"GB2-06":26.905258816068116,"GB2-07":12.860028797665068,"GB2-08":34.68292491261459},"none":{"GB2-01":11.889197636057522,"GB2-02":40.64170891813389,"GB2-03":35.5688241643462,"GB2-04":32.900129281581734,"GB2-05":12.217027539469118,"GB2-06":18.27169535223141,"GB2-08":34.163757149767484}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.466982499030866,"none":23.20654250519842},"reasoning_agg":{"highest":{"max":44.839085585535564,"mean":29.466982499030866,"min":0.0},"none":{"max":40.64170891813389,"mean":23.20654250519842,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":6.2604399938324455}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:ffc7b0980fa12b22","codegen_cost_by_reasoning":{"medium":{"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":0.81977125},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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":0.81977125},"historical-provider-setting-baseline":{"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":2.586028}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.215758025,"mean":0.132049078125,"median":0.1281735,"min":0.061553000000000004,"recorded_attempt_count":53,"run_count":24,"total":3.4057992500000007},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":19.024026450118704,"none":35.692875688056574},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":53,"finish_reasons":["length","stop"],"indexed_attempts":53,"output_token_observations":53,"total_output_tokens":2639964},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"mixed","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":5,"evaluated_cells":6,"failed_game_aliases":["GB2-04"],"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02"],"infra_failures_excluded":2,"model_code_failure_rate":0.16666666666666666,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":7,"evaluated_cells":7,"game_attempts":{"GB2-01":{"infra_failures_excluded":2},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"admitted":1,"infra_failures_excluded":1},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"admitted":1,"infra_failures_excluded":1},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":1,"infra_failures_excluded":1},"GB2-08":{"admitted":1,"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"infra_failures_excluded":9,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":7,"repaired_rate":1.0}},"headline_games_all":{"GB2-02":{"attempts":1,"playable":36.763612721559795,"score":36.763612721559795},"GB2-03":{"attempts":2,"playable":32.304571477674926,"score":32.304571477674926},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.29006486375035,"score":21.145032431875176},"GB2-05":{"attempts":2,"playable":21.229345820775347,"score":21.229345820775347},"GB2-06":{"attempts":2,"playable":12.11134949151734,"score":12.11134949151734},"GB2-07":{"attempts":2,"playable":45.150815127903385,"score":45.150815127903385},"GB2-08":{"attempts":2,"playable":22.162210322968704,"score":22.162210322968704}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":31.400352397874222,"score":31.400352397874222},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":12.429853137828665,"score":12.429853137828665},"GB2-06":{"attempts":1,"playable":14.108228858294217,"score":14.108228858294217},"GB2-07":{"attempts":1,"playable":24.847399720929634,"score":24.847399720929634},"GB2-08":{"attempts":1,"playable":12.33429813566679,"score":12.33429813566679}},"none":{"GB2-02":{"attempts":1,"playable":36.763612721559795,"score":36.763612721559795},"GB2-03":{"attempts":1,"playable":33.20879055747562,"score":33.20879055747562},"GB2-04":{"attempts":1,"playable":42.29006486375035,"score":42.29006486375035},"GB2-05":{"attempts":1,"playable":30.028838503722028,"score":30.028838503722028},"GB2-06":{"attempts":1,"playable":10.114470124740462,"score":10.114470124740462},"GB2-07":{"attempts":1,"playable":65.45423053487714,"score":65.45423053487714},"GB2-08":{"attempts":1,"playable":31.99012251027062,"score":31.99012251027062}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-10-13T21:50:19Z","match_totals_all":{"draws":1847,"losses":4064,"wins":1171},"match_totals_tracks":{"medium":{"draws":308,"losses":2249,"wins":441},"none":{"draws":1539,"losses":1815,"wins":730}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":65.45423053487714,"mean":25.773115531577748,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":403,"losses":152,"wins":9},"GB2-03":{"draws":459,"losses":503,"wins":112},"GB2-04":{"draws":449,"losses":114,"wins":29},"GB2-05":{"draws":0,"losses":926,"wins":290},"GB2-06":{"draws":53,"losses":981,"wins":128},"GB2-07":{"draws":0,"losses":657,"wins":553},"GB2-08":{"draws":483,"losses":731,"wins":50}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":191,"losses":279,"wins":70},"GB2-05":{"draws":0,"losses":519,"wins":93},"GB2-06":{"draws":45,"losses":484,"wins":67},"GB2-07":{"draws":0,"losses":454,"wins":164},"GB2-08":{"draws":72,"losses":513,"wins":47}},"none":{"GB2-02":{"draws":403,"losses":152,"wins":9},"GB2-03":{"draws":268,"losses":224,"wins":42},"GB2-04":{"draws":449,"losses":114,"wins":29},"GB2-05":{"draws":0,"losses":407,"wins":197},"GB2-06":{"draws":8,"losses":497,"wins":61},"GB2-07":{"draws":0,"losses":203,"wins":389},"GB2-08":{"draws":411,"losses":218,"wins":3}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1274.832834782755,"GB2-05":861.0161214387075,"GB2-06":883.2803848505062,"GB2-07":1119.9911072774746,"GB2-08":993.7708161858434},"none":{"GB2-02":1372.8383783853637,"GB2-03":1291.5810085037488,"GB2-04":1418.3876833565255,"GB2-05":1185.3583126608005,"GB2-06":797.4175847782718,"GB2-07":1653.3414495885695,"GB2-08":1240.55859625213}},"per_game_tracks":{"medium":{"GB2-03":31.400352397874222,"GB2-05":12.429853137828665,"GB2-06":14.108228858294217,"GB2-07":24.847399720929634,"GB2-08":12.33429813566679},"none":{"GB2-02":36.763612721559795,"GB2-03":33.20879055747562,"GB2-04":42.29006486375035,"GB2-05":30.028838503722028,"GB2-06":10.114470124740462,"GB2-07":65.45423053487714,"GB2-08":31.99012251027062}},"provider_color":"#111827","provider_company":"Nex AGI","provider_key":"nex-agi","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":15.85335537509892,"none":35.692875688056574},"reasoning_agg":{"medium":{"max":31.400352397874222,"mean":15.85335537509892,"min":0.0},"none":{"max":65.45423053487714,"mean":35.692875688056574,"min":10.114470124740462}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":19.839520312957653}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:c142af8439c129ad","codegen_cost_by_reasoning":{"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":44.46851853242895,"none":25.758818038092155},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"total_output_tokens":343242},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.7-plus","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-04"],"first_pass_admitted":1,"first_pass_rate":0.125,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":5,"repaired_rate":0.625},"baseline":{"admitted_plugins":6,"evaluated_cells":9,"failed_game_aliases":["GB2-01","GB2-03","GB2-08"],"first_pass_admitted":4,"first_pass_rate":0.4444444444444444,"game_attempts":{"GB2-01":{"admitted":1,"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.3333333333333333,"model_code_failures":3,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.2222222222222222}},"headline_games_all":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":34.543410711978865,"score":29.539868065954188},"GB2-02":{"attempts":2,"playable":41.40882753196705,"score":41.40882753196705},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.77261258228823,"score":21.886306291144116},"GB2-05":{"attempts":2,"playable":37.97920959832432,"score":37.97920959832432},"GB2-06":{"attempts":2,"playable":41.51096982991176,"score":41.51096982991176},"GB2-07":{"attempts":2,"playable":16.859356262203246,"score":16.859356262203246},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":32.98785897206795,"score":16.493929486033974}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":49.072650839859016,"score":49.072650839859016},"GB2-02":{"attempts":1,"playable":43.509358410239166,"score":43.509358410239166},"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":45.406161005731455,"score":45.406161005731455},"GB2-06":{"attempts":1,"playable":70.92709386756192,"score":70.92709386756192},"GB2-07":{"attempts":1,"playable":24.90798809911423,"score":24.90798809911423},"GB2-08":{"attempts":1,"playable":32.98785897206795,"score":32.98785897206795}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":20.01417058409872,"score":10.00708529204936},"GB2-02":{"attempts":1,"playable":39.30829665369494,"score":39.30829665369494},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.77261258228823,"score":43.77261258228823},"GB2-05":{"attempts":1,"playable":30.55225819091718,"score":30.55225819091718},"GB2-06":{"attempts":1,"playable":12.094845792261602,"score":12.094845792261602},"GB2-07":{"attempts":1,"playable":8.810724425292262,"score":8.810724425292262},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-10-13T11:42:13Z","match_totals_all":{"draws":2035,"losses":3560,"wins":1560},"match_totals_tracks":{"medium":{"draws":1041,"losses":1498,"wins":1105},"none":{"draws":994,"losses":2062,"wins":455}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":70.92709386756192,"mean":25.70980838319233,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":235,"losses":652,"wins":299},"GB2-02":{"draws":922,"losses":189,"wins":9},"GB2-04":{"draws":403,"losses":114,"wins":50},"GB2-05":{"draws":0,"losses":732,"wins":496},"GB2-06":{"draws":28,"losses":659,"wins":475},"GB2-07":{"draws":0,"losses":1009,"wins":231},"GB2-08":{"draws":447,"losses":205,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":103,"losses":255,"wins":240},"GB2-02":{"draws":467,"losses":75,"wins":8},"GB2-05":{"draws":0,"losses":336,"wins":290},"GB2-06":{"draws":24,"losses":159,"wins":397},"GB2-07":{"draws":0,"losses":468,"wins":170},"GB2-08":{"draws":447,"losses":205,"wins":0}},"none":{"GB2-01":{"draws":132,"losses":397,"wins":59},"GB2-02":{"draws":455,"losses":114,"wins":1},"GB2-04":{"draws":403,"losses":114,"wins":50},"GB2-05":{"draws":0,"losses":396,"wins":206},"GB2-06":{"draws":4,"losses":500,"wins":78},"GB2-07":{"draws":0,"losses":541,"wins":61}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1473.48448712916,"GB2-02":1425.8265645383326,"GB2-05":1394.0870163187624,"GB2-06":1809.6074941172903,"GB2-07":1120.9023239233054,"GB2-08":1250.7638239197945},"none":{"GB2-01":1163.5868457618458,"GB2-02":1393.081684910273,"GB2-04":1429.9041317533793,"GB2-05":1193.2066036219082,"GB2-06":842.2709165364757,"GB2-07":798.2222222122574}},"per_game_tracks":{"medium":{"GB2-01":49.072650839859016,"GB2-02":43.509358410239166,"GB2-05":45.406161005731455,"GB2-06":70.92709386756192,"GB2-07":24.90798809911423,"GB2-08":32.98785897206795},"none":{"GB2-01":20.01417058409872,"GB2-02":39.30829665369494,"GB2-04":43.77261258228823,"GB2-05":30.55225819091718,"GB2-06":12.094845792261602,"GB2-07":8.810724425292262}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.35138889932171,"none":18.068227867062944},"reasoning_agg":{"medium":{"max":70.92709386756192,"mean":33.35138889932171,"min":0.0},"none":{"max":43.77261258228823,"mean":18.068227867062944,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":15.283161032258768}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:34309b55f784132e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.00217964,"mean":0.000272455,"median":0.0,"min":0.0,"recorded_attempt_count":53,"run_count":17,"total":0.00653892},"none":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":43},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.0010891599999999998,"mean":0.00013614499999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":43,"run_count":17,"total":0.0032674799999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":1,"cost_basis_counts":{"provider_reported":1},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00653892,"mean":0.00653892,"median":0.00653892,"min":0.00653892,"recorded_attempt_count":1,"run_count":1,"total":0.00653892},"historical-provider-setting-balanced-variant-2":{"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},"historical-provider-setting-baseline-variant-1":{"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},"historical-provider-setting-baseline-variant-2":{"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_cost_usd":{"admitted_cell_count":17,"cell_count":16,"cost_basis_counts":{"provider_reported":96},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00217964,"mean":0.00020429999999999998,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":3},"recorded_attempt_count":96,"run_count":34,"total":0.0098064},"codegen_latency_ms":{"attempt_count":96,"max_ms":410978,"mean_ms":155707.0,"min_ms":18717,"run_count":33},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":53,"max_ms":410978,"mean_ms":269539.1875,"min_ms":161500,"run_count":16},"none":{"attempt_count":43,"max_ms":90441,"mean_ms":48570.82352941176,"min_ms":18717,"run_count":17}},"codegen_output_tokens":{"attempt_count":96,"output_max":92074,"output_mean":32817.64705882353,"output_min":2036,"run_count":34},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":53,"output_max":92074,"output_mean":58883.76470588235,"output_min":20000,"run_count":17},"none":{"attempt_count":43,"output_max":17378,"output_mean":6751.529411764706,"output_min":2036,"run_count":17}},"display_name":"Ling 3.0 Flash","economics":{"medium":30.356265697386164,"none":31.619117159931942},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":4,"effective_max_output_tokens":[32768],"finish_reason_observations":96,"finish_reasons":["length","stop","unknown"],"indexed_attempts":98,"output_token_observations":97,"provider_post_attempt_observations":4,"provider_post_attempts":5,"reasoning_token_observations":69,"reconciliation_get_attempt_observations":4,"requested_max_output_token_observations":4,"requested_max_output_tokens":[32768],"total_output_tokens":1115800,"total_reasoning_output_tokens":656294,"total_visible_output_tokens":120852,"visible_token_observations":59},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"inclusionai","provider_model":"inclusionai/ling-3.0-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":6,"first_pass_admitted":1,"first_pass_rate":0.16666666666666666,"game_attempts":{"GB2-01":{"admitted":1,"infra_failures_excluded":1},"GB2-02":{"admitted":1,"infra_failures_excluded":1},"GB2-03":{"infra_failures_excluded":2},"GB2-04":{"admitted":1,"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":2},"GB2-06":{"admitted":1,"infra_failures_excluded":1},"GB2-07":{"admitted":2},"GB2-08":{"infra_failures_excluded":2}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":10,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":false,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":5,"repaired_rate":0.8333333333333334},"baseline":{"admitted_plugins":11,"evaluated_cells":17,"failed_game_aliases":["GB2-02","GB2-04","GB2-05","GB2-07"],"first_pass_admitted":7,"first_pass_rate":0.4117647058823529,"game_attempts":{"GB2-01":{"admitted":2},"GB2-02":{"admitted":1,"model_code_failures":1},"GB2-03":{"admitted":2},"GB2-04":{"admitted":1,"model_code_failures":1},"GB2-05":{"model_code_failures":2},"GB2-06":{"admitted":2},"GB2-07":{"model_code_failures":2},"GB2-08":{"admitted":3}},"model_code_failure_rate":0.35294117647058826,"model_code_failures":6,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":4,"repaired_rate":0.23529411764705882}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":27.768899869990317,"score":27.768899869990317},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":38.795468551031874,"score":28.842391937387333},"GB2-03":{"attempts":2,"playable":27.66516464272556,"score":27.66516464272556},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.27339378130093,"score":31.20787051769826},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.503052126428551,"score":14.503052126428551},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":36.28774746445646,"score":18.14387373222823},"GB2-08":{"attempts":3,"playable":31.077903735801943,"score":31.077903735801943}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.260196257097824,"score":18.260196257097824},"GB2-02":{"attempts":1,"playable":37.778630647485585,"score":37.778630647485585},"GB2-04":{"attempts":1,"playable":40.28469450819117,"score":40.28469450819117},"GB2-06":{"attempts":1,"playable":19.17005960969976,"score":19.17005960969976},"GB2-07":{"attempts":2,"playable":36.28774746445646,"score":36.28774746445646}},"none":{"GB2-01":{"attempts":2,"playable":37.27760348288281,"score":37.27760348288281},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.81230645457816,"score":19.90615322728908},"GB2-03":{"attempts":2,"playable":27.66516464272556,"score":27.66516464272556},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.26209305441069,"score":22.131046527205346},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.836044643157344,"score":9.836044643157344},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":31.077903735801943,"score":31.077903735801943}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-10-14T17:26:42Z","match_totals_all":{"draws":3973,"losses":5753,"wins":1538},"match_totals_tracks":{"medium":{"draws":1282,"losses":2510,"wins":840},"none":{"draws":2691,"losses":3243,"wins":698}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":40.28469450819117,"mean":24.42150261488446,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":472,"losses":1151,"wins":373},"GB2-02":{"draws":1016,"losses":273,"wins":11},"GB2-03":{"draws":379,"losses":633,"wins":128},"GB2-04":{"draws":1009,"losses":264,"wins":87},"GB2-06":{"draws":14,"losses":1684,"wins":288},"GB2-07":{"draws":0,"losses":1053,"wins":599},"GB2-08":{"draws":1083,"losses":695,"wins":52}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":198,"losses":514,"wins":36},"GB2-02":{"draws":538,"losses":160,"wins":6},"GB2-04":{"draws":543,"losses":163,"wins":42},"GB2-06":{"draws":3,"losses":620,"wins":157},"GB2-07":{"draws":0,"losses":1053,"wins":599}},"none":{"GB2-01":{"draws":274,"losses":637,"wins":337},"GB2-02":{"draws":478,"losses":113,"wins":5},"GB2-03":{"draws":379,"losses":633,"wins":128},"GB2-04":{"draws":466,"losses":101,"wins":45},"GB2-06":{"draws":11,"losses":1064,"wins":131},"GB2-08":{"draws":1083,"losses":695,"wins":52}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1138.9557529111266,"GB2-02":1380.9615489814125,"GB2-04":1402.6994931160293,"GB2-06":974.1905810811018,"GB2-07":1276.910642452011},"none":{"GB2-01":1357.9504677740251,"GB2-02":1397.0473128858275,"GB2-03":1237.745398937783,"GB2-04":1433.6955785064176,"GB2-06":640.208835484918,"GB2-08":1228.8081173966743}},"per_game_tracks":{"medium":{"GB2-01":18.260196257097824,"GB2-02":37.778630647485585,"GB2-04":40.28469450819117,"GB2-06":19.17005960969976,"GB2-07":36.28774746445646},"none":{"GB2-01":37.27760348288281,"GB2-02":39.81230645457816,"GB2-03":27.66516464272556,"GB2-04":44.26209305441069,"GB2-06":9.836044643157344,"GB2-08":30.861490681837065}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.356265697386164,"none":18.48673953238276},"reasoning_agg":{"medium":{"max":40.28469450819117,"mean":30.356265697386164,"min":18.260196257097824},"none":{"max":37.27760348288281,"mean":18.48673953238276,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.869526165003403}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:305083fd896b3511","codegen_cost_by_reasoning":{"medium":{"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},"none":{"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_cost_by_setting":{"historical-provider-setting-balanced":{"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},"historical-provider-setting-baseline":{"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_cost_usd":{"admitted_cell_count":9,"cell_count":16,"cost_basis_counts":{"provider_reported":30},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":30,"run_count":16,"total":0.0},"codegen_latency_ms":{"attempt_count":30,"max_ms":905283,"mean_ms":265606.6875,"min_ms":7507,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":905283,"mean_ms":509118.375,"min_ms":288605,"run_count":8},"none":{"attempt_count":15,"max_ms":59126,"mean_ms":22095.0,"min_ms":7507,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":52275,"output_mean":16877.75,"output_min":1148,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":52275,"output_mean":30105.875,"output_min":9014,"run_count":8},"none":{"attempt_count":15,"output_max":7281,"output_mean":3649.625,"output_min":1148,"run_count":8}},"display_name":"North Mini Code","economics":{"medium":30.71893423707562,"none":18.128310861067018},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[64000],"finish_reason_observations":30,"finish_reasons":["stop"],"indexed_attempts":30,"output_token_observations":30,"provider_post_attempt_observations":15,"provider_post_attempts":15,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[64000],"total_output_tokens":270044,"total_visible_output_tokens":29197,"visible_token_observations":15},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"cohere","provider_model":"cohere/north-mini-code","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"admitted":1},"GB2-04":{"admitted":1},"GB2-05":{"admitted":1},"GB2-06":{"admitted":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.25,"model_code_failures":2,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":3,"repaired_rate":0.375},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-06"],"first_pass_admitted":2,"first_pass_rate":0.25,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"model_code_failures":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"admitted":1},"GB2-06":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false},"repaired_admitted":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":21.02984714237202,"score":10.51492357118601},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.23918777764652,"score":20.61959388882326},"GB2-05":{"attempts":2,"playable":33.26564756760488,"score":33.26564756760488},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":18.455232702854204,"score":9.227616351427102},"GB2-07":{"attempts":2,"playable":15.603056227734465,"score":15.603056227734465},"GB2-08":{"attempts":2,"playable":30.118431396051673,"score":30.118431396051673}},"headline_games_tracks":{"medium":{"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":21.02984714237202,"score":21.02984714237202},"GB2-04":{"attempts":1,"playable":41.23918777764652,"score":41.23918777764652},"GB2-05":{"attempts":1,"playable":46.562986005425074,"score":46.562986005425074},"GB2-06":{"attempts":1,"playable":18.455232702854204,"score":18.455232702854204},"GB2-07":{"attempts":1,"playable":28.997506611257577,"score":28.997506611257577},"GB2-08":{"attempts":1,"playable":28.028845182898323,"score":28.028845182898323}},"none":{"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":19.968309129784682,"score":19.968309129784682},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.2086058442113505,"score":2.2086058442113505},"GB2-08":{"attempts":1,"playable":32.20801760920502,"score":32.20801760920502}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":1203,"losses":3024,"wins":825},"match_totals_tracks":{"medium":{"draws":920,"losses":1976,"wins":712},"none":{"draws":283,"losses":1048,"wins":113}},"model_slug":"cohere-north-mini-code","overall":{"max":46.562986005425074,"mean":14.918658625353423,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-03":{"draws":136,"losses":351,"wins":41},"GB2-04":{"draws":402,"losses":148,"wins":48},"GB2-05":{"draws":0,"losses":707,"wins":405},"GB2-06":{"draws":7,"losses":462,"wins":119},"GB2-07":{"draws":0,"losses":910,"wins":202},"GB2-08":{"draws":658,"losses":446,"wins":10}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":136,"losses":351,"wins":41},"GB2-04":{"draws":402,"losses":148,"wins":48},"GB2-05":{"draws":0,"losses":319,"wins":309},"GB2-06":{"draws":7,"losses":462,"wins":119},"GB2-07":{"draws":0,"losses":443,"wins":195},"GB2-08":{"draws":375,"losses":253,"wins":0}},"none":{"GB2-05":{"draws":0,"losses":388,"wins":96},"GB2-07":{"draws":0,"losses":467,"wins":7},"GB2-08":{"draws":283,"losses":193,"wins":10}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1168.0050183994322,"GB2-04":1410.1853942960124,"GB2-05":1408.6643465576237,"GB2-06":962.0853946148192,"GB2-07":1180.0198551608585,"GB2-08":1199.136561886746},"none":{"GB2-05":1017.9811282776476,"GB2-07":479.09103168983165,"GB2-08":1242.793331959961}},"per_game_tracks":{"medium":{"GB2-03":21.02984714237202,"GB2-04":41.23918777764652,"GB2-05":46.562986005425074,"GB2-06":18.455232702854204,"GB2-07":28.997506611257577,"GB2-08":28.028845182898323},"none":{"GB2-05":19.968309129784682,"GB2-07":2.2086058442113505,"GB2-08":32.20801760920502}},"provider_color":"#FF7759","provider_company":"Cohere","provider_key":"cohere","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.039200677806715,"none":6.798116572900132},"reasoning_agg":{"medium":{"max":46.562986005425074,"mean":23.039200677806715,"min":0.0},"none":{"max":32.20801760920502,"mean":6.798116572900132,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.241084104906584}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:b9eef861e1de91ea","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":5,"max":0.0034966000000000003,"mean":0.002188375,"median":0.0022738000000000003,"min":0.0011728,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"run_count":8,"token_priced_attempt_count":13,"total":0.017507},"codegen_latency_ms":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":13,"max_ms":44784,"mean_ms":22388.5,"min_ms":11128,"run_count":8}},"codegen_output_tokens":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":13,"output_max":4341,"output_mean":2556.0,"output_min":1068,"run_count":8}},"display_name":"GPT-4.1 Nano","economics":{"none":31.449719214714943},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":13,"effective_max_output_tokens":[32768],"finish_reason_observations":13,"finish_reasons":["stop"],"indexed_attempts":13,"output_token_observations":13,"provider_post_attempt_observations":13,"provider_post_attempts":13,"reasoning_token_observations":13,"reconciliation_get_attempt_observations":13,"requested_max_output_token_observations":13,"requested_max_output_tokens":[32768],"total_output_tokens":20448,"total_visible_output_tokens":20448,"visible_token_observations":13},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":32768,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-4.1-nano","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"b3f37977ef2a5a477d53f21e45438911a4e8651380229f062ef8dbf4b56e6096","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-07","GB2-08"],"first_pass_admitted":3,"first_pass_rate":0.375,"game_attempts":{"GB2-01":{"model_code_failures":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"model_code_failures":1},"GB2-05":{"model_code_failures":1},"GB2-06":{"admitted":1},"GB2-07":{"model_code_failures":1},"GB2-08":{"model_code_failures":1}},"model_code_failure_rate":0.625,"model_code_failures":5,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":false,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":false}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.65894104205029,"score":41.65894104205029},"GB2-03":{"attempts":1,"playable":34.79248324695654,"score":34.79248324695654},"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":17.89773335513799,"score":17.89773335513799},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":41.65894104205029,"score":41.65894104205029},"GB2-03":{"attempts":1,"playable":34.79248324695654,"score":34.79248324695654},"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":17.89773335513799,"score":17.89773335513799},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"gpt-4.1-nano","is_recent_addition":false,"last_measured_at":"2026-10-12T23:41:16Z","match_totals_all":{"draws":620,"losses":634,"wins":80},"match_totals_tracks":{"none":{"draws":620,"losses":634,"wins":80}},"model_slug":"gpt-4-1-nano","overall":{"max":41.65894104205029,"mean":11.793644705518103,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-02":{"draws":343,"losses":86,"wins":3},"GB2-03":{"draws":271,"losses":169,"wins":6},"GB2-06":{"draws":6,"losses":379,"wins":71}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":343,"losses":86,"wins":3},"GB2-03":{"draws":271,"losses":169,"wins":6},"GB2-06":{"draws":6,"losses":379,"wins":71}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1411.4806097375767,"GB2-03":1305.9759828060699,"GB2-06":952.5104845344645}},"per_game_tracks":{"none":{"GB2-02":41.65894104205029,"GB2-03":34.79248324695654,"GB2-06":17.89773335513799}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":11.793644705518103},"reasoning_agg":{"none":{"max":41.65894104205029,"mean":11.793644705518103,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"}}],"public_release_id":"gb2-20261016-1cf51d8598b5","rating_method":{"bootstrap_iterations":0,"first_player_advantage":true,"method":"bradley_terry_newton","reference_field":{"manifest_sha256":"f02ffdc046ccbb060241b53df78dedf7e60ba7d8e68807f11921754cf4f0345a","population_revision":"62c0f9ac87b4c843aacf3d3e0c418e498bb133c2c43cf3ae7fd93c0d1fef2ed0","rule":"model_balanced_common_field_v1","source":"frozen_manifest","version":"v1"}},"results_cut_id":"gb2-20261016-1cf51d8598b5","schema_version":2,"snapshot_id":"20261016_184128","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-10-16 18:41 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":51,"wins":51},"claude-fable-5":{"draws":35,"losses":131,"wins":30},"claude-fable-5-1":{"draws":8,"losses":196,"wins":6},"claude-haiku-5-5":{"draws":27,"losses":74,"wins":25},"claude-opus-4-5":{"draws":95,"losses":135,"wins":64},"claude-opus-4-8":{"draws":32,"losses":70,"wins":22},"claude-opus-5":{"draws":30,"losses":182,"wins":24},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":77,"losses":118,"wins":45},"claude-sonnet-5-5":{"draws":28,"losses":79,"wins":25},"cohere/north-mini-code":{"draws":15,"losses":14,"wins":25},"deepseek/deepseek-v4-flash":{"draws":102,"losses":101,"wins":97},"deepseek/deepseek-v4-pro":{"draws":63,"losses":107,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":68,"losses":93,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":60,"wins":32},"fireworks/ember-1":{"draws":40,"losses":68,"wins":24},"gemini-3.1-pro-preview":{"draws":36,"losses":57,"wins":39},"google/gemini-3.1-flash-lite":{"draws":30,"losses":20,"wins":48},"google/gemini-3.5-flash":{"draws":75,"losses":120,"wins":61},"google/gemini-3.5-flash-lite":{"draws":157,"losses":138,"wins":145},"google/gemini-3.6-flash":{"draws":115,"losses":201,"wins":88},"google/gemini-3.8-flash":{"draws":57,"losses":111,"wins":38},"google/gemma-4-31b-it":{"draws":27,"losses":24,"wins":25},"gpt-4.1":{"draws":18,"losses":17,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":40,"losses":44,"wins":38},"gpt-5.4":{"draws":54,"losses":91,"wins":47},"gpt-5.4-mini":{"draws":35,"losses":25,"wins":32},"gpt-5.4-nano":{"draws":31,"losses":49,"wins":58},"gpt-5.5":{"draws":54,"losses":56,"wins":24},"gpt-5.6-luna":{"draws":77,"losses":71,"wins":86},"gpt-5.6-sol":{"draws":33,"losses":147,"wins":28},"gpt-5.6-terra":{"draws":68,"losses":107,"wins":43},"gpt-6-astra":{"draws":10,"losses":153,"wins":15},"gpt-6-luna":{"draws":39,"losses":54,"wins":39},"gpt-6-sol":{"draws":15,"losses":102,"wins":15},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":72,"losses":47,"wins":57},"inclusionai/ling-3.0-flash":{"draws":52,"losses":22,"wins":52},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":63,"losses":54,"wins":83},"meta/muse-glimmer-30b":{"draws":92,"losses":64,"wins":68},"meta/muse-spark-1.2":{"draws":52,"losses":83,"wins":53},"meta/muse-spark-1.3":{"draws":47,"losses":106,"wins":35},"meta/muse-wonder":{"draws":30,"losses":86,"wins":16},"minimax/minimax-m3":{"draws":20,"losses":17,"wins":41},"mistralai/mistral-large-4-0":{"draws":25,"losses":33,"wins":24},"mistralai/mistral-medium-3-5":{"draws":58,"losses":35,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":16,"wins":9},"moonshotai/kimi-k3":{"draws":59,"losses":95,"wins":48},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":39},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":37,"wins":42},"o3":{"draws":54,"losses":135,"wins":85},"openai/gpt-oss-120b":{"draws":75,"losses":59,"wins":76},"poolside/laguna-s-2.1":{"draws":81,"losses":52,"wins":61},"qwen/qwen3.7-max":{"draws":28,"losses":30,"wins":26},"qwen/qwen3.7-plus":{"draws":22,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":73,"losses":100,"wins":49},"qwen/qwen3.8-27b":{"draws":25,"losses":60,"wins":29},"qwen/qwen3.8-flash":{"draws":57,"losses":65,"wins":36},"qwen/qwen3.8-max":{"draws":84,"losses":87,"wins":67},"qwen/qwen3.8-max-0902":{"draws":37,"losses":74,"wins":21},"stealth/ox-alpha":{"draws":176,"losses":404,"wins":158},"stealth/space-bunny-alpha":{"draws":35,"losses":38,"wins":31},"stepfun/step-3.7-flash":{"draws":25,"losses":33,"wins":42},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":27,"losses":23,"wins":24},"tencent/hy4-preview":{"draws":78,"losses":122,"wins":30},"thinkingmachines/inkling":{"draws":77,"losses":58,"wins":93},"thinkingmachines/inkling-small":{"draws":96,"losses":56,"wins":100},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":15,"wins":14},"x-ai/grok-4.5":{"draws":49,"losses":120,"wins":29},"x-ai/grok-4.6":{"draws":62,"losses":121,"wins":31},"x-ai/grok-4.7":{"draws":6,"losses":91,"wins":17},"x-ai/grok-build-0.1":{"draws":18,"losses":10,"wins":22},"xiaomi/mimo-v2.5":{"draws":82,"losses":52,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":27,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":49,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":143,"losses":128,"wins":103},"z-ai/glm-5.3":{"draws":41,"losses":112,"wins":29},"z-ai/glm-5.3-flash":{"draws":66,"losses":111,"wins":37},"z-ai/glm-5.3-flashx":{"draws":24,"losses":83,"wins":25}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":30,"wins":131},"claude-fable-5":{"draws":24,"losses":76,"wins":76},"claude-fable-5-1":{"draws":15,"losses":242,"wins":45},"claude-haiku-5-5":{"draws":24,"losses":42,"wins":72},"claude-opus-4-5":{"draws":57,"losses":46,"wins":219},"claude-opus-4-8":{"draws":28,"losses":38,"wins":74},"claude-opus-5":{"draws":41,"losses":178,"wins":75},"claude-opus-5-5":{"draws":13,"losses":122,"wins":21},"claude-sonnet-5":{"draws":55,"losses":42,"wins":159},"claude-sonnet-5-5":{"draws":24,"losses":58,"wins":62},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":48},"deepseek/deepseek-v4-flash":{"draws":59,"losses":21,"wins":220},"deepseek/deepseek-v4-pro":{"draws":50,"losses":54,"wins":124},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":44,"wins":135},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":36,"wins":74},"fireworks/ember-1":{"draws":31,"losses":22,"wins":91},"gemini-3.1-pro-preview":{"draws":27,"losses":30,"wins":87},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":83},"google/gemini-3.5-flash":{"draws":59,"losses":54,"wins":171},"google/gemini-3.5-flash-lite":{"draws":84,"losses":55,"wins":257},"google/gemini-3.6-flash":{"draws":77,"losses":132,"wins":225},"google/gemini-3.8-flash":{"draws":41,"losses":97,"wins":126},"google/gemma-4-31b-it":{"draws":18,"losses":8,"wins":58},"gpt-4.1":{"draws":7,"losses":12,"wins":29},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":28,"losses":27,"wins":81},"gpt-5.4":{"draws":65,"losses":83,"wins":112},"gpt-5.4-mini":{"draws":22,"losses":11,"wins":63},"gpt-5.4-nano":{"draws":19,"losses":15,"wins":112},"gpt-5.5":{"draws":31,"losses":41,"wins":66},"gpt-5.6-luna":{"draws":61,"losses":34,"wins":133},"gpt-5.6-sol":{"draws":35,"losses":111,"wins":124},"gpt-5.6-terra":{"draws":68,"losses":40,"wins":150},"gpt-6-astra":{"draws":19,"losses":204,"wins":53},"gpt-6-luna":{"draws":31,"losses":28,"wins":85},"gpt-6-sol":{"draws":19,"losses":82,"wins":43},"gpt-6.1-sol":{"draws":11,"losses":101,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":45,"losses":7,"wins":88},"inclusionai/ling-3.0-flash":{"draws":22,"losses":5,"wins":87},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":34,"losses":30,"wins":132},"meta/muse-glimmer-30b":{"draws":48,"losses":14,"wins":120},"meta/muse-spark-1.2":{"draws":34,"losses":48,"wins":122},"meta/muse-spark-1.3":{"draws":39,"losses":58,"wins":109},"meta/muse-wonder":{"draws":25,"losses":57,"wins":62},"minimax/minimax-m3":{"draws":20,"losses":6,"wins":54},"mistralai/mistral-large-4-0":{"draws":18,"losses":23,"wins":49},"mistralai/mistral-medium-3-5":{"draws":37,"losses":11,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":40,"losses":36,"wins":138},"nex-agi/nex-n2-pro":{"draws":15,"losses":1,"wins":56},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":12,"wins":89},"o3":{"draws":29,"losses":44,"wins":209},"openai/gpt-oss-120b":{"draws":50,"losses":20,"wins":114},"poolside/laguna-s-2.1":{"draws":43,"losses":29,"wins":108},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":58},"qwen/qwen3.7-plus":{"draws":13,"losses":8,"wins":51},"qwen/qwen3.8-2.4t-a95b":{"draws":68,"losses":65,"wins":123},"qwen/qwen3.8-27b":{"draws":23,"losses":26,"wins":83},"qwen/qwen3.8-flash":{"draws":45,"losses":28,"wins":85},"qwen/qwen3.8-max":{"draws":41,"losses":70,"wins":131},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":81},"stealth/ox-alpha":{"draws":172,"losses":188,"wins":474},"stealth/space-bunny-alpha":{"draws":31,"losses":15,"wins":68},"stepfun/step-3.7-flash":{"draws":15,"losses":8,"wins":83},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":47},"tencent/hy4-preview":{"draws":42,"losses":57,"wins":141},"thinkingmachines/inkling":{"draws":49,"losses":11,"wins":162},"thinkingmachines/inkling-small":{"draws":51,"losses":26,"wins":141},"unbiased/pareto-26.10-preview":{"draws":5,"losses":33,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":28},"x-ai/grok-4.5":{"draws":31,"losses":77,"wins":114},"x-ai/grok-4.6":{"draws":64,"losses":90,"wins":116},"x-ai/grok-4.7":{"draws":7,"losses":76,"wins":43},"x-ai/grok-build-0.1":{"draws":11,"losses":8,"wins":31},"xiaomi/mimo-v2.5":{"draws":45,"losses":5,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":71},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":41,"wins":47},"z-ai/glm-5.2":{"draws":88,"losses":61,"wins":221},"z-ai/glm-5.3":{"draws":35,"losses":97,"wins":90},"z-ai/glm-5.3-flash":{"draws":44,"losses":80,"wins":124},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":73}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":6,"wins":196},"claude-fable-5":{"draws":15,"losses":45,"wins":242},"claude-fable-5-1":{"draws":20,"losses":122,"wins":122},"claude-haiku-5-5":{"draws":8,"losses":8,"wins":138},"claude-opus-4-5":{"draws":15,"losses":11,"wins":332},"claude-opus-4-8":{"draws":8,"losses":11,"wins":127},"claude-opus-5":{"draws":32,"losses":86,"wins":174},"claude-opus-5-5":{"draws":16,"losses":95,"wins":63},"claude-sonnet-5":{"draws":15,"losses":9,"wins":266},"claude-sonnet-5-5":{"draws":9,"losses":34,"wins":119},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":62},"deepseek/deepseek-v4-flash":{"draws":13,"losses":2,"wins":299},"deepseek/deepseek-v4-pro":{"draws":16,"losses":6,"wins":224},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":6,"wins":237},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":133},"fireworks/ember-1":{"draws":4,"losses":8,"wins":150},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":150},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":105},"google/gemini-3.5-flash":{"draws":23,"losses":14,"wins":279},"google/gemini-3.5-flash-lite":{"draws":28,"losses":3,"wins":375},"google/gemini-3.6-flash":{"draws":34,"losses":32,"wins":410},"google/gemini-3.8-flash":{"draws":22,"losses":27,"wins":257},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":89},"gpt-4.1":{"draws":1,"losses":2,"wins":51},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":7,"losses":1,"wins":134},"gpt-5.4":{"draws":19,"losses":33,"wins":230},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":104},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":155},"gpt-5.5":{"draws":5,"losses":18,"wins":131},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":206},"gpt-5.6-sol":{"draws":25,"losses":44,"wins":249},"gpt-5.6-terra":{"draws":22,"losses":6,"wins":244},"gpt-6-astra":{"draws":27,"losses":186,"wins":111},"gpt-6-luna":{"draws":10,"losses":6,"wins":146},"gpt-6-sol":{"draws":14,"losses":38,"wins":110},"gpt-6.1-sol":{"draws":13,"losses":77,"wins":72},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":129},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":117},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":6,"wins":189},"meta/muse-glimmer-30b":{"draws":13,"losses":1,"wins":161},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":205},"meta/muse-spark-1.3":{"draws":13,"losses":20,"wins":201},"meta/muse-wonder":{"draws":13,"losses":31,"wins":118},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":92},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":97},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":36},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":213},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":78},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":129},"o3":{"draws":5,"losses":14,"wins":277},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":170},"poolside/laguna-s-2.1":{"draws":10,"losses":2,"wins":178},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":90},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":72},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":13,"wins":250},"qwen/qwen3.8-27b":{"draws":7,"losses":2,"wins":139},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":157},"qwen/qwen3.8-max":{"draws":14,"losses":8,"wins":246},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":141},"stealth/ox-alpha":{"draws":78,"losses":49,"wins":859},"stealth/space-bunny-alpha":{"draws":6,"losses":3,"wins":121},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":111},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":74},"tencent/hy4-preview":{"draws":12,"losses":25,"wins":229},"thinkingmachines/inkling":{"draws":13,"losses":0,"wins":229},"thinkingmachines/inkling-small":{"draws":14,"losses":1,"wins":221},"unbiased/pareto-26.10-preview":{"draws":3,"losses":29,"wins":22},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":37},"x-ai/grok-4.5":{"draws":8,"losses":19,"wins":213},"x-ai/grok-4.6":{"draws":18,"losses":44,"wins":246},"x-ai/grok-4.7":{"draws":6,"losses":39,"wins":95},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":53},"xiaomi/mimo-v2.5":{"draws":12,"losses":3,"wins":229},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":90},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":85},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":10,"wins":84},"z-ai/glm-5.2":{"draws":29,"losses":10,"wins":359},"z-ai/glm-5.3":{"draws":16,"losses":38,"wins":196},"z-ai/glm-5.3-flash":{"draws":24,"losses":30,"wins":238},"z-ai/glm-5.3-flashx":{"draws":15,"losses":13,"wins":134}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":74},"claude-fable-5":{"draws":24,"losses":72,"wins":42},"claude-fable-5-1":{"draws":8,"losses":138,"wins":8},"claude-haiku-5-5":{"draws":16,"losses":36,"wins":36},"claude-opus-4-5":{"draws":64,"losses":57,"wins":105},"claude-opus-4-8":{"draws":28,"losses":57,"wins":45},"claude-opus-5":{"draws":35,"losses":160,"wins":39},"claude-opus-5-5":{"draws":16,"losses":126,"wins":8},"claude-sonnet-5":{"draws":35,"losses":40,"wins":63},"claude-sonnet-5-5":{"draws":25,"losses":70,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":57,"losses":30,"wins":121},"deepseek/deepseek-v4-pro":{"draws":35,"losses":41,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":29,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":39,"wins":56},"fireworks/ember-1":{"draws":36,"losses":38,"wins":64},"gemini-3.1-pro-preview":{"draws":32,"losses":46,"wins":60},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":66},"google/gemini-3.5-flash":{"draws":39,"losses":58,"wins":77},"google/gemini-3.5-flash-lite":{"draws":53,"losses":40,"wins":149},"google/gemini-3.6-flash":{"draws":65,"losses":99,"wins":100},"google/gemini-3.8-flash":{"draws":33,"losses":62,"wins":43},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":50},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":31,"losses":27,"wins":62},"gpt-5.4":{"draws":31,"losses":50,"wins":51},"gpt-5.4-mini":{"draws":27,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":27,"losses":39,"wins":76},"gpt-5.5":{"draws":46,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":40,"losses":24,"wins":74},"gpt-5.6-sol":{"draws":21,"losses":76,"wins":41},"gpt-5.6-terra":{"draws":39,"losses":37,"wins":56},"gpt-6-astra":{"draws":10,"losses":121,"wins":7},"gpt-6-luna":{"draws":36,"losses":39,"wins":63},"gpt-6-sol":{"draws":27,"losses":84,"wins":27},"gpt-6.1-sol":{"draws":15,"losses":113,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":68},"inclusionai/ling-3.0-flash":{"draws":32,"losses":5,"wins":61},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":96},"meta/muse-glimmer-30b":{"draws":37,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":65},"meta/muse-spark-1.3":{"draws":26,"losses":51,"wins":61},"meta/muse-wonder":{"draws":30,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":53},"mistralai/mistral-large-4-0":{"draws":30,"losses":28,"wins":28},"mistralai/mistral-medium-3-5":{"draws":22,"losses":4,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":40,"wins":58},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":26,"wins":66},"o3":{"draws":32,"losses":61,"wins":101},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":78},"poolside/laguna-s-2.1":{"draws":34,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":27,"losses":20,"wins":35},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":47,"wins":55},"qwen/qwen3.8-27b":{"draws":22,"losses":29,"wins":47},"qwen/qwen3.8-flash":{"draws":28,"losses":19,"wins":45},"qwen/qwen3.8-max":{"draws":34,"losses":37,"wins":67},"qwen/qwen3.8-max-0902":{"draws":40,"losses":48,"wins":50},"stealth/ox-alpha":{"draws":96,"losses":165,"wins":173},"stealth/space-bunny-alpha":{"draws":33,"losses":23,"wins":54},"stepfun/step-3.7-flash":{"draws":15,"losses":16,"wins":67},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy3-preview":{"draws":25,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":30,"losses":54,"wins":48},"thinkingmachines/inkling":{"draws":49,"losses":23,"wins":110},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":92},"unbiased/pareto-26.10-preview":{"draws":2,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":30,"losses":60,"wins":48},"x-ai/grok-4.6":{"draws":36,"losses":60,"wins":42},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":20},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":29},"xiaomi/mimo-v2.5":{"draws":56,"losses":31,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":18,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":27,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":64,"losses":64,"wins":148},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":32},"z-ai/glm-5.3-flash":{"draws":27,"losses":57,"wins":54},"z-ai/glm-5.3-flashx":{"draws":27,"losses":51,"wins":60}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":43,"wins":107},"claude-fable-5":{"draws":40,"losses":154,"wins":36},"claude-fable-5-1":{"draws":13,"losses":237,"wins":8},"claude-haiku-5-5":{"draws":40,"losses":55,"wins":43},"claude-opus-4-5":{"draws":110,"losses":93,"wins":121},"claude-opus-4-8":{"draws":56,"losses":103,"wins":63},"claude-opus-5":{"draws":69,"losses":343,"wins":46},"claude-opus-5-5":{"draws":12,"losses":136,"wins":8},"claude-sonnet-5":{"draws":109,"losses":76,"wins":137},"claude-sonnet-5-5":{"draws":30,"losses":75,"wins":39},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":53},"deepseek/deepseek-v4-flash":{"draws":82,"losses":67,"wins":157},"deepseek/deepseek-v4-pro":{"draws":52,"losses":75,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":77,"wins":72},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":62,"wins":44},"fireworks/ember-1":{"draws":50,"losses":56,"wins":38},"gemini-3.1-pro-preview":{"draws":36,"losses":46,"wins":62},"google/gemini-3.1-flash-lite":{"draws":34,"losses":8,"wins":98},"google/gemini-3.5-flash":{"draws":68,"losses":110,"wins":88},"google/gemini-3.5-flash-lite":{"draws":217,"losses":137,"wins":302},"google/gemini-3.6-flash":{"draws":174,"losses":284,"wins":202},"google/gemini-3.8-flash":{"draws":67,"losses":125,"wins":46},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":34,"losses":21,"wins":19},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":58,"losses":51,"wins":63},"gpt-5.4":{"draws":83,"losses":153,"wins":64},"gpt-5.4-mini":{"draws":62,"losses":33,"wins":55},"gpt-5.4-nano":{"draws":61,"losses":56,"wins":109},"gpt-5.5":{"draws":95,"losses":84,"wins":39},"gpt-5.6-luna":{"draws":111,"losses":78,"wins":127},"gpt-5.6-sol":{"draws":51,"losses":211,"wins":66},"gpt-5.6-terra":{"draws":78,"losses":57,"wins":75},"gpt-6-astra":{"draws":17,"losses":200,"wins":15},"gpt-6-luna":{"draws":45,"losses":47,"wins":52},"gpt-6-sol":{"draws":24,"losses":103,"wins":17},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":61,"losses":10,"wins":85},"inclusionai/ling-3.0-flash":{"draws":62,"losses":25,"wins":91},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":83,"losses":54,"wins":171},"meta/muse-glimmer-30b":{"draws":65,"losses":27,"wins":96},"meta/muse-spark-1.2":{"draws":60,"losses":114,"wins":72},"meta/muse-spark-1.3":{"draws":40,"losses":107,"wins":53},"meta/muse-wonder":{"draws":27,"losses":87,"wins":30},"minimax/minimax-m3":{"draws":34,"losses":15,"wins":67},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":33},"mistralai/mistral-medium-3-5":{"draws":34,"losses":11,"wins":79},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":15,"wins":30},"moonshotai/kimi-k3":{"draws":107,"losses":107,"wins":94},"nex-agi/nex-n2-pro":{"draws":27,"losses":14,"wins":67},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":63,"losses":26,"wins":91},"o3":{"draws":61,"losses":119,"wins":266},"openai/gpt-oss-120b":{"draws":55,"losses":28,"wins":105},"poolside/laguna-s-2.1":{"draws":111,"losses":32,"wins":139},"qwen/qwen3.7-max":{"draws":34,"losses":34,"wins":64},"qwen/qwen3.7-plus":{"draws":32,"losses":24,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":81,"losses":85,"wins":58},"qwen/qwen3.8-27b":{"draws":34,"losses":48,"wins":42},"qwen/qwen3.8-flash":{"draws":49,"losses":46,"wins":51},"qwen/qwen3.8-max":{"draws":65,"losses":102,"wins":64},"qwen/qwen3.8-max-0902":{"draws":36,"losses":58,"wins":50},"stealth/ox-alpha":{"draws":218,"losses":307,"wins":231},"stealth/space-bunny-alpha":{"draws":36,"losses":27,"wins":51},"stepfun/step-3.7-flash":{"draws":17,"losses":23,"wins":74},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":43,"losses":28,"wins":51},"tencent/hy4-preview":{"draws":55,"losses":99,"wins":66},"thinkingmachines/inkling":{"draws":91,"losses":49,"wins":168},"thinkingmachines/inkling-small":{"draws":76,"losses":31,"wins":122},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":110,"losses":149,"wins":99},"x-ai/grok-4.6":{"draws":61,"losses":118,"wins":49},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":27,"losses":8,"wins":41},"xiaomi/mimo-v2.5":{"draws":114,"losses":51,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":50,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":127,"losses":114,"wins":183},"z-ai/glm-5.3":{"draws":51,"losses":109,"wins":36},"z-ai/glm-5.3-flash":{"draws":54,"losses":112,"wins":60},"z-ai/glm-5.3-flashx":{"draws":37,"losses":74,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":22,"wins":70},"claude-fable-5":{"draws":28,"losses":74,"wins":38},"claude-fable-5-1":{"draws":8,"losses":127,"wins":11},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":57},"claude-opus-4-5":{"draws":96,"losses":92,"wins":186},"claude-opus-4-8":{"draws":32,"losses":64,"wins":64},"claude-opus-5":{"draws":79,"losses":273,"wins":82},"claude-opus-5-5":{"draws":13,"losses":114,"wins":17},"claude-sonnet-5":{"draws":38,"losses":38,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":62,"wins":42},"cohere/north-mini-code":{"draws":17,"losses":7,"wins":50},"deepseek/deepseek-v4-flash":{"draws":64,"losses":26,"wins":146},"deepseek/deepseek-v4-pro":{"draws":31,"losses":41,"wins":58},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":42,"wins":60},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":53,"wins":47},"fireworks/ember-1":{"draws":44,"losses":37,"wins":51},"gemini-3.1-pro-preview":{"draws":36,"losses":35,"wins":61},"google/gemini-3.1-flash-lite":{"draws":39,"losses":10,"wins":121},"google/gemini-3.5-flash":{"draws":55,"losses":52,"wins":93},"google/gemini-3.5-flash-lite":{"draws":83,"losses":34,"wins":175},"google/gemini-3.6-flash":{"draws":83,"losses":136,"wins":119},"google/gemini-3.8-flash":{"draws":30,"losses":63,"wins":51},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":29,"losses":9,"wins":42},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":49,"losses":52,"wins":101},"gpt-5.4":{"draws":29,"losses":56,"wins":51},"gpt-5.4-mini":{"draws":46,"losses":43,"wins":75},"gpt-5.4-nano":{"draws":52,"losses":59,"wins":147},"gpt-5.5":{"draws":71,"losses":99,"wins":68},"gpt-5.6-luna":{"draws":42,"losses":30,"wins":62},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":55},"gpt-5.6-terra":{"draws":36,"losses":37,"wins":61},"gpt-6-astra":{"draws":11,"losses":120,"wins":11},"gpt-6-luna":{"draws":35,"losses":36,"wins":61},"gpt-6-sol":{"draws":20,"losses":80,"wins":32},"gpt-6.1-sol":{"draws":7,"losses":110,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":11,"wins":57},"inclusionai/ling-3.0-flash":{"draws":59,"losses":0,"wins":83},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":43,"losses":31,"wins":114},"meta/muse-glimmer-30b":{"draws":34,"losses":17,"wins":69},"meta/muse-spark-1.2":{"draws":31,"losses":44,"wins":61},"meta/muse-spark-1.3":{"draws":28,"losses":58,"wins":54},"meta/muse-wonder":{"draws":26,"losses":62,"wins":44},"minimax/minimax-m3":{"draws":33,"losses":18,"wins":79},"mistralai/mistral-large-4-0":{"draws":18,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":14,"wins":32},"moonshotai/kimi-k3":{"draws":41,"losses":53,"wins":56},"nex-agi/nex-n2-pro":{"draws":41,"losses":10,"wins":73},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":32,"wins":127},"o3":{"draws":36,"losses":68,"wins":152},"openai/gpt-oss-120b":{"draws":38,"losses":10,"wins":68},"poolside/laguna-s-2.1":{"draws":58,"losses":24,"wins":102},"qwen/qwen3.7-max":{"draws":48,"losses":40,"wins":64},"qwen/qwen3.7-plus":{"draws":31,"losses":24,"wins":77},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":54,"wins":46},"qwen/qwen3.8-27b":{"draws":21,"losses":31,"wins":42},"qwen/qwen3.8-flash":{"draws":34,"losses":20,"wins":42},"qwen/qwen3.8-max":{"draws":30,"losses":49,"wins":65},"qwen/qwen3.8-max-0902":{"draws":35,"losses":47,"wins":50},"stealth/ox-alpha":{"draws":100,"losses":168,"wins":160},"stealth/space-bunny-alpha":{"draws":30,"losses":24,"wins":52},"stepfun/step-3.7-flash":{"draws":18,"losses":22,"wins":74},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":41,"losses":28,"wins":63},"tencent/hy4-preview":{"draws":34,"losses":61,"wins":51},"thinkingmachines/inkling":{"draws":57,"losses":32,"wins":143},"thinkingmachines/inkling-small":{"draws":42,"losses":12,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":3,"wins":27},"x-ai/grok-4.5":{"draws":58,"losses":81,"wins":71},"x-ai/grok-4.6":{"draws":37,"losses":60,"wins":47},"x-ai/grok-4.7":{"draws":16,"losses":73,"wins":29},"x-ai/grok-build-0.1":{"draws":24,"losses":14,"wins":50},"xiaomi/mimo-v2.5":{"draws":123,"losses":39,"wins":224},"xiaomi/mimo-v2.5-pro":{"draws":33,"losses":33,"wins":72},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":38,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":42,"wins":35},"z-ai/glm-5.2":{"draws":121,"losses":85,"wins":194},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":34},"z-ai/glm-5.3-flash":{"draws":22,"losses":62,"wins":58},"z-ai/glm-5.3-flashx":{"draws":25,"losses":49,"wins":58}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":24,"wins":182},"claude-fable-5":{"draws":41,"losses":75,"wins":178},"claude-fable-5-1":{"draws":32,"losses":174,"wins":86},"claude-haiku-5-5":{"draws":35,"losses":39,"wins":160},"claude-opus-4-5":{"draws":121,"losses":83,"wins":534},"claude-opus-4-8":{"draws":79,"losses":82,"wins":273},"claude-opus-5":{"draws":122,"losses":435,"wins":435},"claude-opus-5-5":{"draws":25,"losses":167,"wins":78},"claude-sonnet-5":{"draws":35,"losses":43,"wins":190},"claude-sonnet-5-5":{"draws":25,"losses":81,"wins":140},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":91},"deepseek/deepseek-v4-flash":{"draws":48,"losses":25,"wins":353},"deepseek/deepseek-v4-pro":{"draws":30,"losses":33,"wins":185},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":28,"wins":188},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":36,"wins":170},"fireworks/ember-1":{"draws":27,"losses":43,"wins":176},"gemini-3.1-pro-preview":{"draws":24,"losses":37,"wins":185},"google/gemini-3.1-flash-lite":{"draws":28,"losses":9,"wins":175},"google/gemini-3.5-flash":{"draws":43,"losses":33,"wins":270},"google/gemini-3.5-flash-lite":{"draws":74,"losses":43,"wins":449},"google/gemini-3.6-flash":{"draws":85,"losses":121,"wins":460},"google/gemini-3.8-flash":{"draws":34,"losses":61,"wins":203},"google/gemma-4-31b-it":{"draws":21,"losses":10,"wins":109},"gpt-4.1":{"draws":20,"losses":11,"wins":126},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":18},"gpt-5":{"draws":44,"losses":29,"wins":281},"gpt-5.4":{"draws":29,"losses":36,"wins":189},"gpt-5.4-mini":{"draws":52,"losses":20,"wins":182},"gpt-5.4-nano":{"draws":43,"losses":37,"wins":306},"gpt-5.5":{"draws":61,"losses":104,"wins":301},"gpt-5.6-luna":{"draws":26,"losses":26,"wins":204},"gpt-5.6-sol":{"draws":37,"losses":63,"wins":196},"gpt-5.6-terra":{"draws":30,"losses":21,"wins":197},"gpt-6-astra":{"draws":30,"losses":169,"wins":65},"gpt-6-luna":{"draws":47,"losses":21,"wins":178},"gpt-6-sol":{"draws":33,"losses":93,"wins":120},"gpt-6.1-sol":{"draws":30,"losses":140,"wins":76},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":129},"inclusionai/ling-3.0-flash":{"draws":46,"losses":11,"wins":167},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":45,"losses":36,"wins":291},"meta/muse-glimmer-30b":{"draws":14,"losses":23,"wins":195},"meta/muse-spark-1.2":{"draws":33,"losses":36,"wins":193},"meta/muse-spark-1.3":{"draws":39,"losses":54,"wins":173},"meta/muse-wonder":{"draws":29,"losses":76,"wins":141},"minimax/minimax-m3":{"draws":25,"losses":14,"wins":169},"mistralai/mistral-large-4-0":{"draws":24,"losses":19,"wins":119},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":112},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":7,"wins":112},"moonshotai/kimi-k3":{"draws":49,"losses":53,"wins":212},"nex-agi/nex-n2-pro":{"draws":3,"losses":10,"wins":147},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":8,"wins":269},"o3":{"draws":28,"losses":26,"wins":364},"openai/gpt-oss-120b":{"draws":32,"losses":11,"wins":183},"poolside/laguna-s-2.1":{"draws":34,"losses":27,"wins":325},"qwen/qwen3.7-max":{"draws":30,"losses":24,"wins":192},"qwen/qwen3.7-plus":{"draws":24,"losses":15,"wins":129},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":46,"wins":199},"qwen/qwen3.8-27b":{"draws":28,"losses":13,"wins":131},"qwen/qwen3.8-flash":{"draws":28,"losses":16,"wins":136},"qwen/qwen3.8-max":{"draws":39,"losses":32,"wins":195},"qwen/qwen3.8-max-0902":{"draws":35,"losses":42,"wins":169},"stealth/ox-alpha":{"draws":137,"losses":134,"wins":655},"stealth/space-bunny-alpha":{"draws":29,"losses":14,"wins":153},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":157},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":45,"losses":20,"wins":179},"tencent/hy4-preview":{"draws":29,"losses":36,"wins":199},"thinkingmachines/inkling":{"draws":59,"losses":44,"wins":335},"thinkingmachines/inkling-small":{"draws":35,"losses":13,"wins":204},"unbiased/pareto-26.10-preview":{"draws":3,"losses":50,"wins":29},"upstage/solar-mini4":{"draws":7,"losses":1,"wins":40},"x-ai/grok-4.5":{"draws":59,"losses":79,"wins":280},"x-ai/grok-4.6":{"draws":39,"losses":59,"wins":177},"x-ai/grok-4.7":{"draws":21,"losses":99,"wins":100},"x-ai/grok-build-0.1":{"draws":22,"losses":8,"wins":84},"xiaomi/mimo-v2.5":{"draws":87,"losses":35,"wins":426},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":8,"wins":169},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":17,"wins":119},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":39,"wins":99},"z-ai/glm-5.2":{"draws":111,"losses":49,"wins":492},"z-ai/glm-5.3":{"draws":33,"losses":63,"wins":148},"z-ai/glm-5.3-flash":{"draws":35,"losses":61,"wins":196},"z-ai/glm-5.3-flashx":{"draws":36,"losses":44,"wins":166}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":13,"losses":21,"wins":122},"claude-fable-5-1":{"draws":16,"losses":63,"wins":95},"claude-haiku-5-5":{"draws":16,"losses":8,"wins":126},"claude-opus-4-5":{"draws":20,"losses":15,"wins":219},"claude-opus-4-8":{"draws":13,"losses":17,"wins":114},"claude-opus-5":{"draws":25,"losses":78,"wins":167},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":11,"losses":11,"wins":134},"claude-sonnet-5-5":{"draws":16,"losses":29,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":217},"deepseek/deepseek-v4-pro":{"draws":12,"losses":4,"wins":128},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":134},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":132},"fireworks/ember-1":{"draws":8,"losses":11,"wins":137},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":138},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":98},"google/gemini-3.5-flash":{"draws":13,"losses":9,"wins":174},"google/gemini-3.5-flash-lite":{"draws":17,"losses":2,"wins":253},"google/gemini-3.6-flash":{"draws":26,"losses":19,"wins":251},"google/gemini-3.8-flash":{"draws":16,"losses":20,"wins":120},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":87},"gpt-4.1":{"draws":5,"losses":1,"wins":46},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":5,"wins":124},"gpt-5.4":{"draws":11,"losses":11,"wins":128},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":97},"gpt-5.4-nano":{"draws":6,"losses":2,"wins":152},"gpt-5.5":{"draws":15,"losses":15,"wins":114},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":134},"gpt-5.6-sol":{"draws":12,"losses":21,"wins":123},"gpt-5.6-terra":{"draws":9,"losses":3,"wins":138},"gpt-6-astra":{"draws":17,"losses":74,"wins":65},"gpt-6-luna":{"draws":16,"losses":1,"wins":139},"gpt-6-sol":{"draws":13,"losses":39,"wins":104},"gpt-6.1-sol":{"draws":18,"losses":63,"wins":75},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":102},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":107},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":154},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":131},"meta/muse-spark-1.2":{"draws":12,"losses":10,"wins":128},"meta/muse-spark-1.3":{"draws":8,"losses":14,"wins":134},"meta/muse-wonder":{"draws":9,"losses":31,"wins":116},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"mistralai/mistral-large-4-0":{"draws":14,"losses":5,"wins":79},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":36},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":132},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":74},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":137},"o3":{"draws":11,"losses":4,"wins":203},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":130},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":144},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":86},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":127},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":92},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":131},"qwen/qwen3.8-max-0902":{"draws":16,"losses":12,"wins":128},"stealth/ox-alpha":{"draws":50,"losses":31,"wins":425},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":116},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":106},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":78},"tencent/hy4-preview":{"draws":12,"losses":13,"wins":125},"thinkingmachines/inkling":{"draws":18,"losses":0,"wins":186},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":26},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":18,"losses":15,"wins":123},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":123},"x-ai/grok-4.7":{"draws":11,"losses":31,"wins":96},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":51},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":227},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":82},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":2,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":80},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":283},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":116},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":132},"z-ai/glm-5.3-flashx":{"draws":15,"losses":10,"wins":131}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":77,"losses":45,"wins":118},"claude-fable-5":{"draws":55,"losses":159,"wins":42},"claude-fable-5-1":{"draws":15,"losses":266,"wins":9},"claude-haiku-5-5":{"draws":35,"losses":63,"wins":40},"claude-opus-4-5":{"draws":136,"losses":168,"wins":112},"claude-opus-4-8":{"draws":38,"losses":58,"wins":38},"claude-opus-5":{"draws":35,"losses":190,"wins":43},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":76,"losses":96,"wins":96},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":36},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":39},"deepseek/deepseek-v4-flash":{"draws":105,"losses":64,"wins":171},"deepseek/deepseek-v4-pro":{"draws":78,"losses":80,"wins":78},"deepseek/deepseek-v4-pro-0813":{"draws":75,"losses":92,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":53,"wins":48},"fireworks/ember-1":{"draws":44,"losses":60,"wins":40},"gemini-3.1-pro-preview":{"draws":43,"losses":50,"wins":51},"google/gemini-3.1-flash-lite":{"draws":34,"losses":7,"wins":67},"google/gemini-3.5-flash":{"draws":88,"losses":120,"wins":88},"google/gemini-3.5-flash-lite":{"draws":198,"losses":155,"wins":345},"google/gemini-3.6-flash":{"draws":167,"losses":291,"wins":222},"google/gemini-3.8-flash":{"draws":66,"losses":127,"wins":65},"google/gemma-4-31b-it":{"draws":27,"losses":12,"wins":45},"gpt-4.1":{"draws":17,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":40,"losses":35,"wins":53},"gpt-5.4":{"draws":116,"losses":188,"wins":80},"gpt-5.4-mini":{"draws":41,"losses":33,"wins":32},"gpt-5.4-nano":{"draws":37,"losses":41,"wins":74},"gpt-5.5":{"draws":52,"losses":65,"wins":25},"gpt-5.6-luna":{"draws":134,"losses":107,"wins":165},"gpt-5.6-sol":{"draws":66,"losses":312,"wins":61},"gpt-5.6-terra":{"draws":94,"losses":81,"wins":73},"gpt-6-astra":{"draws":12,"losses":232,"wins":16},"gpt-6-luna":{"draws":38,"losses":56,"wins":50},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":6,"losses":129,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":73,"losses":17,"wins":94},"inclusionai/ling-3.0-flash":{"draws":59,"losses":18,"wins":103},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":87,"losses":40,"wins":155},"meta/muse-glimmer-30b":{"draws":81,"losses":35,"wins":110},"meta/muse-spark-1.2":{"draws":93,"losses":118,"wins":93},"meta/muse-spark-1.3":{"draws":64,"losses":102,"wins":54},"meta/muse-wonder":{"draws":31,"losses":85,"wins":28},"minimax/minimax-m3":{"draws":21,"losses":17,"wins":46},"mistralai/mistral-large-4-0":{"draws":27,"losses":24,"wins":39},"mistralai/mistral-medium-3-5":{"draws":63,"losses":19,"wins":72},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":104,"losses":136,"wins":80},"nex-agi/nex-n2-pro":{"draws":29,"losses":11,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":30,"wins":56},"o3":{"draws":48,"losses":190,"wins":174},"openai/gpt-oss-120b":{"draws":79,"losses":31,"wins":122},"poolside/laguna-s-2.1":{"draws":93,"losses":35,"wins":138},"qwen/qwen3.7-max":{"draws":28,"losses":18,"wins":44},"qwen/qwen3.7-plus":{"draws":22,"losses":18,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":94,"losses":102,"wins":66},"qwen/qwen3.8-27b":{"draws":30,"losses":53,"wins":47},"qwen/qwen3.8-flash":{"draws":58,"losses":53,"wins":59},"qwen/qwen3.8-max":{"draws":81,"losses":102,"wins":82},"qwen/qwen3.8-max-0902":{"draws":42,"losses":66,"wins":36},"stealth/ox-alpha":{"draws":203,"losses":414,"wins":245},"stealth/space-bunny-alpha":{"draws":30,"losses":37,"wins":47},"stepfun/step-3.7-flash":{"draws":26,"losses":31,"wins":51},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":32,"losses":25,"wins":33},"tencent/hy4-preview":{"draws":78,"losses":116,"wins":64},"thinkingmachines/inkling":{"draws":92,"losses":42,"wins":164},"thinkingmachines/inkling-small":{"draws":80,"losses":47,"wins":133},"unbiased/pareto-26.10-preview":{"draws":0,"losses":48,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":103,"losses":157,"wins":66},"x-ai/grok-4.6":{"draws":71,"losses":129,"wins":60},"x-ai/grok-4.7":{"draws":12,"losses":90,"wins":24},"x-ai/grok-build-0.1":{"draws":21,"losses":3,"wins":28},"xiaomi/mimo-v2.5":{"draws":88,"losses":37,"wins":113},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":29,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":50,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":121,"losses":126,"wins":169},"z-ai/glm-5.3":{"draws":46,"losses":133,"wins":31},"z-ai/glm-5.3-flash":{"draws":55,"losses":132,"wins":69},"z-ai/glm-5.3-flashx":{"draws":39,"losses":72,"wins":33}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":79},"claude-fable-5":{"draws":24,"losses":62,"wins":58},"claude-fable-5-1":{"draws":9,"losses":119,"wins":34},"claude-haiku-5-5":{"draws":25,"losses":43,"wins":70},"claude-opus-4-5":{"draws":48,"losses":57,"wins":129},"claude-opus-4-8":{"draws":28,"losses":42,"wins":62},"claude-opus-5":{"draws":25,"losses":140,"wins":81},"claude-opus-5-5":{"draws":16,"losses":111,"wins":29},"claude-sonnet-5":{"draws":25,"losses":36,"wins":83},"claude-sonnet-5-5":{"draws":10,"losses":43,"wins":43},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":40},"deepseek/deepseek-v4-flash":{"draws":46,"losses":31,"wins":139},"deepseek/deepseek-v4-pro":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":33,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":72},"fireworks/ember-1":{"draws":30,"losses":42,"wins":72},"gemini-3.1-pro-preview":{"draws":22,"losses":39,"wins":83},"google/gemini-3.1-flash-lite":{"draws":15,"losses":12,"wins":69},"google/gemini-3.5-flash":{"draws":28,"losses":47,"wins":105},"google/gemini-3.5-flash-lite":{"draws":49,"losses":40,"wins":163},"google/gemini-3.6-flash":{"draws":54,"losses":96,"wins":126},"google/gemini-3.8-flash":{"draws":20,"losses":56,"wins":68},"google/gemma-4-31b-it":{"draws":14,"losses":16,"wins":54},"gpt-4.1":{"draws":10,"losses":8,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":27,"losses":26,"wins":73},"gpt-5.4":{"draws":37,"losses":42,"wins":59},"gpt-5.4-mini":{"draws":18,"losses":18,"wins":60},"gpt-5.4-nano":{"draws":21,"losses":18,"wins":105},"gpt-5.5":{"draws":29,"losses":42,"wins":61},"gpt-5.6-luna":{"draws":33,"losses":28,"wins":83},"gpt-5.6-sol":{"draws":15,"losses":70,"wins":59},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":74},"gpt-6-astra":{"draws":13,"losses":105,"wins":26},"gpt-6-luna":{"draws":32,"losses":44,"wins":68},"gpt-6-sol":{"draws":15,"losses":81,"wins":48},"gpt-6.1-sol":{"draws":5,"losses":103,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":69},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":21,"losses":31,"wins":104},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":27,"losses":41,"wins":70},"meta/muse-spark-1.3":{"draws":22,"losses":54,"wins":68},"meta/muse-wonder":{"draws":21,"losses":54,"wins":69},"minimax/minimax-m3":{"draws":13,"losses":13,"wins":52},"mistralai/mistral-large-4-0":{"draws":23,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":19,"losses":8,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":28,"losses":47,"wins":63},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":22,"wins":82},"o3":{"draws":17,"losses":45,"wins":136},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":82},"poolside/laguna-s-2.1":{"draws":25,"losses":26,"wins":87},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":17,"losses":12,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":49,"wins":63},"qwen/qwen3.8-27b":{"draws":17,"losses":25,"wins":60},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":23,"losses":41,"wins":80},"qwen/qwen3.8-max-0902":{"draws":26,"losses":51,"wins":67},"stealth/ox-alpha":{"draws":85,"losses":164,"wins":225},"stealth/space-bunny-alpha":{"draws":22,"losses":24,"wins":68},"stepfun/step-3.7-flash":{"draws":11,"losses":26,"wins":65},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":49},"tencent/hy4-preview":{"draws":24,"losses":47,"wins":67},"thinkingmachines/inkling":{"draws":41,"losses":41,"wins":110},"thinkingmachines/inkling-small":{"draws":32,"losses":21,"wins":91},"unbiased/pareto-26.10-preview":{"draws":2,"losses":37,"wins":9},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":32,"losses":49,"wins":63},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":61},"x-ai/grok-4.7":{"draws":15,"losses":64,"wins":47},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":49,"losses":26,"wins":147},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":34,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":37,"wins":46},"z-ai/glm-5.2":{"draws":55,"losses":65,"wins":168},"z-ai/glm-5.3":{"draws":25,"losses":61,"wins":52},"z-ai/glm-5.3-flash":{"draws":20,"losses":55,"wins":69},"z-ai/glm-5.3-flashx":{"draws":25,"losses":54,"wins":65}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":25,"wins":14},"claude-fable-5":{"draws":8,"losses":48,"wins":2},"claude-fable-5-1":{"draws":0,"losses":62,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":9},"claude-opus-4-5":{"draws":16,"losses":85,"wins":13},"claude-opus-4-8":{"draws":17,"losses":50,"wins":7},"claude-opus-5":{"draws":9,"losses":91,"wins":4},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":9,"losses":39,"wins":10},"claude-sonnet-5-5":{"draws":6,"losses":40,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":33,"losses":37,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":33,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":31,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":32,"wins":7},"fireworks/ember-1":{"draws":11,"losses":34,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":27,"wins":13},"google/gemini-3.1-flash-lite":{"draws":22,"losses":28,"wins":26},"google/gemini-3.5-flash":{"draws":20,"losses":43,"wins":13},"google/gemini-3.5-flash-lite":{"draws":46,"losses":40,"wins":38},"google/gemini-3.6-flash":{"draws":35,"losses":82,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":37,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":18,"wins":6},"gpt-4.1":{"draws":11,"losses":16,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":51,"wins":10},"gpt-5.4":{"draws":12,"losses":37,"wins":7},"gpt-5.4-mini":{"draws":18,"losses":29,"wins":11},"gpt-5.4-nano":{"draws":23,"losses":52,"wins":17},"gpt-5.5":{"draws":25,"losses":45,"wins":8},"gpt-5.6-luna":{"draws":20,"losses":31,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":48,"wins":6},"gpt-5.6-terra":{"draws":12,"losses":36,"wins":8},"gpt-6-astra":{"draws":2,"losses":52,"wins":0},"gpt-6-luna":{"draws":14,"losses":32,"wins":8},"gpt-6-sol":{"draws":6,"losses":47,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":52,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":16,"wins":16},"inclusionai/ling-3.0-flash":{"draws":26,"losses":24,"wins":14},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":50,"wins":19},"meta/muse-glimmer-30b":{"draws":22,"losses":20,"wins":12},"meta/muse-spark-1.2":{"draws":3,"losses":43,"wins":12},"meta/muse-spark-1.3":{"draws":4,"losses":50,"wins":2},"meta/muse-wonder":{"draws":3,"losses":47,"wins":4},"minimax/minimax-m3":{"draws":11,"losses":26,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":20,"wins":5},"mistralai/mistral-medium-3-5":{"draws":12,"losses":13,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":36,"wins":11},"nex-agi/nex-n2-pro":{"draws":21,"losses":26,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":24,"wins":25},"o3":{"draws":24,"losses":68,"wins":18},"openai/gpt-oss-120b":{"draws":19,"losses":17,"wins":14},"poolside/laguna-s-2.1":{"draws":35,"losses":19,"wins":28},"qwen/qwen3.7-max":{"draws":21,"losses":24,"wins":9},"qwen/qwen3.7-plus":{"draws":12,"losses":23,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":45,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":25,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":18,"wins":9},"qwen/qwen3.8-max":{"draws":10,"losses":42,"wins":4},"qwen/qwen3.8-max-0902":{"draws":10,"losses":39,"wins":5},"stealth/ox-alpha":{"draws":33,"losses":128,"wins":23},"stealth/space-bunny-alpha":{"draws":11,"losses":28,"wins":7},"stepfun/step-3.7-flash":{"draws":12,"losses":25,"wins":5},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":17,"losses":36,"wins":3},"thinkingmachines/inkling":{"draws":22,"losses":35,"wins":27},"thinkingmachines/inkling-small":{"draws":21,"losses":24,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":54,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":42,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":45,"wins":0},"x-ai/grok-build-0.1":{"draws":12,"losses":19,"wins":7},"xiaomi/mimo-v2.5":{"draws":49,"losses":41,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":23,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":22,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":42,"losses":67,"wins":19},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":36,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":39,"wins":4}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":102,"losses":97,"wins":101},"claude-fable-5":{"draws":59,"losses":220,"wins":21},"claude-fable-5-1":{"draws":13,"losses":299,"wins":2},"claude-haiku-5-5":{"draws":57,"losses":121,"wins":30},"claude-opus-4-5":{"draws":142,"losses":236,"wins":94},"claude-opus-4-8":{"draws":64,"losses":146,"wins":26},"claude-opus-5":{"draws":48,"losses":353,"wins":25},"claude-opus-5-5":{"draws":13,"losses":217,"wins":6},"claude-sonnet-5":{"draws":105,"losses":171,"wins":64},"claude-sonnet-5-5":{"draws":46,"losses":139,"wins":31},"cohere/north-mini-code":{"draws":33,"losses":32,"wins":37},"deepseek/deepseek-v4-flash":{"draws":114,"losses":133,"wins":133},"deepseek/deepseek-v4-pro":{"draws":96,"losses":141,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":107,"losses":128,"wins":69},"deepseek/deepseek-v4.1-flash":{"draws":75,"losses":116,"wins":25},"fireworks/ember-1":{"draws":70,"losses":109,"wins":37},"gemini-3.1-pro-preview":{"draws":69,"losses":95,"wins":52},"google/gemini-3.1-flash-lite":{"draws":59,"losses":56,"wins":109},"google/gemini-3.5-flash":{"draws":109,"losses":186,"wins":85},"google/gemini-3.5-flash-lite":{"draws":198,"losses":193,"wins":193},"google/gemini-3.6-flash":{"draws":162,"losses":345,"wins":91},"google/gemini-3.8-flash":{"draws":67,"losses":204,"wins":37},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":40,"losses":43,"wins":21},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":84,"losses":105,"wins":47},"gpt-5.4":{"draws":102,"losses":162,"wins":40},"gpt-5.4-mini":{"draws":82,"losses":67,"wins":51},"gpt-5.4-nano":{"draws":74,"losses":105,"wins":111},"gpt-5.5":{"draws":100,"losses":119,"wins":23},"gpt-5.6-luna":{"draws":132,"losses":115,"wins":85},"gpt-5.6-sol":{"draws":44,"losses":222,"wins":34},"gpt-5.6-terra":{"draws":111,"losses":151,"wins":56},"gpt-6-astra":{"draws":14,"losses":262,"wins":6},"gpt-6-luna":{"draws":66,"losses":105,"wins":45},"gpt-6-sol":{"draws":32,"losses":168,"wins":16},"gpt-6.1-sol":{"draws":14,"losses":197,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":105,"losses":33,"wins":98},"inclusionai/ling-3.0-flash":{"draws":102,"losses":57,"wins":81},"inclusionai/ling-3.1-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":103,"losses":98,"wins":131},"meta/muse-glimmer-30b":{"draws":141,"losses":63,"wins":86},"meta/muse-spark-1.2":{"draws":71,"losses":142,"wins":51},"meta/muse-spark-1.3":{"draws":57,"losses":182,"wins":43},"meta/muse-wonder":{"draws":37,"losses":148,"wins":31},"minimax/minimax-m3":{"draws":54,"losses":60,"wins":58},"mistralai/mistral-large-4-0":{"draws":45,"losses":69,"wins":20},"mistralai/mistral-medium-3-5":{"draws":83,"losses":40,"wins":67},"moonshotai/kimi-k2.7-code":{"draws":19,"losses":36,"wins":17},"moonshotai/kimi-k3":{"draws":80,"losses":133,"wins":65},"nex-agi/nex-n2-pro":{"draws":39,"losses":49,"wins":74},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":110,"losses":67,"wins":87},"o3":{"draws":71,"losses":224,"wins":119},"openai/gpt-oss-120b":{"draws":123,"losses":87,"wins":82},"poolside/laguna-s-2.1":{"draws":136,"losses":93,"wins":89},"qwen/qwen3.7-max":{"draws":75,"losses":61,"wins":34},"qwen/qwen3.7-plus":{"draws":48,"losses":51,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":103,"losses":159,"wins":56},"qwen/qwen3.8-27b":{"draws":41,"losses":94,"wins":45},"qwen/qwen3.8-flash":{"draws":77,"losses":89,"wins":46},"qwen/qwen3.8-max":{"draws":109,"losses":151,"wins":58},"qwen/qwen3.8-max-0902":{"draws":64,"losses":123,"wins":29},"stealth/ox-alpha":{"draws":275,"losses":540,"wins":199},"stealth/space-bunny-alpha":{"draws":60,"losses":70,"wins":38},"stepfun/step-3.7-flash":{"draws":45,"losses":69,"wins":66},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":50,"losses":61,"wins":49},"tencent/hy4-preview":{"draws":87,"losses":157,"wins":58},"thinkingmachines/inkling":{"draws":126,"losses":126,"wins":118},"thinkingmachines/inkling-small":{"draws":151,"losses":66,"wins":127},"unbiased/pareto-26.10-preview":{"draws":0,"losses":71,"wins":1},"upstage/solar-mini4":{"draws":10,"losses":16,"wins":28},"x-ai/grok-4.5":{"draws":62,"losses":187,"wins":55},"x-ai/grok-4.6":{"draws":92,"losses":188,"wins":34},"x-ai/grok-4.7":{"draws":20,"losses":157,"wins":15},"x-ai/grok-build-0.1":{"draws":40,"losses":26,"wins":38},"xiaomi/mimo-v2.5":{"draws":177,"losses":161,"wins":140},"xiaomi/mimo-v2.5-pro":{"draws":55,"losses":63,"wins":52},"xiaomi/mimo-v2.6-flash":{"draws":33,"losses":79,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":223,"losses":246,"wins":139},"z-ai/glm-5.3":{"draws":68,"losses":180,"wins":16},"z-ai/glm-5.3-flash":{"draws":97,"losses":154,"wins":49},"z-ai/glm-5.3-flashx":{"draws":58,"losses":126,"wins":32}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":63,"losses":54,"wins":107},"claude-fable-5":{"draws":50,"losses":124,"wins":54},"claude-fable-5-1":{"draws":16,"losses":224,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":50,"wins":41},"claude-opus-4-5":{"draws":77,"losses":102,"wins":107},"claude-opus-4-8":{"draws":31,"losses":58,"wins":41},"claude-opus-5":{"draws":30,"losses":185,"wins":33},"claude-opus-5-5":{"draws":12,"losses":128,"wins":4},"claude-sonnet-5":{"draws":78,"losses":78,"wins":80},"claude-sonnet-5-5":{"draws":32,"losses":67,"wins":33},"cohere/north-mini-code":{"draws":13,"losses":10,"wins":33},"deepseek/deepseek-v4-flash":{"draws":96,"losses":61,"wins":141},"deepseek/deepseek-v4-pro":{"draws":48,"losses":54,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":75,"losses":76,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":53,"wins":41},"fireworks/ember-1":{"draws":41,"losses":53,"wins":38},"gemini-3.1-pro-preview":{"draws":35,"losses":44,"wins":53},"google/gemini-3.1-flash-lite":{"draws":28,"losses":5,"wins":57},"google/gemini-3.5-flash":{"draws":73,"losses":102,"wins":93},"google/gemini-3.5-flash-lite":{"draws":130,"losses":109,"wins":193},"google/gemini-3.6-flash":{"draws":111,"losses":159,"wins":144},"google/gemini-3.8-flash":{"draws":63,"losses":118,"wins":53},"google/gemma-4-31b-it":{"draws":28,"losses":14,"wins":34},"gpt-4.1":{"draws":13,"losses":9,"wins":22},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":39,"losses":31,"wins":54},"gpt-5.4":{"draws":65,"losses":98,"wins":65},"gpt-5.4-mini":{"draws":34,"losses":21,"wins":33},"gpt-5.4-nano":{"draws":27,"losses":43,"wins":66},"gpt-5.5":{"draws":42,"losses":60,"wins":30},"gpt-5.6-luna":{"draws":82,"losses":65,"wins":89},"gpt-5.6-sol":{"draws":27,"losses":139,"wins":54},"gpt-5.6-terra":{"draws":79,"losses":70,"wins":79},"gpt-6-astra":{"draws":15,"losses":183,"wins":20},"gpt-6-luna":{"draws":37,"losses":54,"wins":41},"gpt-6-sol":{"draws":14,"losses":98,"wins":20},"gpt-6.1-sol":{"draws":9,"losses":115,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":70,"losses":17,"wins":73},"inclusionai/ling-3.0-flash":{"draws":44,"losses":15,"wins":59},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":54,"losses":27,"wins":111},"meta/muse-glimmer-30b":{"draws":77,"losses":45,"wins":90},"meta/muse-spark-1.2":{"draws":33,"losses":83,"wins":74},"meta/muse-spark-1.3":{"draws":33,"losses":107,"wins":58},"meta/muse-wonder":{"draws":23,"losses":79,"wins":30},"minimax/minimax-m3":{"draws":16,"losses":11,"wins":47},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":26},"mistralai/mistral-medium-3-5":{"draws":44,"losses":16,"wins":80},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":14},"moonshotai/kimi-k3":{"draws":50,"losses":76,"wins":62},"nex-agi/nex-n2-pro":{"draws":21,"losses":13,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":18,"wins":52},"o3":{"draws":45,"losses":94,"wins":137},"openai/gpt-oss-120b":{"draws":74,"losses":42,"wins":90},"poolside/laguna-s-2.1":{"draws":67,"losses":49,"wins":72},"qwen/qwen3.7-max":{"draws":27,"losses":16,"wins":39},"qwen/qwen3.7-plus":{"draws":18,"losses":12,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":72,"losses":94,"wins":64},"qwen/qwen3.8-27b":{"draws":27,"losses":48,"wins":41},"qwen/qwen3.8-flash":{"draws":46,"losses":59,"wins":51},"qwen/qwen3.8-max":{"draws":67,"losses":102,"wins":65},"qwen/qwen3.8-max-0902":{"draws":36,"losses":62,"wins":34},"stealth/ox-alpha":{"draws":210,"losses":320,"wins":236},"stealth/space-bunny-alpha":{"draws":31,"losses":28,"wins":47},"stepfun/step-3.7-flash":{"draws":23,"losses":21,"wins":52},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":26,"losses":18,"wins":30},"tencent/hy4-preview":{"draws":67,"losses":100,"wins":65},"thinkingmachines/inkling":{"draws":76,"losses":37,"wins":117},"thinkingmachines/inkling-small":{"draws":98,"losses":30,"wins":118},"unbiased/pareto-26.10-preview":{"draws":0,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":54,"losses":84,"wins":70},"x-ai/grok-4.6":{"draws":62,"losses":122,"wins":52},"x-ai/grok-4.7":{"draws":10,"losses":85,"wins":21},"x-ai/grok-build-0.1":{"draws":18,"losses":11,"wins":19},"xiaomi/mimo-v2.5":{"draws":83,"losses":30,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":25,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":32,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":138,"losses":110,"wins":136},"z-ai/glm-5.3":{"draws":43,"losses":111,"wins":42},"z-ai/glm-5.3-flash":{"draws":58,"losses":105,"wins":65},"z-ai/glm-5.3-flashx":{"draws":32,"losses":60,"wins":40}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":68,"losses":57,"wins":93},"claude-fable-5":{"draws":41,"losses":135,"wins":44},"claude-fable-5-1":{"draws":9,"losses":237,"wins":6},"claude-haiku-5-5":{"draws":34,"losses":63,"wins":29},"claude-opus-4-5":{"draws":80,"losses":101,"wins":109},"claude-opus-4-8":{"draws":30,"losses":60,"wins":42},"claude-opus-5":{"draws":24,"losses":188,"wins":28},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":75,"losses":67,"wins":92},"claude-sonnet-5-5":{"draws":22,"losses":77,"wins":33},"cohere/north-mini-code":{"draws":14,"losses":5,"wins":31},"deepseek/deepseek-v4-flash":{"draws":107,"losses":69,"wins":128},"deepseek/deepseek-v4-pro":{"draws":75,"losses":73,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":52,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":59,"wins":30},"fireworks/ember-1":{"draws":36,"losses":55,"wins":41},"gemini-3.1-pro-preview":{"draws":40,"losses":43,"wins":49},"google/gemini-3.1-flash-lite":{"draws":23,"losses":12,"wins":55},"google/gemini-3.5-flash":{"draws":90,"losses":113,"wins":77},"google/gemini-3.5-flash-lite":{"draws":152,"losses":84,"wins":172},"google/gemini-3.6-flash":{"draws":117,"losses":190,"wins":123},"google/gemini-3.8-flash":{"draws":62,"losses":106,"wins":62},"google/gemma-4-31b-it":{"draws":31,"losses":7,"wins":38},"gpt-4.1":{"draws":19,"losses":7,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":39,"losses":44,"wins":43},"gpt-5.4":{"draws":64,"losses":96,"wins":56},"gpt-5.4-mini":{"draws":33,"losses":19,"wins":38},"gpt-5.4-nano":{"draws":31,"losses":39,"wins":64},"gpt-5.5":{"draws":37,"losses":53,"wins":36},"gpt-5.6-luna":{"draws":83,"losses":70,"wins":85},"gpt-5.6-sol":{"draws":37,"losses":136,"wins":49},"gpt-5.6-terra":{"draws":73,"losses":86,"wins":73},"gpt-6-astra":{"draws":15,"losses":198,"wins":1},"gpt-6-luna":{"draws":39,"losses":48,"wins":45},"gpt-6-sol":{"draws":15,"losses":97,"wins":20},"gpt-6.1-sol":{"draws":8,"losses":121,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":63,"losses":20,"wins":79},"inclusionai/ling-3.0-flash":{"draws":55,"losses":21,"wins":50},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":75,"losses":35,"wins":90},"meta/muse-glimmer-30b":{"draws":82,"losses":35,"wins":95},"meta/muse-spark-1.2":{"draws":53,"losses":75,"wins":62},"meta/muse-spark-1.3":{"draws":47,"losses":94,"wins":57},"meta/muse-wonder":{"draws":27,"losses":78,"wins":27},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":46},"mistralai/mistral-large-4-0":{"draws":30,"losses":24,"wins":28},"mistralai/mistral-medium-3-5":{"draws":43,"losses":21,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":16,"wins":17},"moonshotai/kimi-k3":{"draws":61,"losses":55,"wins":72},"nex-agi/nex-n2-pro":{"draws":19,"losses":7,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":16,"wins":61},"o3":{"draws":49,"losses":76,"wins":139},"openai/gpt-oss-120b":{"draws":72,"losses":45,"wins":73},"poolside/laguna-s-2.1":{"draws":71,"losses":45,"wins":66},"qwen/qwen3.7-max":{"draws":30,"losses":19,"wins":35},"qwen/qwen3.7-plus":{"draws":21,"losses":19,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":88,"wins":75},"qwen/qwen3.8-27b":{"draws":32,"losses":46,"wins":40},"qwen/qwen3.8-flash":{"draws":59,"losses":48,"wins":45},"qwen/qwen3.8-max":{"draws":79,"losses":86,"wins":69},"qwen/qwen3.8-max-0902":{"draws":40,"losses":54,"wins":38},"stealth/ox-alpha":{"draws":204,"losses":299,"wins":267},"stealth/space-bunny-alpha":{"draws":31,"losses":26,"wins":47},"stepfun/step-3.7-flash":{"draws":28,"losses":19,"wins":51},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":33,"losses":19,"wins":26},"tencent/hy4-preview":{"draws":59,"losses":97,"wins":72},"thinkingmachines/inkling":{"draws":76,"losses":54,"wins":94},"thinkingmachines/inkling-small":{"draws":79,"losses":43,"wins":110},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":3,"wins":26},"x-ai/grok-4.5":{"draws":51,"losses":82,"wins":69},"x-ai/grok-4.6":{"draws":79,"losses":101,"wins":54},"x-ai/grok-4.7":{"draws":9,"losses":83,"wins":22},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":21},"xiaomi/mimo-v2.5":{"draws":91,"losses":34,"wins":101},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":30,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":49,"wins":26},"z-ai/glm-5.2":{"draws":140,"losses":108,"wins":132},"z-ai/glm-5.3":{"draws":41,"losses":104,"wins":47},"z-ai/glm-5.3-flash":{"draws":55,"losses":112,"wins":59},"z-ai/glm-5.3-flashx":{"draws":32,"losses":63,"wins":37}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":32,"wins":60},"claude-fable-5":{"draws":34,"losses":74,"wins":36},"claude-fable-5-1":{"draws":17,"losses":133,"wins":12},"claude-haiku-5-5":{"draws":43,"losses":56,"wins":39},"claude-opus-4-5":{"draws":62,"losses":68,"wins":104},"claude-opus-4-8":{"draws":32,"losses":47,"wins":53},"claude-opus-5":{"draws":40,"losses":170,"wins":36},"claude-opus-5-5":{"draws":9,"losses":132,"wins":15},"claude-sonnet-5":{"draws":43,"losses":48,"wins":53},"claude-sonnet-5-5":{"draws":31,"losses":72,"wins":41},"cohere/north-mini-code":{"draws":15,"losses":7,"wins":32},"deepseek/deepseek-v4-flash":{"draws":75,"losses":25,"wins":116},"deepseek/deepseek-v4-pro":{"draws":38,"losses":41,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":30,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":36,"wins":36},"fireworks/ember-1":{"draws":47,"losses":51,"wins":46},"gemini-3.1-pro-preview":{"draws":43,"losses":49,"wins":52},"google/gemini-3.1-flash-lite":{"draws":35,"losses":9,"wins":52},"google/gemini-3.5-flash":{"draws":55,"losses":51,"wins":74},"google/gemini-3.5-flash-lite":{"draws":89,"losses":47,"wins":116},"google/gemini-3.6-flash":{"draws":78,"losses":108,"wins":90},"google/gemini-3.8-flash":{"draws":38,"losses":61,"wins":45},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":43,"losses":28,"wins":55},"gpt-5.4":{"draws":46,"losses":53,"wins":39},"gpt-5.4-mini":{"draws":37,"losses":20,"wins":39},"gpt-5.4-nano":{"draws":36,"losses":35,"wins":73},"gpt-5.5":{"draws":45,"losses":42,"wins":45},"gpt-5.6-luna":{"draws":54,"losses":26,"wins":64},"gpt-5.6-sol":{"draws":26,"losses":75,"wins":43},"gpt-5.6-terra":{"draws":54,"losses":34,"wins":50},"gpt-6-astra":{"draws":16,"losses":122,"wins":6},"gpt-6-luna":{"draws":44,"losses":40,"wins":60},"gpt-6-sol":{"draws":26,"losses":85,"wins":33},"gpt-6.1-sol":{"draws":15,"losses":115,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":45,"losses":9,"wins":48},"inclusionai/ling-3.0-flash":{"draws":43,"losses":9,"wins":50},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":34,"wins":85},"meta/muse-glimmer-30b":{"draws":52,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":35,"losses":50,"wins":53},"meta/muse-spark-1.3":{"draws":29,"losses":61,"wins":54},"meta/muse-wonder":{"draws":37,"losses":71,"wins":36},"minimax/minimax-m3":{"draws":19,"losses":17,"wins":42},"mistralai/mistral-large-4-0":{"draws":33,"losses":26,"wins":31},"mistralai/mistral-medium-3-5":{"draws":30,"losses":9,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":15},"moonshotai/kimi-k3":{"draws":40,"losses":41,"wins":57},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":22,"wins":58},"o3":{"draws":46,"losses":62,"wins":90},"openai/gpt-oss-120b":{"draws":42,"losses":23,"wins":61},"poolside/laguna-s-2.1":{"draws":58,"losses":23,"wins":57},"qwen/qwen3.7-max":{"draws":31,"losses":19,"wins":34},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":50,"wins":58},"qwen/qwen3.8-27b":{"draws":24,"losses":29,"wins":49},"qwen/qwen3.8-flash":{"draws":36,"losses":19,"wins":41},"qwen/qwen3.8-max":{"draws":41,"losses":48,"wins":55},"qwen/qwen3.8-max-0902":{"draws":48,"losses":45,"wins":51},"stealth/ox-alpha":{"draws":111,"losses":181,"wins":181},"stealth/space-bunny-alpha":{"draws":36,"losses":25,"wins":53},"stepfun/step-3.7-flash":{"draws":26,"losses":16,"wins":60},"stepfun/step-5-preview":{"draws":4,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":27,"losses":15,"wins":36},"tencent/hy4-preview":{"draws":41,"losses":56,"wins":41},"thinkingmachines/inkling":{"draws":63,"losses":30,"wins":99},"thinkingmachines/inkling-small":{"draws":46,"losses":25,"wins":73},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":31,"losses":64,"wins":49},"x-ai/grok-4.6":{"draws":40,"losses":61,"wins":43},"x-ai/grok-4.7":{"draws":11,"losses":82,"wins":33},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":27},"xiaomi/mimo-v2.5":{"draws":80,"losses":26,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":32,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":23,"losses":43,"wins":30},"z-ai/glm-5.2":{"draws":103,"losses":63,"wins":122},"z-ai/glm-5.3":{"draws":28,"losses":83,"wins":27},"z-ai/glm-5.3-flash":{"draws":38,"losses":59,"wins":47},"z-ai/glm-5.3-flashx":{"draws":40,"losses":61,"wins":43}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":24,"wins":68},"claude-fable-5":{"draws":31,"losses":91,"wins":22},"claude-fable-5-1":{"draws":4,"losses":150,"wins":8},"claude-haiku-5-5":{"draws":36,"losses":64,"wins":38},"claude-opus-4-5":{"draws":82,"losses":62,"wins":90},"claude-opus-4-8":{"draws":44,"losses":51,"wins":37},"claude-opus-5":{"draws":27,"losses":176,"wins":43},"claude-opus-5-5":{"draws":8,"losses":137,"wins":11},"claude-sonnet-5":{"draws":44,"losses":40,"wins":60},"claude-sonnet-5-5":{"draws":30,"losses":72,"wins":42},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":34},"deepseek/deepseek-v4-flash":{"draws":70,"losses":37,"wins":109},"deepseek/deepseek-v4-pro":{"draws":41,"losses":38,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":41,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":47,"losses":46,"wins":51},"fireworks/ember-1":{"draws":30,"losses":33,"wins":33},"gemini-3.1-pro-preview":{"draws":41,"losses":41,"wins":62},"google/gemini-3.1-flash-lite":{"draws":24,"losses":4,"wins":68},"google/gemini-3.5-flash":{"draws":53,"losses":58,"wins":69},"google/gemini-3.5-flash-lite":{"draws":95,"losses":44,"wins":113},"google/gemini-3.6-flash":{"draws":80,"losses":98,"wins":98},"google/gemini-3.8-flash":{"draws":35,"losses":61,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":14,"losses":15,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":36,"losses":31,"wins":59},"gpt-5.4":{"draws":40,"losses":60,"wins":38},"gpt-5.4-mini":{"draws":37,"losses":15,"wins":44},"gpt-5.4-nano":{"draws":34,"losses":31,"wins":79},"gpt-5.5":{"draws":42,"losses":49,"wins":41},"gpt-5.6-luna":{"draws":50,"losses":40,"wins":54},"gpt-5.6-sol":{"draws":23,"losses":85,"wins":36},"gpt-5.6-terra":{"draws":44,"losses":36,"wins":58},"gpt-6-astra":{"draws":10,"losses":128,"wins":6},"gpt-6-luna":{"draws":39,"losses":41,"wins":64},"gpt-6-sol":{"draws":21,"losses":100,"wins":23},"gpt-6.1-sol":{"draws":10,"losses":117,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":44,"losses":6,"wins":52},"inclusionai/ling-3.0-flash":{"draws":45,"losses":4,"wins":53},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":49,"losses":19,"wins":88},"meta/muse-glimmer-30b":{"draws":44,"losses":15,"wins":67},"meta/muse-spark-1.2":{"draws":37,"losses":49,"wins":52},"meta/muse-spark-1.3":{"draws":39,"losses":63,"wins":42},"meta/muse-wonder":{"draws":38,"losses":76,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":5,"wins":54},"mistralai/mistral-large-4-0":{"draws":26,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":27,"losses":6,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":11,"wins":13},"moonshotai/kimi-k3":{"draws":45,"losses":37,"wins":56},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":19,"wins":58},"o3":{"draws":40,"losses":50,"wins":108},"openai/gpt-oss-120b":{"draws":48,"losses":14,"wins":64},"poolside/laguna-s-2.1":{"draws":53,"losses":22,"wins":63},"qwen/qwen3.7-max":{"draws":26,"losses":19,"wins":39},"qwen/qwen3.7-plus":{"draws":23,"losses":11,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":47,"wins":47},"qwen/qwen3.8-27b":{"draws":29,"losses":38,"wins":35},"qwen/qwen3.8-flash":{"draws":34,"losses":27,"wins":35},"qwen/qwen3.8-max":{"draws":46,"losses":41,"wins":57},"qwen/qwen3.8-max-0902":{"draws":44,"losses":57,"wins":43},"stealth/ox-alpha":{"draws":126,"losses":178,"wins":170},"stealth/space-bunny-alpha":{"draws":36,"losses":23,"wins":55},"stepfun/step-3.7-flash":{"draws":23,"losses":18,"wins":61},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":36},"tencent/hy4-preview":{"draws":42,"losses":54,"wins":42},"thinkingmachines/inkling":{"draws":60,"losses":25,"wins":107},"thinkingmachines/inkling-small":{"draws":50,"losses":17,"wins":77},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":23},"x-ai/grok-4.5":{"draws":34,"losses":71,"wins":39},"x-ai/grok-4.6":{"draws":40,"losses":62,"wins":42},"x-ai/grok-4.7":{"draws":11,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":83,"losses":29,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":18,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":45,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":66,"wins":128},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":32,"losses":67,"wins":45},"z-ai/glm-5.3-flashx":{"draws":35,"losses":58,"wins":51}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":39,"wins":57},"claude-fable-5":{"draws":27,"losses":87,"wins":30},"claude-fable-5-1":{"draws":6,"losses":150,"wins":6},"claude-haiku-5-5":{"draws":32,"losses":60,"wins":46},"claude-opus-4-5":{"draws":62,"losses":97,"wins":75},"claude-opus-4-8":{"draws":36,"losses":61,"wins":35},"claude-opus-5":{"draws":24,"losses":185,"wins":37},"claude-opus-5-5":{"draws":8,"losses":138,"wins":10},"claude-sonnet-5":{"draws":43,"losses":51,"wins":50},"claude-sonnet-5-5":{"draws":22,"losses":83,"wins":39},"cohere/north-mini-code":{"draws":14,"losses":13,"wins":27},"deepseek/deepseek-v4-flash":{"draws":69,"losses":52,"wins":95},"deepseek/deepseek-v4-pro":{"draws":35,"losses":53,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":49,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":52,"wins":49},"fireworks/ember-1":{"draws":41,"losses":62,"wins":41},"gemini-3.1-pro-preview":{"draws":26,"losses":35,"wins":35},"google/gemini-3.1-flash-lite":{"draws":22,"losses":21,"wins":53},"google/gemini-3.5-flash":{"draws":43,"losses":78,"wins":59},"google/gemini-3.5-flash-lite":{"draws":81,"losses":64,"wins":107},"google/gemini-3.6-flash":{"draws":64,"losses":123,"wins":89},"google/gemini-3.8-flash":{"draws":28,"losses":82,"wins":34},"google/gemma-4-31b-it":{"draws":30,"losses":15,"wins":39},"gpt-4.1":{"draws":15,"losses":15,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":40,"losses":35,"wins":51},"gpt-5.4":{"draws":30,"losses":66,"wins":42},"gpt-5.4-mini":{"draws":38,"losses":24,"wins":34},"gpt-5.4-nano":{"draws":36,"losses":41,"wins":67},"gpt-5.5":{"draws":38,"losses":62,"wins":32},"gpt-5.6-luna":{"draws":42,"losses":47,"wins":55},"gpt-5.6-sol":{"draws":18,"losses":95,"wins":31},"gpt-5.6-terra":{"draws":47,"losses":44,"wins":47},"gpt-6-astra":{"draws":10,"losses":130,"wins":4},"gpt-6-luna":{"draws":36,"losses":46,"wins":62},"gpt-6-sol":{"draws":19,"losses":99,"wins":26},"gpt-6.1-sol":{"draws":8,"losses":126,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":22,"wins":40},"inclusionai/ling-3.0-flash":{"draws":39,"losses":10,"wins":53},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":37,"losses":44,"wins":75},"meta/muse-glimmer-30b":{"draws":49,"losses":15,"wins":62},"meta/muse-spark-1.2":{"draws":34,"losses":56,"wins":48},"meta/muse-spark-1.3":{"draws":26,"losses":79,"wins":39},"meta/muse-wonder":{"draws":26,"losses":94,"wins":24},"minimax/minimax-m3":{"draws":19,"losses":22,"wins":37},"mistralai/mistral-large-4-0":{"draws":21,"losses":35,"wins":34},"mistralai/mistral-medium-3-5":{"draws":32,"losses":10,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":62,"wins":40},"nex-agi/nex-n2-pro":{"draws":21,"losses":11,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":28,"wins":50},"o3":{"draws":33,"losses":90,"wins":75},"openai/gpt-oss-120b":{"draws":44,"losses":27,"wins":55},"poolside/laguna-s-2.1":{"draws":47,"losses":32,"wins":59},"qwen/qwen3.7-max":{"draws":26,"losses":29,"wins":29},"qwen/qwen3.7-plus":{"draws":23,"losses":14,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":62,"wins":46},"qwen/qwen3.8-27b":{"draws":23,"losses":47,"wins":32},"qwen/qwen3.8-flash":{"draws":36,"losses":30,"wins":30},"qwen/qwen3.8-max":{"draws":43,"losses":54,"wins":47},"qwen/qwen3.8-max-0902":{"draws":40,"losses":68,"wins":36},"stealth/ox-alpha":{"draws":107,"losses":222,"wins":145},"stealth/space-bunny-alpha":{"draws":36,"losses":34,"wins":44},"stepfun/step-3.7-flash":{"draws":25,"losses":32,"wins":45},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":21,"wins":33},"tencent/hy4-preview":{"draws":33,"losses":65,"wins":40},"thinkingmachines/inkling":{"draws":58,"losses":48,"wins":86},"thinkingmachines/inkling-small":{"draws":45,"losses":29,"wins":70},"unbiased/pareto-26.10-preview":{"draws":1,"losses":46,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":13,"wins":18},"x-ai/grok-4.5":{"draws":31,"losses":73,"wins":40},"x-ai/grok-4.6":{"draws":40,"losses":76,"wins":28},"x-ai/grok-4.7":{"draws":14,"losses":89,"wins":23},"x-ai/grok-build-0.1":{"draws":17,"losses":13,"wins":18},"xiaomi/mimo-v2.5":{"draws":74,"losses":49,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":57,"wins":23},"z-ai/glm-5.2":{"draws":85,"losses":94,"wins":109},"z-ai/glm-5.3":{"draws":25,"losses":82,"wins":31},"z-ai/glm-5.3-flash":{"draws":36,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":35,"losses":75,"wins":34}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":48,"wins":20},"claude-fable-5":{"draws":12,"losses":83,"wins":3},"claude-fable-5-1":{"draws":5,"losses":105,"wins":0},"claude-haiku-5-5":{"draws":22,"losses":66,"wins":8},"claude-opus-4-5":{"draws":63,"losses":179,"wins":12},"claude-opus-4-8":{"draws":39,"losses":121,"wins":10},"claude-opus-5":{"draws":28,"losses":175,"wins":9},"claude-opus-5-5":{"draws":6,"losses":98,"wins":0},"claude-sonnet-5":{"draws":34,"losses":67,"wins":7},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":22,"losses":26,"wins":28},"deepseek/deepseek-v4-flash":{"draws":59,"losses":109,"wins":56},"deepseek/deepseek-v4-pro":{"draws":28,"losses":57,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":55,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":52,"wins":9},"fireworks/ember-1":{"draws":24,"losses":68,"wins":4},"gemini-3.1-pro-preview":{"draws":22,"losses":53,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":48,"wins":48},"google/gemini-3.5-flash":{"draws":35,"losses":89,"wins":18},"google/gemini-3.5-flash-lite":{"draws":65,"losses":107,"wins":46},"google/gemini-3.6-flash":{"draws":49,"losses":152,"wins":15},"google/gemini-3.8-flash":{"draws":26,"losses":70,"wins":4},"google/gemma-4-31b-it":{"draws":19,"losses":26,"wins":15},"gpt-4.1":{"draws":25,"losses":33,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":51,"losses":84,"wins":5},"gpt-5.4":{"draws":22,"losses":71,"wins":7},"gpt-5.4-mini":{"draws":35,"losses":70,"wins":15},"gpt-5.4-nano":{"draws":40,"losses":123,"wins":49},"gpt-5.5":{"draws":44,"losses":89,"wins":9},"gpt-5.6-luna":{"draws":26,"losses":50,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":83,"wins":5},"gpt-5.6-terra":{"draws":30,"losses":66,"wins":10},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":25,"losses":60,"wins":11},"gpt-6-sol":{"draws":13,"losses":82,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":92,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":28,"wins":19},"inclusionai/ling-3.0-flash":{"draws":42,"losses":33,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":38,"losses":96,"wins":50},"meta/muse-glimmer-30b":{"draws":39,"losses":34,"wins":19},"meta/muse-spark-1.2":{"draws":24,"losses":66,"wins":10},"meta/muse-spark-1.3":{"draws":16,"losses":79,"wins":5},"meta/muse-wonder":{"draws":9,"losses":84,"wins":3},"minimax/minimax-m3":{"draws":29,"losses":50,"wins":41},"mistralai/mistral-large-4-0":{"draws":17,"losses":39,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":26,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":36,"wins":3},"moonshotai/kimi-k3":{"draws":24,"losses":58,"wins":12},"nex-agi/nex-n2-pro":{"draws":18,"losses":49,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":76,"wins":44},"o3":{"draws":33,"losses":155,"wins":14},"openai/gpt-oss-120b":{"draws":25,"losses":42,"wins":19},"poolside/laguna-s-2.1":{"draws":35,"losses":64,"wins":33},"qwen/qwen3.7-max":{"draws":33,"losses":55,"wins":18},"qwen/qwen3.7-plus":{"draws":28,"losses":59,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":70,"wins":3},"qwen/qwen3.8-27b":{"draws":15,"losses":48,"wins":11},"qwen/qwen3.8-flash":{"draws":28,"losses":34,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":66,"wins":1},"qwen/qwen3.8-max-0902":{"draws":28,"losses":66,"wins":2},"stealth/ox-alpha":{"draws":56,"losses":197,"wins":31},"stealth/space-bunny-alpha":{"draws":21,"losses":47,"wins":12},"stepfun/step-3.7-flash":{"draws":18,"losses":69,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":34,"losses":40,"wins":24},"tencent/hy4-preview":{"draws":23,"losses":74,"wins":3},"thinkingmachines/inkling":{"draws":55,"losses":84,"wins":49},"thinkingmachines/inkling-small":{"draws":34,"losses":40,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":19,"wins":7},"x-ai/grok-4.5":{"draws":27,"losses":95,"wins":4},"x-ai/grok-4.6":{"draws":18,"losses":72,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":79,"wins":1},"x-ai/grok-build-0.1":{"draws":21,"losses":38,"wins":9},"xiaomi/mimo-v2.5":{"draws":111,"losses":133,"wins":76},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":79,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":44,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":50,"wins":5},"z-ai/glm-5.2":{"draws":67,"losses":168,"wins":35},"z-ai/glm-5.3":{"draws":17,"losses":78,"wins":1},"z-ai/glm-5.3-flash":{"draws":25,"losses":64,"wins":11},"z-ai/glm-5.3-flashx":{"draws":25,"losses":64,"wins":7}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":75,"losses":61,"wins":120},"claude-fable-5":{"draws":59,"losses":171,"wins":54},"claude-fable-5-1":{"draws":23,"losses":279,"wins":14},"claude-haiku-5-5":{"draws":39,"losses":77,"wins":58},"claude-opus-4-5":{"draws":108,"losses":129,"wins":159},"claude-opus-4-8":{"draws":55,"losses":93,"wins":52},"claude-opus-5":{"draws":43,"losses":270,"wins":33},"claude-opus-5-5":{"draws":13,"losses":174,"wins":9},"claude-sonnet-5":{"draws":88,"losses":88,"wins":120},"claude-sonnet-5-5":{"draws":28,"losses":105,"wins":47},"cohere/north-mini-code":{"draws":20,"losses":13,"wins":43},"deepseek/deepseek-v4-flash":{"draws":109,"losses":85,"wins":186},"deepseek/deepseek-v4-pro":{"draws":73,"losses":93,"wins":102},"deepseek/deepseek-v4-pro-0813":{"draws":90,"losses":77,"wins":113},"deepseek/deepseek-v4.1-flash":{"draws":55,"losses":74,"wins":51},"fireworks/ember-1":{"draws":53,"losses":69,"wins":58},"gemini-3.1-pro-preview":{"draws":43,"losses":59,"wins":78},"google/gemini-3.1-flash-lite":{"draws":35,"losses":18,"wins":89},"google/gemini-3.5-flash":{"draws":56,"losses":92,"wins":92},"google/gemini-3.5-flash-lite":{"draws":143,"losses":130,"wins":227},"google/gemini-3.6-flash":{"draws":133,"losses":193,"wins":194},"google/gemini-3.8-flash":{"draws":64,"losses":150,"wins":82},"google/gemma-4-31b-it":{"draws":31,"losses":22,"wins":53},"gpt-4.1":{"draws":19,"losses":20,"wins":27},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":52,"losses":58,"wins":70},"gpt-5.4":{"draws":52,"losses":137,"wins":87},"gpt-5.4-mini":{"draws":48,"losses":31,"wins":57},"gpt-5.4-nano":{"draws":46,"losses":57,"wins":119},"gpt-5.5":{"draws":58,"losses":74,"wins":46},"gpt-5.6-luna":{"draws":91,"losses":75,"wins":120},"gpt-5.6-sol":{"draws":33,"losses":178,"wins":73},"gpt-5.6-terra":{"draws":94,"losses":97,"wins":81},"gpt-6-astra":{"draws":27,"losses":246,"wins":11},"gpt-6-luna":{"draws":52,"losses":59,"wins":69},"gpt-6-sol":{"draws":27,"losses":127,"wins":26},"gpt-6.1-sol":{"draws":12,"losses":151,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":73,"losses":21,"wins":98},"inclusionai/ling-3.0-flash":{"draws":56,"losses":16,"wins":94},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":64,"losses":44,"wins":150},"meta/muse-glimmer-30b":{"draws":82,"losses":44,"wins":118},"meta/muse-spark-1.2":{"draws":54,"losses":98,"wins":88},"meta/muse-spark-1.3":{"draws":50,"losses":134,"wins":70},"meta/muse-wonder":{"draws":30,"losses":121,"wins":29},"minimax/minimax-m3":{"draws":31,"losses":28,"wins":51},"mistralai/mistral-large-4-0":{"draws":38,"losses":39,"wins":35},"mistralai/mistral-medium-3-5":{"draws":49,"losses":26,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":19,"wins":16},"moonshotai/kimi-k3":{"draws":86,"losses":78,"wins":90},"nex-agi/nex-n2-pro":{"draws":29,"losses":21,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":36,"wins":85},"o3":{"draws":55,"losses":113,"wins":186},"openai/gpt-oss-120b":{"draws":81,"losses":51,"wins":114},"poolside/laguna-s-2.1":{"draws":75,"losses":46,"wins":115},"qwen/qwen3.7-max":{"draws":37,"losses":40,"wins":43},"qwen/qwen3.7-plus":{"draws":27,"losses":18,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":79,"losses":117,"wins":96},"qwen/qwen3.8-27b":{"draws":29,"losses":61,"wins":60},"qwen/qwen3.8-flash":{"draws":66,"losses":54,"wins":78},"qwen/qwen3.8-max":{"draws":90,"losses":87,"wins":101},"qwen/qwen3.8-max-0902":{"draws":51,"losses":84,"wins":45},"stealth/ox-alpha":{"draws":204,"losses":392,"wins":330},"stealth/space-bunny-alpha":{"draws":43,"losses":33,"wins":68},"stepfun/step-3.7-flash":{"draws":28,"losses":28,"wins":80},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":29,"wins":43},"tencent/hy4-preview":{"draws":63,"losses":143,"wins":74},"thinkingmachines/inkling":{"draws":72,"losses":61,"wins":159},"thinkingmachines/inkling-small":{"draws":83,"losses":51,"wins":138},"unbiased/pareto-26.10-preview":{"draws":0,"losses":55,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":55,"losses":121,"wins":86},"x-ai/grok-4.6":{"draws":83,"losses":154,"wins":55},"x-ai/grok-4.7":{"draws":15,"losses":118,"wins":25},"x-ai/grok-build-0.1":{"draws":21,"losses":10,"wins":37},"xiaomi/mimo-v2.5":{"draws":98,"losses":57,"wins":153},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":40,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":52,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":62,"wins":37},"z-ai/glm-5.2":{"draws":138,"losses":149,"wins":193},"z-ai/glm-5.3":{"draws":52,"losses":139,"wins":59},"z-ai/glm-5.3-flash":{"draws":67,"losses":127,"wins":96},"z-ai/glm-5.3-flashx":{"draws":48,"losses":89,"wins":43}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":157,"losses":145,"wins":138},"claude-fable-5":{"draws":84,"losses":257,"wins":55},"claude-fable-5-1":{"draws":28,"losses":375,"wins":3},"claude-haiku-5-5":{"draws":53,"losses":149,"wins":40},"claude-opus-4-5":{"draws":269,"losses":373,"wins":182},"claude-opus-4-8":{"draws":83,"losses":175,"wins":34},"claude-opus-5":{"draws":74,"losses":449,"wins":43},"claude-opus-5-5":{"draws":17,"losses":253,"wins":2},"claude-sonnet-5":{"draws":198,"losses":345,"wins":155},"claude-sonnet-5-5":{"draws":49,"losses":163,"wins":40},"cohere/north-mini-code":{"draws":46,"losses":38,"wins":40},"deepseek/deepseek-v4-flash":{"draws":198,"losses":193,"wins":193},"deepseek/deepseek-v4-pro":{"draws":130,"losses":193,"wins":109},"deepseek/deepseek-v4-pro-0813":{"draws":152,"losses":172,"wins":84},"deepseek/deepseek-v4.1-flash":{"draws":89,"losses":116,"wins":47},"fireworks/ember-1":{"draws":95,"losses":113,"wins":44},"gemini-3.1-pro-preview":{"draws":81,"losses":107,"wins":64},"google/gemini-3.1-flash-lite":{"draws":65,"losses":46,"wins":107},"google/gemini-3.5-flash":{"draws":143,"losses":227,"wins":130},"google/gemini-3.5-flash-lite":{"draws":440,"losses":430,"wins":430},"google/gemini-3.6-flash":{"draws":451,"losses":683,"wins":281},"google/gemini-3.8-flash":{"draws":88,"losses":274,"wins":28},"google/gemma-4-31b-it":{"draws":55,"losses":35,"wins":58},"gpt-4.1":{"draws":38,"losses":35,"wins":39},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":102,"losses":102,"wins":66},"gpt-5.4":{"draws":184,"losses":368,"wins":94},"gpt-5.4-mini":{"draws":82,"losses":80,"wins":54},"gpt-5.4-nano":{"draws":82,"losses":104,"wins":132},"gpt-5.5":{"draws":128,"losses":130,"wins":40},"gpt-5.6-luna":{"draws":230,"losses":274,"wins":214},"gpt-5.6-sol":{"draws":92,"losses":497,"wins":57},"gpt-5.6-terra":{"draws":139,"losses":191,"wins":94},"gpt-6-astra":{"draws":21,"losses":345,"wins":2},"gpt-6-luna":{"draws":83,"losses":114,"wins":55},"gpt-6-sol":{"draws":39,"losses":191,"wins":22},"gpt-6.1-sol":{"draws":16,"losses":235,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":151,"losses":61,"wins":136},"inclusionai/ling-3.0-flash":{"draws":156,"losses":69,"wins":181},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":175,"losses":212,"wins":271},"meta/muse-glimmer-30b":{"draws":180,"losses":97,"wins":149},"meta/muse-spark-1.2":{"draws":134,"losses":271,"wins":107},"meta/muse-spark-1.3":{"draws":84,"losses":219,"wins":67},"meta/muse-wonder":{"draws":43,"losses":182,"wins":27},"minimax/minimax-m3":{"draws":51,"losses":54,"wins":67},"mistralai/mistral-large-4-0":{"draws":52,"losses":75,"wins":29},"mistralai/mistral-medium-3-5":{"draws":105,"losses":60,"wins":119},"moonshotai/kimi-k2.7-code":{"draws":18,"losses":33,"wins":21},"moonshotai/kimi-k3":{"draws":218,"losses":298,"wins":126},"nex-agi/nex-n2-pro":{"draws":56,"losses":40,"wins":64},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":109,"losses":80,"wins":77},"o3":{"draws":139,"losses":518,"wins":229},"openai/gpt-oss-120b":{"draws":149,"losses":117,"wins":142},"poolside/laguna-s-2.1":{"draws":257,"losses":206,"wins":165},"qwen/qwen3.7-max":{"draws":52,"losses":67,"wins":55},"qwen/qwen3.7-plus":{"draws":53,"losses":51,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":145,"losses":207,"wins":78},"qwen/qwen3.8-27b":{"draws":40,"losses":130,"wins":50},"qwen/qwen3.8-flash":{"draws":112,"losses":125,"wins":49},"qwen/qwen3.8-max":{"draws":152,"losses":190,"wins":95},"qwen/qwen3.8-max-0902":{"draws":78,"losses":139,"wins":35},"stealth/ox-alpha":{"draws":338,"losses":760,"wins":296},"stealth/space-bunny-alpha":{"draws":58,"losses":84,"wins":60},"stepfun/step-3.7-flash":{"draws":59,"losses":63,"wins":76},"stepfun/step-5-preview":{"draws":10,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":66,"losses":64,"wins":32},"tencent/hy4-preview":{"draws":126,"losses":218,"wins":84},"thinkingmachines/inkling":{"draws":200,"losses":199,"wins":251},"thinkingmachines/inkling-small":{"draws":176,"losses":143,"wins":177},"unbiased/pareto-26.10-preview":{"draws":2,"losses":81,"wins":1},"upstage/solar-mini4":{"draws":20,"losses":25,"wins":23},"x-ai/grok-4.5":{"draws":175,"losses":369,"wins":132},"x-ai/grok-4.6":{"draws":119,"losses":232,"wins":57},"x-ai/grok-4.7":{"draws":20,"losses":170,"wins":28},"x-ai/grok-build-0.1":{"draws":48,"losses":34,"wins":30},"xiaomi/mimo-v2.5":{"draws":163,"losses":135,"wins":162},"xiaomi/mimo-v2.5-pro":{"draws":52,"losses":73,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":103,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":118,"wins":29},"z-ai/glm-5.2":{"draws":268,"losses":270,"wins":202},"z-ai/glm-5.3":{"draws":73,"losses":251,"wins":30},"z-ai/glm-5.3-flash":{"draws":122,"losses":235,"wins":69},"z-ai/glm-5.3-flashx":{"draws":67,"losses":138,"wins":47}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":115,"losses":88,"wins":201},"claude-fable-5":{"draws":77,"losses":225,"wins":132},"claude-fable-5-1":{"draws":34,"losses":410,"wins":32},"claude-haiku-5-5":{"draws":65,"losses":100,"wins":99},"claude-opus-4-5":{"draws":233,"losses":246,"wins":367},"claude-opus-4-8":{"draws":83,"losses":119,"wins":136},"claude-opus-5":{"draws":85,"losses":460,"wins":121},"claude-opus-5-5":{"draws":26,"losses":251,"wins":19},"claude-sonnet-5":{"draws":167,"losses":222,"wins":291},"claude-sonnet-5-5":{"draws":54,"losses":126,"wins":96},"cohere/north-mini-code":{"draws":35,"losses":11,"wins":82},"deepseek/deepseek-v4-flash":{"draws":162,"losses":91,"wins":345},"deepseek/deepseek-v4-pro":{"draws":111,"losses":144,"wins":159},"deepseek/deepseek-v4-pro-0813":{"draws":117,"losses":123,"wins":190},"deepseek/deepseek-v4.1-flash":{"draws":78,"losses":90,"wins":108},"fireworks/ember-1":{"draws":80,"losses":98,"wins":98},"gemini-3.1-pro-preview":{"draws":64,"losses":89,"wins":123},"google/gemini-3.1-flash-lite":{"draws":49,"losses":15,"wins":152},"google/gemini-3.5-flash":{"draws":133,"losses":194,"wins":193},"google/gemini-3.5-flash-lite":{"draws":451,"losses":281,"wins":683},"google/gemini-3.6-flash":{"draws":258,"losses":459,"wins":459},"google/gemini-3.8-flash":{"draws":100,"losses":210,"wins":139},"google/gemma-4-31b-it":{"draws":51,"losses":20,"wins":89},"gpt-4.1":{"draws":36,"losses":26,"wins":56},"gpt-4.1-nano":{"draws":14,"losses":2,"wins":18},"gpt-5":{"draws":66,"losses":95,"wins":139},"gpt-5.4":{"draws":162,"losses":295,"wins":205},"gpt-5.4-mini":{"draws":71,"losses":43,"wins":123},"gpt-5.4-nano":{"draws":81,"losses":71,"wins":186},"gpt-5.5":{"draws":107,"losses":116,"wins":115},"gpt-5.6-luna":{"draws":201,"losses":157,"wins":316},"gpt-5.6-sol":{"draws":97,"losses":375,"wins":194},"gpt-5.6-terra":{"draws":132,"losses":116,"wins":176},"gpt-6-astra":{"draws":37,"losses":356,"wins":29},"gpt-6-luna":{"draws":83,"losses":65,"wins":128},"gpt-6-sol":{"draws":37,"losses":181,"wins":58},"gpt-6.1-sol":{"draws":18,"losses":230,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":116,"losses":25,"wins":161},"inclusionai/ling-3.0-flash":{"draws":176,"losses":52,"wins":196},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":171,"losses":102,"wins":363},"meta/muse-glimmer-30b":{"draws":146,"losses":56,"wins":200},"meta/muse-spark-1.2":{"draws":103,"losses":218,"wins":201},"meta/muse-spark-1.3":{"draws":72,"losses":177,"wins":143},"meta/muse-wonder":{"draws":50,"losses":155,"wins":71},"minimax/minimax-m3":{"draws":43,"losses":30,"wins":111},"mistralai/mistral-large-4-0":{"draws":41,"losses":59,"wins":72},"mistralai/mistral-medium-3-5":{"draws":97,"losses":28,"wins":125},"moonshotai/kimi-k2.7-code":{"draws":26,"losses":19,"wins":43},"moonshotai/kimi-k3":{"draws":194,"losses":212,"wins":260},"nex-agi/nex-n2-pro":{"draws":42,"losses":23,"wins":111},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":88,"losses":39,"wins":149},"o3":{"draws":126,"losses":295,"wins":451},"openai/gpt-oss-120b":{"draws":137,"losses":53,"wins":194},"poolside/laguna-s-2.1":{"draws":229,"losses":102,"wins":273},"qwen/qwen3.7-max":{"draws":56,"losses":43,"wins":101},"qwen/qwen3.7-plus":{"draws":57,"losses":28,"wins":99},"qwen/qwen3.8-2.4t-a95b":{"draws":123,"losses":156,"wins":177},"qwen/qwen3.8-27b":{"draws":49,"losses":82,"wins":107},"qwen/qwen3.8-flash":{"draws":118,"losses":70,"wins":120},"qwen/qwen3.8-max":{"draws":132,"losses":159,"wins":184},"qwen/qwen3.8-max-0902":{"draws":78,"losses":104,"wins":94},"stealth/ox-alpha":{"draws":320,"losses":565,"wins":597},"stealth/space-bunny-alpha":{"draws":59,"losses":44,"wins":117},"stepfun/step-3.7-flash":{"draws":43,"losses":32,"wins":140},"stepfun/step-5-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":63,"losses":46,"wins":87},"tencent/hy4-preview":{"draws":106,"losses":176,"wins":174},"thinkingmachines/inkling":{"draws":191,"losses":98,"wins":361},"thinkingmachines/inkling-small":{"draws":146,"losses":84,"wins":216},"unbiased/pareto-26.10-preview":{"draws":5,"losses":78,"wins":9},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":49},"x-ai/grok-4.5":{"draws":149,"losses":283,"wins":288},"x-ai/grok-4.6":{"draws":113,"losses":187,"wins":144},"x-ai/grok-4.7":{"draws":14,"losses":172,"wins":54},"x-ai/grok-build-0.1":{"draws":35,"losses":5,"wins":66},"xiaomi/mimo-v2.5":{"draws":180,"losses":62,"wins":264},"xiaomi/mimo-v2.5-pro":{"draws":46,"losses":42,"wins":108},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":73,"wins":71},"xiaomi/mimo-v2.6-pro":{"draws":38,"losses":86,"wins":60},"z-ai/glm-5.2":{"draws":219,"losses":207,"wins":308},"z-ai/glm-5.3":{"draws":76,"losses":211,"wins":93},"z-ai/glm-5.3-flash":{"draws":99,"losses":204,"wins":137},"z-ai/glm-5.3-flashx":{"draws":71,"losses":110,"wins":95}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":38,"wins":111},"claude-fable-5":{"draws":41,"losses":126,"wins":97},"claude-fable-5-1":{"draws":22,"losses":257,"wins":27},"claude-haiku-5-5":{"draws":33,"losses":43,"wins":62},"claude-opus-4-5":{"draws":99,"losses":63,"wins":172},"claude-opus-4-8":{"draws":30,"losses":51,"wins":63},"claude-opus-5":{"draws":34,"losses":203,"wins":61},"claude-opus-5-5":{"draws":16,"losses":120,"wins":20},"claude-sonnet-5":{"draws":66,"losses":65,"wins":127},"claude-sonnet-5-5":{"draws":20,"losses":68,"wins":56},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":37},"deepseek/deepseek-v4-flash":{"draws":67,"losses":37,"wins":204},"deepseek/deepseek-v4-pro":{"draws":63,"losses":53,"wins":118},"deepseek/deepseek-v4-pro-0813":{"draws":62,"losses":62,"wins":106},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":45,"wins":61},"fireworks/ember-1":{"draws":35,"losses":48,"wins":61},"gemini-3.1-pro-preview":{"draws":28,"losses":34,"wins":82},"google/gemini-3.1-flash-lite":{"draws":26,"losses":4,"wins":70},"google/gemini-3.5-flash":{"draws":64,"losses":82,"wins":150},"google/gemini-3.5-flash-lite":{"draws":88,"losses":28,"wins":274},"google/gemini-3.6-flash":{"draws":100,"losses":139,"wins":210},"google/gemini-3.8-flash":{"draws":46,"losses":67,"wins":67},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":52},"gpt-4.1":{"draws":17,"losses":7,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":34,"losses":35,"wins":69},"gpt-5.4":{"draws":61,"losses":103,"wins":92},"gpt-5.4-mini":{"draws":28,"losses":19,"wins":63},"gpt-5.4-nano":{"draws":32,"losses":27,"wins":93},"gpt-5.5":{"draws":49,"losses":46,"wins":43},"gpt-5.6-luna":{"draws":57,"losses":48,"wins":133},"gpt-5.6-sol":{"draws":37,"losses":136,"wins":99},"gpt-5.6-terra":{"draws":79,"losses":63,"wins":102},"gpt-6-astra":{"draws":29,"losses":227,"wins":18},"gpt-6-luna":{"draws":42,"losses":33,"wins":69},"gpt-6-sol":{"draws":22,"losses":89,"wins":33},"gpt-6.1-sol":{"draws":20,"losses":106,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":60,"losses":6,"wins":92},"inclusionai/ling-3.0-flash":{"draws":33,"losses":3,"wins":84},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":44,"losses":22,"wins":128},"meta/muse-glimmer-30b":{"draws":61,"losses":25,"wins":112},"meta/muse-spark-1.2":{"draws":39,"losses":83,"wins":84},"meta/muse-spark-1.3":{"draws":45,"losses":77,"wins":90},"meta/muse-wonder":{"draws":36,"losses":68,"wins":40},"minimax/minimax-m3":{"draws":19,"losses":7,"wins":58},"mistralai/mistral-large-4-0":{"draws":28,"losses":26,"wins":36},"mistralai/mistral-medium-3-5":{"draws":37,"losses":7,"wins":80},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":16,"wins":14},"moonshotai/kimi-k3":{"draws":59,"losses":48,"wins":113},"nex-agi/nex-n2-pro":{"draws":15,"losses":7,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":11,"wins":80},"o3":{"draws":40,"losses":69,"wins":183},"openai/gpt-oss-120b":{"draws":50,"losses":14,"wins":122},"poolside/laguna-s-2.1":{"draws":46,"losses":21,"wins":117},"qwen/qwen3.7-max":{"draws":29,"losses":24,"wins":37},"qwen/qwen3.7-plus":{"draws":21,"losses":7,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":63,"losses":79,"wins":116},"qwen/qwen3.8-27b":{"draws":21,"losses":36,"wins":73},"qwen/qwen3.8-flash":{"draws":42,"losses":43,"wins":81},"qwen/qwen3.8-max":{"draws":68,"losses":81,"wins":101},"qwen/qwen3.8-max-0902":{"draws":39,"losses":45,"wins":60},"stealth/ox-alpha":{"draws":185,"losses":276,"wins":399},"stealth/space-bunny-alpha":{"draws":31,"losses":17,"wins":66},"stepfun/step-3.7-flash":{"draws":22,"losses":9,"wins":75},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":38,"losses":9,"wins":39},"tencent/hy4-preview":{"draws":55,"losses":91,"wins":90},"thinkingmachines/inkling":{"draws":63,"losses":21,"wins":138},"thinkingmachines/inkling-small":{"draws":79,"losses":30,"wins":121},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":40,"losses":104,"wins":76},"x-ai/grok-4.6":{"draws":76,"losses":99,"wins":87},"x-ai/grok-4.7":{"draws":14,"losses":85,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":70,"losses":20,"wins":138},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":15,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":28,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":49,"wins":27},"z-ai/glm-5.2":{"draws":103,"losses":86,"wins":203},"z-ai/glm-5.3":{"draws":46,"losses":107,"wins":67},"z-ai/glm-5.3-flash":{"draws":53,"losses":91,"wins":114},"z-ai/glm-5.3-flashx":{"draws":29,"losses":51,"wins":64}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":24},"claude-fable-5":{"draws":18,"losses":58,"wins":8},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":23,"losses":50,"wins":9},"claude-opus-4-5":{"draws":46,"losses":77,"wins":15},"claude-opus-4-8":{"draws":23,"losses":47,"wins":10},"claude-opus-5":{"draws":21,"losses":109,"wins":10},"claude-opus-5-5":{"draws":5,"losses":87,"wins":0},"claude-sonnet-5":{"draws":27,"losses":45,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":54,"wins":16},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":58,"losses":46,"wins":22},"deepseek/deepseek-v4-pro":{"draws":28,"losses":34,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":38,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":38,"wins":12},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":30,"losses":39,"wins":15},"google/gemini-3.1-flash-lite":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":31,"losses":53,"wins":22},"google/gemini-3.5-flash-lite":{"draws":55,"losses":58,"wins":35},"google/gemini-3.6-flash":{"draws":51,"losses":89,"wins":20},"google/gemini-3.8-flash":{"draws":23,"losses":52,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":7,"wins":7},"gpt-4.1":{"draws":11,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":31,"losses":32,"wins":9},"gpt-5.4":{"draws":28,"losses":43,"wins":9},"gpt-5.4-mini":{"draws":22,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":26,"losses":43,"wins":17},"gpt-5.5":{"draws":30,"losses":40,"wins":6},"gpt-5.6-luna":{"draws":34,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":67,"wins":6},"gpt-5.6-terra":{"draws":32,"losses":39,"wins":9},"gpt-6-astra":{"draws":4,"losses":80,"wins":0},"gpt-6-luna":{"draws":28,"losses":38,"wins":18},"gpt-6-sol":{"draws":9,"losses":73,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":80,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":16,"wins":18},"inclusionai/ling-3.0-flash":{"draws":32,"losses":13,"wins":13},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":35,"wins":26},"meta/muse-glimmer-30b":{"draws":38,"losses":17,"wins":17},"meta/muse-spark-1.2":{"draws":23,"losses":40,"wins":17},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":8},"meta/muse-wonder":{"draws":17,"losses":60,"wins":7},"minimax/minimax-m3":{"draws":19,"losses":16,"wins":11},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":29,"losses":38,"wins":13},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":18,"wins":18},"o3":{"draws":26,"losses":71,"wins":21},"openai/gpt-oss-120b":{"draws":31,"losses":33,"wins":10},"poolside/laguna-s-2.1":{"draws":33,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":17,"losses":20,"wins":13},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":45,"wins":10},"qwen/qwen3.8-27b":{"draws":19,"losses":29,"wins":10},"qwen/qwen3.8-flash":{"draws":27,"losses":23,"wins":6},"qwen/qwen3.8-max":{"draws":33,"losses":43,"wins":8},"qwen/qwen3.8-max-0902":{"draws":29,"losses":46,"wins":9},"stealth/ox-alpha":{"draws":60,"losses":160,"wins":40},"stealth/space-bunny-alpha":{"draws":26,"losses":26,"wins":16},"stepfun/step-3.7-flash":{"draws":18,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":21,"losses":16,"wins":9},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":11},"thinkingmachines/inkling":{"draws":40,"losses":36,"wins":32},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":27,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":19,"losses":55,"wins":10},"x-ai/grok-4.6":{"draws":24,"losses":54,"wins":6},"x-ai/grok-4.7":{"draws":8,"losses":62,"wins":4},"x-ai/grok-build-0.1":{"draws":11,"losses":9,"wins":8},"xiaomi/mimo-v2.5":{"draws":61,"losses":41,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":32,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":41,"wins":4},"z-ai/glm-5.2":{"draws":69,"losses":70,"wins":29},"z-ai/glm-5.3":{"draws":22,"losses":53,"wins":7},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":14},"z-ai/glm-5.3-flashx":{"draws":28,"losses":45,"wins":11}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":11,"wins":17},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":58,"losses":37,"wins":27},"claude-opus-4-8":{"draws":29,"losses":42,"wins":9},"claude-opus-5":{"draws":20,"losses":126,"wins":11},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":11,"losses":5,"wins":16},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":43},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":38,"losses":39,"wins":35},"google/gemini-3.6-flash":{"draws":36,"losses":56,"wins":26},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":7},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":24,"losses":21,"wins":25},"gpt-5.4":{"draws":15,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":29,"losses":27,"wins":12},"gpt-5.4-nano":{"draws":21,"losses":37,"wins":34},"gpt-5.5":{"draws":27,"losses":38,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"gpt-6-astra":{"draws":5,"losses":45,"wins":0},"gpt-6-luna":{"draws":11,"losses":18,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":29,"losses":1,"wins":36},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":26,"losses":16,"wins":42},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":16},"meta/muse-spark-1.2":{"draws":19,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":18,"losses":30,"wins":4},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":28},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":15,"wins":33},"o3":{"draws":19,"losses":35,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":24,"losses":20,"wins":30},"qwen/qwen3.7-max":{"draws":26,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":19,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":79,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":25},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":20},"tencent/hy4-preview":{"draws":13,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":24,"losses":35,"wins":33},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":36,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":14,"losses":8,"wins":12},"xiaomi/mimo-v2.5":{"draws":60,"losses":30,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":14,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":49,"losses":54,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":38,"wins":44},"claude-fable-5":{"draws":28,"losses":81,"wins":27},"claude-fable-5-1":{"draws":7,"losses":134,"wins":1},"claude-haiku-5-5":{"draws":31,"losses":62,"wins":27},"claude-opus-4-5":{"draws":104,"losses":105,"wins":95},"claude-opus-4-8":{"draws":49,"losses":101,"wins":52},"claude-opus-5":{"draws":44,"losses":281,"wins":29},"claude-opus-5-5":{"draws":9,"losses":124,"wins":5},"claude-sonnet-5":{"draws":40,"losses":53,"wins":35},"claude-sonnet-5-5":{"draws":27,"losses":73,"wins":26},"cohere/north-mini-code":{"draws":19,"losses":10,"wins":51},"deepseek/deepseek-v4-flash":{"draws":84,"losses":47,"wins":105},"deepseek/deepseek-v4-pro":{"draws":39,"losses":54,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":43,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":55,"wins":28},"fireworks/ember-1":{"draws":36,"losses":59,"wins":31},"gemini-3.1-pro-preview":{"draws":40,"losses":51,"wins":35},"google/gemini-3.1-flash-lite":{"draws":51,"losses":5,"wins":84},"google/gemini-3.5-flash":{"draws":52,"losses":70,"wins":58},"google/gemini-3.5-flash-lite":{"draws":102,"losses":66,"wins":102},"google/gemini-3.6-flash":{"draws":66,"losses":139,"wins":95},"google/gemini-3.8-flash":{"draws":34,"losses":69,"wins":35},"google/gemma-4-31b-it":{"draws":31,"losses":9,"wins":32},"gpt-4.1":{"draws":24,"losses":25,"wins":21},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":32,"losses":42,"wins":42},"gpt-5.4":{"draws":32,"losses":68,"wins":26},"gpt-5.4-mini":{"draws":53,"losses":49,"wins":42},"gpt-5.4-nano":{"draws":38,"losses":64,"wins":94},"gpt-5.5":{"draws":72,"losses":92,"wins":48},"gpt-5.6-luna":{"draws":40,"losses":36,"wins":52},"gpt-5.6-sol":{"draws":20,"losses":93,"wins":19},"gpt-5.6-terra":{"draws":36,"losses":56,"wins":36},"gpt-6-astra":{"draws":9,"losses":115,"wins":2},"gpt-6-luna":{"draws":39,"losses":45,"wins":42},"gpt-6-sol":{"draws":15,"losses":95,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":115,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":10,"wins":41},"inclusionai/ling-3.0-flash":{"draws":49,"losses":38,"wins":45},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":66,"losses":47,"wins":95},"meta/muse-glimmer-30b":{"draws":46,"losses":26,"wins":54},"meta/muse-spark-1.2":{"draws":34,"losses":67,"wins":35},"meta/muse-spark-1.3":{"draws":31,"losses":76,"wins":29},"meta/muse-wonder":{"draws":23,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":36,"losses":30,"wins":54},"mistralai/mistral-large-4-0":{"draws":30,"losses":34,"wins":16},"mistralai/mistral-medium-3-5":{"draws":27,"losses":17,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":24,"wins":21},"moonshotai/kimi-k3":{"draws":38,"losses":50,"wins":44},"nex-agi/nex-n2-pro":{"draws":30,"losses":20,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":78,"losses":36,"wins":76},"o3":{"draws":49,"losses":79,"wins":112},"openai/gpt-oss-120b":{"draws":40,"losses":21,"wins":53},"poolside/laguna-s-2.1":{"draws":67,"losses":58,"wins":57},"qwen/qwen3.7-max":{"draws":54,"losses":26,"wins":48},"qwen/qwen3.7-plus":{"draws":30,"losses":17,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":58,"wins":36},"qwen/qwen3.8-27b":{"draws":18,"losses":42,"wins":34},"qwen/qwen3.8-flash":{"draws":31,"losses":31,"wins":32},"qwen/qwen3.8-max":{"draws":43,"losses":56,"wins":29},"qwen/qwen3.8-max-0902":{"draws":38,"losses":58,"wins":30},"stealth/ox-alpha":{"draws":107,"losses":209,"wins":130},"stealth/space-bunny-alpha":{"draws":26,"losses":35,"wins":39},"stepfun/step-3.7-flash":{"draws":35,"losses":19,"wins":64},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":42,"losses":43,"wins":39},"tencent/hy4-preview":{"draws":42,"losses":52,"wins":36},"thinkingmachines/inkling":{"draws":65,"losses":50,"wins":113},"thinkingmachines/inkling-small":{"draws":53,"losses":20,"wins":55},"unbiased/pareto-26.10-preview":{"draws":1,"losses":40,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":23},"x-ai/grok-4.5":{"draws":35,"losses":95,"wins":44},"x-ai/grok-4.6":{"draws":42,"losses":73,"wins":21},"x-ai/grok-4.7":{"draws":10,"losses":84,"wins":18},"x-ai/grok-build-0.1":{"draws":27,"losses":16,"wins":33},"xiaomi/mimo-v2.5":{"draws":129,"losses":63,"wins":128},"xiaomi/mimo-v2.5-pro":{"draws":36,"losses":30,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":33,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":22},"z-ai/glm-5.2":{"draws":123,"losses":109,"wins":126},"z-ai/glm-5.3":{"draws":19,"losses":81,"wins":22},"z-ai/glm-5.3-flash":{"draws":38,"losses":68,"wins":30},"z-ai/glm-5.3-flashx":{"draws":38,"losses":56,"wins":32}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":47,"wins":91},"claude-fable-5":{"draws":65,"losses":112,"wins":83},"claude-fable-5-1":{"draws":19,"losses":230,"wins":33},"claude-haiku-5-5":{"draws":31,"losses":51,"wins":50},"claude-opus-4-5":{"draws":109,"losses":81,"wins":196},"claude-opus-4-8":{"draws":29,"losses":51,"wins":56},"claude-opus-5":{"draws":29,"losses":189,"wins":36},"claude-opus-5-5":{"draws":11,"losses":128,"wins":11},"claude-sonnet-5":{"draws":116,"losses":80,"wins":188},"claude-sonnet-5-5":{"draws":37,"losses":59,"wins":42},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":37},"deepseek/deepseek-v4-flash":{"draws":102,"losses":40,"wins":162},"deepseek/deepseek-v4-pro":{"draws":65,"losses":65,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":64,"losses":56,"wins":96},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":39,"wins":53},"fireworks/ember-1":{"draws":40,"losses":38,"wins":60},"gemini-3.1-pro-preview":{"draws":30,"losses":42,"wins":66},"google/gemini-3.1-flash-lite":{"draws":22,"losses":7,"wins":71},"google/gemini-3.5-flash":{"draws":52,"losses":87,"wins":137},"google/gemini-3.5-flash-lite":{"draws":184,"losses":94,"wins":368},"google/gemini-3.6-flash":{"draws":162,"losses":205,"wins":295},"google/gemini-3.8-flash":{"draws":61,"losses":92,"wins":103},"google/gemma-4-31b-it":{"draws":28,"losses":9,"wins":43},"gpt-4.1":{"draws":15,"losses":10,"wins":25},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":6},"gpt-5":{"draws":32,"losses":26,"wins":68},"gpt-5.4":{"draws":72,"losses":112,"wins":112},"gpt-5.4-mini":{"draws":32,"losses":6,"wins":54},"gpt-5.4-nano":{"draws":25,"losses":36,"wins":83},"gpt-5.5":{"draws":44,"losses":43,"wins":45},"gpt-5.6-luna":{"draws":141,"losses":56,"wins":200},"gpt-5.6-sol":{"draws":77,"losses":192,"wins":133},"gpt-5.6-terra":{"draws":79,"losses":50,"wins":111},"gpt-6-astra":{"draws":18,"losses":201,"wins":31},"gpt-6-luna":{"draws":43,"losses":35,"wins":60},"gpt-6-sol":{"draws":15,"losses":101,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":109,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":74,"losses":3,"wins":61},"inclusionai/ling-3.0-flash":{"draws":42,"losses":24,"wins":86},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":76,"losses":35,"wins":153},"meta/muse-glimmer-30b":{"draws":68,"losses":30,"wins":98},"meta/muse-spark-1.2":{"draws":63,"losses":96,"wins":123},"meta/muse-spark-1.3":{"draws":49,"losses":72,"wins":87},"meta/muse-wonder":{"draws":29,"losses":66,"wins":43},"minimax/minimax-m3":{"draws":18,"losses":17,"wins":43},"mistralai/mistral-large-4-0":{"draws":30,"losses":16,"wins":40},"mistralai/mistral-medium-3-5":{"draws":50,"losses":20,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":20},"moonshotai/kimi-k3":{"draws":65,"losses":72,"wins":171},"nex-agi/nex-n2-pro":{"draws":20,"losses":14,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":7,"wins":71},"o3":{"draws":47,"losses":83,"wins":262},"openai/gpt-oss-120b":{"draws":81,"losses":25,"wins":90},"poolside/laguna-s-2.1":{"draws":93,"losses":22,"wins":131},"qwen/qwen3.7-max":{"draws":18,"losses":21,"wins":43},"qwen/qwen3.7-plus":{"draws":14,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":96,"wins":93},"qwen/qwen3.8-27b":{"draws":27,"losses":29,"wins":70},"qwen/qwen3.8-flash":{"draws":44,"losses":45,"wins":65},"qwen/qwen3.8-max":{"draws":76,"losses":84,"wins":92},"qwen/qwen3.8-max-0902":{"draws":34,"losses":44,"wins":60},"stealth/ox-alpha":{"draws":246,"losses":253,"wins":317},"stealth/space-bunny-alpha":{"draws":34,"losses":16,"wins":60},"stepfun/step-3.7-flash":{"draws":24,"losses":15,"wins":63},"stepfun/step-5-preview":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":32,"losses":15,"wins":33},"tencent/hy4-preview":{"draws":61,"losses":79,"wins":102},"thinkingmachines/inkling":{"draws":74,"losses":47,"wins":153},"thinkingmachines/inkling-small":{"draws":98,"losses":24,"wins":101},"unbiased/pareto-26.10-preview":{"draws":2,"losses":38,"wins":6},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":29},"x-ai/grok-4.5":{"draws":68,"losses":104,"wins":143},"x-ai/grok-4.6":{"draws":81,"losses":87,"wins":92},"x-ai/grok-4.7":{"draws":13,"losses":79,"wins":28},"x-ai/grok-build-0.1":{"draws":12,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":67,"losses":13,"wins":138},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":12,"wins":61},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":27,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":38,"wins":37},"z-ai/glm-5.2":{"draws":123,"losses":79,"wins":172},"z-ai/glm-5.3":{"draws":43,"losses":95,"wins":72},"z-ai/glm-5.3-flash":{"draws":51,"losses":90,"wins":105},"z-ai/glm-5.3-flashx":{"draws":34,"losses":54,"wins":50}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":32,"wins":25},"claude-fable-5":{"draws":22,"losses":63,"wins":11},"claude-fable-5-1":{"draws":4,"losses":104,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":12},"claude-opus-4-5":{"draws":95,"losses":109,"wins":66},"claude-opus-4-8":{"draws":46,"losses":75,"wins":43},"claude-opus-5":{"draws":52,"losses":182,"wins":20},"claude-opus-5-5":{"draws":5,"losses":97,"wins":2},"claude-sonnet-5":{"draws":41,"losses":32,"wins":33},"claude-sonnet-5-5":{"draws":18,"losses":60,"wins":18},"cohere/north-mini-code":{"draws":18,"losses":11,"wins":29},"deepseek/deepseek-v4-flash":{"draws":82,"losses":51,"wins":67},"deepseek/deepseek-v4-pro":{"draws":34,"losses":33,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":38,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":39,"wins":20},"fireworks/ember-1":{"draws":37,"losses":44,"wins":15},"gemini-3.1-pro-preview":{"draws":38,"losses":34,"wins":24},"google/gemini-3.1-flash-lite":{"draws":35,"losses":15,"wins":70},"google/gemini-3.5-flash":{"draws":48,"losses":57,"wins":31},"google/gemini-3.5-flash-lite":{"draws":82,"losses":54,"wins":80},"google/gemini-3.6-flash":{"draws":71,"losses":123,"wins":43},"google/gemini-3.8-flash":{"draws":28,"losses":63,"wins":19},"google/gemma-4-31b-it":{"draws":22,"losses":10,"wins":24},"gpt-4.1":{"draws":29,"losses":12,"wins":27},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":53,"losses":42,"wins":49},"gpt-5.4":{"draws":32,"losses":54,"wins":6},"gpt-5.4-mini":{"draws":28,"losses":18,"wins":18},"gpt-5.4-nano":{"draws":54,"losses":89,"wins":53},"gpt-5.5":{"draws":77,"losses":56,"wins":23},"gpt-5.6-luna":{"draws":38,"losses":33,"wins":29},"gpt-5.6-sol":{"draws":23,"losses":67,"wins":14},"gpt-5.6-terra":{"draws":42,"losses":35,"wins":23},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":43,"losses":40,"wins":13},"gpt-6-sol":{"draws":13,"losses":72,"wins":11},"gpt-6.1-sol":{"draws":5,"losses":87,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":15,"wins":23},"inclusionai/ling-3.0-flash":{"draws":59,"losses":20,"wins":43},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":71,"losses":44,"wins":61},"meta/muse-glimmer-30b":{"draws":43,"losses":11,"wins":30},"meta/muse-spark-1.2":{"draws":27,"losses":49,"wins":22},"meta/muse-spark-1.3":{"draws":19,"losses":66,"wins":13},"meta/muse-wonder":{"draws":24,"losses":62,"wins":10},"minimax/minimax-m3":{"draws":38,"losses":40,"wins":42},"mistralai/mistral-large-4-0":{"draws":28,"losses":20,"wins":12},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":25,"wins":11},"moonshotai/kimi-k3":{"draws":45,"losses":50,"wins":31},"nex-agi/nex-n2-pro":{"draws":40,"losses":22,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":82,"losses":40,"wins":40},"o3":{"draws":36,"losses":75,"wins":45},"openai/gpt-oss-120b":{"draws":37,"losses":21,"wins":32},"poolside/laguna-s-2.1":{"draws":71,"losses":34,"wins":49},"qwen/qwen3.7-max":{"draws":37,"losses":45,"wins":26},"qwen/qwen3.7-plus":{"draws":32,"losses":40,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":51,"wins":13},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":19},"qwen/qwen3.8-flash":{"draws":25,"losses":26,"wins":13},"qwen/qwen3.8-max":{"draws":47,"losses":40,"wins":19},"qwen/qwen3.8-max-0902":{"draws":38,"losses":44,"wins":14},"stealth/ox-alpha":{"draws":95,"losses":167,"wins":66},"stealth/space-bunny-alpha":{"draws":28,"losses":33,"wins":15},"stepfun/step-3.7-flash":{"draws":28,"losses":25,"wins":23},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":36,"losses":28,"wins":22},"tencent/hy4-preview":{"draws":35,"losses":48,"wins":13},"thinkingmachines/inkling":{"draws":71,"losses":49,"wins":54},"thinkingmachines/inkling-small":{"draws":45,"losses":26,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":31,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":11},"x-ai/grok-4.5":{"draws":47,"losses":69,"wins":16},"x-ai/grok-4.6":{"draws":34,"losses":50,"wins":16},"x-ai/grok-4.7":{"draws":14,"losses":66,"wins":4},"x-ai/grok-build-0.1":{"draws":28,"losses":16,"wins":26},"xiaomi/mimo-v2.5":{"draws":126,"losses":76,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":29,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":31,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":40,"wins":9},"z-ai/glm-5.2":{"draws":140,"losses":96,"wins":46},"z-ai/glm-5.3":{"draws":23,"losses":62,"wins":9},"z-ai/glm-5.3-flash":{"draws":35,"losses":51,"wins":16},"z-ai/glm-5.3-flashx":{"draws":27,"losses":56,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":58,"wins":49},"claude-fable-5":{"draws":19,"losses":112,"wins":15},"claude-fable-5-1":{"draws":1,"losses":155,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":76,"wins":39},"claude-opus-4-5":{"draws":105,"losses":174,"wins":115},"claude-opus-4-8":{"draws":52,"losses":147,"wins":59},"claude-opus-5":{"draws":43,"losses":306,"wins":37},"claude-opus-5-5":{"draws":6,"losses":152,"wins":2},"claude-sonnet-5":{"draws":37,"losses":74,"wins":41},"claude-sonnet-5-5":{"draws":21,"losses":105,"wins":18},"cohere/north-mini-code":{"draws":23,"losses":17,"wins":52},"deepseek/deepseek-v4-flash":{"draws":74,"losses":111,"wins":105},"deepseek/deepseek-v4-pro":{"draws":27,"losses":66,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":64,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":73,"wins":35},"fireworks/ember-1":{"draws":34,"losses":79,"wins":31},"gemini-3.1-pro-preview":{"draws":36,"losses":67,"wins":41},"google/gemini-3.1-flash-lite":{"draws":40,"losses":49,"wins":123},"google/gemini-3.5-flash":{"draws":46,"losses":119,"wins":57},"google/gemini-3.5-flash-lite":{"draws":82,"losses":132,"wins":104},"google/gemini-3.6-flash":{"draws":81,"losses":186,"wins":71},"google/gemini-3.8-flash":{"draws":32,"losses":93,"wins":27},"google/gemma-4-31b-it":{"draws":26,"losses":17,"wins":43},"gpt-4.1":{"draws":21,"losses":34,"wins":37},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":38,"losses":94,"wins":64},"gpt-5.4":{"draws":25,"losses":83,"wins":36},"gpt-5.4-mini":{"draws":54,"losses":53,"wins":89},"gpt-5.4-nano":{"draws":50,"losses":103,"wins":103},"gpt-5.5":{"draws":69,"losses":115,"wins":68},"gpt-5.6-luna":{"draws":40,"losses":63,"wins":49},"gpt-5.6-sol":{"draws":19,"losses":115,"wins":14},"gpt-5.6-terra":{"draws":27,"losses":76,"wins":39},"gpt-6-astra":{"draws":4,"losses":141,"wins":1},"gpt-6-luna":{"draws":30,"losses":72,"wins":42},"gpt-6-sol":{"draws":19,"losses":113,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":132,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":34,"losses":18,"wins":58},"inclusionai/ling-3.0-flash":{"draws":65,"losses":37,"wins":74},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":52,"losses":83,"wins":135},"meta/muse-glimmer-30b":{"draws":31,"losses":43,"wins":50},"meta/muse-spark-1.2":{"draws":21,"losses":71,"wins":44},"meta/muse-spark-1.3":{"draws":27,"losses":90,"wins":27},"meta/muse-wonder":{"draws":12,"losses":110,"wins":22},"minimax/minimax-m3":{"draws":46,"losses":52,"wins":76},"mistralai/mistral-large-4-0":{"draws":16,"losses":48,"wins":24},"mistralai/mistral-medium-3-5":{"draws":19,"losses":18,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":28,"wins":28},"moonshotai/kimi-k3":{"draws":47,"losses":92,"wins":39},"nex-agi/nex-n2-pro":{"draws":31,"losses":47,"wins":64},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":73,"losses":77,"wins":90},"o3":{"draws":28,"losses":132,"wins":120},"openai/gpt-oss-120b":{"draws":39,"losses":50,"wins":43},"poolside/laguna-s-2.1":{"draws":74,"losses":85,"wins":73},"qwen/qwen3.7-max":{"draws":51,"losses":71,"wins":54},"qwen/qwen3.7-plus":{"draws":36,"losses":65,"wins":63},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":89,"wins":32},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":34},"qwen/qwen3.8-flash":{"draws":31,"losses":46,"wins":29},"qwen/qwen3.8-max":{"draws":36,"losses":77,"wins":37},"qwen/qwen3.8-max-0902":{"draws":38,"losses":71,"wins":35},"stealth/ox-alpha":{"draws":85,"losses":246,"wins":121},"stealth/space-bunny-alpha":{"draws":26,"losses":47,"wins":39},"stepfun/step-3.7-flash":{"draws":22,"losses":43,"wins":67},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":36,"losses":61,"wins":31},"tencent/hy4-preview":{"draws":23,"losses":91,"wins":32},"thinkingmachines/inkling":{"draws":51,"losses":85,"wins":96},"thinkingmachines/inkling-small":{"draws":53,"losses":45,"wins":56},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":15,"wins":22},"x-ai/grok-4.5":{"draws":36,"losses":113,"wins":49},"x-ai/grok-4.6":{"draws":24,"losses":96,"wins":24},"x-ai/grok-4.7":{"draws":17,"losses":104,"wins":11},"x-ai/grok-build-0.1":{"draws":20,"losses":27,"wins":51},"xiaomi/mimo-v2.5":{"draws":118,"losses":160,"wins":198},"xiaomi/mimo-v2.5-pro":{"draws":38,"losses":75,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":50,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":66,"wins":17},"z-ai/glm-5.2":{"draws":113,"losses":163,"wins":138},"z-ai/glm-5.3":{"draws":20,"losses":99,"wins":25},"z-ai/glm-5.3-flash":{"draws":29,"losses":79,"wins":36},"z-ai/glm-5.3-flashx":{"draws":29,"losses":82,"wins":33}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":24,"wins":56},"claude-fable-5":{"draws":31,"losses":66,"wins":41},"claude-fable-5-1":{"draws":5,"losses":131,"wins":18},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":153,"losses":86,"wins":131},"claude-opus-4-8":{"draws":71,"losses":68,"wins":99},"claude-opus-5":{"draws":61,"losses":301,"wins":104},"claude-opus-5-5":{"draws":15,"losses":114,"wins":15},"claude-sonnet-5":{"draws":52,"losses":25,"wins":65},"claude-sonnet-5-5":{"draws":29,"losses":61,"wins":42},"cohere/north-mini-code":{"draws":25,"losses":8,"wins":45},"deepseek/deepseek-v4-flash":{"draws":100,"losses":23,"wins":119},"deepseek/deepseek-v4-pro":{"draws":42,"losses":30,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":36,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":45,"wins":42},"fireworks/ember-1":{"draws":42,"losses":41,"wins":49},"gemini-3.1-pro-preview":{"draws":38,"losses":32,"wins":62},"google/gemini-3.1-flash-lite":{"draws":44,"losses":9,"wins":89},"google/gemini-3.5-flash":{"draws":58,"losses":46,"wins":74},"google/gemini-3.5-flash-lite":{"draws":128,"losses":40,"wins":130},"google/gemini-3.6-flash":{"draws":107,"losses":115,"wins":116},"google/gemini-3.8-flash":{"draws":49,"losses":43,"wins":46},"google/gemma-4-31b-it":{"draws":30,"losses":6,"wins":40},"gpt-4.1":{"draws":27,"losses":19,"wins":38},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":72,"losses":48,"wins":92},"gpt-5.4":{"draws":44,"losses":45,"wins":43},"gpt-5.4-mini":{"draws":77,"losses":23,"wins":56},"gpt-5.4-nano":{"draws":69,"losses":68,"wins":115},"gpt-5.5":{"draws":76,"losses":48,"wins":48},"gpt-5.6-luna":{"draws":49,"losses":24,"wins":59},"gpt-5.6-sol":{"draws":30,"losses":60,"wins":48},"gpt-5.6-terra":{"draws":48,"losses":31,"wins":49},"gpt-6-astra":{"draws":5,"losses":119,"wins":10},"gpt-6-luna":{"draws":52,"losses":27,"wins":53},"gpt-6-sol":{"draws":20,"losses":83,"wins":29},"gpt-6.1-sol":{"draws":8,"losses":103,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":42},"inclusionai/ling-3.0-flash":{"draws":80,"losses":12,"wins":62},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":87,"losses":42,"wins":95},"meta/muse-glimmer-30b":{"draws":54,"losses":18,"wins":60},"meta/muse-spark-1.2":{"draws":29,"losses":44,"wins":63},"meta/muse-spark-1.3":{"draws":31,"losses":53,"wins":48},"meta/muse-wonder":{"draws":37,"losses":59,"wins":36},"minimax/minimax-m3":{"draws":40,"losses":21,"wins":67},"mistralai/mistral-large-4-0":{"draws":29,"losses":22,"wins":33},"mistralai/mistral-medium-3-5":{"draws":28,"losses":8,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":30,"losses":19,"wins":17},"moonshotai/kimi-k3":{"draws":50,"losses":59,"wins":49},"nex-agi/nex-n2-pro":{"draws":33,"losses":11,"wins":76},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":94,"losses":14,"wins":96},"o3":{"draws":55,"losses":50,"wins":135},"openai/gpt-oss-120b":{"draws":49,"losses":16,"wins":57},"poolside/laguna-s-2.1":{"draws":78,"losses":41,"wins":79},"qwen/qwen3.7-max":{"draws":55,"losses":29,"wins":58},"qwen/qwen3.7-plus":{"draws":53,"losses":12,"wins":59},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":45,"wins":49},"qwen/qwen3.8-27b":{"draws":28,"losses":26,"wins":44},"qwen/qwen3.8-flash":{"draws":37,"losses":21,"wins":42},"qwen/qwen3.8-max":{"draws":44,"losses":43,"wins":51},"qwen/qwen3.8-max-0902":{"draws":47,"losses":43,"wins":42},"stealth/ox-alpha":{"draws":129,"losses":172,"wins":161},"stealth/space-bunny-alpha":{"draws":41,"losses":19,"wins":46},"stepfun/step-3.7-flash":{"draws":29,"losses":15,"wins":72},"stepfun/step-5-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":67,"losses":17,"wins":52},"tencent/hy4-preview":{"draws":46,"losses":47,"wins":41},"thinkingmachines/inkling":{"draws":77,"losses":45,"wins":130},"thinkingmachines/inkling-small":{"draws":50,"losses":18,"wins":64},"unbiased/pareto-26.10-preview":{"draws":1,"losses":39,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":20},"x-ai/grok-4.5":{"draws":57,"losses":79,"wins":66},"x-ai/grok-4.6":{"draws":47,"losses":58,"wins":39},"x-ai/grok-4.7":{"draws":11,"losses":69,"wins":36},"x-ai/grok-build-0.1":{"draws":51,"losses":14,"wins":21},"xiaomi/mimo-v2.5":{"draws":164,"losses":34,"wins":156},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":27,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":26,"losses":23,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":37,"wins":31},"z-ai/glm-5.2":{"draws":148,"losses":75,"wins":157},"z-ai/glm-5.3":{"draws":33,"losses":73,"wins":26},"z-ai/glm-5.3-flash":{"draws":33,"losses":60,"wins":45},"z-ai/glm-5.3-flashx":{"draws":42,"losses":46,"wins":44}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":77,"losses":86,"wins":71},"claude-fable-5":{"draws":61,"losses":133,"wins":34},"claude-fable-5-1":{"draws":15,"losses":206,"wins":9},"claude-haiku-5-5":{"draws":40,"losses":74,"wins":24},"claude-opus-4-5":{"draws":142,"losses":159,"wins":105},"claude-opus-4-8":{"draws":42,"losses":62,"wins":30},"claude-opus-5":{"draws":26,"losses":204,"wins":26},"claude-opus-5-5":{"draws":17,"losses":134,"wins":5},"claude-sonnet-5":{"draws":134,"losses":165,"wins":107},"claude-sonnet-5-5":{"draws":33,"losses":83,"wins":28},"cohere/north-mini-code":{"draws":20,"losses":9,"wins":31},"deepseek/deepseek-v4-flash":{"draws":132,"losses":85,"wins":115},"deepseek/deepseek-v4-pro":{"draws":82,"losses":89,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":83,"losses":85,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":64,"wins":26},"fireworks/ember-1":{"draws":50,"losses":54,"wins":40},"gemini-3.1-pro-preview":{"draws":42,"losses":55,"wins":47},"google/gemini-3.1-flash-lite":{"draws":26,"losses":20,"wins":50},"google/gemini-3.5-flash":{"draws":91,"losses":120,"wins":75},"google/gemini-3.5-flash-lite":{"draws":230,"losses":214,"wins":274},"google/gemini-3.6-flash":{"draws":201,"losses":316,"wins":157},"google/gemini-3.8-flash":{"draws":57,"losses":133,"wins":48},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":30},"gpt-4.1":{"draws":17,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":40,"losses":52,"wins":36},"gpt-5.4":{"draws":141,"losses":200,"wins":56},"gpt-5.4-mini":{"draws":38,"losses":29,"wins":33},"gpt-5.4-nano":{"draws":40,"losses":49,"wins":63},"gpt-5.5":{"draws":49,"losses":59,"wins":24},"gpt-5.6-luna":{"draws":124,"losses":75,"wins":75},"gpt-5.6-sol":{"draws":59,"losses":247,"wins":66},"gpt-5.6-terra":{"draws":82,"losses":85,"wins":85},"gpt-6-astra":{"draws":25,"losses":177,"wins":2},"gpt-6-luna":{"draws":48,"losses":58,"wins":38},"gpt-6-sol":{"draws":24,"losses":106,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":125,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":94,"losses":33,"wins":61},"inclusionai/ling-3.0-flash":{"draws":70,"losses":43,"wins":57},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":85,"losses":83,"wins":120},"meta/muse-glimmer-30b":{"draws":103,"losses":61,"wins":74},"meta/muse-spark-1.2":{"draws":80,"losses":140,"wins":78},"meta/muse-spark-1.3":{"draws":56,"losses":106,"wins":46},"meta/muse-wonder":{"draws":28,"losses":91,"wins":25},"minimax/minimax-m3":{"draws":25,"losses":21,"wins":32},"mistralai/mistral-large-4-0":{"draws":32,"losses":43,"wins":15},"mistralai/mistral-medium-3-5":{"draws":66,"losses":24,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":103,"losses":137,"wins":70},"nex-agi/nex-n2-pro":{"draws":24,"losses":12,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":33,"wins":42},"o3":{"draws":70,"losses":189,"wins":147},"openai/gpt-oss-120b":{"draws":110,"losses":52,"wins":74},"poolside/laguna-s-2.1":{"draws":111,"losses":73,"wins":94},"qwen/qwen3.7-max":{"draws":31,"losses":32,"wins":21},"qwen/qwen3.7-plus":{"draws":26,"losses":21,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":95,"losses":98,"wins":49},"qwen/qwen3.8-27b":{"draws":37,"losses":55,"wins":32},"qwen/qwen3.8-flash":{"draws":60,"losses":62,"wins":50},"qwen/qwen3.8-max":{"draws":90,"losses":106,"wins":54},"qwen/qwen3.8-max-0902":{"draws":51,"losses":61,"wins":32},"stealth/ox-alpha":{"draws":260,"losses":355,"wins":187},"stealth/space-bunny-alpha":{"draws":43,"losses":40,"wins":31},"stepfun/step-3.7-flash":{"draws":30,"losses":33,"wins":41},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":28,"wins":21},"tencent/hy4-preview":{"draws":77,"losses":111,"wins":46},"thinkingmachines/inkling":{"draws":107,"losses":63,"wins":126},"thinkingmachines/inkling-small":{"draws":115,"losses":78,"wins":85},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":17},"x-ai/grok-4.5":{"draws":80,"losses":133,"wins":95},"x-ai/grok-4.6":{"draws":67,"losses":131,"wins":42},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":19,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":93,"losses":47,"wins":88},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":34,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":62,"wins":17},"z-ai/glm-5.2":{"draws":154,"losses":153,"wins":93},"z-ai/glm-5.3":{"draws":47,"losses":126,"wins":29},"z-ai/glm-5.3-flash":{"draws":75,"losses":113,"wins":52},"z-ai/glm-5.3-flashx":{"draws":42,"losses":73,"wins":29}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":28,"wins":147},"claude-fable-5":{"draws":35,"losses":124,"wins":111},"claude-fable-5-1":{"draws":25,"losses":249,"wins":44},"claude-haiku-5-5":{"draws":21,"losses":41,"wins":76},"claude-opus-4-5":{"draws":73,"losses":83,"wins":264},"claude-opus-4-8":{"draws":26,"losses":55,"wins":75},"claude-opus-5":{"draws":37,"losses":196,"wins":63},"claude-opus-5-5":{"draws":12,"losses":123,"wins":21},"claude-sonnet-5":{"draws":66,"losses":61,"wins":312},"claude-sonnet-5-5":{"draws":15,"losses":59,"wins":70},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":48},"deepseek/deepseek-v4-flash":{"draws":44,"losses":34,"wins":222},"deepseek/deepseek-v4-pro":{"draws":27,"losses":54,"wins":139},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":49,"wins":136},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":43,"wins":75},"fireworks/ember-1":{"draws":23,"losses":36,"wins":85},"gemini-3.1-pro-preview":{"draws":18,"losses":31,"wins":95},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":83},"google/gemini-3.5-flash":{"draws":33,"losses":73,"wins":178},"google/gemini-3.5-flash-lite":{"draws":92,"losses":57,"wins":497},"google/gemini-3.6-flash":{"draws":97,"losses":194,"wins":375},"google/gemini-3.8-flash":{"draws":37,"losses":99,"wins":136},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":67},"gpt-4.1":{"draws":10,"losses":6,"wins":34},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":20,"losses":19,"wins":93},"gpt-5.4":{"draws":77,"losses":133,"wins":192},"gpt-5.4-mini":{"draws":23,"losses":14,"wins":67},"gpt-5.4-nano":{"draws":19,"losses":14,"wins":115},"gpt-5.5":{"draws":30,"losses":48,"wins":60},"gpt-5.6-luna":{"draws":59,"losses":66,"wins":247},"gpt-5.6-sol":{"draws":40,"losses":132,"wins":132},"gpt-5.6-terra":{"draws":64,"losses":45,"wins":147},"gpt-6-astra":{"draws":29,"losses":226,"wins":27},"gpt-6-luna":{"draws":30,"losses":22,"wins":92},"gpt-6-sol":{"draws":13,"losses":85,"wins":46},"gpt-6.1-sol":{"draws":13,"losses":110,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":33,"losses":1,"wins":116},"inclusionai/ling-3.0-flash":{"draws":22,"losses":10,"wins":126},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":43,"losses":27,"wins":206},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":129},"meta/muse-spark-1.2":{"draws":37,"losses":72,"wins":193},"meta/muse-spark-1.3":{"draws":35,"losses":65,"wins":112},"meta/muse-wonder":{"draws":22,"losses":65,"wins":57},"minimax/minimax-m3":{"draws":15,"losses":4,"wins":61},"mistralai/mistral-large-4-0":{"draws":19,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":24,"losses":7,"wins":91},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":24},"moonshotai/kimi-k3":{"draws":53,"losses":67,"wins":192},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":12,"wins":100},"o3":{"draws":25,"losses":70,"wins":301},"openai/gpt-oss-120b":{"draws":29,"losses":13,"wins":148},"poolside/laguna-s-2.1":{"draws":47,"losses":10,"wins":211},"qwen/qwen3.7-max":{"draws":13,"losses":15,"wins":60},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":67,"wins":149},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":85},"qwen/qwen3.8-flash":{"draws":35,"losses":35,"wins":94},"qwen/qwen3.8-max":{"draws":50,"losses":61,"wins":146},"qwen/qwen3.8-max-0902":{"draws":23,"losses":34,"wins":87},"stealth/ox-alpha":{"draws":128,"losses":219,"wins":515},"stealth/space-bunny-alpha":{"draws":20,"losses":14,"wins":80},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":85},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":10,"wins":58},"tencent/hy4-preview":{"draws":35,"losses":83,"wins":132},"thinkingmachines/inkling":{"draws":47,"losses":25,"wins":206},"thinkingmachines/inkling-small":{"draws":35,"losses":25,"wins":171},"unbiased/pareto-26.10-preview":{"draws":3,"losses":43,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":32},"x-ai/grok-4.5":{"draws":41,"losses":106,"wins":181},"x-ai/grok-4.6":{"draws":53,"losses":105,"wins":118},"x-ai/grok-4.7":{"draws":16,"losses":66,"wins":44},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":34},"xiaomi/mimo-v2.5":{"draws":41,"losses":16,"wins":173},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":21,"wins":59},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":36,"wins":42},"z-ai/glm-5.2":{"draws":48,"losses":62,"wins":268},"z-ai/glm-5.3":{"draws":39,"losses":77,"wins":106},"z-ai/glm-5.3-flash":{"draws":46,"losses":90,"wins":132},"z-ai/glm-5.3-flashx":{"draws":23,"losses":41,"wins":80}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":68,"losses":43,"wins":107},"claude-fable-5":{"draws":68,"losses":150,"wins":40},"claude-fable-5-1":{"draws":22,"losses":244,"wins":6},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":106,"losses":109,"wins":85},"claude-opus-4-8":{"draws":36,"losses":61,"wins":37},"claude-opus-5":{"draws":30,"losses":197,"wins":21},"claude-opus-5-5":{"draws":9,"losses":138,"wins":3},"claude-sonnet-5":{"draws":94,"losses":73,"wins":81},"claude-sonnet-5-5":{"draws":34,"losses":74,"wins":30},"cohere/north-mini-code":{"draws":12,"losses":8,"wins":36},"deepseek/deepseek-v4-flash":{"draws":111,"losses":56,"wins":151},"deepseek/deepseek-v4-pro":{"draws":79,"losses":79,"wins":70},"deepseek/deepseek-v4-pro-0813":{"draws":73,"losses":73,"wins":86},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":50,"wins":34},"fireworks/ember-1":{"draws":44,"losses":58,"wins":36},"gemini-3.1-pro-preview":{"draws":47,"losses":47,"wins":44},"google/gemini-3.1-flash-lite":{"draws":30,"losses":10,"wins":66},"google/gemini-3.5-flash":{"draws":94,"losses":81,"wins":97},"google/gemini-3.5-flash-lite":{"draws":139,"losses":94,"wins":191},"google/gemini-3.6-flash":{"draws":132,"losses":176,"wins":116},"google/gemini-3.8-flash":{"draws":79,"losses":102,"wins":63},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":23,"losses":15,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":36,"losses":36,"wins":56},"gpt-5.4":{"draws":79,"losses":111,"wins":50},"gpt-5.4-mini":{"draws":42,"losses":23,"wins":35},"gpt-5.4-nano":{"draws":27,"losses":39,"wins":76},"gpt-5.5":{"draws":48,"losses":49,"wins":31},"gpt-5.6-luna":{"draws":82,"losses":85,"wins":85},"gpt-5.6-sol":{"draws":64,"losses":147,"wins":45},"gpt-5.6-terra":{"draws":60,"losses":52,"wins":52},"gpt-6-astra":{"draws":20,"losses":216,"wins":10},"gpt-6-luna":{"draws":40,"losses":57,"wins":41},"gpt-6-sol":{"draws":24,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":9,"losses":122,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":78,"losses":14,"wins":82},"inclusionai/ling-3.0-flash":{"draws":45,"losses":11,"wins":78},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":66,"losses":47,"wins":103},"meta/muse-glimmer-30b":{"draws":92,"losses":31,"wins":97},"meta/muse-spark-1.2":{"draws":68,"losses":81,"wins":59},"meta/muse-spark-1.3":{"draws":51,"losses":95,"wins":60},"meta/muse-wonder":{"draws":31,"losses":77,"wins":30},"minimax/minimax-m3":{"draws":23,"losses":15,"wins":44},"mistralai/mistral-large-4-0":{"draws":41,"losses":26,"wins":19},"mistralai/mistral-medium-3-5":{"draws":48,"losses":16,"wins":80},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":12,"wins":16},"moonshotai/kimi-k3":{"draws":65,"losses":80,"wins":69},"nex-agi/nex-n2-pro":{"draws":21,"losses":8,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":60},"o3":{"draws":57,"losses":108,"wins":117},"openai/gpt-oss-120b":{"draws":82,"losses":25,"wins":115},"poolside/laguna-s-2.1":{"draws":77,"losses":21,"wins":86},"qwen/qwen3.7-max":{"draws":29,"losses":18,"wins":47},"qwen/qwen3.7-plus":{"draws":27,"losses":12,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":94,"losses":109,"wins":53},"qwen/qwen3.8-27b":{"draws":44,"losses":41,"wins":41},"qwen/qwen3.8-flash":{"draws":52,"losses":50,"wins":52},"qwen/qwen3.8-max":{"draws":106,"losses":80,"wins":66},"qwen/qwen3.8-max-0902":{"draws":48,"losses":53,"wins":37},"stealth/ox-alpha":{"draws":248,"losses":319,"wins":227},"stealth/space-bunny-alpha":{"draws":37,"losses":32,"wins":39},"stepfun/step-3.7-flash":{"draws":30,"losses":20,"wins":50},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":34,"losses":16,"wins":30},"tencent/hy4-preview":{"draws":61,"losses":100,"wins":65},"thinkingmachines/inkling":{"draws":70,"losses":42,"wins":114},"thinkingmachines/inkling-small":{"draws":83,"losses":42,"wins":121},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":4},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":25},"x-ai/grok-4.5":{"draws":60,"losses":115,"wins":53},"x-ai/grok-4.6":{"draws":82,"losses":136,"wins":44},"x-ai/grok-4.7":{"draws":13,"losses":86,"wins":21},"x-ai/grok-build-0.1":{"draws":17,"losses":7,"wins":26},"xiaomi/mimo-v2.5":{"draws":86,"losses":15,"wins":127},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":14,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":32,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":44,"wins":24},"z-ai/glm-5.2":{"draws":176,"losses":87,"wins":145},"z-ai/glm-5.3":{"draws":63,"losses":108,"wins":35},"z-ai/glm-5.3-flash":{"draws":66,"losses":104,"wins":72},"z-ai/glm-5.3-flashx":{"draws":38,"losses":63,"wins":37}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":15,"wins":153},"claude-fable-5":{"draws":19,"losses":53,"wins":204},"claude-fable-5-1":{"draws":27,"losses":111,"wins":186},"claude-haiku-5-5":{"draws":10,"losses":7,"wins":121},"claude-opus-4-5":{"draws":23,"losses":19,"wins":280},"claude-opus-4-8":{"draws":11,"losses":11,"wins":120},"claude-opus-5":{"draws":30,"losses":65,"wins":169},"claude-opus-5-5":{"draws":17,"losses":65,"wins":74},"claude-sonnet-5":{"draws":12,"losses":16,"wins":232},"claude-sonnet-5-5":{"draws":13,"losses":26,"wins":105},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":14,"losses":6,"wins":262},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":183},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":1,"wins":198},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":6,"wins":122},"fireworks/ember-1":{"draws":10,"losses":6,"wins":128},"gemini-3.1-pro-preview":{"draws":10,"losses":4,"wins":130},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":27,"losses":11,"wins":246},"google/gemini-3.5-flash-lite":{"draws":21,"losses":2,"wins":345},"google/gemini-3.6-flash":{"draws":37,"losses":29,"wins":356},"google/gemini-3.8-flash":{"draws":29,"losses":18,"wins":227},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":80},"gpt-4.1":{"draws":5,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":2,"wins":115},"gpt-5.4":{"draws":18,"losses":31,"wins":201},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":141},"gpt-5.5":{"draws":5,"losses":10,"wins":119},"gpt-5.6-luna":{"draws":25,"losses":2,"wins":177},"gpt-5.6-sol":{"draws":29,"losses":27,"wins":226},"gpt-5.6-terra":{"draws":20,"losses":10,"wins":216},"gpt-6-astra":{"draws":18,"losses":87,"wins":87},"gpt-6-luna":{"draws":16,"losses":8,"wins":120},"gpt-6-sol":{"draws":15,"losses":26,"wins":103},"gpt-6.1-sol":{"draws":18,"losses":49,"wins":77},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":112},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":105},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":170},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":146},"meta/muse-spark-1.2":{"draws":12,"losses":6,"wins":184},"meta/muse-spark-1.3":{"draws":22,"losses":17,"wins":167},"meta/muse-wonder":{"draws":14,"losses":16,"wins":114},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":77},"mistralai/mistral-large-4-0":{"draws":9,"losses":5,"wins":76},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":87},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":34},"moonshotai/kimi-k3":{"draws":17,"losses":18,"wins":183},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":68},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":116},"o3":{"draws":8,"losses":2,"wins":266},"openai/gpt-oss-120b":{"draws":13,"losses":0,"wins":145},"poolside/laguna-s-2.1":{"draws":18,"losses":0,"wins":156},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":78},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":71},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":13,"wins":227},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":129},"qwen/qwen3.8-flash":{"draws":22,"losses":5,"wins":131},"qwen/qwen3.8-max":{"draws":26,"losses":4,"wins":210},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":129},"stealth/ox-alpha":{"draws":93,"losses":44,"wins":709},"stealth/space-bunny-alpha":{"draws":6,"losses":0,"wins":108},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":96},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":11,"losses":0,"wins":67},"tencent/hy4-preview":{"draws":20,"losses":14,"wins":210},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":197},"thinkingmachines/inkling-small":{"draws":15,"losses":0,"wins":187},"unbiased/pareto-26.10-preview":{"draws":6,"losses":20,"wins":22},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":34},"x-ai/grok-4.5":{"draws":10,"losses":22,"wins":184},"x-ai/grok-4.6":{"draws":22,"losses":28,"wins":224},"x-ai/grok-4.7":{"draws":12,"losses":22,"wins":92},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":209},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":80},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":81},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":27,"losses":13,"wins":312},"z-ai/glm-5.3":{"draws":34,"losses":15,"wins":173},"z-ai/glm-5.3-flash":{"draws":32,"losses":15,"wins":209},"z-ai/glm-5.3-flashx":{"draws":14,"losses":9,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":39,"wins":54},"claude-fable-5":{"draws":31,"losses":85,"wins":28},"claude-fable-5-1":{"draws":10,"losses":146,"wins":6},"claude-haiku-5-5":{"draws":36,"losses":63,"wins":39},"claude-opus-4-5":{"draws":79,"losses":80,"wins":75},"claude-opus-4-8":{"draws":35,"losses":61,"wins":36},"claude-opus-5":{"draws":47,"losses":178,"wins":21},"claude-opus-5-5":{"draws":16,"losses":139,"wins":1},"claude-sonnet-5":{"draws":38,"losses":50,"wins":56},"claude-sonnet-5-5":{"draws":32,"losses":68,"wins":44},"cohere/north-mini-code":{"draws":14,"losses":8,"wins":32},"deepseek/deepseek-v4-flash":{"draws":66,"losses":45,"wins":105},"deepseek/deepseek-v4-pro":{"draws":37,"losses":41,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":45,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":44,"losses":60,"wins":40},"fireworks/ember-1":{"draws":39,"losses":64,"wins":41},"gemini-3.1-pro-preview":{"draws":36,"losses":62,"wins":46},"google/gemini-3.1-flash-lite":{"draws":25,"losses":11,"wins":60},"google/gemini-3.5-flash":{"draws":52,"losses":69,"wins":59},"google/gemini-3.5-flash-lite":{"draws":83,"losses":55,"wins":114},"google/gemini-3.6-flash":{"draws":83,"losses":128,"wins":65},"google/gemini-3.8-flash":{"draws":42,"losses":69,"wins":33},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":38},"gpt-4.1":{"draws":11,"losses":19,"wins":18},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":39,"losses":42,"wins":45},"gpt-5.4":{"draws":43,"losses":60,"wins":35},"gpt-5.4-mini":{"draws":43,"losses":13,"wins":40},"gpt-5.4-nano":{"draws":30,"losses":42,"wins":72},"gpt-5.5":{"draws":52,"losses":53,"wins":27},"gpt-5.6-luna":{"draws":48,"losses":38,"wins":58},"gpt-5.6-sol":{"draws":30,"losses":92,"wins":22},"gpt-5.6-terra":{"draws":40,"losses":41,"wins":57},"gpt-6-astra":{"draws":16,"losses":120,"wins":8},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":24,"losses":101,"wins":19},"gpt-6.1-sol":{"draws":13,"losses":125,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":41,"losses":9,"wins":52},"inclusionai/ling-3.0-flash":{"draws":35,"losses":13,"wins":54},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":33,"wins":84},"meta/muse-glimmer-30b":{"draws":45,"losses":18,"wins":63},"meta/muse-spark-1.2":{"draws":40,"losses":60,"wins":38},"meta/muse-spark-1.3":{"draws":25,"losses":83,"wins":36},"meta/muse-wonder":{"draws":34,"losses":77,"wins":33},"minimax/minimax-m3":{"draws":22,"losses":14,"wins":42},"mistralai/mistral-large-4-0":{"draws":27,"losses":31,"wins":32},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":10,"wins":14},"moonshotai/kimi-k3":{"draws":45,"losses":51,"wins":42},"nex-agi/nex-n2-pro":{"draws":15,"losses":11,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":25,"wins":59},"o3":{"draws":35,"losses":63,"wins":100},"openai/gpt-oss-120b":{"draws":43,"losses":25,"wins":58},"poolside/laguna-s-2.1":{"draws":45,"losses":34,"wins":59},"qwen/qwen3.7-max":{"draws":22,"losses":27,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":12,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":59,"wins":48},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":37,"losses":57,"wins":50},"qwen/qwen3.8-max-0902":{"draws":41,"losses":56,"wins":47},"stealth/ox-alpha":{"draws":113,"losses":208,"wins":153},"stealth/space-bunny-alpha":{"draws":41,"losses":23,"wins":50},"stepfun/step-3.7-flash":{"draws":22,"losses":23,"wins":57},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":27,"losses":20,"wins":31},"tencent/hy4-preview":{"draws":39,"losses":64,"wins":35},"thinkingmachines/inkling":{"draws":56,"losses":40,"wins":96},"thinkingmachines/inkling-small":{"draws":40,"losses":32,"wins":72},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":35,"losses":66,"wins":43},"x-ai/grok-4.6":{"draws":39,"losses":81,"wins":24},"x-ai/grok-4.7":{"draws":10,"losses":96,"wins":20},"x-ai/grok-build-0.1":{"draws":20,"losses":4,"wins":24},"xiaomi/mimo-v2.5":{"draws":81,"losses":29,"wins":112},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":18,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":50,"wins":27},"z-ai/glm-5.2":{"draws":103,"losses":72,"wins":113},"z-ai/glm-5.3":{"draws":26,"losses":85,"wins":27},"z-ai/glm-5.3-flash":{"draws":40,"losses":70,"wins":34},"z-ai/glm-5.3-flashx":{"draws":30,"losses":72,"wins":42}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":102},"claude-fable-5":{"draws":19,"losses":43,"wins":82},"claude-fable-5-1":{"draws":14,"losses":110,"wins":38},"claude-haiku-5-5":{"draws":27,"losses":27,"wins":84},"claude-opus-4-5":{"draws":36,"losses":28,"wins":170},"claude-opus-4-8":{"draws":20,"losses":32,"wins":80},"claude-opus-5":{"draws":33,"losses":120,"wins":93},"claude-opus-5-5":{"draws":13,"losses":104,"wins":39},"claude-sonnet-5":{"draws":24,"losses":19,"wins":101},"claude-sonnet-5-5":{"draws":15,"losses":48,"wins":81},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":47},"deepseek/deepseek-v4-flash":{"draws":32,"losses":16,"wins":168},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":97},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":33,"wins":85},"fireworks/ember-1":{"draws":21,"losses":23,"wins":100},"gemini-3.1-pro-preview":{"draws":19,"losses":26,"wins":99},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":82},"google/gemini-3.5-flash":{"draws":27,"losses":26,"wins":127},"google/gemini-3.5-flash-lite":{"draws":39,"losses":22,"wins":191},"google/gemini-3.6-flash":{"draws":37,"losses":58,"wins":181},"google/gemini-3.8-flash":{"draws":22,"losses":33,"wins":89},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":73},"gpt-4.1":{"draws":7,"losses":7,"wins":34},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":15,"losses":16,"wins":95},"gpt-5.4":{"draws":15,"losses":22,"wins":101},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":72},"gpt-5.4-nano":{"draws":19,"losses":12,"wins":113},"gpt-5.5":{"draws":20,"losses":29,"wins":83},"gpt-5.6-luna":{"draws":24,"losses":14,"wins":106},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":85},"gpt-5.6-terra":{"draws":24,"losses":16,"wins":98},"gpt-6-astra":{"draws":15,"losses":103,"wins":26},"gpt-6-luna":{"draws":24,"losses":19,"wins":101},"gpt-6-sol":{"draws":14,"losses":41,"wins":41},"gpt-6.1-sol":{"draws":17,"losses":91,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":82},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":132},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":97},"meta/muse-spark-1.2":{"draws":18,"losses":24,"wins":96},"meta/muse-spark-1.3":{"draws":24,"losses":21,"wins":99},"meta/muse-wonder":{"draws":18,"losses":45,"wins":81},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"mistralai/mistral-large-4-0":{"draws":15,"losses":14,"wins":61},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":28},"moonshotai/kimi-k3":{"draws":14,"losses":24,"wins":100},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":106},"o3":{"draws":10,"losses":16,"wins":172},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":101},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":58},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":32,"wins":93},"qwen/qwen3.8-27b":{"draws":17,"losses":14,"wins":71},"qwen/qwen3.8-flash":{"draws":9,"losses":18,"wins":69},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":99},"qwen/qwen3.8-max-0902":{"draws":16,"losses":28,"wins":100},"stealth/ox-alpha":{"draws":62,"losses":72,"wins":340},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":87},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":85},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":8},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":58},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":92},"thinkingmachines/inkling":{"draws":25,"losses":13,"wins":154},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":118},"unbiased/pareto-26.10-preview":{"draws":5,"losses":34,"wins":9},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":32},"x-ai/grok-4.5":{"draws":21,"losses":30,"wins":93},"x-ai/grok-4.6":{"draws":21,"losses":30,"wins":93},"x-ai/grok-4.7":{"draws":13,"losses":63,"wins":50},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":38},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":170},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":63},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":18,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":24,"wins":54},"z-ai/glm-5.2":{"draws":45,"losses":31,"wins":212},"z-ai/glm-5.3":{"draws":21,"losses":47,"wins":70},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":20,"losses":37,"wins":87}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":114},"claude-fable-5":{"draws":11,"losses":32,"wins":101},"claude-fable-5-1":{"draws":13,"losses":72,"wins":77},"claude-haiku-5-5":{"draws":15,"losses":10,"wins":113},"claude-opus-4-5":{"draws":20,"losses":16,"wins":198},"claude-opus-4-8":{"draws":7,"losses":15,"wins":110},"claude-opus-5":{"draws":30,"losses":76,"wins":140},"claude-opus-5-5":{"draws":18,"losses":75,"wins":63},"claude-sonnet-5":{"draws":6,"losses":9,"wins":129},"claude-sonnet-5-5":{"draws":5,"losses":36,"wins":103},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":197},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":115},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":121},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":115},"fireworks/ember-1":{"draws":10,"losses":17,"wins":117},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":126},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":12,"losses":17,"wins":151},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":235},"google/gemini-3.6-flash":{"draws":18,"losses":28,"wins":230},"google/gemini-3.8-flash":{"draws":20,"losses":18,"wins":106},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":80},"gpt-4.1":{"draws":4,"losses":1,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":17},"gpt-5":{"draws":6,"losses":5,"wins":115},"gpt-5.4":{"draws":9,"losses":20,"wins":109},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":87},"gpt-5.4-nano":{"draws":7,"losses":5,"wins":132},"gpt-5.5":{"draws":8,"losses":21,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":13,"losses":21,"wins":110},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":122},"gpt-6-astra":{"draws":18,"losses":77,"wins":49},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":17,"losses":36,"wins":91},"gpt-6.1-sol":{"draws":6,"losses":45,"wins":45},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":93},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":98},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":10,"wins":140},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":117},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":111},"meta/muse-spark-1.3":{"draws":14,"losses":14,"wins":116},"meta/muse-wonder":{"draws":19,"losses":29,"wins":96},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":70},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":31},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":114},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":68},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":112},"o3":{"draws":3,"losses":9,"wins":186},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":118},"poolside/laguna-s-2.1":{"draws":9,"losses":1,"wins":128},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":75},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":113},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":82},"qwen/qwen3.8-max":{"draws":11,"losses":9,"wins":124},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":121},"stealth/ox-alpha":{"draws":44,"losses":30,"wins":400},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":100},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":99},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":68},"tencent/hy4-preview":{"draws":7,"losses":13,"wins":118},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":173},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":18},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":35},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":118},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":114},"x-ai/grok-4.7":{"draws":6,"losses":41,"wins":79},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":195},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":70},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":20,"wins":62},"z-ai/glm-5.2":{"draws":30,"losses":12,"wins":246},"z-ai/glm-5.3":{"draws":22,"losses":24,"wins":92},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":115},"z-ai/glm-5.3-flashx":{"draws":19,"losses":18,"wins":107}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":72,"losses":57,"wins":47},"claude-fable-5":{"draws":45,"losses":88,"wins":7},"claude-fable-5-1":{"draws":11,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":68,"wins":4},"claude-opus-4-5":{"draws":90,"losses":120,"wins":12},"claude-opus-4-8":{"draws":32,"losses":57,"wins":11},"claude-opus-5":{"draws":31,"losses":129,"wins":6},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":73,"losses":94,"wins":17},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":14,"losses":16,"wins":16},"deepseek/deepseek-v4-flash":{"draws":105,"losses":98,"wins":33},"deepseek/deepseek-v4-pro":{"draws":70,"losses":73,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":63,"losses":79,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":45,"losses":48,"wins":9},"fireworks/ember-1":{"draws":44,"losses":52,"wins":6},"gemini-3.1-pro-preview":{"draws":40,"losses":40,"wins":22},"google/gemini-3.1-flash-lite":{"draws":29,"losses":19,"wins":28},"google/gemini-3.5-flash":{"draws":73,"losses":98,"wins":21},"google/gemini-3.5-flash-lite":{"draws":151,"losses":136,"wins":61},"google/gemini-3.6-flash":{"draws":116,"losses":161,"wins":25},"google/gemini-3.8-flash":{"draws":60,"losses":92,"wins":6},"google/gemma-4-31b-it":{"draws":30,"losses":18,"wins":16},"gpt-4.1":{"draws":15,"losses":13,"wins":14},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":35,"losses":41,"wins":10},"gpt-5.4":{"draws":74,"losses":61,"wins":3},"gpt-5.4-mini":{"draws":34,"losses":23,"wins":15},"gpt-5.4-nano":{"draws":34,"losses":58,"wins":18},"gpt-5.5":{"draws":40,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":94,"losses":61,"wins":33},"gpt-5.6-sol":{"draws":33,"losses":116,"wins":1},"gpt-5.6-terra":{"draws":78,"losses":82,"wins":14},"gpt-6-astra":{"draws":12,"losses":112,"wins":0},"gpt-6-luna":{"draws":41,"losses":52,"wins":9},"gpt-6-sol":{"draws":16,"losses":82,"wins":4},"gpt-6.1-sol":{"draws":9,"losses":93,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":56,"losses":20,"wins":20},"inclusionai/ling-3.0-flash":{"draws":51,"losses":30,"wins":23},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":63,"losses":60,"wins":39},"meta/muse-glimmer-30b":{"draws":87,"losses":47,"wins":34},"meta/muse-spark-1.2":{"draws":54,"losses":78,"wins":16},"meta/muse-spark-1.3":{"draws":47,"losses":85,"wins":14},"meta/muse-wonder":{"draws":28,"losses":70,"wins":4},"minimax/minimax-m3":{"draws":26,"losses":21,"wins":13},"mistralai/mistral-large-4-0":{"draws":26,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":57,"losses":32,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":20,"wins":2},"moonshotai/kimi-k3":{"draws":70,"losses":72,"wins":14},"nex-agi/nex-n2-pro":{"draws":22,"losses":19,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":29,"wins":25},"o3":{"draws":44,"losses":133,"wins":23},"openai/gpt-oss-120b":{"draws":75,"losses":55,"wins":38},"poolside/laguna-s-2.1":{"draws":64,"losses":40,"wins":34},"qwen/qwen3.7-max":{"draws":29,"losses":26,"wins":15},"qwen/qwen3.7-plus":{"draws":22,"losses":28,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":84,"wins":13},"qwen/qwen3.8-27b":{"draws":23,"losses":55,"wins":8},"qwen/qwen3.8-flash":{"draws":60,"losses":52,"wins":12},"qwen/qwen3.8-max":{"draws":80,"losses":78,"wins":16},"qwen/qwen3.8-max-0902":{"draws":44,"losses":48,"wins":10},"stealth/ox-alpha":{"draws":170,"losses":272,"wins":64},"stealth/space-bunny-alpha":{"draws":37,"losses":35,"wins":10},"stepfun/step-3.7-flash":{"draws":28,"losses":40,"wins":8},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":17,"wins":15},"tencent/hy4-preview":{"draws":71,"losses":78,"wins":15},"thinkingmachines/inkling":{"draws":72,"losses":54,"wins":40},"thinkingmachines/inkling-small":{"draws":95,"losses":63,"wins":44},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":56,"losses":91,"wins":7},"x-ai/grok-4.6":{"draws":52,"losses":89,"wins":17},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":20,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":81,"losses":66,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":27,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":41,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":48,"wins":1},"z-ai/glm-5.2":{"draws":126,"losses":135,"wins":31},"z-ai/glm-5.3":{"draws":48,"losses":83,"wins":7},"z-ai/glm-5.3-flash":{"draws":56,"losses":87,"wins":17},"z-ai/glm-5.3-flashx":{"draws":29,"losses":68,"wins":5}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":52,"losses":52,"wins":22},"claude-fable-5":{"draws":22,"losses":87,"wins":5},"claude-fable-5-1":{"draws":7,"losses":117,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":61,"wins":5},"claude-opus-4-5":{"draws":96,"losses":130,"wins":40},"claude-opus-4-8":{"draws":59,"losses":83,"wins":0},"claude-opus-5":{"draws":46,"losses":167,"wins":11},"claude-opus-5-5":{"draws":7,"losses":107,"wins":0},"claude-sonnet-5":{"draws":59,"losses":103,"wins":18},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":26,"losses":14,"wins":24},"deepseek/deepseek-v4-flash":{"draws":102,"losses":81,"wins":57},"deepseek/deepseek-v4-pro":{"draws":44,"losses":59,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":55,"losses":50,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":50,"wins":9},"fireworks/ember-1":{"draws":45,"losses":53,"wins":4},"gemini-3.1-pro-preview":{"draws":39,"losses":53,"wins":10},"google/gemini-3.1-flash-lite":{"draws":42,"losses":39,"wins":33},"google/gemini-3.5-flash":{"draws":56,"losses":94,"wins":16},"google/gemini-3.5-flash-lite":{"draws":156,"losses":181,"wins":69},"google/gemini-3.6-flash":{"draws":176,"losses":196,"wins":52},"google/gemini-3.8-flash":{"draws":33,"losses":84,"wins":3},"google/gemma-4-31b-it":{"draws":32,"losses":13,"wins":13},"gpt-4.1":{"draws":29,"losses":36,"wins":1},"gpt-4.1-nano":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":49,"losses":45,"wins":38},"gpt-5.4":{"draws":42,"losses":86,"wins":24},"gpt-5.4-mini":{"draws":59,"losses":43,"wins":20},"gpt-5.4-nano":{"draws":65,"losses":74,"wins":37},"gpt-5.5":{"draws":80,"losses":62,"wins":12},"gpt-5.6-luna":{"draws":70,"losses":57,"wins":43},"gpt-5.6-sol":{"draws":22,"losses":126,"wins":10},"gpt-5.6-terra":{"draws":45,"losses":78,"wins":11},"gpt-6-astra":{"draws":6,"losses":105,"wins":1},"gpt-6-luna":{"draws":35,"losses":54,"wins":13},"gpt-6-sol":{"draws":15,"losses":79,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":98,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":51,"losses":23,"wins":30},"inclusionai/ling-3.0-flash":{"draws":48,"losses":40,"wins":40},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":114,"losses":97,"wins":63},"meta/muse-glimmer-30b":{"draws":67,"losses":37,"wins":20},"meta/muse-spark-1.2":{"draws":44,"losses":73,"wins":21},"meta/muse-spark-1.3":{"draws":20,"losses":87,"wins":13},"meta/muse-wonder":{"draws":18,"losses":79,"wins":5},"minimax/minimax-m3":{"draws":52,"losses":47,"wins":23},"mistralai/mistral-large-4-0":{"draws":28,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":36,"losses":31,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":22,"wins":8},"moonshotai/kimi-k3":{"draws":65,"losses":89,"wins":26},"nex-agi/nex-n2-pro":{"draws":50,"losses":30,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":74,"losses":38,"wins":32},"o3":{"draws":41,"losses":154,"wins":35},"openai/gpt-oss-120b":{"draws":49,"losses":55,"wins":14},"poolside/laguna-s-2.1":{"draws":110,"losses":76,"wins":30},"qwen/qwen3.7-max":{"draws":58,"losses":43,"wins":13},"qwen/qwen3.7-plus":{"draws":44,"losses":31,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":75,"wins":7},"qwen/qwen3.8-27b":{"draws":15,"losses":54,"wins":13},"qwen/qwen3.8-flash":{"draws":39,"losses":50,"wins":11},"qwen/qwen3.8-max":{"draws":54,"losses":62,"wins":21},"qwen/qwen3.8-max-0902":{"draws":39,"losses":54,"wins":9},"stealth/ox-alpha":{"draws":109,"losses":250,"wins":41},"stealth/space-bunny-alpha":{"draws":34,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":32,"losses":36,"wins":18},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":37,"losses":42,"wins":11},"tencent/hy4-preview":{"draws":43,"losses":76,"wins":9},"thinkingmachines/inkling":{"draws":98,"losses":91,"wins":57},"thinkingmachines/inkling-small":{"draws":63,"losses":50,"wins":28},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":10,"losses":11,"wins":5},"x-ai/grok-4.5":{"draws":62,"losses":145,"wins":19},"x-ai/grok-4.6":{"draws":44,"losses":73,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":75,"wins":5},"x-ai/grok-build-0.1":{"draws":26,"losses":36,"wins":4},"xiaomi/mimo-v2.5":{"draws":119,"losses":91,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":35,"losses":49,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":41,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":49,"wins":5},"z-ai/glm-5.2":{"draws":143,"losses":94,"wins":41},"z-ai/glm-5.3":{"draws":28,"losses":81,"wins":3},"z-ai/glm-5.3-flash":{"draws":40,"losses":71,"wins":9},"z-ai/glm-5.3-flashx":{"draws":35,"losses":59,"wins":8}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":63,"losses":83,"wins":54},"claude-fable-5":{"draws":34,"losses":132,"wins":30},"claude-fable-5-1":{"draws":6,"losses":189,"wins":6},"claude-haiku-5-5":{"draws":33,"losses":96,"wins":21},"claude-opus-4-5":{"draws":122,"losses":248,"wins":78},"claude-opus-4-8":{"draws":43,"losses":114,"wins":31},"claude-opus-5":{"draws":45,"losses":291,"wins":36},"claude-opus-5-5":{"draws":11,"losses":154,"wins":7},"claude-sonnet-5":{"draws":87,"losses":155,"wins":40},"claude-sonnet-5-5":{"draws":21,"losses":104,"wins":31},"cohere/north-mini-code":{"draws":29,"losses":19,"wins":50},"deepseek/deepseek-v4-flash":{"draws":103,"losses":131,"wins":98},"deepseek/deepseek-v4-pro":{"draws":54,"losses":111,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":75,"losses":90,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":85,"wins":34},"fireworks/ember-1":{"draws":49,"losses":88,"wins":19},"gemini-3.1-pro-preview":{"draws":37,"losses":75,"wins":44},"google/gemini-3.1-flash-lite":{"draws":38,"losses":50,"wins":96},"google/gemini-3.5-flash":{"draws":64,"losses":150,"wins":44},"google/gemini-3.5-flash-lite":{"draws":175,"losses":271,"wins":212},"google/gemini-3.6-flash":{"draws":171,"losses":363,"wins":102},"google/gemini-3.8-flash":{"draws":44,"losses":128,"wins":22},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":26,"losses":42,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":66,"losses":95,"wins":47},"gpt-5.4":{"draws":76,"losses":153,"wins":35},"gpt-5.4-mini":{"draws":71,"losses":61,"wins":44},"gpt-5.4-nano":{"draws":52,"losses":135,"wins":83},"gpt-5.5":{"draws":87,"losses":95,"wins":42},"gpt-5.6-luna":{"draws":85,"losses":120,"wins":83},"gpt-5.6-sol":{"draws":43,"losses":206,"wins":27},"gpt-5.6-terra":{"draws":66,"losses":103,"wins":47},"gpt-6-astra":{"draws":10,"losses":170,"wins":4},"gpt-6-luna":{"draws":39,"losses":84,"wins":33},"gpt-6-sol":{"draws":11,"losses":132,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":140,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":63,"losses":39,"wins":60},"inclusionai/ling-3.0-flash":{"draws":114,"losses":63,"wins":97},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":82,"losses":75,"wins":75},"meta/muse-glimmer-30b":{"draws":71,"losses":66,"wins":53},"meta/muse-spark-1.2":{"draws":54,"losses":127,"wins":55},"meta/muse-spark-1.3":{"draws":45,"losses":123,"wins":26},"meta/muse-wonder":{"draws":31,"losses":105,"wins":20},"minimax/minimax-m3":{"draws":31,"losses":49,"wins":56},"mistralai/mistral-large-4-0":{"draws":34,"losses":46,"wins":16},"mistralai/mistral-medium-3-5":{"draws":54,"losses":35,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":35,"wins":10},"moonshotai/kimi-k3":{"draws":94,"losses":153,"wins":45},"nex-agi/nex-n2-pro":{"draws":34,"losses":41,"wins":65},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":86,"losses":64,"wins":56},"o3":{"draws":61,"losses":249,"wins":104},"openai/gpt-oss-120b":{"draws":68,"losses":47,"wins":73},"poolside/laguna-s-2.1":{"draws":130,"losses":105,"wins":99},"qwen/qwen3.7-max":{"draws":53,"losses":69,"wins":24},"qwen/qwen3.7-plus":{"draws":32,"losses":43,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":122,"wins":30},"qwen/qwen3.8-27b":{"draws":25,"losses":78,"wins":21},"qwen/qwen3.8-flash":{"draws":56,"losses":60,"wins":30},"qwen/qwen3.8-max":{"draws":70,"losses":110,"wins":39},"qwen/qwen3.8-max-0902":{"draws":32,"losses":101,"wins":23},"stealth/ox-alpha":{"draws":160,"losses":410,"wins":100},"stealth/space-bunny-alpha":{"draws":40,"losses":57,"wins":29},"stepfun/step-3.7-flash":{"draws":36,"losses":54,"wins":44},"stepfun/step-5-preview":{"draws":7,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":47,"losses":46,"wins":39},"tencent/hy4-preview":{"draws":57,"losses":116,"wins":27},"thinkingmachines/inkling":{"draws":90,"losses":137,"wins":115},"thinkingmachines/inkling-small":{"draws":69,"losses":70,"wins":81},"unbiased/pareto-26.10-preview":{"draws":1,"losses":49,"wins":2},"upstage/solar-mini4":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.5":{"draws":75,"losses":220,"wins":59},"x-ai/grok-4.6":{"draws":61,"losses":117,"wins":30},"x-ai/grok-4.7":{"draws":8,"losses":120,"wins":8},"x-ai/grok-build-0.1":{"draws":31,"losses":31,"wins":28},"xiaomi/mimo-v2.5":{"draws":131,"losses":117,"wins":132},"xiaomi/mimo-v2.5-pro":{"draws":45,"losses":65,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":54,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":75,"wins":10},"z-ai/glm-5.2":{"draws":137,"losses":197,"wins":112},"z-ai/glm-5.3":{"draws":38,"losses":126,"wins":16},"z-ai/glm-5.3-flash":{"draws":49,"losses":114,"wins":41},"z-ai/glm-5.3-flashx":{"draws":36,"losses":101,"wins":19}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":92,"losses":68,"wins":64},"claude-fable-5":{"draws":48,"losses":120,"wins":14},"claude-fable-5-1":{"draws":13,"losses":161,"wins":1},"claude-haiku-5-5":{"draws":37,"losses":68,"wins":15},"claude-opus-4-5":{"draws":96,"losses":132,"wins":38},"claude-opus-4-8":{"draws":34,"losses":69,"wins":17},"claude-opus-5":{"draws":14,"losses":195,"wins":23},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":81,"losses":110,"wins":35},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":22,"losses":12,"wins":20},"deepseek/deepseek-v4-flash":{"draws":141,"losses":86,"wins":63},"deepseek/deepseek-v4-pro":{"draws":77,"losses":90,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":82,"losses":95,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":60,"wins":14},"fireworks/ember-1":{"draws":44,"losses":67,"wins":15},"gemini-3.1-pro-preview":{"draws":49,"losses":62,"wins":15},"google/gemini-3.1-flash-lite":{"draws":39,"losses":19,"wins":34},"google/gemini-3.5-flash":{"draws":82,"losses":118,"wins":44},"google/gemini-3.5-flash-lite":{"draws":180,"losses":149,"wins":97},"google/gemini-3.6-flash":{"draws":146,"losses":200,"wins":56},"google/gemini-3.8-flash":{"draws":61,"losses":112,"wins":25},"google/gemma-4-31b-it":{"draws":38,"losses":17,"wins":17},"gpt-4.1":{"draws":19,"losses":16,"wins":11},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":46,"losses":54,"wins":26},"gpt-5.4":{"draws":68,"losses":98,"wins":30},"gpt-5.4-mini":{"draws":43,"losses":30,"wins":11},"gpt-5.4-nano":{"draws":31,"losses":50,"wins":43},"gpt-5.5":{"draws":54,"losses":60,"wins":18},"gpt-5.6-luna":{"draws":103,"losses":74,"wins":61},"gpt-5.6-sol":{"draws":31,"losses":129,"wins":14},"gpt-5.6-terra":{"draws":92,"losses":97,"wins":31},"gpt-6-astra":{"draws":8,"losses":146,"wins":0},"gpt-6-luna":{"draws":45,"losses":63,"wins":18},"gpt-6-sol":{"draws":19,"losses":97,"wins":10},"gpt-6.1-sol":{"draws":8,"losses":117,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":87,"losses":34,"wins":47},"inclusionai/ling-3.0-flash":{"draws":67,"losses":20,"wins":37},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":71,"losses":53,"wins":66},"meta/muse-glimmer-30b":{"draws":74,"losses":35,"wins":35},"meta/muse-spark-1.2":{"draws":48,"losses":97,"wins":33},"meta/muse-spark-1.3":{"draws":62,"losses":93,"wins":25},"meta/muse-wonder":{"draws":26,"losses":85,"wins":15},"minimax/minimax-m3":{"draws":28,"losses":28,"wins":22},"mistralai/mistral-large-4-0":{"draws":27,"losses":36,"wins":19},"mistralai/mistral-medium-3-5":{"draws":70,"losses":20,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":19,"wins":10},"moonshotai/kimi-k3":{"draws":60,"losses":92,"wins":30},"nex-agi/nex-n2-pro":{"draws":27,"losses":14,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":27,"wins":30},"o3":{"draws":57,"losses":148,"wins":43},"openai/gpt-oss-120b":{"draws":96,"losses":63,"wins":53},"poolside/laguna-s-2.1":{"draws":90,"losses":59,"wins":43},"qwen/qwen3.7-max":{"draws":30,"losses":29,"wins":19},"qwen/qwen3.7-plus":{"draws":29,"losses":16,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":87,"losses":98,"wins":27},"qwen/qwen3.8-27b":{"draws":30,"losses":60,"wins":14},"qwen/qwen3.8-flash":{"draws":67,"losses":38,"wins":39},"qwen/qwen3.8-max":{"draws":69,"losses":90,"wins":47},"qwen/qwen3.8-max-0902":{"draws":46,"losses":68,"wins":12},"stealth/ox-alpha":{"draws":191,"losses":397,"wins":104},"stealth/space-bunny-alpha":{"draws":39,"losses":36,"wins":27},"stepfun/step-3.7-flash":{"draws":26,"losses":27,"wins":41},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":30,"wins":12},"tencent/hy4-preview":{"draws":81,"losses":105,"wins":20},"thinkingmachines/inkling":{"draws":80,"losses":67,"wins":77},"thinkingmachines/inkling-small":{"draws":115,"losses":46,"wins":83},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":9},"x-ai/grok-4.5":{"draws":51,"losses":107,"wins":24},"x-ai/grok-4.6":{"draws":69,"losses":107,"wins":20},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":13},"x-ai/grok-build-0.1":{"draws":18,"losses":16,"wins":10},"xiaomi/mimo-v2.5":{"draws":85,"losses":50,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":31,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":43,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":13},"z-ai/glm-5.2":{"draws":167,"losses":128,"wins":63},"z-ai/glm-5.3":{"draws":37,"losses":109,"wins":20},"z-ai/glm-5.3-flash":{"draws":67,"losses":116,"wins":23},"z-ai/glm-5.3-flashx":{"draws":36,"losses":71,"wins":19}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":52,"losses":53,"wins":83},"claude-fable-5":{"draws":34,"losses":122,"wins":48},"claude-fable-5-1":{"draws":13,"losses":205,"wins":12},"claude-haiku-5-5":{"draws":26,"losses":65,"wins":41},"claude-opus-4-5":{"draws":90,"losses":100,"wins":152},"claude-opus-4-8":{"draws":31,"losses":61,"wins":44},"claude-opus-5":{"draws":33,"losses":193,"wins":36},"claude-opus-5-5":{"draws":12,"losses":128,"wins":10},"claude-sonnet-5":{"draws":93,"losses":93,"wins":118},"claude-sonnet-5-5":{"draws":27,"losses":70,"wins":41},"cohere/north-mini-code":{"draws":3,"losses":12,"wins":43},"deepseek/deepseek-v4-flash":{"draws":71,"losses":51,"wins":142},"deepseek/deepseek-v4-pro":{"draws":33,"losses":74,"wins":83},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":62,"wins":75},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":50},"fireworks/ember-1":{"draws":37,"losses":52,"wins":49},"gemini-3.1-pro-preview":{"draws":34,"losses":48,"wins":56},"google/gemini-3.1-flash-lite":{"draws":24,"losses":10,"wins":66},"google/gemini-3.5-flash":{"draws":54,"losses":88,"wins":98},"google/gemini-3.5-flash-lite":{"draws":134,"losses":107,"wins":271},"google/gemini-3.6-flash":{"draws":103,"losses":201,"wins":218},"google/gemini-3.8-flash":{"draws":39,"losses":84,"wins":83},"google/gemma-4-31b-it":{"draws":23,"losses":17,"wins":40},"gpt-4.1":{"draws":19,"losses":10,"wins":23},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":34,"losses":35,"wins":67},"gpt-5.4":{"draws":63,"losses":123,"wins":96},"gpt-5.4-mini":{"draws":27,"losses":22,"wins":49},"gpt-5.4-nano":{"draws":21,"losses":44,"wins":71},"gpt-5.5":{"draws":29,"losses":63,"wins":44},"gpt-5.6-luna":{"draws":80,"losses":78,"wins":140},"gpt-5.6-sol":{"draws":37,"losses":193,"wins":72},"gpt-5.6-terra":{"draws":68,"losses":59,"wins":81},"gpt-6-astra":{"draws":12,"losses":184,"wins":6},"gpt-6-luna":{"draws":40,"losses":38,"wins":60},"gpt-6-sol":{"draws":18,"losses":96,"wins":24},"gpt-6.1-sol":{"draws":9,"losses":111,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":54,"losses":16,"wins":78},"inclusionai/ling-3.0-flash":{"draws":44,"losses":21,"wins":73},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":54,"losses":55,"wins":127},"meta/muse-glimmer-30b":{"draws":48,"losses":33,"wins":97},"meta/muse-spark-1.2":{"draws":36,"losses":54,"wins":54},"meta/muse-spark-1.3":{"draws":38,"losses":76,"wins":66},"meta/muse-wonder":{"draws":26,"losses":71,"wins":41},"minimax/minimax-m3":{"draws":18,"losses":11,"wins":59},"mistralai/mistral-large-4-0":{"draws":16,"losses":27,"wins":45},"mistralai/mistral-medium-3-5":{"draws":33,"losses":18,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":15,"wins":16},"moonshotai/kimi-k3":{"draws":53,"losses":98,"wins":89},"nex-agi/nex-n2-pro":{"draws":13,"losses":13,"wins":54},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":19,"wins":72},"o3":{"draws":34,"losses":148,"wins":136},"openai/gpt-oss-120b":{"draws":54,"losses":22,"wins":106},"poolside/laguna-s-2.1":{"draws":58,"losses":31,"wins":131},"qwen/qwen3.7-max":{"draws":11,"losses":20,"wins":61},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":55,"losses":85,"wins":66},"qwen/qwen3.8-27b":{"draws":24,"losses":51,"wins":41},"qwen/qwen3.8-flash":{"draws":40,"losses":44,"wins":56},"qwen/qwen3.8-max":{"draws":59,"losses":82,"wins":68},"qwen/qwen3.8-max-0902":{"draws":31,"losses":55,"wins":52},"stealth/ox-alpha":{"draws":164,"losses":317,"wins":215},"stealth/space-bunny-alpha":{"draws":31,"losses":26,"wins":53},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":61},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":23,"losses":16,"wins":49},"tencent/hy4-preview":{"draws":35,"losses":92,"wins":73},"thinkingmachines/inkling":{"draws":78,"losses":41,"wins":133},"thinkingmachines/inkling-small":{"draws":63,"losses":43,"wins":108},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":22},"x-ai/grok-4.5":{"draws":59,"losses":128,"wins":65},"x-ai/grok-4.6":{"draws":49,"losses":114,"wins":47},"x-ai/grok-4.7":{"draws":9,"losses":84,"wins":29},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":33},"xiaomi/mimo-v2.5":{"draws":66,"losses":28,"wins":128},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":29,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":27,"wins":48},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":52,"wins":28},"z-ai/glm-5.2":{"draws":84,"losses":104,"wins":166},"z-ai/glm-5.3":{"draws":29,"losses":88,"wins":59},"z-ai/glm-5.3-flash":{"draws":33,"losses":93,"wins":78},"z-ai/glm-5.3-flashx":{"draws":29,"losses":60,"wins":49}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":35,"wins":106},"claude-fable-5":{"draws":39,"losses":109,"wins":58},"claude-fable-5-1":{"draws":13,"losses":201,"wins":20},"claude-haiku-5-5":{"draws":26,"losses":61,"wins":51},"claude-opus-4-5":{"draws":66,"losses":71,"wins":155},"claude-opus-4-8":{"draws":28,"losses":54,"wins":58},"claude-opus-5":{"draws":39,"losses":173,"wins":54},"claude-opus-5-5":{"draws":8,"losses":134,"wins":14},"claude-sonnet-5":{"draws":64,"losses":54,"wins":102},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":54},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":50},"deepseek/deepseek-v4-flash":{"draws":57,"losses":43,"wins":182},"deepseek/deepseek-v4-pro":{"draws":33,"losses":58,"wins":107},"deepseek/deepseek-v4-pro-0813":{"draws":47,"losses":57,"wins":94},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":54,"wins":61},"fireworks/ember-1":{"draws":39,"losses":42,"wins":63},"gemini-3.1-pro-preview":{"draws":26,"losses":39,"wins":79},"google/gemini-3.1-flash-lite":{"draws":16,"losses":5,"wins":79},"google/gemini-3.5-flash":{"draws":50,"losses":70,"wins":134},"google/gemini-3.5-flash-lite":{"draws":84,"losses":67,"wins":219},"google/gemini-3.6-flash":{"draws":72,"losses":143,"wins":177},"google/gemini-3.8-flash":{"draws":45,"losses":90,"wins":77},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":53},"gpt-4.1":{"draws":18,"losses":4,"wins":30},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":31,"losses":29,"wins":76},"gpt-5.4":{"draws":49,"losses":87,"wins":72},"gpt-5.4-mini":{"draws":19,"losses":13,"wins":66},"gpt-5.4-nano":{"draws":27,"losses":27,"wins":90},"gpt-5.5":{"draws":31,"losses":48,"wins":53},"gpt-5.6-luna":{"draws":56,"losses":46,"wins":106},"gpt-5.6-sol":{"draws":35,"losses":112,"wins":65},"gpt-5.6-terra":{"draws":51,"losses":60,"wins":95},"gpt-6-astra":{"draws":22,"losses":167,"wins":17},"gpt-6-luna":{"draws":25,"losses":36,"wins":83},"gpt-6-sol":{"draws":24,"losses":99,"wins":21},"gpt-6.1-sol":{"draws":14,"losses":116,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":47,"losses":14,"wins":85},"inclusionai/ling-3.0-flash":{"draws":20,"losses":13,"wins":87},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":45,"losses":26,"wins":123},"meta/muse-glimmer-30b":{"draws":62,"losses":25,"wins":93},"meta/muse-spark-1.2":{"draws":38,"losses":66,"wins":76},"meta/muse-spark-1.3":{"draws":20,"losses":48,"wins":48},"meta/muse-wonder":{"draws":28,"losses":74,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":66},"mistralai/mistral-large-4-0":{"draws":24,"losses":22,"wins":44},"mistralai/mistral-medium-3-5":{"draws":31,"losses":6,"wins":83},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":43,"losses":58,"wins":95},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":57},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":14,"wins":87},"o3":{"draws":26,"losses":78,"wins":158},"openai/gpt-oss-120b":{"draws":49,"losses":23,"wins":112},"poolside/laguna-s-2.1":{"draws":46,"losses":35,"wins":95},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":48},"qwen/qwen3.7-plus":{"draws":15,"losses":16,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":83,"wins":85},"qwen/qwen3.8-27b":{"draws":21,"losses":42,"wins":57},"qwen/qwen3.8-flash":{"draws":41,"losses":42,"wins":69},"qwen/qwen3.8-max":{"draws":55,"losses":57,"wins":104},"qwen/qwen3.8-max-0902":{"draws":39,"losses":53,"wins":52},"stealth/ox-alpha":{"draws":148,"losses":256,"wins":308},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":69},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":83},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":14,"losses":16,"wins":56},"tencent/hy4-preview":{"draws":46,"losses":79,"wins":83},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":158},"thinkingmachines/inkling-small":{"draws":63,"losses":23,"wins":130},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":26},"x-ai/grok-4.5":{"draws":28,"losses":87,"wins":87},"x-ai/grok-4.6":{"draws":47,"losses":91,"wins":74},"x-ai/grok-4.7":{"draws":11,"losses":84,"wins":31},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":30},"xiaomi/mimo-v2.5":{"draws":57,"losses":21,"wins":156},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":63},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":52},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":48,"wins":33},"z-ai/glm-5.2":{"draws":79,"losses":84,"wins":187},"z-ai/glm-5.3":{"draws":36,"losses":96,"wins":56},"z-ai/glm-5.3-flash":{"draws":46,"losses":95,"wins":77},"z-ai/glm-5.3-flashx":{"draws":28,"losses":57,"wins":59}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":16,"wins":86},"claude-fable-5":{"draws":25,"losses":62,"wins":57},"claude-fable-5-1":{"draws":13,"losses":118,"wins":31},"claude-haiku-5-5":{"draws":30,"losses":29,"wins":79},"claude-opus-4-5":{"draws":47,"losses":48,"wins":139},"claude-opus-4-8":{"draws":26,"losses":44,"wins":62},"claude-opus-5":{"draws":29,"losses":141,"wins":76},"claude-opus-5-5":{"draws":9,"losses":116,"wins":31},"claude-sonnet-5":{"draws":31,"losses":28,"wins":85},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":54},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":47},"deepseek/deepseek-v4-flash":{"draws":37,"losses":31,"wins":148},"deepseek/deepseek-v4-pro":{"draws":23,"losses":30,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":27,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":71},"fireworks/ember-1":{"draws":38,"losses":30,"wins":76},"gemini-3.1-pro-preview":{"draws":26,"losses":24,"wins":94},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":84},"google/gemini-3.5-flash":{"draws":30,"losses":29,"wins":121},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":182},"google/gemini-3.6-flash":{"draws":50,"losses":71,"wins":155},"google/gemini-3.8-flash":{"draws":36,"losses":40,"wins":68},"google/gemma-4-31b-it":{"draws":17,"losses":7,"wins":60},"gpt-4.1":{"draws":7,"losses":6,"wins":35},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":23,"losses":23,"wins":80},"gpt-5.4":{"draws":29,"losses":43,"wins":66},"gpt-5.4-mini":{"draws":24,"losses":10,"wins":62},"gpt-5.4-nano":{"draws":12,"losses":22,"wins":110},"gpt-5.5":{"draws":37,"losses":36,"wins":59},"gpt-5.6-luna":{"draws":28,"losses":25,"wins":91},"gpt-5.6-sol":{"draws":22,"losses":57,"wins":65},"gpt-5.6-terra":{"draws":31,"losses":30,"wins":77},"gpt-6-astra":{"draws":14,"losses":114,"wins":16},"gpt-6-luna":{"draws":34,"losses":33,"wins":77},"gpt-6-sol":{"draws":18,"losses":81,"wins":45},"gpt-6.1-sol":{"draws":19,"losses":96,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":70},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":31,"losses":20,"wins":105},"meta/muse-glimmer-30b":{"draws":26,"losses":15,"wins":85},"meta/muse-spark-1.2":{"draws":26,"losses":41,"wins":71},"meta/muse-spark-1.3":{"draws":28,"losses":42,"wins":74},"meta/muse-wonder":{"draws":18,"losses":39,"wins":39},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":53},"mistralai/mistral-large-4-0":{"draws":19,"losses":23,"wins":48},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":62},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":26,"losses":27,"wins":85},"nex-agi/nex-n2-pro":{"draws":13,"losses":6,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":8,"wins":82},"o3":{"draws":13,"losses":34,"wins":151},"openai/gpt-oss-120b":{"draws":23,"losses":10,"wins":93},"poolside/laguna-s-2.1":{"draws":22,"losses":11,"wins":105},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":61},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":44,"wins":73},"qwen/qwen3.8-27b":{"draws":19,"losses":14,"wins":69},"qwen/qwen3.8-flash":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-max":{"draws":31,"losses":32,"wins":81},"qwen/qwen3.8-max-0902":{"draws":33,"losses":33,"wins":78},"stealth/ox-alpha":{"draws":93,"losses":128,"wins":253},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":68},"stepfun/step-3.7-flash":{"draws":12,"losses":10,"wins":80},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":15,"losses":12,"wins":51},"tencent/hy4-preview":{"draws":28,"losses":39,"wins":71},"thinkingmachines/inkling":{"draws":44,"losses":22,"wins":126},"thinkingmachines/inkling-small":{"draws":33,"losses":15,"wins":96},"unbiased/pareto-26.10-preview":{"draws":4,"losses":35,"wins":9},"upstage/solar-mini4":{"draws":3,"losses":1,"wins":32},"x-ai/grok-4.5":{"draws":29,"losses":36,"wins":79},"x-ai/grok-4.6":{"draws":41,"losses":41,"wins":62},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":38},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":33},"xiaomi/mimo-v2.5":{"draws":45,"losses":17,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":56},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":63},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":36,"wins":43},"z-ai/glm-5.2":{"draws":65,"losses":45,"wins":178},"z-ai/glm-5.3":{"draws":17,"losses":59,"wins":62},"z-ai/glm-5.3-flash":{"draws":30,"losses":43,"wins":71},"z-ai/glm-5.3-flashx":{"draws":34,"losses":37,"wins":73}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":41,"wins":17},"claude-fable-5":{"draws":20,"losses":54,"wins":6},"claude-fable-5-1":{"draws":2,"losses":83,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":53,"wins":15},"claude-opus-4-5":{"draws":60,"losses":120,"wins":22},"claude-opus-4-8":{"draws":33,"losses":79,"wins":18},"claude-opus-5":{"draws":25,"losses":169,"wins":14},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":21,"losses":46,"wins":17},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":11,"losses":19,"wins":26},"deepseek/deepseek-v4-flash":{"draws":54,"losses":58,"wins":60},"deepseek/deepseek-v4-pro":{"draws":16,"losses":47,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":46,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":42,"wins":17},"fireworks/ember-1":{"draws":19,"losses":54,"wins":5},"gemini-3.1-pro-preview":{"draws":19,"losses":37,"wins":22},"google/gemini-3.1-flash-lite":{"draws":29,"losses":41,"wins":50},"google/gemini-3.5-flash":{"draws":31,"losses":51,"wins":28},"google/gemini-3.5-flash-lite":{"draws":51,"losses":67,"wins":54},"google/gemini-3.6-flash":{"draws":43,"losses":111,"wins":30},"google/gemini-3.8-flash":{"draws":19,"losses":58,"wins":7},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":18,"losses":28,"wins":14},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":36,"losses":54,"wins":30},"gpt-5.4":{"draws":18,"losses":43,"wins":17},"gpt-5.4-mini":{"draws":38,"losses":42,"wins":40},"gpt-5.4-nano":{"draws":46,"losses":76,"wins":52},"gpt-5.5":{"draws":40,"losses":67,"wins":21},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":21},"gpt-5.6-sol":{"draws":15,"losses":61,"wins":4},"gpt-5.6-terra":{"draws":23,"losses":44,"wins":15},"gpt-6-astra":{"draws":1,"losses":77,"wins":2},"gpt-6-luna":{"draws":22,"losses":42,"wins":14},"gpt-6-sol":{"draws":9,"losses":62,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":70,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":13,"wins":21},"inclusionai/ling-3.0-flash":{"draws":52,"losses":23,"wins":47},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":31,"losses":56,"wins":49},"meta/muse-glimmer-30b":{"draws":28,"losses":22,"wins":28},"meta/muse-spark-1.2":{"draws":18,"losses":59,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":66,"wins":7},"meta/muse-wonder":{"draws":13,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":13},"mistralai/mistral-medium-3-5":{"draws":15,"losses":18,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":25,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":58,"wins":16},"nex-agi/nex-n2-pro":{"draws":24,"losses":21,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":39,"wins":49},"o3":{"draws":26,"losses":84,"wins":30},"openai/gpt-oss-120b":{"draws":25,"losses":30,"wins":21},"poolside/laguna-s-2.1":{"draws":46,"losses":48,"wins":38},"qwen/qwen3.7-max":{"draws":41,"losses":45,"wins":20},"qwen/qwen3.7-plus":{"draws":24,"losses":33,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":53,"wins":9},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":28,"wins":19},"qwen/qwen3.8-max":{"draws":25,"losses":41,"wins":14},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":8},"stealth/ox-alpha":{"draws":64,"losses":155,"wins":41},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":13},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":32},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":34,"losses":40,"wins":22},"tencent/hy4-preview":{"draws":19,"losses":52,"wins":7},"thinkingmachines/inkling":{"draws":35,"losses":57,"wins":50},"thinkingmachines/inkling-small":{"draws":25,"losses":21,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":26,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":10,"wins":6},"x-ai/grok-4.5":{"draws":20,"losses":80,"wins":8},"x-ai/grok-4.6":{"draws":24,"losses":56,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":61,"wins":9},"x-ai/grok-build-0.1":{"draws":20,"losses":25,"wins":17},"xiaomi/mimo-v2.5":{"draws":92,"losses":80,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":39,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":28,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":37,"wins":8},"z-ai/glm-5.2":{"draws":72,"losses":88,"wins":46},"z-ai/glm-5.3":{"draws":17,"losses":53,"wins":6},"z-ai/glm-5.3-flash":{"draws":20,"losses":44,"wins":14},"z-ai/glm-5.3-flashx":{"draws":20,"losses":46,"wins":12}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":33},"claude-fable-5":{"draws":18,"losses":49,"wins":23},"claude-fable-5-1":{"draws":4,"losses":92,"wins":6},"claude-haiku-5-5":{"draws":30,"losses":28,"wins":28},"claude-opus-4-5":{"draws":46,"losses":53,"wins":47},"claude-opus-4-8":{"draws":18,"losses":31,"wins":33},"claude-opus-5":{"draws":24,"losses":119,"wins":19},"claude-opus-5-5":{"draws":14,"losses":79,"wins":5},"claude-sonnet-5":{"draws":27,"losses":39,"wins":24},"claude-sonnet-5-5":{"draws":23,"losses":43,"wins":24},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":20},"deepseek/deepseek-v4-flash":{"draws":45,"losses":20,"wins":69},"deepseek/deepseek-v4-pro":{"draws":26,"losses":26,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":28,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":31,"wins":26},"fireworks/ember-1":{"draws":26,"losses":31,"wins":33},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":35},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":38,"losses":35,"wins":39},"google/gemini-3.5-flash-lite":{"draws":52,"losses":29,"wins":75},"google/gemini-3.6-flash":{"draws":41,"losses":72,"wins":59},"google/gemini-3.8-flash":{"draws":28,"losses":36,"wins":26},"google/gemma-4-31b-it":{"draws":19,"losses":9,"wins":24},"gpt-4.1":{"draws":12,"losses":8,"wins":10},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":5},"gpt-5":{"draws":30,"losses":16,"wins":34},"gpt-5.4":{"draws":30,"losses":40,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":12,"wins":20},"gpt-5.4-nano":{"draws":16,"losses":24,"wins":48},"gpt-5.5":{"draws":29,"losses":33,"wins":22},"gpt-5.6-luna":{"draws":32,"losses":15,"wins":43},"gpt-5.6-sol":{"draws":19,"losses":51,"wins":20},"gpt-5.6-terra":{"draws":41,"losses":19,"wins":26},"gpt-6-astra":{"draws":9,"losses":76,"wins":5},"gpt-6-luna":{"draws":27,"losses":32,"wins":31},"gpt-6-sol":{"draws":15,"losses":61,"wins":14},"gpt-6.1-sol":{"draws":9,"losses":70,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":27},"inclusionai/ling-3.0-flash":{"draws":28,"losses":9,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":16,"wins":46},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":36},"meta/muse-spark-1.2":{"draws":16,"losses":45,"wins":27},"meta/muse-spark-1.3":{"draws":24,"losses":44,"wins":22},"meta/muse-wonder":{"draws":19,"losses":48,"wins":23},"minimax/minimax-m3":{"draws":12,"losses":13,"wins":25},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":7,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":30,"losses":31,"wins":27},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":18,"wins":32},"o3":{"draws":28,"losses":39,"wins":53},"openai/gpt-oss-120b":{"draws":31,"losses":14,"wins":35},"poolside/laguna-s-2.1":{"draws":32,"losses":20,"wins":36},"qwen/qwen3.7-max":{"draws":21,"losses":5,"wins":26},"qwen/qwen3.7-plus":{"draws":13,"losses":2,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":42,"wins":26},"qwen/qwen3.8-27b":{"draws":19,"losses":21,"wins":22},"qwen/qwen3.8-flash":{"draws":22,"losses":17,"wins":21},"qwen/qwen3.8-max":{"draws":31,"losses":29,"wins":30},"qwen/qwen3.8-max-0902":{"draws":32,"losses":40,"wins":18},"stealth/ox-alpha":{"draws":98,"losses":120,"wins":82},"stealth/space-bunny-alpha":{"draws":26,"losses":14,"wins":32},"stepfun/step-3.7-flash":{"draws":20,"losses":9,"wins":33},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":20,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":22,"losses":36,"wins":28},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":58},"thinkingmachines/inkling-small":{"draws":31,"losses":14,"wins":45},"unbiased/pareto-26.10-preview":{"draws":3,"losses":24,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":13},"x-ai/grok-4.5":{"draws":20,"losses":41,"wins":29},"x-ai/grok-4.6":{"draws":30,"losses":43,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":50,"wins":16},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":58,"losses":19,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":11,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":20,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":28,"wins":19},"z-ai/glm-5.2":{"draws":71,"losses":37,"wins":72},"z-ai/glm-5.3":{"draws":15,"losses":51,"wins":20},"z-ai/glm-5.3-flash":{"draws":26,"losses":42,"wins":22},"z-ai/glm-5.3-flashx":{"draws":29,"losses":34,"wins":27}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":47,"wins":35},"claude-fable-5":{"draws":37,"losses":68,"wins":11},"claude-fable-5-1":{"draws":6,"losses":97,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":54,"wins":4},"claude-opus-4-5":{"draws":52,"losses":109,"wins":15},"claude-opus-4-8":{"draws":27,"losses":47,"wins":6},"claude-opus-5":{"draws":22,"losses":112,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":63,"losses":72,"wins":19},"claude-sonnet-5-5":{"draws":19,"losses":57,"wins":8},"cohere/north-mini-code":{"draws":12,"losses":11,"wins":13},"deepseek/deepseek-v4-flash":{"draws":83,"losses":67,"wins":40},"deepseek/deepseek-v4-pro":{"draws":44,"losses":80,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":68,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":45,"wins":9},"fireworks/ember-1":{"draws":27,"losses":51,"wins":6},"gemini-3.1-pro-preview":{"draws":32,"losses":42,"wins":10},"google/gemini-3.1-flash-lite":{"draws":14,"losses":18,"wins":26},"google/gemini-3.5-flash":{"draws":49,"losses":81,"wins":26},"google/gemini-3.5-flash-lite":{"draws":105,"losses":119,"wins":60},"google/gemini-3.6-flash":{"draws":97,"losses":125,"wins":28},"google/gemini-3.8-flash":{"draws":37,"losses":80,"wins":7},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":15,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":27,"losses":34,"wins":17},"gpt-5.4":{"draws":50,"losses":56,"wins":20},"gpt-5.4-mini":{"draws":24,"losses":24,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":47,"wins":18},"gpt-5.5":{"draws":28,"losses":42,"wins":8},"gpt-5.6-luna":{"draws":66,"losses":68,"wins":24},"gpt-5.6-sol":{"draws":24,"losses":91,"wins":7},"gpt-5.6-terra":{"draws":48,"losses":80,"wins":16},"gpt-6-astra":{"draws":7,"losses":87,"wins":0},"gpt-6-luna":{"draws":30,"losses":47,"wins":7},"gpt-6-sol":{"draws":7,"losses":73,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":81,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":57,"losses":35,"wins":32},"inclusionai/ling-3.0-flash":{"draws":36,"losses":21,"wins":31},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":54,"losses":51,"wins":35},"meta/muse-glimmer-30b":{"draws":70,"losses":54,"wins":20},"meta/muse-spark-1.2":{"draws":33,"losses":71,"wins":18},"meta/muse-spark-1.3":{"draws":31,"losses":83,"wins":6},"meta/muse-wonder":{"draws":16,"losses":62,"wins":6},"minimax/minimax-m3":{"draws":15,"losses":21,"wins":18},"mistralai/mistral-large-4-0":{"draws":22,"losses":23,"wins":7},"mistralai/mistral-medium-3-5":{"draws":24,"losses":12,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":42,"losses":73,"wins":15},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":26,"wins":12},"o3":{"draws":37,"losses":107,"wins":20},"openai/gpt-oss-120b":{"draws":69,"losses":45,"wins":28},"poolside/laguna-s-2.1":{"draws":57,"losses":49,"wins":26},"qwen/qwen3.7-max":{"draws":26,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":19,"losses":14,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":94,"wins":6},"qwen/qwen3.8-27b":{"draws":21,"losses":42,"wins":5},"qwen/qwen3.8-flash":{"draws":39,"losses":48,"wins":11},"qwen/qwen3.8-max":{"draws":50,"losses":79,"wins":17},"qwen/qwen3.8-max-0902":{"draws":29,"losses":49,"wins":6},"stealth/ox-alpha":{"draws":130,"losses":258,"wins":72},"stealth/space-bunny-alpha":{"draws":24,"losses":30,"wins":12},"stepfun/step-3.7-flash":{"draws":21,"losses":25,"wins":12},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":50,"losses":75,"wins":11},"thinkingmachines/inkling":{"draws":52,"losses":63,"wins":29},"thinkingmachines/inkling-small":{"draws":79,"losses":59,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":15,"wins":1},"x-ai/grok-4.5":{"draws":32,"losses":78,"wins":14},"x-ai/grok-4.6":{"draws":49,"losses":71,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":13,"wins":3},"xiaomi/mimo-v2.5":{"draws":60,"losses":43,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":24,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":33,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":42,"wins":7},"z-ai/glm-5.2":{"draws":106,"losses":103,"wins":31},"z-ai/glm-5.3":{"draws":27,"losses":81,"wins":8},"z-ai/glm-5.3-flash":{"draws":45,"losses":66,"wins":21},"z-ai/glm-5.3-flashx":{"draws":21,"losses":55,"wins":8}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":16},"claude-fable-5":{"draws":9,"losses":21,"wins":8},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":29,"losses":50,"wins":29},"claude-opus-4-8":{"draws":16,"losses":32,"wins":14},"claude-opus-5":{"draws":13,"losses":112,"wins":7},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":12},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"fireworks/ember-1":{"draws":12,"losses":13,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":36},"google/gemini-3.5-flash":{"draws":13,"losses":16,"wins":19},"google/gemini-3.5-flash-lite":{"draws":18,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":26,"losses":43,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":11,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":21,"wins":24},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":11,"wins":25},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":28},"gpt-5.5":{"draws":30,"losses":17,"wins":19},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":12},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":25},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":20},"nex-agi/nex-n2-pro":{"draws":12,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":33},"o3":{"draws":7,"losses":29,"wins":34},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":17},"poolside/laguna-s-2.1":{"draws":17,"losses":28,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":16,"wins":12},"qwen/qwen3.7-plus":{"draws":21,"losses":4,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":25,"losses":50,"wins":31},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":8},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":34},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":22},"xiaomi/mimo-v2.5":{"draws":50,"losses":22,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":23,"losses":43,"wins":42},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":59,"losses":48,"wins":95},"claude-fable-5":{"draws":40,"losses":138,"wins":36},"claude-fable-5-1":{"draws":14,"losses":213,"wins":15},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":40},"claude-opus-4-5":{"draws":137,"losses":116,"wins":141},"claude-opus-4-8":{"draws":41,"losses":56,"wins":53},"claude-opus-5":{"draws":49,"losses":212,"wins":53},"claude-opus-5-5":{"draws":5,"losses":132,"wins":13},"claude-sonnet-5":{"draws":104,"losses":80,"wins":136},"claude-sonnet-5-5":{"draws":28,"losses":63,"wins":47},"cohere/north-mini-code":{"draws":13,"losses":11,"wins":36},"deepseek/deepseek-v4-flash":{"draws":80,"losses":65,"wins":133},"deepseek/deepseek-v4-pro":{"draws":50,"losses":62,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":61,"losses":72,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":57,"wins":41},"fireworks/ember-1":{"draws":45,"losses":56,"wins":37},"gemini-3.1-pro-preview":{"draws":36,"losses":40,"wins":62},"google/gemini-3.1-flash-lite":{"draws":24,"losses":12,"wins":58},"google/gemini-3.5-flash":{"draws":86,"losses":90,"wins":78},"google/gemini-3.5-flash-lite":{"draws":218,"losses":126,"wins":298},"google/gemini-3.6-flash":{"draws":194,"losses":260,"wins":212},"google/gemini-3.8-flash":{"draws":59,"losses":113,"wins":48},"google/gemma-4-31b-it":{"draws":29,"losses":13,"wins":38},"gpt-4.1":{"draws":14,"losses":13,"wins":25},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":38,"losses":44,"wins":50},"gpt-5.4":{"draws":65,"losses":171,"wins":72},"gpt-5.4-mini":{"draws":45,"losses":31,"wins":50},"gpt-5.4-nano":{"draws":47,"losses":39,"wins":92},"gpt-5.5":{"draws":50,"losses":49,"wins":59},"gpt-5.6-luna":{"draws":103,"losses":70,"wins":137},"gpt-5.6-sol":{"draws":53,"losses":192,"wins":67},"gpt-5.6-terra":{"draws":65,"losses":69,"wins":80},"gpt-6-astra":{"draws":17,"losses":183,"wins":18},"gpt-6-luna":{"draws":45,"losses":42,"wins":51},"gpt-6-sol":{"draws":14,"losses":100,"wins":24},"gpt-6.1-sol":{"draws":10,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":70,"losses":14,"wins":72},"inclusionai/ling-3.0-flash":{"draws":65,"losses":26,"wins":89},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":94,"losses":45,"wins":153},"meta/muse-glimmer-30b":{"draws":60,"losses":30,"wins":92},"meta/muse-spark-1.2":{"draws":53,"losses":89,"wins":98},"meta/muse-spark-1.3":{"draws":43,"losses":95,"wins":58},"meta/muse-wonder":{"draws":26,"losses":85,"wins":27},"minimax/minimax-m3":{"draws":20,"losses":16,"wins":58},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":31},"mistralai/mistral-medium-3-5":{"draws":42,"losses":15,"wins":73},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":20,"wins":12},"moonshotai/kimi-k3":{"draws":68,"losses":56,"wins":56},"nex-agi/nex-n2-pro":{"draws":20,"losses":13,"wins":57},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":31,"wins":54},"o3":{"draws":56,"losses":168,"wins":152},"openai/gpt-oss-120b":{"draws":58,"losses":30,"wins":96},"poolside/laguna-s-2.1":{"draws":106,"losses":31,"wins":137},"qwen/qwen3.7-max":{"draws":26,"losses":24,"wins":54},"qwen/qwen3.7-plus":{"draws":33,"losses":22,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":65,"losses":79,"wins":80},"qwen/qwen3.8-27b":{"draws":31,"losses":32,"wins":53},"qwen/qwen3.8-flash":{"draws":51,"losses":45,"wins":52},"qwen/qwen3.8-max":{"draws":59,"losses":80,"wins":78},"qwen/qwen3.8-max-0902":{"draws":36,"losses":68,"wins":34},"stealth/ox-alpha":{"draws":182,"losses":289,"wins":247},"stealth/space-bunny-alpha":{"draws":37,"losses":20,"wins":53},"stepfun/step-3.7-flash":{"draws":23,"losses":16,"wins":57},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":32,"losses":21,"wins":35},"tencent/hy4-preview":{"draws":59,"losses":80,"wins":71},"thinkingmachines/inkling":{"draws":95,"losses":53,"wins":150},"thinkingmachines/inkling-small":{"draws":79,"losses":35,"wins":108},"unbiased/pareto-26.10-preview":{"draws":2,"losses":43,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":91,"losses":135,"wins":100},"x-ai/grok-4.6":{"draws":58,"losses":104,"wins":54},"x-ai/grok-4.7":{"draws":13,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":21,"losses":6,"wins":31},"xiaomi/mimo-v2.5":{"draws":90,"losses":38,"wins":130},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":38,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":23,"losses":32,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":25},"z-ai/glm-5.2":{"draws":127,"losses":88,"wins":135},"z-ai/glm-5.3":{"draws":44,"losses":86,"wins":52},"z-ai/glm-5.3-flash":{"draws":61,"losses":85,"wins":66},"z-ai/glm-5.3-flashx":{"draws":41,"losses":63,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":39,"wins":12},"claude-fable-5":{"draws":15,"losses":56,"wins":1},"claude-fable-5-1":{"draws":4,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":43,"wins":10},"claude-opus-4-5":{"draws":39,"losses":111,"wins":26},"claude-opus-4-8":{"draws":41,"losses":73,"wins":10},"claude-opus-5":{"draws":3,"losses":147,"wins":10},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":29,"losses":44,"wins":11},"claude-sonnet-5-5":{"draws":15,"losses":46,"wins":11},"cohere/north-mini-code":{"draws":21,"losses":23,"wins":26},"deepseek/deepseek-v4-flash":{"draws":39,"losses":74,"wins":49},"deepseek/deepseek-v4-pro":{"draws":21,"losses":38,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":46,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":50,"wins":6},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":21,"losses":40,"wins":11},"google/gemini-3.1-flash-lite":{"draws":18,"losses":33,"wins":49},"google/gemini-3.5-flash":{"draws":29,"losses":52,"wins":21},"google/gemini-3.5-flash-lite":{"draws":56,"losses":64,"wins":40},"google/gemini-3.6-flash":{"draws":42,"losses":111,"wins":23},"google/gemini-3.8-flash":{"draws":15,"losses":52,"wins":7},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":11,"losses":20,"wins":11},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":30,"losses":50,"wins":20},"gpt-5.4":{"draws":20,"losses":36,"wins":14},"gpt-5.4-mini":{"draws":40,"losses":34,"wins":22},"gpt-5.4-nano":{"draws":31,"losses":64,"wins":47},"gpt-5.5":{"draws":33,"losses":76,"wins":11},"gpt-5.6-luna":{"draws":24,"losses":42,"wins":12},"gpt-5.6-sol":{"draws":8,"losses":61,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":43,"wins":8},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":15,"losses":46,"wins":11},"gpt-6-sol":{"draws":7,"losses":61,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":68,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":17,"wins":19},"inclusionai/ling-3.0-flash":{"draws":50,"losses":32,"wins":30},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":65,"wins":41},"meta/muse-glimmer-30b":{"draws":27,"losses":25,"wins":14},"meta/muse-spark-1.2":{"draws":13,"losses":54,"wins":13},"meta/muse-spark-1.3":{"draws":11,"losses":57,"wins":6},"meta/muse-wonder":{"draws":13,"losses":53,"wins":6},"minimax/minimax-m3":{"draws":24,"losses":41,"wins":21},"mistralai/mistral-large-4-0":{"draws":13,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":26,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":17,"wins":1},"moonshotai/kimi-k3":{"draws":20,"losses":57,"wins":13},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":59,"wins":27},"o3":{"draws":17,"losses":94,"wins":21},"openai/gpt-oss-120b":{"draws":21,"losses":24,"wins":21},"poolside/laguna-s-2.1":{"draws":45,"losses":48,"wins":17},"qwen/qwen3.7-max":{"draws":26,"losses":48,"wins":10},"qwen/qwen3.7-plus":{"draws":22,"losses":27,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":48,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":34,"wins":8},"qwen/qwen3.8-flash":{"draws":24,"losses":36,"wins":6},"qwen/qwen3.8-max":{"draws":23,"losses":45,"wins":6},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":9},"stealth/ox-alpha":{"draws":63,"losses":171,"wins":32},"stealth/space-bunny-alpha":{"draws":17,"losses":28,"wins":13},"stepfun/step-3.7-flash":{"draws":16,"losses":28,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":35,"losses":17,"wins":20},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":6},"thinkingmachines/inkling":{"draws":37,"losses":50,"wins":35},"thinkingmachines/inkling-small":{"draws":25,"losses":32,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":5},"x-ai/grok-4.5":{"draws":26,"losses":69,"wins":7},"x-ai/grok-4.6":{"draws":21,"losses":55,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":21,"losses":23,"wins":10},"xiaomi/mimo-v2.5":{"draws":59,"losses":88,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":36,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":31,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":36,"wins":4},"z-ai/glm-5.2":{"draws":85,"losses":83,"wins":24},"z-ai/glm-5.3":{"draws":14,"losses":59,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":49,"wins":6},"z-ai/glm-5.3-flashx":{"draws":14,"losses":53,"wins":5}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":42,"wins":37},"claude-fable-5":{"draws":27,"losses":89,"wins":12},"claude-fable-5-1":{"draws":7,"losses":129,"wins":0},"claude-haiku-5-5":{"draws":32,"losses":66,"wins":26},"claude-opus-4-5":{"draws":127,"losses":151,"wins":52},"claude-opus-4-8":{"draws":47,"losses":127,"wins":32},"claude-opus-5":{"draws":51,"losses":269,"wins":8},"claude-opus-5-5":{"draws":4,"losses":137,"wins":1},"claude-sonnet-5":{"draws":52,"losses":56,"wins":30},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":22},"cohere/north-mini-code":{"draws":29,"losses":25,"wins":24},"deepseek/deepseek-v4-flash":{"draws":110,"losses":87,"wins":67},"deepseek/deepseek-v4-pro":{"draws":46,"losses":52,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":61,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":58,"wins":22},"fireworks/ember-1":{"draws":49,"losses":58,"wins":19},"gemini-3.1-pro-preview":{"draws":48,"losses":50,"wins":28},"google/gemini-3.1-flash-lite":{"draws":57,"losses":44,"wins":76},"google/gemini-3.5-flash":{"draws":57,"losses":85,"wins":36},"google/gemini-3.5-flash-lite":{"draws":109,"losses":77,"wins":80},"google/gemini-3.6-flash":{"draws":88,"losses":149,"wins":39},"google/gemini-3.8-flash":{"draws":43,"losses":80,"wins":11},"google/gemma-4-31b-it":{"draws":40,"losses":18,"wins":18},"gpt-4.1":{"draws":32,"losses":33,"wins":15},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":4},"gpt-5":{"draws":78,"losses":76,"wins":36},"gpt-5.4":{"draws":46,"losses":71,"wins":7},"gpt-5.4-mini":{"draws":82,"losses":40,"wins":40},"gpt-5.4-nano":{"draws":73,"losses":90,"wins":77},"gpt-5.5":{"draws":94,"losses":96,"wins":14},"gpt-5.6-luna":{"draws":51,"losses":42,"wins":33},"gpt-5.6-sol":{"draws":18,"losses":100,"wins":12},"gpt-5.6-terra":{"draws":48,"losses":60,"wins":22},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":42,"losses":59,"wins":25},"gpt-6-sol":{"draws":12,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":112,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":44,"losses":25,"wins":29},"inclusionai/ling-3.0-flash":{"draws":74,"losses":32,"wins":38},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":86,"losses":56,"wins":64},"meta/muse-glimmer-30b":{"draws":55,"losses":30,"wins":27},"meta/muse-spark-1.2":{"draws":35,"losses":72,"wins":19},"meta/muse-spark-1.3":{"draws":31,"losses":87,"wins":14},"meta/muse-wonder":{"draws":36,"losses":82,"wins":8},"minimax/minimax-m3":{"draws":52,"losses":49,"wins":39},"mistralai/mistral-large-4-0":{"draws":28,"losses":32,"wins":18},"mistralai/mistral-medium-3-5":{"draws":40,"losses":12,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":22,"losses":33,"wins":7},"moonshotai/kimi-k3":{"draws":47,"losses":54,"wins":31},"nex-agi/nex-n2-pro":{"draws":56,"losses":27,"wins":59},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":86,"losses":35,"wins":35},"o3":{"draws":77,"losses":127,"wins":50},"openai/gpt-oss-120b":{"draws":52,"losses":36,"wins":28},"poolside/laguna-s-2.1":{"draws":87,"losses":48,"wins":41},"qwen/qwen3.7-max":{"draws":75,"losses":48,"wins":29},"qwen/qwen3.7-plus":{"draws":51,"losses":41,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":65,"wins":15},"qwen/qwen3.8-27b":{"draws":30,"losses":43,"wins":19},"qwen/qwen3.8-flash":{"draws":41,"losses":33,"wins":18},"qwen/qwen3.8-max":{"draws":48,"losses":60,"wins":22},"qwen/qwen3.8-max-0902":{"draws":49,"losses":65,"wins":12},"stealth/ox-alpha":{"draws":112,"losses":212,"wins":60},"stealth/space-bunny-alpha":{"draws":41,"losses":32,"wins":25},"stepfun/step-3.7-flash":{"draws":48,"losses":44,"wins":38},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":77,"losses":43,"wins":26},"tencent/hy4-preview":{"draws":43,"losses":67,"wins":14},"thinkingmachines/inkling":{"draws":84,"losses":75,"wins":83},"thinkingmachines/inkling-small":{"draws":59,"losses":34,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":14,"wins":13},"x-ai/grok-4.5":{"draws":45,"losses":109,"wins":12},"x-ai/grok-4.6":{"draws":50,"losses":67,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":98,"wins":9},"x-ai/grok-build-0.1":{"draws":56,"losses":20,"wins":18},"xiaomi/mimo-v2.5":{"draws":179,"losses":98,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":45,"losses":54,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":43,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":56,"wins":10},"z-ai/glm-5.2":{"draws":160,"losses":116,"wins":68},"z-ai/glm-5.3":{"draws":28,"losses":84,"wins":16},"z-ai/glm-5.3-flash":{"draws":41,"losses":56,"wins":29},"z-ai/glm-5.3-flashx":{"draws":31,"losses":74,"wins":21}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":54,"losses":85,"wins":135},"claude-fable-5":{"draws":29,"losses":209,"wins":44},"claude-fable-5-1":{"draws":5,"losses":277,"wins":14},"claude-haiku-5-5":{"draws":32,"losses":101,"wins":61},"claude-opus-4-5":{"draws":91,"losses":351,"wins":168},"claude-opus-4-8":{"draws":36,"losses":152,"wins":68},"claude-opus-5":{"draws":28,"losses":364,"wins":26},"claude-opus-5-5":{"draws":11,"losses":203,"wins":4},"claude-sonnet-5":{"draws":48,"losses":174,"wins":190},"claude-sonnet-5-5":{"draws":17,"losses":136,"wins":45},"cohere/north-mini-code":{"draws":24,"losses":18,"wins":68},"deepseek/deepseek-v4-flash":{"draws":71,"losses":119,"wins":224},"deepseek/deepseek-v4-pro":{"draws":45,"losses":137,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":139,"wins":76},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":90,"wins":62},"fireworks/ember-1":{"draws":40,"losses":108,"wins":50},"gemini-3.1-pro-preview":{"draws":33,"losses":75,"wins":90},"google/gemini-3.1-flash-lite":{"draws":33,"losses":14,"wins":155},"google/gemini-3.5-flash":{"draws":55,"losses":186,"wins":113},"google/gemini-3.5-flash-lite":{"draws":139,"losses":229,"wins":518},"google/gemini-3.6-flash":{"draws":126,"losses":451,"wins":295},"google/gemini-3.8-flash":{"draws":40,"losses":183,"wins":69},"google/gemma-4-31b-it":{"draws":26,"losses":21,"wins":71},"gpt-4.1":{"draws":19,"losses":30,"wins":35},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":10},"gpt-5":{"draws":49,"losses":112,"wins":79},"gpt-5.4":{"draws":47,"losses":262,"wins":83},"gpt-5.4-mini":{"draws":36,"losses":45,"wins":75},"gpt-5.4-nano":{"draws":28,"losses":120,"wins":132},"gpt-5.5":{"draws":55,"losses":135,"wins":50},"gpt-5.6-luna":{"draws":70,"losses":147,"wins":189},"gpt-5.6-sol":{"draws":25,"losses":301,"wins":70},"gpt-5.6-terra":{"draws":57,"losses":117,"wins":108},"gpt-6-astra":{"draws":8,"losses":266,"wins":2},"gpt-6-luna":{"draws":35,"losses":100,"wins":63},"gpt-6-sol":{"draws":10,"losses":172,"wins":16},"gpt-6.1-sol":{"draws":3,"losses":186,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":44,"losses":23,"wins":133},"inclusionai/ling-3.0-flash":{"draws":41,"losses":35,"wins":154},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":61,"losses":104,"wins":249},"meta/muse-glimmer-30b":{"draws":57,"losses":43,"wins":148},"meta/muse-spark-1.2":{"draws":34,"losses":136,"wins":148},"meta/muse-spark-1.3":{"draws":26,"losses":158,"wins":78},"meta/muse-wonder":{"draws":13,"losses":151,"wins":34},"minimax/minimax-m3":{"draws":26,"losses":30,"wins":84},"mistralai/mistral-large-4-0":{"draws":28,"losses":53,"wins":39},"mistralai/mistral-medium-3-5":{"draws":37,"losses":20,"wins":107},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":34,"wins":29},"moonshotai/kimi-k3":{"draws":56,"losses":152,"wins":168},"nex-agi/nex-n2-pro":{"draws":17,"losses":21,"wins":94},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":77,"losses":50,"wins":127},"o3":{"draws":48,"losses":250,"wins":250},"openai/gpt-oss-120b":{"draws":49,"losses":41,"wins":162},"poolside/laguna-s-2.1":{"draws":73,"losses":86,"wins":163},"qwen/qwen3.7-max":{"draws":37,"losses":51,"wins":66},"qwen/qwen3.7-plus":{"draws":21,"losses":35,"wins":76},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":154,"wins":91},"qwen/qwen3.8-27b":{"draws":17,"losses":91,"wins":68},"qwen/qwen3.8-flash":{"draws":42,"losses":79,"wins":71},"qwen/qwen3.8-max":{"draws":55,"losses":148,"wins":99},"qwen/qwen3.8-max-0902":{"draws":37,"losses":97,"wins":64},"stealth/ox-alpha":{"draws":122,"losses":433,"wins":329},"stealth/space-bunny-alpha":{"draws":28,"losses":56,"wins":76},"stepfun/step-3.7-flash":{"draws":37,"losses":52,"wins":113},"stepfun/step-5-preview":{"draws":8,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":35,"losses":55,"wins":58},"tencent/hy4-preview":{"draws":46,"losses":154,"wins":92},"thinkingmachines/inkling":{"draws":64,"losses":95,"wins":259},"thinkingmachines/inkling-small":{"draws":73,"losses":71,"wins":159},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":3},"upstage/solar-mini4":{"draws":10,"losses":13,"wins":39},"x-ai/grok-4.5":{"draws":34,"losses":237,"wins":127},"x-ai/grok-4.6":{"draws":54,"losses":160,"wins":70},"x-ai/grok-4.7":{"draws":11,"losses":131,"wins":36},"x-ai/grok-build-0.1":{"draws":22,"losses":13,"wins":51},"xiaomi/mimo-v2.5":{"draws":89,"losses":61,"wins":232},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":66,"wins":74},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":74,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":95,"wins":26},"z-ai/glm-5.2":{"draws":100,"losses":195,"wins":229},"z-ai/glm-5.3":{"draws":25,"losses":171,"wins":54},"z-ai/glm-5.3-flash":{"draws":45,"losses":130,"wins":113},"z-ai/glm-5.3-flashx":{"draws":21,"losses":118,"wins":59}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":75,"losses":76,"wins":59},"claude-fable-5":{"draws":50,"losses":114,"wins":20},"claude-fable-5-1":{"draws":11,"losses":170,"wins":1},"claude-haiku-5-5":{"draws":30,"losses":78,"wins":12},"claude-opus-4-5":{"draws":81,"losses":147,"wins":40},"claude-opus-4-8":{"draws":38,"losses":68,"wins":10},"claude-opus-5":{"draws":32,"losses":183,"wins":11},"claude-opus-5-5":{"draws":8,"losses":130,"wins":0},"claude-sonnet-5":{"draws":79,"losses":122,"wins":31},"claude-sonnet-5-5":{"draws":26,"losses":82,"wins":18},"cohere/north-mini-code":{"draws":19,"losses":14,"wins":17},"deepseek/deepseek-v4-flash":{"draws":123,"losses":82,"wins":87},"deepseek/deepseek-v4-pro":{"draws":74,"losses":90,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":72,"losses":73,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":61,"wins":23},"fireworks/ember-1":{"draws":48,"losses":64,"wins":14},"gemini-3.1-pro-preview":{"draws":44,"losses":55,"wins":27},"google/gemini-3.1-flash-lite":{"draws":25,"losses":19,"wins":42},"google/gemini-3.5-flash":{"draws":81,"losses":114,"wins":51},"google/gemini-3.5-flash-lite":{"draws":149,"losses":142,"wins":117},"google/gemini-3.6-flash":{"draws":137,"losses":194,"wins":53},"google/gemini-3.8-flash":{"draws":50,"losses":122,"wins":14},"google/gemma-4-31b-it":{"draws":31,"losses":10,"wins":33},"gpt-4.1":{"draws":14,"losses":19,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":40,"losses":53,"wins":21},"gpt-5.4":{"draws":81,"losses":90,"wins":25},"gpt-5.4-mini":{"draws":37,"losses":32,"wins":21},"gpt-5.4-nano":{"draws":39,"losses":43,"wins":50},"gpt-5.5":{"draws":49,"losses":57,"wins":16},"gpt-5.6-luna":{"draws":110,"losses":74,"wins":52},"gpt-5.6-sol":{"draws":29,"losses":148,"wins":13},"gpt-5.6-terra":{"draws":82,"losses":115,"wins":25},"gpt-6-astra":{"draws":13,"losses":145,"wins":0},"gpt-6-luna":{"draws":43,"losses":58,"wins":25},"gpt-6-sol":{"draws":19,"losses":101,"wins":6},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":75,"losses":38,"wins":55},"inclusionai/ling-3.0-flash":{"draws":49,"losses":14,"wins":55},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":68,"losses":73,"wins":47},"meta/muse-glimmer-30b":{"draws":96,"losses":53,"wins":63},"meta/muse-spark-1.2":{"draws":54,"losses":106,"wins":22},"meta/muse-spark-1.3":{"draws":49,"losses":112,"wins":23},"meta/muse-wonder":{"draws":23,"losses":93,"wins":10},"minimax/minimax-m3":{"draws":25,"losses":21,"wins":30},"mistralai/mistral-large-4-0":{"draws":31,"losses":35,"wins":14},"mistralai/mistral-medium-3-5":{"draws":69,"losses":28,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":58,"losses":96,"wins":30},"nex-agi/nex-n2-pro":{"draws":21,"losses":21,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":28,"wins":36},"o3":{"draws":49,"losses":162,"wins":41},"openai/gpt-oss-120b":{"draws":58,"losses":39,"wins":39},"poolside/laguna-s-2.1":{"draws":90,"losses":58,"wins":42},"qwen/qwen3.7-max":{"draws":29,"losses":31,"wins":18},"qwen/qwen3.7-plus":{"draws":23,"losses":19,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":84,"losses":106,"wins":18},"qwen/qwen3.8-27b":{"draws":22,"losses":63,"wins":21},"qwen/qwen3.8-flash":{"draws":56,"losses":50,"wins":36},"qwen/qwen3.8-max":{"draws":81,"losses":112,"wins":17},"qwen/qwen3.8-max-0902":{"draws":43,"losses":70,"wins":13},"stealth/ox-alpha":{"draws":197,"losses":393,"wins":100},"stealth/space-bunny-alpha":{"draws":33,"losses":44,"wins":23},"stepfun/step-3.7-flash":{"draws":35,"losses":36,"wins":19},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":25,"wins":19},"tencent/hy4-preview":{"draws":74,"losses":88,"wins":32},"thinkingmachines/inkling":{"draws":63,"losses":81,"wins":66},"thinkingmachines/inkling-small":{"draws":105,"losses":58,"wins":81},"unbiased/pareto-26.10-preview":{"draws":0,"losses":42,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":11},"x-ai/grok-4.5":{"draws":57,"losses":108,"wins":19},"x-ai/grok-4.6":{"draws":65,"losses":105,"wins":22},"x-ai/grok-4.7":{"draws":9,"losses":99,"wins":4},"x-ai/grok-build-0.1":{"draws":19,"losses":16,"wins":9},"xiaomi/mimo-v2.5":{"draws":73,"losses":55,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":29,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":52,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":62,"wins":6},"z-ai/glm-5.2":{"draws":145,"losses":141,"wins":74},"z-ai/glm-5.3":{"draws":53,"losses":107,"wins":8},"z-ai/glm-5.3-flash":{"draws":61,"losses":112,"wins":19},"z-ai/glm-5.3-flashx":{"draws":37,"losses":76,"wins":13}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":81,"losses":61,"wins":52},"claude-fable-5":{"draws":43,"losses":108,"wins":29},"claude-fable-5-1":{"draws":10,"losses":178,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":61,"wins":35},"claude-opus-4-5":{"draws":148,"losses":192,"wins":52},"claude-opus-4-8":{"draws":58,"losses":102,"wins":24},"claude-opus-5":{"draws":34,"losses":325,"wins":27},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":93,"losses":138,"wins":35},"claude-sonnet-5-5":{"draws":25,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":35,"losses":28,"wins":19},"deepseek/deepseek-v4-flash":{"draws":136,"losses":89,"wins":93},"deepseek/deepseek-v4-pro":{"draws":67,"losses":72,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":71,"losses":66,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":58,"losses":57,"wins":23},"fireworks/ember-1":{"draws":53,"losses":63,"wins":22},"gemini-3.1-pro-preview":{"draws":47,"losses":59,"wins":32},"google/gemini-3.1-flash-lite":{"draws":35,"losses":33,"wins":64},"google/gemini-3.5-flash":{"draws":75,"losses":115,"wins":46},"google/gemini-3.5-flash-lite":{"draws":257,"losses":165,"wins":206},"google/gemini-3.6-flash":{"draws":229,"losses":273,"wins":102},"google/gemini-3.8-flash":{"draws":46,"losses":117,"wins":21},"google/gemma-4-31b-it":{"draws":33,"losses":20,"wins":25},"gpt-4.1":{"draws":24,"losses":30,"wins":20},"gpt-4.1-nano":{"draws":13,"losses":3,"wins":2},"gpt-5":{"draws":67,"losses":57,"wins":58},"gpt-5.4":{"draws":93,"losses":131,"wins":22},"gpt-5.4-mini":{"draws":71,"losses":49,"wins":34},"gpt-5.4-nano":{"draws":74,"losses":73,"wins":85},"gpt-5.5":{"draws":78,"losses":79,"wins":41},"gpt-5.6-luna":{"draws":111,"losses":94,"wins":73},"gpt-5.6-sol":{"draws":47,"losses":211,"wins":10},"gpt-5.6-terra":{"draws":77,"losses":86,"wins":21},"gpt-6-astra":{"draws":18,"losses":156,"wins":0},"gpt-6-luna":{"draws":45,"losses":59,"wins":34},"gpt-6-sol":{"draws":22,"losses":105,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":128,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":64,"losses":34,"wins":40},"inclusionai/ling-3.0-flash":{"draws":110,"losses":30,"wins":76},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":130,"losses":99,"wins":105},"meta/muse-glimmer-30b":{"draws":90,"losses":43,"wins":59},"meta/muse-spark-1.2":{"draws":58,"losses":131,"wins":31},"meta/muse-spark-1.3":{"draws":46,"losses":95,"wins":35},"meta/muse-wonder":{"draws":22,"losses":105,"wins":11},"minimax/minimax-m3":{"draws":46,"losses":38,"wins":48},"mistralai/mistral-large-4-0":{"draws":32,"losses":36,"wins":20},"mistralai/mistral-medium-3-5":{"draws":57,"losses":26,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":17,"wins":28},"moonshotai/kimi-k3":{"draws":106,"losses":137,"wins":31},"nex-agi/nex-n2-pro":{"draws":45,"losses":17,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":87,"losses":41,"wins":48},"o3":{"draws":73,"losses":163,"wins":86},"openai/gpt-oss-120b":{"draws":90,"losses":42,"wins":58},"poolside/laguna-s-2.1":{"draws":110,"losses":71,"wins":71},"qwen/qwen3.7-max":{"draws":50,"losses":48,"wins":32},"qwen/qwen3.7-plus":{"draws":46,"losses":19,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":70,"losses":102,"wins":20},"qwen/qwen3.8-27b":{"draws":29,"losses":54,"wins":23},"qwen/qwen3.8-flash":{"draws":58,"losses":48,"wins":26},"qwen/qwen3.8-max":{"draws":77,"losses":74,"wins":44},"qwen/qwen3.8-max-0902":{"draws":45,"losses":70,"wins":23},"stealth/ox-alpha":{"draws":194,"losses":354,"wins":118},"stealth/space-bunny-alpha":{"draws":33,"losses":40,"wins":33},"stepfun/step-3.7-flash":{"draws":37,"losses":34,"wins":33},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":38,"wins":32},"tencent/hy4-preview":{"draws":68,"losses":93,"wins":35},"thinkingmachines/inkling":{"draws":111,"losses":93,"wins":130},"thinkingmachines/inkling-small":{"draws":97,"losses":29,"wins":87},"unbiased/pareto-26.10-preview":{"draws":0,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":14,"wins":8},"x-ai/grok-4.5":{"draws":95,"losses":184,"wins":51},"x-ai/grok-4.6":{"draws":60,"losses":107,"wins":21},"x-ai/grok-4.7":{"draws":11,"losses":99,"wins":14},"x-ai/grok-build-0.1":{"draws":37,"losses":27,"wins":18},"xiaomi/mimo-v2.5":{"draws":110,"losses":81,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":37,"losses":49,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":51,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":192,"losses":130,"wins":98},"z-ai/glm-5.3":{"draws":41,"losses":107,"wins":20},"z-ai/glm-5.3-flash":{"draws":67,"losses":94,"wins":29},"z-ai/glm-5.3-flashx":{"draws":40,"losses":75,"wins":23}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":26,"wins":30},"claude-fable-5":{"draws":15,"losses":58,"wins":13},"claude-fable-5-1":{"draws":3,"losses":90,"wins":1},"claude-haiku-5-5":{"draws":27,"losses":35,"wins":20},"claude-opus-4-5":{"draws":82,"losses":108,"wins":54},"claude-opus-4-8":{"draws":48,"losses":64,"wins":40},"claude-opus-5":{"draws":30,"losses":192,"wins":24},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":28,"losses":44,"wins":18},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":21,"losses":9,"wins":24},"deepseek/deepseek-v4-flash":{"draws":75,"losses":34,"wins":61},"deepseek/deepseek-v4-pro":{"draws":27,"losses":39,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":35,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":34,"wins":19},"fireworks/ember-1":{"draws":26,"losses":39,"wins":19},"gemini-3.1-pro-preview":{"draws":26,"losses":29,"wins":29},"google/gemini-3.1-flash-lite":{"draws":33,"losses":18,"wins":55},"google/gemini-3.5-flash":{"draws":37,"losses":43,"wins":40},"google/gemini-3.5-flash-lite":{"draws":52,"losses":55,"wins":67},"google/gemini-3.6-flash":{"draws":56,"losses":101,"wins":43},"google/gemini-3.8-flash":{"draws":29,"losses":37,"wins":24},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":26,"losses":5,"wins":15},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":54,"losses":48,"wins":26},"gpt-5.4":{"draws":18,"losses":43,"wins":21},"gpt-5.4-mini":{"draws":37,"losses":26,"wins":45},"gpt-5.4-nano":{"draws":51,"losses":54,"wins":71},"gpt-5.5":{"draws":55,"losses":58,"wins":29},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":13,"losses":60,"wins":15},"gpt-5.6-terra":{"draws":29,"losses":47,"wins":18},"gpt-6-astra":{"draws":7,"losses":78,"wins":1},"gpt-6-luna":{"draws":22,"losses":35,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":7,"losses":75,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":15,"wins":26},"inclusionai/ling-3.0-flash":{"draws":58,"losses":13,"wins":43},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":53,"losses":24,"wins":69},"meta/muse-glimmer-30b":{"draws":30,"losses":19,"wins":29},"meta/muse-spark-1.2":{"draws":11,"losses":61,"wins":20},"meta/muse-spark-1.3":{"draws":18,"losses":48,"wins":22},"meta/muse-wonder":{"draws":11,"losses":61,"wins":12},"minimax/minimax-m3":{"draws":41,"losses":20,"wins":45},"mistralai/mistral-large-4-0":{"draws":21,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":26,"losses":4,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":16},"moonshotai/kimi-k3":{"draws":26,"losses":54,"wins":24},"nex-agi/nex-n2-pro":{"draws":26,"losses":10,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":75,"losses":29,"wins":48},"o3":{"draws":37,"losses":66,"wins":51},"openai/gpt-oss-120b":{"draws":29,"losses":18,"wins":31},"poolside/laguna-s-2.1":{"draws":50,"losses":32,"wins":48},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":15},"qwen/qwen3.7-plus":{"draws":33,"losses":24,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":42,"wins":18},"qwen/qwen3.8-27b":{"draws":16,"losses":30,"wins":20},"qwen/qwen3.8-flash":{"draws":27,"losses":26,"wins":25},"qwen/qwen3.8-max":{"draws":38,"losses":30,"wins":24},"qwen/qwen3.8-max-0902":{"draws":26,"losses":41,"wins":17},"stealth/ox-alpha":{"draws":69,"losses":147,"wins":62},"stealth/space-bunny-alpha":{"draws":21,"losses":22,"wins":23},"stepfun/step-3.7-flash":{"draws":20,"losses":13,"wins":41},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":44,"losses":19,"wins":33},"tencent/hy4-preview":{"draws":18,"losses":50,"wins":18},"thinkingmachines/inkling":{"draws":53,"losses":25,"wins":80},"thinkingmachines/inkling-small":{"draws":32,"losses":17,"wins":39},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":14},"x-ai/grok-4.5":{"draws":34,"losses":56,"wins":28},"x-ai/grok-4.6":{"draws":21,"losses":47,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":51,"wins":15},"x-ai/grok-build-0.1":{"draws":27,"losses":22,"wins":15},"xiaomi/mimo-v2.5":{"draws":105,"losses":53,"wins":104},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":23,"wins":47},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":28,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":79,"losses":92,"wins":71},"z-ai/glm-5.3":{"draws":21,"losses":48,"wins":15},"z-ai/glm-5.3-flash":{"draws":27,"losses":38,"wins":19},"z-ai/glm-5.3-flashx":{"draws":22,"losses":42,"wins":20}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":24,"wins":20},"claude-fable-5":{"draws":13,"losses":51,"wins":8},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":75,"losses":75,"wins":44},"claude-opus-4-8":{"draws":31,"losses":77,"wins":24},"claude-opus-5":{"draws":24,"losses":129,"wins":15},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":22,"losses":42,"wins":18},"claude-sonnet-5-5":{"draws":17,"losses":43,"wins":12},"cohere/north-mini-code":{"draws":12,"losses":17,"wins":23},"deepseek/deepseek-v4-flash":{"draws":48,"losses":59,"wins":51},"deepseek/deepseek-v4-pro":{"draws":18,"losses":36,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":30,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":40,"wins":7},"fireworks/ember-1":{"draws":23,"losses":38,"wins":11},"gemini-3.1-pro-preview":{"draws":23,"losses":35,"wins":14},"google/gemini-3.1-flash-lite":{"draws":28,"losses":25,"wins":59},"google/gemini-3.5-flash":{"draws":27,"losses":53,"wins":18},"google/gemini-3.5-flash-lite":{"draws":53,"losses":50,"wins":51},"google/gemini-3.6-flash":{"draws":57,"losses":99,"wins":28},"google/gemini-3.8-flash":{"draws":21,"losses":48,"wins":7},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":15},"gpt-4.1":{"draws":18,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":30,"losses":43,"wins":17},"gpt-5.4":{"draws":14,"losses":50,"wins":8},"gpt-5.4-mini":{"draws":32,"losses":26,"wins":40},"gpt-5.4-nano":{"draws":36,"losses":63,"wins":65},"gpt-5.5":{"draws":53,"losses":59,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":29,"wins":21},"gpt-5.6-sol":{"draws":15,"losses":53,"wins":8},"gpt-5.6-terra":{"draws":27,"losses":33,"wins":12},"gpt-6-astra":{"draws":3,"losses":71,"wins":0},"gpt-6-luna":{"draws":25,"losses":35,"wins":12},"gpt-6-sol":{"draws":10,"losses":55,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":66,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":12,"wins":28},"inclusionai/ling-3.0-flash":{"draws":44,"losses":27,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":45,"wins":43},"meta/muse-glimmer-30b":{"draws":29,"losses":23,"wins":16},"meta/muse-spark-1.2":{"draws":16,"losses":55,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":49,"wins":16},"meta/muse-wonder":{"draws":15,"losses":55,"wins":2},"minimax/minimax-m3":{"draws":24,"losses":33,"wins":33},"mistralai/mistral-large-4-0":{"draws":13,"losses":29,"wins":2},"mistralai/mistral-medium-3-5":{"draws":19,"losses":11,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":27,"wins":4},"moonshotai/kimi-k3":{"draws":33,"losses":41,"wins":22},"nex-agi/nex-n2-pro":{"draws":22,"losses":23,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":51,"losses":40,"wins":41},"o3":{"draws":21,"losses":76,"wins":35},"openai/gpt-oss-120b":{"draws":23,"losses":22,"wins":19},"poolside/laguna-s-2.1":{"draws":46,"losses":47,"wins":19},"qwen/qwen3.7-max":{"draws":33,"losses":41,"wins":24},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":38,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":31,"wins":17},"qwen/qwen3.8-flash":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":16},"qwen/qwen3.8-max-0902":{"draws":26,"losses":37,"wins":9},"stealth/ox-alpha":{"draws":47,"losses":142,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":31,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":25,"wins":31},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":34,"losses":29,"wins":21},"tencent/hy4-preview":{"draws":18,"losses":41,"wins":11},"thinkingmachines/inkling":{"draws":37,"losses":45,"wins":52},"thinkingmachines/inkling-small":{"draws":28,"losses":24,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":2},"upstage/solar-mini4":{"draws":3,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":26,"losses":65,"wins":11},"x-ai/grok-4.6":{"draws":21,"losses":45,"wins":6},"x-ai/grok-4.7":{"draws":6,"losses":53,"wins":7},"x-ai/grok-build-0.1":{"draws":17,"losses":13,"wins":22},"xiaomi/mimo-v2.5":{"draws":88,"losses":69,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":42,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":29,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":73,"losses":101,"wins":40},"z-ai/glm-5.3":{"draws":15,"losses":48,"wins":6},"z-ai/glm-5.3-flash":{"draws":23,"losses":45,"wins":10},"z-ai/glm-5.3-flashx":{"draws":17,"losses":45,"wins":10}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":73,"losses":49,"wins":100},"claude-fable-5":{"draws":68,"losses":123,"wins":65},"claude-fable-5-1":{"draws":27,"losses":250,"wins":13},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":117,"losses":82,"wins":117},"claude-opus-4-8":{"draws":48,"losses":46,"wins":54},"claude-opus-5":{"draws":35,"losses":199,"wins":46},"claude-opus-5-5":{"draws":11,"losses":127,"wins":18},"claude-sonnet-5":{"draws":94,"losses":66,"wins":102},"claude-sonnet-5-5":{"draws":32,"losses":63,"wins":49},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":45},"deepseek/deepseek-v4-flash":{"draws":103,"losses":56,"wins":159},"deepseek/deepseek-v4-pro":{"draws":72,"losses":64,"wins":94},"deepseek/deepseek-v4-pro-0813":{"draws":67,"losses":75,"wins":88},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":58,"wins":50},"fireworks/ember-1":{"draws":50,"losses":47,"wins":47},"gemini-3.1-pro-preview":{"draws":36,"losses":46,"wins":62},"google/gemini-3.1-flash-lite":{"draws":29,"losses":3,"wins":70},"google/gemini-3.5-flash":{"draws":79,"losses":96,"wins":117},"google/gemini-3.5-flash-lite":{"draws":145,"losses":78,"wins":207},"google/gemini-3.6-flash":{"draws":123,"losses":177,"wins":156},"google/gemini-3.8-flash":{"draws":63,"losses":116,"wins":79},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":20,"losses":6,"wins":24},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":40,"losses":36,"wins":58},"gpt-5.4":{"draws":57,"losses":93,"wins":96},"gpt-5.4-mini":{"draws":34,"losses":13,"wins":51},"gpt-5.4-nano":{"draws":41,"losses":32,"wins":89},"gpt-5.5":{"draws":44,"losses":49,"wins":45},"gpt-5.6-luna":{"draws":95,"losses":49,"wins":98},"gpt-5.6-sol":{"draws":48,"losses":149,"wins":67},"gpt-5.6-terra":{"draws":94,"losses":53,"wins":109},"gpt-6-astra":{"draws":14,"losses":227,"wins":13},"gpt-6-luna":{"draws":37,"losses":48,"wins":59},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":11,"losses":113,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":67,"losses":13,"wins":84},"inclusionai/ling-3.0-flash":{"draws":50,"losses":7,"wins":75},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":54,"losses":30,"wins":122},"meta/muse-glimmer-30b":{"draws":87,"losses":27,"wins":98},"meta/muse-spark-1.2":{"draws":55,"losses":66,"wins":85},"meta/muse-spark-1.3":{"draws":58,"losses":85,"wins":83},"meta/muse-wonder":{"draws":27,"losses":73,"wins":44},"minimax/minimax-m3":{"draws":22,"losses":9,"wins":53},"mistralai/mistral-large-4-0":{"draws":22,"losses":26,"wins":42},"mistralai/mistral-medium-3-5":{"draws":48,"losses":6,"wins":94},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":9,"wins":16},"moonshotai/kimi-k3":{"draws":65,"losses":80,"wins":79},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":48},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":15,"wins":65},"o3":{"draws":43,"losses":91,"wins":154},"openai/gpt-oss-120b":{"draws":84,"losses":18,"wins":106},"poolside/laguna-s-2.1":{"draws":70,"losses":20,"wins":102},"qwen/qwen3.7-max":{"draws":32,"losses":18,"wins":42},"qwen/qwen3.7-plus":{"draws":29,"losses":11,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":58,"wins":58},"qwen/qwen3.8-27b":{"draws":47,"losses":33,"wins":48},"qwen/qwen3.8-flash":{"draws":49,"losses":52,"wins":69},"qwen/qwen3.8-max":{"draws":84,"losses":83,"wins":87},"qwen/qwen3.8-max-0902":{"draws":47,"losses":53,"wins":44},"stealth/ox-alpha":{"draws":228,"losses":314,"wins":300},"stealth/space-bunny-alpha":{"draws":40,"losses":27,"wins":47},"stepfun/step-3.7-flash":{"draws":18,"losses":15,"wins":71},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":30,"losses":18,"wins":36},"tencent/hy4-preview":{"draws":72,"losses":97,"wins":75},"thinkingmachines/inkling":{"draws":76,"losses":32,"wins":128},"thinkingmachines/inkling-small":{"draws":86,"losses":31,"wins":139},"unbiased/pareto-26.10-preview":{"draws":2,"losses":42,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":58,"losses":90,"wins":74},"x-ai/grok-4.6":{"draws":67,"losses":104,"wins":87},"x-ai/grok-4.7":{"draws":10,"losses":86,"wins":30},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":93,"losses":29,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":35,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":41,"wins":31},"z-ai/glm-5.2":{"draws":146,"losses":97,"wins":151},"z-ai/glm-5.3":{"draws":50,"losses":115,"wins":45},"z-ai/glm-5.3-flash":{"draws":60,"losses":97,"wins":87},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":29,"wins":60},"claude-fable-5":{"draws":23,"losses":83,"wins":26},"claude-fable-5-1":{"draws":7,"losses":139,"wins":2},"claude-haiku-5-5":{"draws":22,"losses":47,"wins":29},"claude-opus-4-5":{"draws":54,"losses":55,"wins":81},"claude-opus-4-8":{"draws":21,"losses":42,"wins":31},"claude-opus-5":{"draws":28,"losses":131,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":30,"losses":47,"wins":53},"claude-sonnet-5-5":{"draws":17,"losses":60,"wins":25},"cohere/north-mini-code":{"draws":7,"losses":4,"wins":25},"deepseek/deepseek-v4-flash":{"draws":41,"losses":45,"wins":94},"deepseek/deepseek-v4-pro":{"draws":27,"losses":41,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":40,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":49,"wins":29},"fireworks/ember-1":{"draws":29,"losses":35,"wins":38},"gemini-3.1-pro-preview":{"draws":23,"losses":32,"wins":47},"google/gemini-3.1-flash-lite":{"draws":15,"losses":11,"wins":48},"google/gemini-3.5-flash":{"draws":29,"losses":60,"wins":61},"google/gemini-3.5-flash-lite":{"draws":40,"losses":50,"wins":130},"google/gemini-3.6-flash":{"draws":49,"losses":107,"wins":82},"google/gemini-3.8-flash":{"draws":21,"losses":73,"wins":36},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":29},"gpt-4.1":{"draws":9,"losses":13,"wins":14},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":6},"gpt-5":{"draws":18,"losses":34,"wins":42},"gpt-5.4":{"draws":27,"losses":70,"wins":29},"gpt-5.4-mini":{"draws":17,"losses":19,"wins":32},"gpt-5.4-nano":{"draws":23,"losses":34,"wins":49},"gpt-5.5":{"draws":28,"losses":44,"wins":26},"gpt-5.6-luna":{"draws":37,"losses":32,"wins":55},"gpt-5.6-sol":{"draws":20,"losses":85,"wins":31},"gpt-5.6-terra":{"draws":44,"losses":41,"wins":41},"gpt-6-astra":{"draws":4,"losses":129,"wins":1},"gpt-6-luna":{"draws":26,"losses":41,"wins":35},"gpt-6-sol":{"draws":17,"losses":71,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":91,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":23,"losses":8,"wins":55},"inclusionai/ling-3.0-flash":{"draws":15,"losses":13,"wins":54},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":25,"losses":21,"wins":78},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":60},"meta/muse-spark-1.2":{"draws":24,"losses":41,"wins":51},"meta/muse-spark-1.3":{"draws":21,"losses":57,"wins":42},"meta/muse-wonder":{"draws":19,"losses":69,"wins":14},"minimax/minimax-m3":{"draws":14,"losses":8,"wins":32},"mistralai/mistral-large-4-0":{"draws":19,"losses":22,"wins":21},"mistralai/mistral-medium-3-5":{"draws":21,"losses":5,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":6,"wins":13},"moonshotai/kimi-k3":{"draws":31,"losses":53,"wins":32},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":19,"wins":43},"o3":{"draws":17,"losses":68,"wins":91},"openai/gpt-oss-120b":{"draws":22,"losses":21,"wins":63},"poolside/laguna-s-2.1":{"draws":29,"losses":23,"wins":54},"qwen/qwen3.7-max":{"draws":16,"losses":20,"wins":30},"qwen/qwen3.7-plus":{"draws":12,"losses":17,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":48,"wins":33},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":21,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":39,"losses":45,"wins":44},"qwen/qwen3.8-max-0902":{"draws":26,"losses":49,"wins":27},"stealth/ox-alpha":{"draws":89,"losses":183,"wins":150},"stealth/space-bunny-alpha":{"draws":21,"losses":20,"wins":39},"stepfun/step-3.7-flash":{"draws":13,"losses":27,"wins":38},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":32},"tencent/hy4-preview":{"draws":30,"losses":56,"wins":38},"thinkingmachines/inkling":{"draws":37,"losses":32,"wins":79},"thinkingmachines/inkling-small":{"draws":33,"losses":17,"wins":80},"unbiased/pareto-26.10-preview":{"draws":0,"losses":34,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":24,"losses":68,"wins":30},"x-ai/grok-4.6":{"draws":32,"losses":64,"wins":38},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":20},"xiaomi/mimo-v2.5":{"draws":46,"losses":29,"wins":87},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":22,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":26,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":36,"wins":20},"z-ai/glm-5.2":{"draws":72,"losses":77,"wins":81},"z-ai/glm-5.3":{"draws":30,"losses":70,"wins":18},"z-ai/glm-5.3-flash":{"draws":27,"losses":60,"wins":47},"z-ai/glm-5.3-flashx":{"draws":24,"losses":53,"wins":25}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":36,"wins":65},"claude-fable-5":{"draws":45,"losses":85,"wins":28},"claude-fable-5-1":{"draws":10,"losses":157,"wins":7},"claude-haiku-5-5":{"draws":28,"losses":45,"wins":19},"claude-opus-4-5":{"draws":73,"losses":72,"wins":63},"claude-opus-4-8":{"draws":34,"losses":42,"wins":20},"claude-opus-5":{"draws":28,"losses":136,"wins":16},"claude-opus-5-5":{"draws":9,"losses":92,"wins":3},"claude-sonnet-5":{"draws":58,"losses":59,"wins":53},"claude-sonnet-5-5":{"draws":17,"losses":49,"wins":30},"cohere/north-mini-code":{"draws":13,"losses":9,"wins":18},"deepseek/deepseek-v4-flash":{"draws":77,"losses":46,"wins":89},"deepseek/deepseek-v4-pro":{"draws":46,"losses":51,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":59,"losses":45,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":41,"wins":19},"fireworks/ember-1":{"draws":34,"losses":35,"wins":27},"gemini-3.1-pro-preview":{"draws":36,"losses":30,"wins":30},"google/gemini-3.1-flash-lite":{"draws":28,"losses":10,"wins":34},"google/gemini-3.5-flash":{"draws":66,"losses":78,"wins":54},"google/gemini-3.5-flash-lite":{"draws":112,"losses":49,"wins":125},"google/gemini-3.6-flash":{"draws":118,"losses":120,"wins":70},"google/gemini-3.8-flash":{"draws":42,"losses":81,"wins":43},"google/gemma-4-31b-it":{"draws":27,"losses":6,"wins":23},"gpt-4.1":{"draws":12,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":31,"losses":32,"wins":31},"gpt-5.4":{"draws":44,"losses":65,"wins":45},"gpt-5.4-mini":{"draws":25,"losses":13,"wins":26},"gpt-5.4-nano":{"draws":31,"losses":29,"wins":46},"gpt-5.5":{"draws":37,"losses":42,"wins":21},"gpt-5.6-luna":{"draws":60,"losses":50,"wins":62},"gpt-5.6-sol":{"draws":35,"losses":94,"wins":35},"gpt-5.6-terra":{"draws":52,"losses":52,"wins":50},"gpt-6-astra":{"draws":22,"losses":131,"wins":5},"gpt-6-luna":{"draws":28,"losses":35,"wins":33},"gpt-6-sol":{"draws":9,"losses":69,"wins":18},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":60,"losses":12,"wins":52},"inclusionai/ling-3.0-flash":{"draws":39,"losses":11,"wins":50},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":56,"losses":30,"wins":60},"meta/muse-glimmer-30b":{"draws":67,"losses":39,"wins":38},"meta/muse-spark-1.2":{"draws":40,"losses":56,"wins":44},"meta/muse-spark-1.3":{"draws":41,"losses":69,"wins":42},"meta/muse-wonder":{"draws":24,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":17,"losses":19,"wins":28},"mistralai/mistral-large-4-0":{"draws":22,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":39,"losses":11,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":10,"wins":11},"moonshotai/kimi-k3":{"draws":51,"losses":52,"wins":45},"nex-agi/nex-n2-pro":{"draws":24,"losses":6,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":18,"wins":33},"o3":{"draws":42,"losses":71,"wins":79},"openai/gpt-oss-120b":{"draws":56,"losses":36,"wins":50},"poolside/laguna-s-2.1":{"draws":58,"losses":26,"wins":48},"qwen/qwen3.7-max":{"draws":27,"losses":25,"wins":26},"qwen/qwen3.7-plus":{"draws":21,"losses":22,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":69,"wins":52},"qwen/qwen3.8-27b":{"draws":21,"losses":31,"wins":32},"qwen/qwen3.8-flash":{"draws":32,"losses":10,"wins":10},"qwen/qwen3.8-max":{"draws":63,"losses":55,"wins":46},"qwen/qwen3.8-max-0902":{"draws":33,"losses":34,"wins":29},"stealth/ox-alpha":{"draws":157,"losses":208,"wins":175},"stealth/space-bunny-alpha":{"draws":28,"losses":18,"wins":30},"stepfun/step-3.7-flash":{"draws":18,"losses":13,"wins":41},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":15,"wins":24},"tencent/hy4-preview":{"draws":45,"losses":66,"wins":49},"thinkingmachines/inkling":{"draws":54,"losses":31,"wins":73},"thinkingmachines/inkling-small":{"draws":81,"losses":30,"wins":61},"unbiased/pareto-26.10-preview":{"draws":2,"losses":26,"wins":4},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":35,"losses":63,"wins":36},"x-ai/grok-4.6":{"draws":63,"losses":71,"wins":32},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":19,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":65,"losses":30,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":18,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":22,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":35,"wins":16},"z-ai/glm-5.2":{"draws":101,"losses":69,"wins":86},"z-ai/glm-5.3":{"draws":44,"losses":73,"wins":25},"z-ai/glm-5.3-flash":{"draws":52,"losses":58,"wins":54},"z-ai/glm-5.3-flashx":{"draws":32,"losses":42,"wins":22}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":84,"losses":67,"wins":87},"claude-fable-5":{"draws":41,"losses":131,"wins":70},"claude-fable-5-1":{"draws":14,"losses":246,"wins":8},"claude-haiku-5-5":{"draws":34,"losses":67,"wins":37},"claude-opus-4-5":{"draws":101,"losses":88,"wins":140},"claude-opus-4-8":{"draws":30,"losses":65,"wins":49},"claude-opus-5":{"draws":39,"losses":195,"wins":32},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":81,"losses":82,"wins":102},"claude-sonnet-5-5":{"draws":23,"losses":80,"wins":41},"cohere/north-mini-code":{"draws":10,"losses":4,"wins":42},"deepseek/deepseek-v4-flash":{"draws":109,"losses":58,"wins":151},"deepseek/deepseek-v4-pro":{"draws":67,"losses":65,"wins":102},"deepseek/deepseek-v4-pro-0813":{"draws":79,"losses":69,"wins":86},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":55,"wins":48},"fireworks/ember-1":{"draws":46,"losses":57,"wins":41},"gemini-3.1-pro-preview":{"draws":43,"losses":47,"wins":54},"google/gemini-3.1-flash-lite":{"draws":29,"losses":1,"wins":66},"google/gemini-3.5-flash":{"draws":90,"losses":101,"wins":87},"google/gemini-3.5-flash-lite":{"draws":152,"losses":95,"wins":190},"google/gemini-3.6-flash":{"draws":132,"losses":184,"wins":159},"google/gemini-3.8-flash":{"draws":68,"losses":101,"wins":81},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":23,"losses":13,"wins":16},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":43,"losses":29,"wins":56},"gpt-5.4":{"draws":76,"losses":92,"wins":84},"gpt-5.4-mini":{"draws":47,"losses":19,"wins":40},"gpt-5.4-nano":{"draws":36,"losses":37,"wins":77},"gpt-5.5":{"draws":44,"losses":51,"wins":43},"gpt-5.6-luna":{"draws":90,"losses":54,"wins":106},"gpt-5.6-sol":{"draws":50,"losses":146,"wins":61},"gpt-5.6-terra":{"draws":106,"losses":66,"wins":80},"gpt-6-astra":{"draws":26,"losses":210,"wins":4},"gpt-6-luna":{"draws":37,"losses":50,"wins":57},"gpt-6-sol":{"draws":17,"losses":99,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":124,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":80,"losses":16,"wins":78},"inclusionai/ling-3.0-flash":{"draws":54,"losses":21,"wins":62},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":70,"losses":39,"wins":110},"meta/muse-glimmer-30b":{"draws":69,"losses":47,"wins":90},"meta/muse-spark-1.2":{"draws":59,"losses":68,"wins":82},"meta/muse-spark-1.3":{"draws":55,"losses":104,"wins":57},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":25,"losses":14,"wins":41},"mistralai/mistral-large-4-0":{"draws":31,"losses":30,"wins":29},"mistralai/mistral-medium-3-5":{"draws":50,"losses":17,"wins":79},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":59,"losses":78,"wins":80},"nex-agi/nex-n2-pro":{"draws":23,"losses":6,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":22,"wins":60},"o3":{"draws":55,"losses":99,"wins":148},"openai/gpt-oss-120b":{"draws":81,"losses":17,"wins":112},"poolside/laguna-s-2.1":{"draws":77,"losses":44,"wins":74},"qwen/qwen3.7-max":{"draws":38,"losses":24,"wins":30},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":84,"losses":87,"wins":83},"qwen/qwen3.8-27b":{"draws":39,"losses":44,"wins":45},"qwen/qwen3.8-flash":{"draws":63,"losses":46,"wins":55},"qwen/qwen3.8-max":{"draws":76,"losses":88,"wins":88},"qwen/qwen3.8-max-0902":{"draws":37,"losses":63,"wins":44},"stealth/ox-alpha":{"draws":224,"losses":327,"wins":281},"stealth/space-bunny-alpha":{"draws":37,"losses":31,"wins":46},"stepfun/step-3.7-flash":{"draws":27,"losses":17,"wins":62},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":30,"losses":13,"wins":35},"tencent/hy4-preview":{"draws":61,"losses":105,"wins":76},"thinkingmachines/inkling":{"draws":75,"losses":43,"wins":112},"thinkingmachines/inkling-small":{"draws":136,"losses":102,"wins":153},"unbiased/pareto-26.10-preview":{"draws":1,"losses":44,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":22},"x-ai/grok-4.5":{"draws":60,"losses":99,"wins":74},"x-ai/grok-4.6":{"draws":72,"losses":113,"wins":77},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":21,"losses":9,"wins":20},"xiaomi/mimo-v2.5":{"draws":86,"losses":43,"wins":105},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":23,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":38,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":52,"wins":19},"z-ai/glm-5.2":{"draws":139,"losses":104,"wins":149},"z-ai/glm-5.3":{"draws":51,"losses":108,"wins":53},"z-ai/glm-5.3-flash":{"draws":70,"losses":87,"wins":89},"z-ai/glm-5.3-flashx":{"draws":40,"losses":56,"wins":48}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":21,"wins":74},"claude-fable-5":{"draws":29,"losses":81,"wins":34},"claude-fable-5-1":{"draws":5,"losses":141,"wins":16},"claude-haiku-5-5":{"draws":40,"losses":50,"wins":48},"claude-opus-4-5":{"draws":66,"losses":77,"wins":91},"claude-opus-4-8":{"draws":35,"losses":50,"wins":47},"claude-opus-5":{"draws":35,"losses":169,"wins":42},"claude-opus-5-5":{"draws":16,"losses":128,"wins":12},"claude-sonnet-5":{"draws":42,"losses":36,"wins":66},"claude-sonnet-5-5":{"draws":26,"losses":67,"wins":51},"cohere/north-mini-code":{"draws":10,"losses":5,"wins":39},"deepseek/deepseek-v4-flash":{"draws":64,"losses":29,"wins":123},"deepseek/deepseek-v4-pro":{"draws":36,"losses":34,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":38,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":48,"losses":51,"wins":45},"fireworks/ember-1":{"draws":44,"losses":43,"wins":57},"gemini-3.1-pro-preview":{"draws":40,"losses":36,"wins":68},"google/gemini-3.1-flash-lite":{"draws":28,"losses":2,"wins":66},"google/gemini-3.5-flash":{"draws":51,"losses":45,"wins":84},"google/gemini-3.5-flash-lite":{"draws":78,"losses":35,"wins":139},"google/gemini-3.6-flash":{"draws":78,"losses":94,"wins":104},"google/gemini-3.8-flash":{"draws":39,"losses":60,"wins":45},"google/gemma-4-31b-it":{"draws":29,"losses":9,"wins":46},"gpt-4.1":{"draws":18,"losses":7,"wins":23},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":38,"losses":30,"wins":58},"gpt-5.4":{"draws":34,"losses":60,"wins":44},"gpt-5.4-mini":{"draws":38,"losses":14,"wins":44},"gpt-5.4-nano":{"draws":38,"losses":35,"wins":71},"gpt-5.5":{"draws":47,"losses":42,"wins":43},"gpt-5.6-luna":{"draws":51,"losses":32,"wins":61},"gpt-5.6-sol":{"draws":23,"losses":87,"wins":34},"gpt-5.6-terra":{"draws":48,"losses":37,"wins":53},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":41,"losses":47,"wins":56},"gpt-6-sol":{"draws":16,"losses":100,"wins":28},"gpt-6.1-sol":{"draws":12,"losses":121,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":44,"losses":10,"wins":48},"inclusionai/ling-3.0-flash":{"draws":39,"losses":9,"wins":54},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":23,"wins":101},"meta/muse-glimmer-30b":{"draws":46,"losses":12,"wins":68},"meta/muse-spark-1.2":{"draws":31,"losses":52,"wins":55},"meta/muse-spark-1.3":{"draws":39,"losses":52,"wins":53},"meta/muse-wonder":{"draws":33,"losses":78,"wins":33},"minimax/minimax-m3":{"draws":21,"losses":8,"wins":49},"mistralai/mistral-large-4-0":{"draws":32,"losses":18,"wins":40},"mistralai/mistral-medium-3-5":{"draws":29,"losses":6,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":8,"wins":17},"moonshotai/kimi-k3":{"draws":36,"losses":34,"wins":68},"nex-agi/nex-n2-pro":{"draws":21,"losses":9,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":12,"wins":65},"o3":{"draws":37,"losses":64,"wins":97},"openai/gpt-oss-120b":{"draws":43,"losses":13,"wins":70},"poolside/laguna-s-2.1":{"draws":45,"losses":23,"wins":70},"qwen/qwen3.7-max":{"draws":26,"losses":17,"wins":41},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":44,"wins":53},"qwen/qwen3.8-27b":{"draws":26,"losses":27,"wins":49},"qwen/qwen3.8-flash":{"draws":33,"losses":29,"wins":34},"qwen/qwen3.8-max":{"draws":37,"losses":44,"wins":63},"qwen/qwen3.8-max-0902":{"draws":24,"losses":36,"wins":36},"stealth/ox-alpha":{"draws":113,"losses":176,"wins":185},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":27,"losses":19,"wins":56},"stepfun/step-5-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":29,"losses":13,"wins":36},"tencent/hy4-preview":{"draws":34,"losses":54,"wins":50},"thinkingmachines/inkling":{"draws":54,"losses":30,"wins":108},"thinkingmachines/inkling-small":{"draws":49,"losses":15,"wins":80},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":31,"losses":61,"wins":52},"x-ai/grok-4.6":{"draws":44,"losses":66,"wins":34},"x-ai/grok-4.7":{"draws":18,"losses":81,"wins":27},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":84,"losses":27,"wins":111},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":20,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":39,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":52,"wins":30},"z-ai/glm-5.2":{"draws":97,"losses":57,"wins":134},"z-ai/glm-5.3":{"draws":36,"losses":72,"wins":30},"z-ai/glm-5.3-flash":{"draws":43,"losses":52,"wins":49},"z-ai/glm-5.3-flashx":{"draws":36,"losses":57,"wins":51}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":176,"losses":158,"wins":404},"claude-fable-5":{"draws":172,"losses":474,"wins":188},"claude-fable-5-1":{"draws":78,"losses":859,"wins":49},"claude-haiku-5-5":{"draws":96,"losses":173,"wins":165},"claude-opus-4-5":{"draws":292,"losses":304,"wins":448},"claude-opus-4-8":{"draws":100,"losses":160,"wins":168},"claude-opus-5":{"draws":137,"losses":655,"wins":134},"claude-opus-5-5":{"draws":50,"losses":425,"wins":31},"claude-sonnet-5":{"draws":203,"losses":245,"wins":414},"claude-sonnet-5-5":{"draws":85,"losses":225,"wins":164},"cohere/north-mini-code":{"draws":33,"losses":23,"wins":128},"deepseek/deepseek-v4-flash":{"draws":275,"losses":199,"wins":540},"deepseek/deepseek-v4-pro":{"draws":210,"losses":236,"wins":320},"deepseek/deepseek-v4-pro-0813":{"draws":204,"losses":267,"wins":299},"deepseek/deepseek-v4.1-flash":{"draws":111,"losses":181,"wins":181},"fireworks/ember-1":{"draws":126,"losses":170,"wins":178},"gemini-3.1-pro-preview":{"draws":107,"losses":145,"wins":222},"google/gemini-3.1-flash-lite":{"draws":56,"losses":31,"wins":197},"google/gemini-3.5-flash":{"draws":204,"losses":330,"wins":392},"google/gemini-3.5-flash-lite":{"draws":338,"losses":296,"wins":760},"google/gemini-3.6-flash":{"draws":320,"losses":597,"wins":565},"google/gemini-3.8-flash":{"draws":185,"losses":399,"wins":276},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":49,"losses":36,"wins":79},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":34},"gpt-5":{"draws":107,"losses":130,"wins":209},"gpt-5.4":{"draws":246,"losses":317,"wins":253},"gpt-5.4-mini":{"draws":95,"losses":66,"wins":167},"gpt-5.4-nano":{"draws":85,"losses":121,"wins":246},"gpt-5.5":{"draws":129,"losses":161,"wins":172},"gpt-5.6-luna":{"draws":260,"losses":187,"wins":355},"gpt-5.6-sol":{"draws":128,"losses":515,"wins":219},"gpt-5.6-terra":{"draws":248,"losses":227,"wins":319},"gpt-6-astra":{"draws":93,"losses":709,"wins":44},"gpt-6-luna":{"draws":113,"losses":153,"wins":208},"gpt-6-sol":{"draws":62,"losses":340,"wins":72},"gpt-6.1-sol":{"draws":44,"losses":400,"wins":30},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":170,"losses":64,"wins":272},"inclusionai/ling-3.0-flash":{"draws":109,"losses":41,"wins":250},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":160,"losses":100,"wins":410},"meta/muse-glimmer-30b":{"draws":191,"losses":104,"wins":397},"meta/muse-spark-1.2":{"draws":164,"losses":215,"wins":317},"meta/muse-spark-1.3":{"draws":148,"losses":308,"wins":256},"meta/muse-wonder":{"draws":93,"losses":253,"wins":128},"minimax/minimax-m3":{"draws":64,"losses":41,"wins":155},"mistralai/mistral-large-4-0":{"draws":98,"losses":82,"wins":120},"mistralai/mistral-medium-3-5":{"draws":130,"losses":72,"wins":258},"moonshotai/kimi-k2.7-code":{"draws":25,"losses":31,"wins":50},"moonshotai/kimi-k3":{"draws":182,"losses":247,"wins":289},"nex-agi/nex-n2-pro":{"draws":63,"losses":32,"wins":171},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":112,"losses":60,"wins":212},"o3":{"draws":122,"losses":329,"wins":433},"openai/gpt-oss-120b":{"draws":197,"losses":100,"wins":393},"poolside/laguna-s-2.1":{"draws":194,"losses":118,"wins":354},"qwen/qwen3.7-max":{"draws":69,"losses":62,"wins":147},"qwen/qwen3.7-plus":{"draws":47,"losses":27,"wins":142},"qwen/qwen3.8-2.4t-a95b":{"draws":228,"losses":300,"wins":314},"qwen/qwen3.8-27b":{"draws":89,"losses":150,"wins":183},"qwen/qwen3.8-flash":{"draws":157,"losses":175,"wins":208},"qwen/qwen3.8-max":{"draws":224,"losses":281,"wins":327},"qwen/qwen3.8-max-0902":{"draws":113,"losses":185,"wins":176},"stealth/ox-alpha":{"draws":630,"losses":1271,"wins":1271},"stealth/space-bunny-alpha":{"draws":99,"losses":83,"wins":188},"stepfun/step-3.7-flash":{"draws":58,"losses":58,"wins":228},"stepfun/step-5-preview":{"draws":8,"losses":15,"wins":9},"tencent/hy3-preview":{"draws":81,"losses":52,"wins":123},"tencent/hy4-preview":{"draws":195,"losses":345,"wins":268},"thinkingmachines/inkling":{"draws":203,"losses":146,"wins":459},"thinkingmachines/inkling-small":{"draws":255,"losses":127,"wins":440},"unbiased/pareto-26.10-preview":{"draws":10,"losses":141,"wins":7},"upstage/solar-mini4":{"draws":13,"losses":15,"wins":74},"x-ai/grok-4.5":{"draws":157,"losses":317,"wins":242},"x-ai/grok-4.6":{"draws":247,"losses":347,"wins":264},"x-ai/grok-4.7":{"draws":48,"losses":281,"wins":71},"x-ai/grok-build-0.1":{"draws":44,"losses":19,"wins":107},"xiaomi/mimo-v2.5":{"draws":179,"losses":97,"wins":404},"xiaomi/mimo-v2.5-pro":{"draws":51,"losses":70,"wins":145},"xiaomi/mimo-v2.6-flash":{"draws":57,"losses":108,"wins":133},"xiaomi/mimo-v2.6-pro":{"draws":57,"losses":154,"wins":105},"z-ai/glm-5.2":{"draws":364,"losses":303,"wins":625},"z-ai/glm-5.3":{"draws":141,"losses":366,"wins":193},"z-ai/glm-5.3-flash":{"draws":181,"losses":352,"wins":313},"z-ai/glm-5.3-flashx":{"draws":85,"losses":221,"wins":168}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":31,"wins":38},"claude-fable-5":{"draws":31,"losses":68,"wins":15},"claude-fable-5-1":{"draws":6,"losses":121,"wins":3},"claude-haiku-5-5":{"draws":33,"losses":54,"wins":23},"claude-opus-4-5":{"draws":58,"losses":79,"wins":49},"claude-opus-4-8":{"draws":30,"losses":52,"wins":24},"claude-opus-5":{"draws":29,"losses":153,"wins":14},"claude-opus-5-5":{"draws":5,"losses":116,"wins":1},"claude-sonnet-5":{"draws":30,"losses":47,"wins":37},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":24},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":60,"losses":38,"wins":70},"deepseek/deepseek-v4-pro":{"draws":31,"losses":47,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":47,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":53,"wins":25},"fireworks/ember-1":{"draws":36,"losses":55,"wins":23},"gemini-3.1-pro-preview":{"draws":36,"losses":44,"wins":34},"google/gemini-3.1-flash-lite":{"draws":21,"losses":12,"wins":47},"google/gemini-3.5-flash":{"draws":43,"losses":68,"wins":33},"google/gemini-3.5-flash-lite":{"draws":58,"losses":60,"wins":84},"google/gemini-3.6-flash":{"draws":59,"losses":117,"wins":44},"google/gemini-3.8-flash":{"draws":31,"losses":66,"wins":17},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":15,"losses":10,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":26,"losses":39,"wins":35},"gpt-5.4":{"draws":34,"losses":60,"wins":16},"gpt-5.4-mini":{"draws":28,"losses":15,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":39,"wins":47},"gpt-5.5":{"draws":41,"losses":46,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":31,"wins":40},"gpt-5.6-sol":{"draws":20,"losses":80,"wins":14},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":41,"losses":50,"wins":23},"gpt-6-sol":{"draws":16,"losses":87,"wins":11},"gpt-6.1-sol":{"draws":9,"losses":100,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":37,"losses":10,"wins":35},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":31},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":29,"wins":57},"meta/muse-glimmer-30b":{"draws":39,"losses":27,"wins":36},"meta/muse-spark-1.2":{"draws":31,"losses":53,"wins":26},"meta/muse-spark-1.3":{"draws":24,"losses":69,"wins":21},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":18,"losses":13,"wins":31},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":14},"mistralai/mistral-medium-3-5":{"draws":24,"losses":12,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":37,"losses":53,"wins":20},"nex-agi/nex-n2-pro":{"draws":17,"losses":13,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":25,"wins":32},"o3":{"draws":28,"losses":76,"wins":56},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":44},"poolside/laguna-s-2.1":{"draws":33,"losses":33,"wins":40},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":22},"qwen/qwen3.7-plus":{"draws":18,"losses":9,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":27},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":28,"losses":30,"wins":18},"qwen/qwen3.8-max":{"draws":37,"losses":46,"wins":31},"qwen/qwen3.8-max-0902":{"draws":36,"losses":59,"wins":19},"stealth/ox-alpha":{"draws":99,"losses":188,"wins":83},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":18},"stepfun/step-3.7-flash":{"draws":21,"losses":23,"wins":36},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":17,"wins":21},"tencent/hy4-preview":{"draws":33,"losses":51,"wins":26},"thinkingmachines/inkling":{"draws":50,"losses":43,"wins":61},"thinkingmachines/inkling-small":{"draws":38,"losses":29,"wins":47},"unbiased/pareto-26.10-preview":{"draws":1,"losses":37,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":9,"wins":16},"x-ai/grok-4.5":{"draws":31,"losses":63,"wins":20},"x-ai/grok-4.6":{"draws":36,"losses":59,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":16},"xiaomi/mimo-v2.5":{"draws":71,"losses":38,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":89,"losses":74,"wins":65},"z-ai/glm-5.3":{"draws":25,"losses":76,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":67,"wins":17},"z-ai/glm-5.3-flashx":{"draws":33,"losses":59,"wins":22}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":42,"wins":33},"claude-fable-5":{"draws":15,"losses":83,"wins":8},"claude-fable-5-1":{"draws":3,"losses":111,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":67,"wins":16},"claude-opus-4-5":{"draws":36,"losses":116,"wins":46},"claude-opus-4-8":{"draws":18,"losses":74,"wins":22},"claude-opus-5":{"draws":14,"losses":157,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":26,"losses":51,"wins":31},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":26},"cohere/north-mini-code":{"draws":12,"losses":5,"wins":25},"deepseek/deepseek-v4-flash":{"draws":45,"losses":66,"wins":69},"deepseek/deepseek-v4-pro":{"draws":23,"losses":52,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":51,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":60,"wins":16},"fireworks/ember-1":{"draws":23,"losses":61,"wins":18},"gemini-3.1-pro-preview":{"draws":25,"losses":45,"wins":32},"google/gemini-3.1-flash-lite":{"draws":18,"losses":13,"wins":69},"google/gemini-3.5-flash":{"draws":28,"losses":80,"wins":28},"google/gemini-3.5-flash-lite":{"draws":59,"losses":76,"wins":63},"google/gemini-3.6-flash":{"draws":43,"losses":140,"wins":32},"google/gemini-3.8-flash":{"draws":22,"losses":75,"wins":9},"google/gemma-4-31b-it":{"draws":18,"losses":13,"wins":27},"gpt-4.1":{"draws":11,"losses":25,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":35,"losses":64,"wins":19},"gpt-5.4":{"draws":24,"losses":63,"wins":15},"gpt-5.4-mini":{"draws":28,"losses":23,"wins":25},"gpt-5.4-nano":{"draws":22,"losses":67,"wins":43},"gpt-5.5":{"draws":29,"losses":72,"wins":15},"gpt-5.6-luna":{"draws":30,"losses":41,"wins":33},"gpt-5.6-sol":{"draws":11,"losses":85,"wins":8},"gpt-5.6-terra":{"draws":30,"losses":50,"wins":20},"gpt-6-astra":{"draws":6,"losses":96,"wins":0},"gpt-6-luna":{"draws":22,"losses":57,"wins":23},"gpt-6-sol":{"draws":13,"losses":85,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":99,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":8,"wins":40},"inclusionai/ling-3.0-flash":{"draws":32,"losses":18,"wins":36},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":44,"wins":54},"meta/muse-glimmer-30b":{"draws":26,"losses":41,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":61,"wins":24},"meta/muse-spark-1.3":{"draws":12,"losses":83,"wins":13},"meta/muse-wonder":{"draws":12,"losses":80,"wins":10},"minimax/minimax-m3":{"draws":14,"losses":32,"wins":18},"mistralai/mistral-large-4-0":{"draws":20,"losses":33,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":12,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":17,"wins":7},"moonshotai/kimi-k3":{"draws":23,"losses":57,"wins":16},"nex-agi/nex-n2-pro":{"draws":16,"losses":20,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":38,"wins":44},"o3":{"draws":37,"losses":113,"wins":52},"openai/gpt-oss-120b":{"draws":35,"losses":19,"wins":36},"poolside/laguna-s-2.1":{"draws":37,"losses":33,"wins":34},"qwen/qwen3.7-max":{"draws":20,"losses":41,"wins":13},"qwen/qwen3.7-plus":{"draws":12,"losses":31,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":71,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":38,"wins":27},"qwen/qwen3.8-flash":{"draws":18,"losses":41,"wins":13},"qwen/qwen3.8-max":{"draws":27,"losses":62,"wins":17},"qwen/qwen3.8-max-0902":{"draws":27,"losses":56,"wins":19},"stealth/ox-alpha":{"draws":58,"losses":228,"wins":58},"stealth/space-bunny-alpha":{"draws":21,"losses":36,"wins":23},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":19},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":31,"wins":19},"tencent/hy4-preview":{"draws":22,"losses":61,"wins":17},"thinkingmachines/inkling":{"draws":43,"losses":45,"wins":78},"thinkingmachines/inkling-small":{"draws":32,"losses":33,"wins":37},"unbiased/pareto-26.10-preview":{"draws":1,"losses":33,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":9,"wins":19},"x-ai/grok-4.5":{"draws":12,"losses":80,"wins":20},"x-ai/grok-4.6":{"draws":24,"losses":64,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":75,"wins":10},"x-ai/grok-build-0.1":{"draws":14,"losses":14,"wins":18},"xiaomi/mimo-v2.5":{"draws":56,"losses":69,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":38,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":44,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":52,"wins":8},"z-ai/glm-5.2":{"draws":58,"losses":108,"wins":56},"z-ai/glm-5.3":{"draws":15,"losses":78,"wins":3},"z-ai/glm-5.3-flash":{"draws":25,"losses":65,"wins":18},"z-ai/glm-5.3-flashx":{"draws":17,"losses":71,"wins":14}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":4},"claude-fable-5":{"draws":2,"losses":5,"wins":5},"claude-fable-5-1":{"draws":0,"losses":10,"wins":2},"claude-haiku-5-5":{"draws":3,"losses":4,"wins":5},"claude-opus-4-5":{"draws":3,"losses":7,"wins":10},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":0,"losses":17,"wins":7},"claude-opus-5-5":{"draws":0,"losses":16,"wins":4},"claude-sonnet-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":7},"fireworks/ember-1":{"draws":3,"losses":5,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":5,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":7},"gpt-5.4":{"draws":5,"losses":1,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":9},"gpt-5.5":{"draws":6,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":10,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":8,"wins":4},"gpt-6-luna":{"draws":3,"losses":3,"wins":6},"gpt-6-sol":{"draws":1,"losses":8,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":10,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":5},"meta/muse-wonder":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"o3":{"draws":8,"losses":2,"wins":10},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":8,"losses":9,"wins":15},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":6},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":13},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":7},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":8}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":24,"wins":23},"claude-fable-5":{"draws":22,"losses":47,"wins":11},"claude-fable-5-1":{"draws":8,"losses":74,"wins":4},"claude-haiku-5-5":{"draws":25,"losses":31,"wins":20},"claude-opus-4-5":{"draws":74,"losses":81,"wins":41},"claude-opus-4-8":{"draws":41,"losses":63,"wins":28},"claude-opus-5":{"draws":45,"losses":179,"wins":20},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":32,"losses":33,"wins":25},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":14,"losses":10,"wins":20},"deepseek/deepseek-v4-flash":{"draws":50,"losses":49,"wins":61},"deepseek/deepseek-v4-pro":{"draws":26,"losses":30,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":26,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":36,"wins":15},"fireworks/ember-1":{"draws":30,"losses":36,"wins":12},"gemini-3.1-pro-preview":{"draws":24,"losses":33,"wins":21},"google/gemini-3.1-flash-lite":{"draws":34,"losses":24,"wins":40},"google/gemini-3.5-flash":{"draws":32,"losses":43,"wins":29},"google/gemini-3.5-flash-lite":{"draws":66,"losses":32,"wins":64},"google/gemini-3.6-flash":{"draws":63,"losses":87,"wins":46},"google/gemini-3.8-flash":{"draws":38,"losses":39,"wins":9},"google/gemma-4-31b-it":{"draws":21,"losses":9,"wins":16},"gpt-4.1":{"draws":30,"losses":20,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":42,"losses":39,"wins":43},"gpt-5.4":{"draws":32,"losses":33,"wins":15},"gpt-5.4-mini":{"draws":36,"losses":22,"wins":28},"gpt-5.4-nano":{"draws":36,"losses":31,"wins":61},"gpt-5.5":{"draws":67,"losses":52,"wins":17},"gpt-5.6-luna":{"draws":31,"losses":21,"wins":28},"gpt-5.6-sol":{"draws":14,"losses":58,"wins":10},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":16},"gpt-6-astra":{"draws":11,"losses":67,"wins":0},"gpt-6-luna":{"draws":27,"losses":31,"wins":20},"gpt-6-sol":{"draws":15,"losses":58,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":68,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":15,"wins":17},"inclusionai/ling-3.0-flash":{"draws":37,"losses":11,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":47,"losses":39,"wins":46},"meta/muse-glimmer-30b":{"draws":30,"losses":12,"wins":30},"meta/muse-spark-1.2":{"draws":23,"losses":49,"wins":16},"meta/muse-spark-1.3":{"draws":14,"losses":56,"wins":16},"meta/muse-wonder":{"draws":15,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":34,"losses":22,"wins":40},"mistralai/mistral-large-4-0":{"draws":20,"losses":14,"wins":16},"mistralai/mistral-medium-3-5":{"draws":22,"losses":12,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":14,"wins":10},"moonshotai/kimi-k3":{"draws":32,"losses":35,"wins":21},"nex-agi/nex-n2-pro":{"draws":35,"losses":20,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":77,"losses":26,"wins":43},"o3":{"draws":35,"losses":58,"wins":55},"openai/gpt-oss-120b":{"draws":30,"losses":19,"wins":25},"poolside/laguna-s-2.1":{"draws":36,"losses":32,"wins":38},"qwen/qwen3.7-max":{"draws":44,"losses":33,"wins":19},"qwen/qwen3.7-plus":{"draws":34,"losses":21,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":36,"wins":18},"qwen/qwen3.8-27b":{"draws":17,"losses":32,"wins":15},"qwen/qwen3.8-flash":{"draws":27,"losses":24,"wins":15},"qwen/qwen3.8-max":{"draws":30,"losses":35,"wins":13},"qwen/qwen3.8-max-0902":{"draws":29,"losses":36,"wins":13},"stealth/ox-alpha":{"draws":81,"losses":123,"wins":52},"stealth/space-bunny-alpha":{"draws":24,"losses":21,"wins":17},"stepfun/step-3.7-flash":{"draws":22,"losses":19,"wins":31},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":28,"losses":36,"wins":20},"thinkingmachines/inkling":{"draws":47,"losses":41,"wins":56},"thinkingmachines/inkling-small":{"draws":36,"losses":16,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.5":{"draws":29,"losses":69,"wins":12},"x-ai/grok-4.6":{"draws":31,"losses":46,"wins":13},"x-ai/grok-4.7":{"draws":12,"losses":55,"wins":3},"x-ai/grok-build-0.1":{"draws":13,"losses":8,"wins":21},"xiaomi/mimo-v2.5":{"draws":87,"losses":59,"wins":78},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":26,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":22,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.2":{"draws":85,"losses":72,"wins":65},"z-ai/glm-5.3":{"draws":15,"losses":52,"wins":11},"z-ai/glm-5.3-flash":{"draws":25,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":46,"wins":14}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":30,"wins":122},"claude-fable-5":{"draws":42,"losses":141,"wins":57},"claude-fable-5-1":{"draws":12,"losses":229,"wins":25},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":86,"losses":83,"wins":141},"claude-opus-4-8":{"draws":34,"losses":51,"wins":61},"claude-opus-5":{"draws":29,"losses":199,"wins":36},"claude-opus-5-5":{"draws":12,"losses":125,"wins":13},"claude-sonnet-5":{"draws":78,"losses":64,"wins":116},"claude-sonnet-5-5":{"draws":24,"losses":67,"wins":47},"cohere/north-mini-code":{"draws":17,"losses":3,"wins":36},"deepseek/deepseek-v4-flash":{"draws":87,"losses":58,"wins":157},"deepseek/deepseek-v4-pro":{"draws":67,"losses":65,"wins":100},"deepseek/deepseek-v4-pro-0813":{"draws":59,"losses":72,"wins":97},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":41,"wins":56},"fireworks/ember-1":{"draws":42,"losses":42,"wins":54},"gemini-3.1-pro-preview":{"draws":33,"losses":40,"wins":65},"google/gemini-3.1-flash-lite":{"draws":23,"losses":3,"wins":74},"google/gemini-3.5-flash":{"draws":63,"losses":74,"wins":143},"google/gemini-3.5-flash-lite":{"draws":126,"losses":84,"wins":218},"google/gemini-3.6-flash":{"draws":106,"losses":174,"wins":176},"google/gemini-3.8-flash":{"draws":55,"losses":90,"wins":91},"google/gemma-4-31b-it":{"draws":26,"losses":11,"wins":43},"gpt-4.1":{"draws":13,"losses":11,"wins":28},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":11},"gpt-5":{"draws":42,"losses":36,"wins":52},"gpt-5.4":{"draws":61,"losses":102,"wins":79},"gpt-5.4-mini":{"draws":35,"losses":13,"wins":48},"gpt-5.4-nano":{"draws":23,"losses":32,"wins":91},"gpt-5.5":{"draws":46,"losses":41,"wins":47},"gpt-5.6-luna":{"draws":77,"losses":46,"wins":111},"gpt-5.6-sol":{"draws":35,"losses":132,"wins":83},"gpt-5.6-terra":{"draws":61,"losses":65,"wins":100},"gpt-6-astra":{"draws":20,"losses":210,"wins":14},"gpt-6-luna":{"draws":39,"losses":35,"wins":64},"gpt-6-sol":{"draws":19,"losses":92,"wins":27},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":71,"losses":15,"wins":78},"inclusionai/ling-3.0-flash":{"draws":43,"losses":9,"wins":76},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":57,"losses":27,"wins":116},"meta/muse-glimmer-30b":{"draws":81,"losses":20,"wins":105},"meta/muse-spark-1.2":{"draws":35,"losses":73,"wins":92},"meta/muse-spark-1.3":{"draws":46,"losses":83,"wins":79},"meta/muse-wonder":{"draws":28,"losses":71,"wins":39},"minimax/minimax-m3":{"draws":19,"losses":7,"wins":52},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":36},"mistralai/mistral-medium-3-5":{"draws":50,"losses":11,"wins":75},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":20},"moonshotai/kimi-k3":{"draws":59,"losses":71,"wins":80},"nex-agi/nex-n2-pro":{"draws":19,"losses":6,"wins":51},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":14,"wins":67},"o3":{"draws":46,"losses":92,"wins":154},"openai/gpt-oss-120b":{"draws":74,"losses":32,"wins":88},"poolside/laguna-s-2.1":{"draws":68,"losses":35,"wins":93},"qwen/qwen3.7-max":{"draws":18,"losses":18,"wins":50},"qwen/qwen3.7-plus":{"draws":18,"losses":11,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":72,"losses":75,"wins":97},"qwen/qwen3.8-27b":{"draws":30,"losses":38,"wins":56},"qwen/qwen3.8-flash":{"draws":45,"losses":49,"wins":66},"qwen/qwen3.8-max":{"draws":61,"losses":76,"wins":105},"qwen/qwen3.8-max-0902":{"draws":34,"losses":50,"wins":54},"stealth/ox-alpha":{"draws":195,"losses":268,"wins":345},"stealth/space-bunny-alpha":{"draws":33,"losses":26,"wins":51},"stepfun/step-3.7-flash":{"draws":22,"losses":17,"wins":61},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":36},"tencent/hy4-preview":{"draws":30,"losses":55,"wins":55},"thinkingmachines/inkling":{"draws":70,"losses":35,"wins":127},"thinkingmachines/inkling-small":{"draws":85,"losses":27,"wins":136},"unbiased/pareto-26.10-preview":{"draws":2,"losses":41,"wins":3},"upstage/solar-mini4":{"draws":6,"losses":4,"wins":26},"x-ai/grok-4.5":{"draws":46,"losses":83,"wins":85},"x-ai/grok-4.6":{"draws":74,"losses":102,"wins":66},"x-ai/grok-4.7":{"draws":12,"losses":73,"wins":35},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":72,"losses":19,"wins":135},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":16,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":35,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":43,"wins":33},"z-ai/glm-5.2":{"draws":105,"losses":79,"wins":186},"z-ai/glm-5.3":{"draws":39,"losses":126,"wins":43},"z-ai/glm-5.3-flash":{"draws":55,"losses":100,"wins":81},"z-ai/glm-5.3-flashx":{"draws":32,"losses":49,"wins":57}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":77,"losses":93,"wins":58},"claude-fable-5":{"draws":49,"losses":162,"wins":11},"claude-fable-5-1":{"draws":13,"losses":229,"wins":0},"claude-haiku-5-5":{"draws":49,"losses":110,"wins":23},"claude-opus-4-5":{"draws":161,"losses":247,"wins":74},"claude-opus-4-8":{"draws":57,"losses":143,"wins":32},"claude-opus-5":{"draws":59,"losses":335,"wins":44},"claude-opus-5-5":{"draws":18,"losses":186,"wins":0},"claude-sonnet-5":{"draws":92,"losses":164,"wins":42},"claude-sonnet-5-5":{"draws":41,"losses":110,"wins":41},"cohere/north-mini-code":{"draws":22,"losses":27,"wins":35},"deepseek/deepseek-v4-flash":{"draws":126,"losses":118,"wins":126},"deepseek/deepseek-v4-pro":{"draws":76,"losses":117,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":76,"losses":94,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":63,"losses":99,"wins":30},"fireworks/ember-1":{"draws":60,"losses":107,"wins":25},"gemini-3.1-pro-preview":{"draws":58,"losses":86,"wins":48},"google/gemini-3.1-flash-lite":{"draws":55,"losses":49,"wins":84},"google/gemini-3.5-flash":{"draws":72,"losses":159,"wins":61},"google/gemini-3.5-flash-lite":{"draws":200,"losses":251,"wins":199},"google/gemini-3.6-flash":{"draws":191,"losses":361,"wins":98},"google/gemini-3.8-flash":{"draws":63,"losses":138,"wins":21},"google/gemma-4-31b-it":{"draws":40,"losses":32,"wins":36},"gpt-4.1":{"draws":24,"losses":33,"wins":35},"gpt-4.1-nano":{"draws":14,"losses":1,"wins":7},"gpt-5":{"draws":65,"losses":113,"wins":50},"gpt-5.4":{"draws":74,"losses":153,"wins":47},"gpt-5.4-mini":{"draws":71,"losses":54,"wins":49},"gpt-5.4-nano":{"draws":51,"losses":96,"wins":85},"gpt-5.5":{"draws":77,"losses":130,"wins":45},"gpt-5.6-luna":{"draws":107,"losses":126,"wins":63},"gpt-5.6-sol":{"draws":47,"losses":206,"wins":25},"gpt-5.6-terra":{"draws":70,"losses":114,"wins":42},"gpt-6-astra":{"draws":12,"losses":197,"wins":3},"gpt-6-luna":{"draws":56,"losses":96,"wins":40},"gpt-6-sol":{"draws":25,"losses":154,"wins":13},"gpt-6.1-sol":{"draws":13,"losses":173,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":72,"losses":40,"wins":54},"inclusionai/ling-3.0-flash":{"draws":98,"losses":57,"wins":91},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":90,"losses":115,"wins":137},"meta/muse-glimmer-30b":{"draws":80,"losses":77,"wins":67},"meta/muse-spark-1.2":{"draws":78,"losses":133,"wins":41},"meta/muse-spark-1.3":{"draws":42,"losses":158,"wins":22},"meta/muse-wonder":{"draws":44,"losses":126,"wins":22},"minimax/minimax-m3":{"draws":35,"losses":50,"wins":57},"mistralai/mistral-large-4-0":{"draws":42,"losses":58,"wins":22},"mistralai/mistral-medium-3-5":{"draws":52,"losses":29,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":34,"wins":19},"moonshotai/kimi-k3":{"draws":95,"losses":150,"wins":53},"nex-agi/nex-n2-pro":{"draws":37,"losses":35,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":84,"losses":83,"wins":75},"o3":{"draws":64,"losses":259,"wins":95},"openai/gpt-oss-120b":{"draws":63,"losses":66,"wins":81},"poolside/laguna-s-2.1":{"draws":111,"losses":130,"wins":93},"qwen/qwen3.7-max":{"draws":53,"losses":80,"wins":25},"qwen/qwen3.7-plus":{"draws":37,"losses":52,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":76,"losses":128,"wins":32},"qwen/qwen3.8-27b":{"draws":37,"losses":79,"wins":32},"qwen/qwen3.8-flash":{"draws":54,"losses":73,"wins":31},"qwen/qwen3.8-max":{"draws":75,"losses":112,"wins":43},"qwen/qwen3.8-max-0902":{"draws":54,"losses":108,"wins":30},"stealth/ox-alpha":{"draws":203,"losses":459,"wins":146},"stealth/space-bunny-alpha":{"draws":50,"losses":61,"wins":43},"stepfun/step-3.7-flash":{"draws":43,"losses":78,"wins":45},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":47,"losses":56,"wins":41},"tencent/hy4-preview":{"draws":70,"losses":127,"wins":35},"thinkingmachines/inkling":{"draws":84,"losses":86,"wins":86},"thinkingmachines/inkling-small":{"draws":91,"losses":57,"wins":98},"unbiased/pareto-26.10-preview":{"draws":0,"losses":63,"wins":1},"upstage/solar-mini4":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.5":{"draws":98,"losses":184,"wins":44},"x-ai/grok-4.6":{"draws":77,"losses":118,"wins":25},"x-ai/grok-4.7":{"draws":21,"losses":134,"wins":13},"x-ai/grok-build-0.1":{"draws":32,"losses":32,"wins":22},"xiaomi/mimo-v2.5":{"draws":133,"losses":161,"wins":106},"xiaomi/mimo-v2.5-pro":{"draws":28,"losses":77,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":30,"losses":69,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":89,"wins":14},"z-ai/glm-5.2":{"draws":155,"losses":215,"wins":122},"z-ai/glm-5.3":{"draws":44,"losses":141,"wins":25},"z-ai/glm-5.3-flash":{"draws":57,"losses":140,"wins":37},"z-ai/glm-5.3-flashx":{"draws":44,"losses":123,"wins":25}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":96,"losses":100,"wins":56},"claude-fable-5":{"draws":51,"losses":141,"wins":26},"claude-fable-5-1":{"draws":14,"losses":221,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":106,"losses":169,"wins":46},"claude-opus-4-8":{"draws":42,"losses":80,"wins":12},"claude-opus-5":{"draws":35,"losses":204,"wins":13},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":80,"losses":133,"wins":47},"claude-sonnet-5-5":{"draws":32,"losses":91,"wins":21},"cohere/north-mini-code":{"draws":21,"losses":13,"wins":24},"deepseek/deepseek-v4-flash":{"draws":151,"losses":127,"wins":66},"deepseek/deepseek-v4-pro":{"draws":98,"losses":118,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":79,"losses":110,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":73,"wins":25},"fireworks/ember-1":{"draws":50,"losses":77,"wins":17},"gemini-3.1-pro-preview":{"draws":45,"losses":70,"wins":29},"google/gemini-3.1-flash-lite":{"draws":34,"losses":30,"wins":40},"google/gemini-3.5-flash":{"draws":83,"losses":138,"wins":51},"google/gemini-3.5-flash-lite":{"draws":176,"losses":177,"wins":143},"google/gemini-3.6-flash":{"draws":146,"losses":216,"wins":84},"google/gemini-3.8-flash":{"draws":79,"losses":121,"wins":30},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":17,"losses":18,"wins":13},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":53,"losses":55,"wins":20},"gpt-5.4":{"draws":98,"losses":101,"wins":24},"gpt-5.4-mini":{"draws":45,"losses":29,"wins":26},"gpt-5.4-nano":{"draws":53,"losses":56,"wins":45},"gpt-5.5":{"draws":50,"losses":64,"wins":18},"gpt-5.6-luna":{"draws":115,"losses":85,"wins":78},"gpt-5.6-sol":{"draws":35,"losses":171,"wins":25},"gpt-5.6-terra":{"draws":83,"losses":121,"wins":42},"gpt-6-astra":{"draws":15,"losses":187,"wins":0},"gpt-6-luna":{"draws":40,"losses":72,"wins":32},"gpt-6-sol":{"draws":18,"losses":118,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":138,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":95,"losses":44,"wins":63},"inclusionai/ling-3.0-flash":{"draws":63,"losses":28,"wins":50},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":69,"losses":81,"wins":70},"meta/muse-glimmer-30b":{"draws":115,"losses":83,"wins":46},"meta/muse-spark-1.2":{"draws":63,"losses":108,"wins":43},"meta/muse-spark-1.3":{"draws":63,"losses":130,"wins":23},"meta/muse-wonder":{"draws":33,"losses":96,"wins":15},"minimax/minimax-m3":{"draws":25,"losses":34,"wins":21},"mistralai/mistral-large-4-0":{"draws":31,"losses":45,"wins":14},"mistralai/mistral-medium-3-5":{"draws":79,"losses":30,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":79,"losses":108,"wins":35},"nex-agi/nex-n2-pro":{"draws":25,"losses":17,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":59,"losses":35,"wins":34},"o3":{"draws":73,"losses":159,"wins":71},"openai/gpt-oss-120b":{"draws":105,"losses":81,"wins":58},"poolside/laguna-s-2.1":{"draws":97,"losses":87,"wins":29},"qwen/qwen3.7-max":{"draws":32,"losses":39,"wins":17},"qwen/qwen3.7-plus":{"draws":28,"losses":20,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":86,"losses":139,"wins":31},"qwen/qwen3.8-27b":{"draws":33,"losses":80,"wins":17},"qwen/qwen3.8-flash":{"draws":81,"losses":61,"wins":30},"qwen/qwen3.8-max":{"draws":136,"losses":153,"wins":102},"qwen/qwen3.8-max-0902":{"draws":49,"losses":80,"wins":15},"stealth/ox-alpha":{"draws":255,"losses":440,"wins":127},"stealth/space-bunny-alpha":{"draws":38,"losses":47,"wins":29},"stepfun/step-3.7-flash":{"draws":32,"losses":37,"wins":33},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":30,"wins":16},"tencent/hy4-preview":{"draws":85,"losses":136,"wins":27},"thinkingmachines/inkling":{"draws":91,"losses":98,"wins":57},"thinkingmachines/inkling-small":{"draws":110,"losses":85,"wins":85},"unbiased/pareto-26.10-preview":{"draws":1,"losses":47,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.5":{"draws":58,"losses":131,"wins":34},"x-ai/grok-4.6":{"draws":81,"losses":128,"wins":31},"x-ai/grok-4.7":{"draws":15,"losses":109,"wins":2},"x-ai/grok-build-0.1":{"draws":22,"losses":14,"wins":14},"xiaomi/mimo-v2.5":{"draws":98,"losses":67,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":32,"losses":36,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":54,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":71,"wins":12},"z-ai/glm-5.2":{"draws":160,"losses":166,"wins":88},"z-ai/glm-5.3":{"draws":43,"losses":136,"wins":21},"z-ai/glm-5.3-flash":{"draws":81,"losses":128,"wins":39},"z-ai/glm-5.3-flashx":{"draws":36,"losses":85,"wins":23}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"o3":{"draws":0,"losses":3,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":41},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":4,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":27,"wins":4},"claude-opus-4-5":{"draws":9,"losses":39,"wins":12},"claude-opus-4-8":{"draws":6,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":40,"wins":1},"claude-opus-5-5":{"draws":2,"losses":34,"wins":0},"claude-sonnet-5":{"draws":6,"losses":22,"wins":8},"claude-sonnet-5-5":{"draws":4,"losses":26,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":28,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":4},"fireworks/ember-1":{"draws":5,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":19},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":12},"google/gemini-3.5-flash-lite":{"draws":20,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":14,"losses":49,"wins":9},"google/gemini-3.8-flash":{"draws":3,"losses":29,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":11},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":4,"losses":23,"wins":3},"gpt-5.4":{"draws":3,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":11,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":22,"wins":15},"gpt-5.5":{"draws":5,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":17,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":32,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":25,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":1,"losses":25,"wins":10},"gpt-6-sol":{"draws":1,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":26,"wins":8},"meta/muse-wonder":{"draws":3,"losses":32,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":3},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":24,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":14},"o3":{"draws":10,"losses":39,"wins":13},"openai/gpt-oss-120b":{"draws":6,"losses":11,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":26,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":22,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":29,"wins":5},"stealth/ox-alpha":{"draws":13,"losses":74,"wins":15},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":26,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":15,"wins":22},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":6,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":48,"wins":16},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":22,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":29,"wins":120},"claude-fable-5":{"draws":31,"losses":114,"wins":77},"claude-fable-5-1":{"draws":8,"losses":213,"wins":19},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":60},"claude-opus-4-5":{"draws":139,"losses":124,"wins":203},"claude-opus-4-8":{"draws":58,"losses":71,"wins":81},"claude-opus-5":{"draws":59,"losses":280,"wins":79},"claude-opus-5-5":{"draws":18,"losses":123,"wins":15},"claude-sonnet-5":{"draws":103,"losses":66,"wins":157},"claude-sonnet-5-5":{"draws":32,"losses":63,"wins":49},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":54},"deepseek/deepseek-v4-flash":{"draws":62,"losses":55,"wins":187},"deepseek/deepseek-v4-pro":{"draws":54,"losses":70,"wins":84},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":69,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":49,"wins":64},"fireworks/ember-1":{"draws":34,"losses":39,"wins":71},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":73},"google/gemini-3.1-flash-lite":{"draws":27,"losses":4,"wins":95},"google/gemini-3.5-flash":{"draws":55,"losses":86,"wins":121},"google/gemini-3.5-flash-lite":{"draws":175,"losses":132,"wins":369},"google/gemini-3.6-flash":{"draws":149,"losses":288,"wins":283},"google/gemini-3.8-flash":{"draws":40,"losses":76,"wins":104},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":55},"gpt-4.1":{"draws":18,"losses":12,"wins":36},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":35,"losses":44,"wins":95},"gpt-5.4":{"draws":68,"losses":143,"wins":104},"gpt-5.4-mini":{"draws":47,"losses":16,"wins":69},"gpt-5.4-nano":{"draws":36,"losses":49,"wins":113},"gpt-5.5":{"draws":57,"losses":66,"wins":79},"gpt-5.6-luna":{"draws":80,"losses":95,"wins":133},"gpt-5.6-sol":{"draws":41,"losses":181,"wins":106},"gpt-5.6-terra":{"draws":60,"losses":53,"wins":115},"gpt-6-astra":{"draws":10,"losses":184,"wins":22},"gpt-6-luna":{"draws":35,"losses":43,"wins":66},"gpt-6-sol":{"draws":21,"losses":93,"wins":30},"gpt-6.1-sol":{"draws":10,"losses":118,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":56,"losses":7,"wins":91},"inclusionai/ling-3.0-flash":{"draws":62,"losses":19,"wins":145},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":75,"losses":59,"wins":220},"meta/muse-glimmer-30b":{"draws":51,"losses":24,"wins":107},"meta/muse-spark-1.2":{"draws":59,"losses":65,"wins":128},"meta/muse-spark-1.3":{"draws":28,"losses":87,"wins":87},"meta/muse-wonder":{"draws":29,"losses":79,"wins":36},"minimax/minimax-m3":{"draws":20,"losses":8,"wins":80},"mistralai/mistral-large-4-0":{"draws":20,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":32,"losses":14,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":5,"wins":29},"moonshotai/kimi-k3":{"draws":91,"losses":100,"wins":135},"nex-agi/nex-n2-pro":{"draws":26,"losses":7,"wins":69},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":12,"wins":109},"o3":{"draws":34,"losses":127,"wins":237},"openai/gpt-oss-120b":{"draws":57,"losses":19,"wins":108},"poolside/laguna-s-2.1":{"draws":95,"losses":51,"wins":184},"qwen/qwen3.7-max":{"draws":34,"losses":28,"wins":56},"qwen/qwen3.7-plus":{"draws":26,"losses":11,"wins":65},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":74,"wins":90},"qwen/qwen3.8-27b":{"draws":24,"losses":30,"wins":68},"qwen/qwen3.8-flash":{"draws":35,"losses":36,"wins":63},"qwen/qwen3.8-max":{"draws":60,"losses":74,"wins":99},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"stealth/ox-alpha":{"draws":157,"losses":242,"wins":317},"stealth/space-bunny-alpha":{"draws":31,"losses":20,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":20,"wins":80},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":29,"losses":12,"wins":69},"tencent/hy4-preview":{"draws":46,"losses":85,"wins":83},"thinkingmachines/inkling":{"draws":98,"losses":44,"wins":184},"thinkingmachines/inkling-small":{"draws":58,"losses":34,"wins":131},"unbiased/pareto-26.10-preview":{"draws":1,"losses":41,"wins":6},"upstage/solar-mini4":{"draws":5,"losses":6,"wins":25},"x-ai/grok-4.5":{"draws":76,"losses":74,"wins":74},"x-ai/grok-4.6":{"draws":63,"losses":84,"wins":81},"x-ai/grok-4.7":{"draws":17,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":23,"losses":5,"wins":46},"xiaomi/mimo-v2.5":{"draws":91,"losses":26,"wins":177},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":42,"wins":68},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":31,"wins":46},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":101,"losses":88,"wins":199},"z-ai/glm-5.3":{"draws":38,"losses":103,"wins":47},"z-ai/glm-5.3-flash":{"draws":33,"losses":89,"wins":84},"z-ai/glm-5.3-flashx":{"draws":25,"losses":60,"wins":59}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":62,"losses":31,"wins":121},"claude-fable-5":{"draws":64,"losses":116,"wins":90},"claude-fable-5-1":{"draws":18,"losses":246,"wins":44},"claude-haiku-5-5":{"draws":36,"losses":42,"wins":60},"claude-opus-4-5":{"draws":85,"losses":69,"wins":166},"claude-opus-4-8":{"draws":37,"losses":47,"wins":60},"claude-opus-5":{"draws":39,"losses":177,"wins":59},"claude-opus-5-5":{"draws":18,"losses":123,"wins":15},"claude-sonnet-5":{"draws":71,"losses":60,"wins":129},"claude-sonnet-5-5":{"draws":24,"losses":61,"wins":59},"cohere/north-mini-code":{"draws":14,"losses":2,"wins":42},"deepseek/deepseek-v4-flash":{"draws":92,"losses":34,"wins":188},"deepseek/deepseek-v4-pro":{"draws":62,"losses":52,"wins":122},"deepseek/deepseek-v4-pro-0813":{"draws":79,"losses":54,"wins":101},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":40,"losses":42,"wins":62},"gemini-3.1-pro-preview":{"draws":40,"losses":28,"wins":76},"google/gemini-3.1-flash-lite":{"draws":18,"losses":6,"wins":72},"google/gemini-3.5-flash":{"draws":83,"losses":55,"wins":154},"google/gemini-3.5-flash-lite":{"draws":119,"losses":57,"wins":232},"google/gemini-3.6-flash":{"draws":113,"losses":144,"wins":187},"google/gemini-3.8-flash":{"draws":76,"losses":87,"wins":99},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":20,"losses":6,"wins":24},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":42,"losses":21,"wins":73},"gpt-5.4":{"draws":81,"losses":92,"wins":87},"gpt-5.4-mini":{"draws":34,"losses":16,"wins":50},"gpt-5.4-nano":{"draws":24,"losses":24,"wins":96},"gpt-5.5":{"draws":47,"losses":39,"wins":58},"gpt-5.6-luna":{"draws":67,"losses":42,"wins":131},"gpt-5.6-sol":{"draws":53,"losses":118,"wins":105},"gpt-5.6-terra":{"draws":82,"losses":44,"wins":136},"gpt-6-astra":{"draws":22,"losses":224,"wins":28},"gpt-6-luna":{"draws":39,"losses":24,"wins":81},"gpt-6-sol":{"draws":21,"losses":93,"wins":30},"gpt-6.1-sol":{"draws":16,"losses":114,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":52,"losses":17,"wins":89},"inclusionai/ling-3.0-flash":{"draws":44,"losses":7,"wins":73},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":61,"losses":30,"wins":117},"meta/muse-glimmer-30b":{"draws":69,"losses":20,"wins":107},"meta/muse-spark-1.2":{"draws":49,"losses":47,"wins":114},"meta/muse-spark-1.3":{"draws":47,"losses":74,"wins":91},"meta/muse-wonder":{"draws":41,"losses":62,"wins":41},"minimax/minimax-m3":{"draws":24,"losses":4,"wins":56},"mistralai/mistral-large-4-0":{"draws":30,"losses":17,"wins":43},"mistralai/mistral-medium-3-5":{"draws":49,"losses":10,"wins":71},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":8,"wins":18},"moonshotai/kimi-k3":{"draws":58,"losses":54,"wins":104},"nex-agi/nex-n2-pro":{"draws":21,"losses":4,"wins":55},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":13,"wins":67},"o3":{"draws":54,"losses":70,"wins":160},"openai/gpt-oss-120b":{"draws":65,"losses":22,"wins":105},"poolside/laguna-s-2.1":{"draws":60,"losses":21,"wins":107},"qwen/qwen3.7-max":{"draws":21,"losses":16,"wins":47},"qwen/qwen3.7-plus":{"draws":21,"losses":6,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":87,"wins":104},"qwen/qwen3.8-27b":{"draws":32,"losses":38,"wins":64},"qwen/qwen3.8-flash":{"draws":63,"losses":32,"wins":71},"qwen/qwen3.8-max":{"draws":72,"losses":77,"wins":113},"qwen/qwen3.8-max-0902":{"draws":44,"losses":34,"wins":66},"stealth/ox-alpha":{"draws":247,"losses":264,"wins":347},"stealth/space-bunny-alpha":{"draws":36,"losses":19,"wins":59},"stepfun/step-3.7-flash":{"draws":24,"losses":14,"wins":64},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":31,"losses":13,"wins":46},"tencent/hy4-preview":{"draws":74,"losses":66,"wins":102},"thinkingmachines/inkling":{"draws":77,"losses":25,"wins":118},"thinkingmachines/inkling-small":{"draws":81,"losses":31,"wins":128},"unbiased/pareto-26.10-preview":{"draws":4,"losses":40,"wins":4},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":63,"losses":81,"wins":84},"x-ai/grok-4.6":{"draws":64,"losses":56,"wins":56},"x-ai/grok-4.7":{"draws":16,"losses":79,"wins":31},"x-ai/grok-build-0.1":{"draws":17,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":82,"losses":19,"wins":127},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":13,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":32,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":41,"wins":34},"z-ai/glm-5.2":{"draws":115,"losses":69,"wins":216},"z-ai/glm-5.3":{"draws":49,"losses":97,"wins":76},"z-ai/glm-5.3-flash":{"draws":63,"losses":94,"wins":97},"z-ai/glm-5.3-flashx":{"draws":33,"losses":52,"wins":59}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":17,"wins":91},"claude-fable-5":{"draws":7,"losses":43,"wins":76},"claude-fable-5-1":{"draws":6,"losses":95,"wins":39},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":90},"claude-opus-4-5":{"draws":17,"losses":34,"wins":155},"claude-opus-4-8":{"draws":16,"losses":29,"wins":73},"claude-opus-5":{"draws":21,"losses":100,"wins":99},"claude-opus-5-5":{"draws":11,"losses":96,"wins":31},"claude-sonnet-5":{"draws":12,"losses":24,"wins":90},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":64},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":45},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":157},"deepseek/deepseek-v4-pro":{"draws":10,"losses":21,"wins":85},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":83},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":33,"wins":82},"fireworks/ember-1":{"draws":11,"losses":26,"wins":89},"gemini-3.1-pro-preview":{"draws":14,"losses":23,"wins":89},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":79},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":118},"google/gemini-3.5-flash-lite":{"draws":20,"losses":28,"wins":170},"google/gemini-3.6-flash":{"draws":14,"losses":54,"wins":172},"google/gemini-3.8-flash":{"draws":14,"losses":27,"wins":85},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":62},"gpt-4.1":{"draws":4,"losses":4,"wins":34},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":10},"gpt-5":{"draws":10,"losses":18,"wins":84},"gpt-5.4":{"draws":13,"losses":28,"wins":79},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":66},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":104},"gpt-5.5":{"draws":11,"losses":36,"wins":69},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":96},"gpt-5.6-sol":{"draws":16,"losses":44,"wins":66},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":86},"gpt-6-astra":{"draws":12,"losses":92,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":96},"gpt-6-sol":{"draws":13,"losses":50,"wins":63},"gpt-6.1-sol":{"draws":6,"losses":79,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":75},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":120},"meta/muse-glimmer-30b":{"draws":6,"losses":13,"wins":93},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":84},"meta/muse-spark-1.3":{"draws":11,"losses":31,"wins":84},"meta/muse-wonder":{"draws":16,"losses":38,"wins":72},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":61},"mistralai/mistral-large-4-0":{"draws":14,"losses":16,"wins":50},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":24},"moonshotai/kimi-k3":{"draws":13,"losses":27,"wins":82},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":54},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":98},"o3":{"draws":11,"losses":36,"wins":131},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":99},"poolside/laguna-s-2.1":{"draws":11,"losses":14,"wins":99},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":51},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":53},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":30,"wins":86},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":58},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":63},"qwen/qwen3.8-max":{"draws":12,"losses":26,"wins":88},"qwen/qwen3.8-max-0902":{"draws":18,"losses":27,"wins":81},"stealth/ox-alpha":{"draws":48,"losses":71,"wins":281},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":73},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":75},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":12,"losses":3,"wins":55},"tencent/hy4-preview":{"draws":12,"losses":35,"wins":73},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":134},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":109},"unbiased/pareto-26.10-preview":{"draws":3,"losses":31,"wins":8},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":23},"x-ai/grok-4.5":{"draws":17,"losses":27,"wins":82},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":79},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":35},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":35},"xiaomi/mimo-v2.5":{"draws":22,"losses":16,"wins":160},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":18,"wins":55},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":58},"z-ai/glm-5.2":{"draws":29,"losses":34,"wins":189},"z-ai/glm-5.3":{"draws":16,"losses":32,"wins":72},"z-ai/glm-5.3-flash":{"draws":15,"losses":34,"wins":77},"z-ai/glm-5.3-flashx":{"draws":15,"losses":27,"wins":84}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":8},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":47,"losses":65,"wins":18},"claude-opus-4-8":{"draws":24,"losses":50,"wins":14},"claude-opus-5":{"draws":22,"losses":84,"wins":8},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":21,"losses":28,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":40,"losses":38,"wins":26},"deepseek/deepseek-v4-pro":{"draws":18,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":38},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":10},"google/gemini-3.5-flash-lite":{"draws":48,"losses":30,"wins":34},"google/gemini-3.6-flash":{"draws":35,"losses":66,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":14,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":27,"losses":33,"wins":16},"gpt-5.4":{"draws":12,"losses":29,"wins":7},"gpt-5.4-mini":{"draws":28,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":20,"losses":51,"wins":27},"gpt-5.5":{"draws":51,"losses":21,"wins":14},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":26,"wins":7},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":26,"losses":4,"wins":36},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":28,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":33,"wins":11},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":8},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":20,"losses":17,"wins":25},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":16,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":22,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":31,"wins":6},"nex-agi/nex-n2-pro":{"draws":21,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":18,"wins":20},"o3":{"draws":22,"losses":51,"wins":13},"openai/gpt-oss-120b":{"draws":19,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":37,"losses":18,"wins":27},"qwen/qwen3.7-max":{"draws":27,"losses":15,"wins":22},"qwen/qwen3.7-plus":{"draws":17,"losses":22,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":19,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":21,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":44,"losses":107,"wins":19},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":21,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":32,"losses":22,"wins":32},"thinkingmachines/inkling-small":{"draws":22,"losses":14,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":23,"losses":46,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":69,"losses":37,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":26,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":47,"losses":48,"wins":23},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":28,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":82,"losses":82,"wins":52},"claude-fable-5":{"draws":45,"losses":174,"wins":5},"claude-fable-5-1":{"draws":12,"losses":229,"wins":3},"claude-haiku-5-5":{"draws":56,"losses":133,"wins":31},"claude-opus-4-5":{"draws":251,"losses":282,"wins":103},"claude-opus-4-8":{"draws":123,"losses":224,"wins":39},"claude-opus-5":{"draws":87,"losses":426,"wins":35},"claude-opus-5-5":{"draws":11,"losses":227,"wins":4},"claude-sonnet-5":{"draws":88,"losses":113,"wins":37},"claude-sonnet-5-5":{"draws":49,"losses":147,"wins":26},"cohere/north-mini-code":{"draws":49,"losses":40,"wins":41},"deepseek/deepseek-v4-flash":{"draws":177,"losses":140,"wins":161},"deepseek/deepseek-v4-pro":{"draws":83,"losses":99,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":91,"losses":101,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":80,"losses":116,"wins":26},"fireworks/ember-1":{"draws":83,"losses":110,"wins":29},"gemini-3.1-pro-preview":{"draws":74,"losses":99,"wins":49},"google/gemini-3.1-flash-lite":{"draws":111,"losses":76,"wins":133},"google/gemini-3.5-flash":{"draws":98,"losses":153,"wins":57},"google/gemini-3.5-flash-lite":{"draws":163,"losses":162,"wins":135},"google/gemini-3.6-flash":{"draws":180,"losses":264,"wins":62},"google/gemini-3.8-flash":{"draws":70,"losses":138,"wins":20},"google/gemma-4-31b-it":{"draws":61,"losses":32,"wins":41},"gpt-4.1":{"draws":60,"losses":50,"wins":30},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":129,"losses":128,"wins":63},"gpt-5.4":{"draws":67,"losses":138,"wins":13},"gpt-5.4-mini":{"draws":126,"losses":88,"wins":76},"gpt-5.4-nano":{"draws":118,"losses":198,"wins":160},"gpt-5.5":{"draws":164,"losses":156,"wins":34},"gpt-5.6-luna":{"draws":93,"losses":88,"wins":47},"gpt-5.6-sol":{"draws":41,"losses":173,"wins":16},"gpt-5.6-terra":{"draws":86,"losses":127,"wins":15},"gpt-6-astra":{"draws":13,"losses":209,"wins":2},"gpt-6-luna":{"draws":81,"losses":112,"wins":29},"gpt-6-sol":{"draws":36,"losses":170,"wins":16},"gpt-6.1-sol":{"draws":19,"losses":195,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":81,"losses":23,"wins":66},"inclusionai/ling-3.0-flash":{"draws":119,"losses":54,"wins":91},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":131,"losses":132,"wins":117},"meta/muse-glimmer-30b":{"draws":85,"losses":67,"wins":50},"meta/muse-spark-1.2":{"draws":66,"losses":128,"wins":28},"meta/muse-spark-1.3":{"draws":57,"losses":156,"wins":21},"meta/muse-wonder":{"draws":45,"losses":160,"wins":17},"minimax/minimax-m3":{"draws":92,"losses":82,"wins":80},"mistralai/mistral-large-4-0":{"draws":58,"losses":61,"wins":19},"mistralai/mistral-medium-3-5":{"draws":60,"losses":27,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":50,"losses":62,"wins":22},"moonshotai/kimi-k3":{"draws":90,"losses":130,"wins":38},"nex-agi/nex-n2-pro":{"draws":59,"losses":51,"wins":88},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":179,"losses":117,"wins":98},"o3":{"draws":89,"losses":232,"wins":61},"openai/gpt-oss-120b":{"draws":73,"losses":64,"wins":55},"poolside/laguna-s-2.1":{"draws":110,"losses":117,"wins":81},"qwen/qwen3.7-max":{"draws":105,"losses":104,"wins":53},"qwen/qwen3.7-plus":{"draws":88,"losses":79,"wins":69},"qwen/qwen3.8-2.4t-a95b":{"draws":93,"losses":114,"wins":29},"qwen/qwen3.8-27b":{"draws":46,"losses":87,"wins":29},"qwen/qwen3.8-flash":{"draws":65,"losses":57,"wins":30},"qwen/qwen3.8-max":{"draws":86,"losses":105,"wins":43},"qwen/qwen3.8-max-0902":{"draws":84,"losses":111,"wins":27},"stealth/ox-alpha":{"draws":179,"losses":404,"wins":97},"stealth/space-bunny-alpha":{"draws":71,"losses":69,"wins":38},"stepfun/step-3.7-flash":{"draws":56,"losses":63,"wins":69},"stepfun/step-5-preview":{"draws":8,"losses":12,"wins":0},"tencent/hy3-preview":{"draws":87,"losses":78,"wins":59},"tencent/hy4-preview":{"draws":72,"losses":135,"wins":19},"thinkingmachines/inkling":{"draws":133,"losses":106,"wins":161},"thinkingmachines/inkling-small":{"draws":98,"losses":61,"wins":67},"unbiased/pareto-26.10-preview":{"draws":4,"losses":70,"wins":0},"upstage/solar-mini4":{"draws":16,"losses":30,"wins":16},"x-ai/grok-4.5":{"draws":91,"losses":177,"wins":26},"x-ai/grok-4.6":{"draws":82,"losses":127,"wins":19},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":69,"losses":50,"wins":37},"xiaomi/mimo-v2.5":{"draws":286,"losses":173,"wins":173},"xiaomi/mimo-v2.5-pro":{"draws":79,"losses":108,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":81,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":37,"losses":98,"wins":13},"z-ai/glm-5.2":{"draws":249,"losses":260,"wins":129},"z-ai/glm-5.3":{"draws":51,"losses":161,"wins":4},"z-ai/glm-5.3-flash":{"draws":67,"losses":126,"wins":35},"z-ai/glm-5.3-flashx":{"draws":73,"losses":133,"wins":16}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":26,"wins":27},"claude-fable-5":{"draws":9,"losses":71,"wins":4},"claude-fable-5-1":{"draws":2,"losses":90,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":41,"wins":18},"claude-opus-4-5":{"draws":50,"losses":90,"wins":74},"claude-opus-4-8":{"draws":33,"losses":72,"wins":33},"claude-opus-5":{"draws":27,"losses":169,"wins":8},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":13,"losses":50,"wins":29},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":16,"losses":11,"wins":23},"deepseek/deepseek-v4-flash":{"draws":55,"losses":52,"wins":63},"deepseek/deepseek-v4-pro":{"draws":17,"losses":42,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":42,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":20},"fireworks/ember-1":{"draws":25,"losses":35,"wins":18},"gemini-3.1-pro-preview":{"draws":20,"losses":34,"wins":24},"google/gemini-3.1-flash-lite":{"draws":23,"losses":6,"wins":79},"google/gemini-3.5-flash":{"draws":25,"losses":49,"wins":40},"google/gemini-3.5-flash-lite":{"draws":52,"losses":61,"wins":73},"google/gemini-3.6-flash":{"draws":46,"losses":108,"wins":42},"google/gemini-3.8-flash":{"draws":20,"losses":49,"wins":15},"google/gemma-4-31b-it":{"draws":19,"losses":5,"wins":22},"gpt-4.1":{"draws":12,"losses":28,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":36,"losses":44,"wins":30},"gpt-5.4":{"draws":15,"losses":61,"wins":12},"gpt-5.4-mini":{"draws":24,"losses":37,"wins":29},"gpt-5.4-nano":{"draws":38,"losses":55,"wins":75},"gpt-5.5":{"draws":39,"losses":58,"wins":27},"gpt-5.6-luna":{"draws":28,"losses":26,"wins":34},"gpt-5.6-sol":{"draws":14,"losses":59,"wins":21},"gpt-5.6-terra":{"draws":19,"losses":51,"wins":14},"gpt-6-astra":{"draws":4,"losses":80,"wins":2},"gpt-6-luna":{"draws":20,"losses":40,"wins":18},"gpt-6-sol":{"draws":6,"losses":63,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":70,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":16,"wins":27},"inclusionai/ling-3.0-flash":{"draws":35,"losses":20,"wins":49},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":40,"wins":65},"meta/muse-glimmer-30b":{"draws":27,"losses":18,"wins":31},"meta/muse-spark-1.2":{"draws":11,"losses":54,"wins":29},"meta/muse-spark-1.3":{"draws":10,"losses":63,"wins":15},"meta/muse-wonder":{"draws":7,"losses":56,"wins":15},"minimax/minimax-m3":{"draws":23,"losses":30,"wins":39},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":21,"wins":5},"moonshotai/kimi-k3":{"draws":26,"losses":42,"wins":38},"nex-agi/nex-n2-pro":{"draws":22,"losses":20,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":27,"wins":54},"o3":{"draws":28,"losses":74,"wins":66},"openai/gpt-oss-120b":{"draws":23,"losses":20,"wins":29},"poolside/laguna-s-2.1":{"draws":37,"losses":40,"wins":49},"qwen/qwen3.7-max":{"draws":30,"losses":47,"wins":23},"qwen/qwen3.7-plus":{"draws":31,"losses":15,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":45,"wins":22},"qwen/qwen3.8-27b":{"draws":12,"losses":28,"wins":22},"qwen/qwen3.8-flash":{"draws":16,"losses":34,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":45,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":40,"wins":20},"stealth/ox-alpha":{"draws":51,"losses":145,"wins":70},"stealth/space-bunny-alpha":{"draws":24,"losses":23,"wins":15},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":32,"wins":26},"tencent/hy4-preview":{"draws":18,"losses":46,"wins":16},"thinkingmachines/inkling":{"draws":28,"losses":31,"wins":77},"thinkingmachines/inkling-small":{"draws":32,"losses":18,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":18,"losses":68,"wins":42},"x-ai/grok-4.6":{"draws":23,"losses":58,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":7},"x-ai/grok-build-0.1":{"draws":20,"losses":6,"wins":26},"xiaomi/mimo-v2.5":{"draws":79,"losses":51,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":11,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":27,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":29,"wins":16},"z-ai/glm-5.2":{"draws":79,"losses":79,"wins":70},"z-ai/glm-5.3":{"draws":16,"losses":58,"wins":6},"z-ai/glm-5.3-flash":{"draws":18,"losses":52,"wins":16},"z-ai/glm-5.3-flashx":{"draws":24,"losses":39,"wins":15}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":49},"claude-fable-5":{"draws":18,"losses":50,"wins":22},"claude-fable-5-1":{"draws":5,"losses":85,"wins":10},"claude-haiku-5-5":{"draws":21,"losses":38,"wins":27},"claude-opus-4-5":{"draws":33,"losses":45,"wins":68},"claude-opus-4-8":{"draws":16,"losses":28,"wins":38},"claude-opus-5":{"draws":16,"losses":119,"wins":17},"claude-opus-5-5":{"draws":9,"losses":87,"wins":2},"claude-sonnet-5":{"draws":17,"losses":23,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":46,"wins":34},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":33,"losses":26,"wins":79},"deepseek/deepseek-v4-pro":{"draws":22,"losses":28,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":33,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":33,"wins":32},"fireworks/ember-1":{"draws":18,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":17,"losses":31,"wins":42},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":44},"google/gemini-3.5-flash":{"draws":21,"losses":39,"wins":52},"google/gemini-3.5-flash-lite":{"draws":28,"losses":25,"wins":103},"google/gemini-3.6-flash":{"draws":28,"losses":71,"wins":73},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":28},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":32},"gpt-4.1":{"draws":10,"losses":3,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":18,"losses":29,"wins":33},"gpt-5.4":{"draws":23,"losses":36,"wins":27},"gpt-5.4-mini":{"draws":16,"losses":13,"wins":31},"gpt-5.4-nano":{"draws":25,"losses":19,"wins":50},"gpt-5.5":{"draws":26,"losses":33,"wins":23},"gpt-5.6-luna":{"draws":22,"losses":25,"wins":43},"gpt-5.6-sol":{"draws":9,"losses":62,"wins":19},"gpt-5.6-terra":{"draws":20,"losses":34,"wins":32},"gpt-6-astra":{"draws":3,"losses":81,"wins":6},"gpt-6-luna":{"draws":22,"losses":33,"wins":35},"gpt-6-sol":{"draws":10,"losses":62,"wins":18},"gpt-6.1-sol":{"draws":4,"losses":79,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":41},"inclusionai/ling-3.0-flash":{"draws":18,"losses":5,"wins":41},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":54},"meta/muse-glimmer-30b":{"draws":19,"losses":16,"wins":43},"meta/muse-spark-1.2":{"draws":11,"losses":48,"wins":27},"meta/muse-spark-1.3":{"draws":13,"losses":52,"wins":25},"meta/muse-wonder":{"draws":5,"losses":63,"wins":22},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":28},"mistralai/mistral-large-4-0":{"draws":17,"losses":19,"wins":20},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":11},"moonshotai/kimi-k3":{"draws":23,"losses":31,"wins":32},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":15,"wins":43},"o3":{"draws":18,"losses":36,"wins":74},"openai/gpt-oss-120b":{"draws":22,"losses":6,"wins":52},"poolside/laguna-s-2.1":{"draws":25,"losses":14,"wins":51},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":28},"qwen/qwen3.7-plus":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":33,"wins":35},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":16,"losses":22,"wins":22},"qwen/qwen3.8-max":{"draws":21,"losses":31,"wins":38},"qwen/qwen3.8-max-0902":{"draws":19,"losses":32,"wins":39},"stealth/ox-alpha":{"draws":57,"losses":133,"wins":108},"stealth/space-bunny-alpha":{"draws":18,"losses":16,"wins":36},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":44},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":13,"wins":22},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":30,"losses":21,"wins":69},"thinkingmachines/inkling-small":{"draws":27,"losses":9,"wins":54},"unbiased/pareto-26.10-preview":{"draws":0,"losses":29,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":13,"losses":46,"wins":31},"x-ai/grok-4.6":{"draws":19,"losses":39,"wins":32},"x-ai/grok-4.7":{"draws":7,"losses":55,"wins":18},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":39,"losses":16,"wins":81},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":9,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":30,"wins":17},"z-ai/glm-5.2":{"draws":39,"losses":50,"wins":91},"z-ai/glm-5.3":{"draws":14,"losses":54,"wins":18},"z-ai/glm-5.3-flash":{"draws":22,"losses":41,"wins":27},"z-ai/glm-5.3-flashx":{"draws":21,"losses":35,"wins":34}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":57},"claude-fable-5":{"draws":8,"losses":47,"wins":41},"claude-fable-5-1":{"draws":14,"losses":84,"wins":10},"claude-haiku-5-5":{"draws":17,"losses":32,"wins":43},"claude-opus-4-5":{"draws":39,"losses":33,"wins":84},"claude-opus-4-8":{"draws":11,"losses":35,"wins":42},"claude-opus-5":{"draws":26,"losses":99,"wins":39},"claude-opus-5-5":{"draws":10,"losses":80,"wins":14},"claude-sonnet-5":{"draws":15,"losses":24,"wins":57},"claude-sonnet-5-5":{"draws":13,"losses":46,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":31},"deepseek/deepseek-v4-flash":{"draws":25,"losses":24,"wins":95},"deepseek/deepseek-v4-pro":{"draws":16,"losses":25,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":26,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":30,"wins":43},"fireworks/ember-1":{"draws":21,"losses":30,"wins":45},"gemini-3.1-pro-preview":{"draws":16,"losses":23,"wins":57},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":50},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":62},"google/gemini-3.5-flash-lite":{"draws":21,"losses":29,"wins":118},"google/gemini-3.6-flash":{"draws":38,"losses":60,"wins":86},"google/gemini-3.8-flash":{"draws":20,"losses":27,"wins":49},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":41},"gpt-4.1":{"draws":6,"losses":7,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":8},"gpt-5":{"draws":11,"losses":22,"wins":51},"gpt-5.4":{"draws":17,"losses":37,"wins":38},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":40},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":66},"gpt-5.5":{"draws":20,"losses":31,"wins":37},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":62},"gpt-5.6-sol":{"draws":18,"losses":42,"wins":36},"gpt-5.6-terra":{"draws":24,"losses":24,"wins":44},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":19,"losses":27,"wins":50},"gpt-6-sol":{"draws":18,"losses":54,"wins":24},"gpt-6.1-sol":{"draws":14,"losses":62,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":1,"wins":48},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":49},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":75},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":56},"meta/muse-spark-1.2":{"draws":12,"losses":28,"wins":52},"meta/muse-spark-1.3":{"draws":15,"losses":33,"wins":48},"meta/muse-wonder":{"draws":17,"losses":43,"wins":36},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":37},"mistralai/mistral-large-4-0":{"draws":13,"losses":19,"wins":28},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":16},"moonshotai/kimi-k3":{"draws":18,"losses":25,"wins":49},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":56},"o3":{"draws":11,"losses":26,"wins":95},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":62},"poolside/laguna-s-2.1":{"draws":10,"losses":18,"wins":64},"qwen/qwen3.7-max":{"draws":9,"losses":13,"wins":34},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":31,"wins":41},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":36},"qwen/qwen3.8-flash":{"draws":13,"losses":16,"wins":35},"qwen/qwen3.8-max":{"draws":25,"losses":19,"wins":52},"qwen/qwen3.8-max-0902":{"draws":14,"losses":30,"wins":52},"stealth/ox-alpha":{"draws":57,"losses":105,"wins":154},"stealth/space-bunny-alpha":{"draws":19,"losses":19,"wins":38},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":52},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":33},"tencent/hy4-preview":{"draws":16,"losses":33,"wins":43},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":89},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":71},"unbiased/pareto-26.10-preview":{"draws":1,"losses":25,"wins":6},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":16},"x-ai/grok-4.5":{"draws":17,"losses":35,"wins":44},"x-ai/grok-4.6":{"draws":21,"losses":34,"wins":41},"x-ai/grok-4.7":{"draws":6,"losses":58,"wins":20},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":22},"xiaomi/mimo-v2.5":{"draws":37,"losses":13,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":17,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":49,"losses":37,"wins":106},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":34},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":50},"z-ai/glm-5.3-flashx":{"draws":17,"losses":35,"wins":44}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":143,"losses":103,"wins":128},"claude-fable-5":{"draws":88,"losses":221,"wins":61},"claude-fable-5-1":{"draws":29,"losses":359,"wins":10},"claude-haiku-5-5":{"draws":64,"losses":148,"wins":64},"claude-opus-4-5":{"draws":216,"losses":283,"wins":205},"claude-opus-4-8":{"draws":121,"losses":194,"wins":85},"claude-opus-5":{"draws":111,"losses":492,"wins":49},"claude-opus-5-5":{"draws":18,"losses":283,"wins":11},"claude-sonnet-5":{"draws":121,"losses":169,"wins":126},"claude-sonnet-5-5":{"draws":55,"losses":168,"wins":65},"cohere/north-mini-code":{"draws":42,"losses":19,"wins":67},"deepseek/deepseek-v4-flash":{"draws":223,"losses":139,"wins":246},"deepseek/deepseek-v4-pro":{"draws":138,"losses":136,"wins":110},"deepseek/deepseek-v4-pro-0813":{"draws":140,"losses":132,"wins":108},"deepseek/deepseek-v4.1-flash":{"draws":103,"losses":122,"wins":63},"fireworks/ember-1":{"draws":94,"losses":128,"wins":66},"gemini-3.1-pro-preview":{"draws":85,"losses":109,"wins":94},"google/gemini-3.1-flash-lite":{"draws":67,"losses":35,"wins":168},"google/gemini-3.5-flash":{"draws":138,"losses":193,"wins":149},"google/gemini-3.5-flash-lite":{"draws":268,"losses":202,"wins":270},"google/gemini-3.6-flash":{"draws":219,"losses":308,"wins":207},"google/gemini-3.8-flash":{"draws":103,"losses":203,"wins":86},"google/gemma-4-31b-it":{"draws":69,"losses":29,"wins":70},"gpt-4.1":{"draws":49,"losses":37,"wins":54},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":123,"losses":126,"wins":109},"gpt-5.4":{"draws":123,"losses":172,"wins":79},"gpt-5.4-mini":{"draws":140,"losses":46,"wins":96},"gpt-5.4-nano":{"draws":113,"losses":138,"wins":163},"gpt-5.5":{"draws":148,"losses":157,"wins":75},"gpt-5.6-luna":{"draws":154,"losses":93,"wins":153},"gpt-5.6-sol":{"draws":48,"losses":268,"wins":62},"gpt-5.6-terra":{"draws":176,"losses":145,"wins":87},"gpt-6-astra":{"draws":27,"losses":312,"wins":13},"gpt-6-luna":{"draws":103,"losses":113,"wins":72},"gpt-6-sol":{"draws":45,"losses":212,"wins":31},"gpt-6.1-sol":{"draws":30,"losses":246,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":126,"losses":31,"wins":135},"inclusionai/ling-3.0-flash":{"draws":143,"losses":41,"wins":94},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":137,"losses":112,"wins":197},"meta/muse-glimmer-30b":{"draws":167,"losses":63,"wins":128},"meta/muse-spark-1.2":{"draws":84,"losses":166,"wins":104},"meta/muse-spark-1.3":{"draws":79,"losses":187,"wins":84},"meta/muse-wonder":{"draws":65,"losses":178,"wins":45},"minimax/minimax-m3":{"draws":72,"losses":46,"wins":88},"mistralai/mistral-large-4-0":{"draws":71,"losses":72,"wins":37},"mistralai/mistral-medium-3-5":{"draws":106,"losses":31,"wins":103},"moonshotai/kimi-k2.7-code":{"draws":23,"losses":42,"wins":43},"moonshotai/kimi-k3":{"draws":127,"losses":135,"wins":88},"nex-agi/nex-n2-pro":{"draws":85,"losses":24,"wins":83},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":160,"losses":68,"wins":116},"o3":{"draws":100,"losses":229,"wins":195},"openai/gpt-oss-120b":{"draws":145,"losses":74,"wins":141},"poolside/laguna-s-2.1":{"draws":192,"losses":98,"wins":130},"qwen/qwen3.7-max":{"draws":79,"losses":71,"wins":92},"qwen/qwen3.7-plus":{"draws":73,"losses":40,"wins":101},"qwen/qwen3.8-2.4t-a95b":{"draws":146,"losses":151,"wins":97},"qwen/qwen3.8-27b":{"draws":72,"losses":81,"wins":77},"qwen/qwen3.8-flash":{"draws":101,"losses":86,"wins":69},"qwen/qwen3.8-max":{"draws":139,"losses":149,"wins":104},"qwen/qwen3.8-max-0902":{"draws":97,"losses":134,"wins":57},"stealth/ox-alpha":{"draws":364,"losses":625,"wins":303},"stealth/space-bunny-alpha":{"draws":89,"losses":65,"wins":74},"stepfun/step-3.7-flash":{"draws":58,"losses":56,"wins":108},"stepfun/step-5-preview":{"draws":8,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":85,"losses":65,"wins":72},"tencent/hy4-preview":{"draws":105,"losses":186,"wins":79},"thinkingmachines/inkling":{"draws":155,"losses":122,"wins":215},"thinkingmachines/inkling-small":{"draws":160,"losses":88,"wins":166},"unbiased/pareto-26.10-preview":{"draws":4,"losses":88,"wins":4},"upstage/solar-mini4":{"draws":8,"losses":16,"wins":48},"x-ai/grok-4.5":{"draws":101,"losses":199,"wins":88},"x-ai/grok-4.6":{"draws":115,"losses":216,"wins":69},"x-ai/grok-4.7":{"draws":29,"losses":189,"wins":34},"x-ai/grok-build-0.1":{"draws":47,"losses":23,"wins":48},"xiaomi/mimo-v2.5":{"draws":249,"losses":129,"wins":260},"xiaomi/mimo-v2.5-pro":{"draws":79,"losses":70,"wins":79},"xiaomi/mimo-v2.6-flash":{"draws":39,"losses":91,"wins":50},"xiaomi/mimo-v2.6-pro":{"draws":49,"losses":106,"wins":37},"z-ai/glm-5.2":{"draws":260,"losses":206,"wins":206},"z-ai/glm-5.3":{"draws":90,"losses":197,"wins":59},"z-ai/glm-5.3-flash":{"draws":126,"losses":193,"wins":79},"z-ai/glm-5.3-flashx":{"draws":82,"losses":142,"wins":64}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":29,"wins":112},"claude-fable-5":{"draws":35,"losses":90,"wins":97},"claude-fable-5-1":{"draws":16,"losses":196,"wins":38},"claude-haiku-5-5":{"draws":24,"losses":32,"wins":76},"claude-opus-4-5":{"draws":66,"losses":49,"wins":171},"claude-opus-4-8":{"draws":24,"losses":34,"wins":76},"claude-opus-5":{"draws":33,"losses":148,"wins":63},"claude-opus-5-5":{"draws":8,"losses":116,"wins":26},"claude-sonnet-5":{"draws":46,"losses":31,"wins":133},"claude-sonnet-5-5":{"draws":25,"losses":52,"wins":61},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":68,"losses":16,"wins":180},"deepseek/deepseek-v4-pro":{"draws":43,"losses":42,"wins":111},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":47,"wins":104},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":27,"wins":83},"fireworks/ember-1":{"draws":26,"losses":27,"wins":85},"gemini-3.1-pro-preview":{"draws":25,"losses":31,"wins":82},"google/gemini-3.1-flash-lite":{"draws":17,"losses":1,"wins":78},"google/gemini-3.5-flash":{"draws":52,"losses":59,"wins":139},"google/gemini-3.5-flash-lite":{"draws":73,"losses":30,"wins":251},"google/gemini-3.6-flash":{"draws":76,"losses":93,"wins":211},"google/gemini-3.8-flash":{"draws":46,"losses":67,"wins":107},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":8,"losses":8,"wins":32},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":19,"losses":22,"wins":81},"gpt-5.4":{"draws":43,"losses":72,"wins":95},"gpt-5.4-mini":{"draws":23,"losses":9,"wins":62},"gpt-5.4-nano":{"draws":20,"losses":25,"wins":99},"gpt-5.5":{"draws":33,"losses":26,"wins":73},"gpt-5.6-luna":{"draws":47,"losses":29,"wins":126},"gpt-5.6-sol":{"draws":39,"losses":106,"wins":77},"gpt-5.6-terra":{"draws":63,"losses":35,"wins":108},"gpt-6-astra":{"draws":34,"losses":173,"wins":15},"gpt-6-luna":{"draws":26,"losses":27,"wins":85},"gpt-6-sol":{"draws":21,"losses":70,"wins":47},"gpt-6.1-sol":{"draws":22,"losses":92,"wins":24},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":48,"losses":7,"wins":83},"inclusionai/ling-3.0-flash":{"draws":28,"losses":3,"wins":81},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":38,"losses":16,"wins":126},"meta/muse-glimmer-30b":{"draws":37,"losses":20,"wins":109},"meta/muse-spark-1.2":{"draws":29,"losses":59,"wins":88},"meta/muse-spark-1.3":{"draws":36,"losses":56,"wins":96},"meta/muse-wonder":{"draws":17,"losses":62,"wins":59},"minimax/minimax-m3":{"draws":17,"losses":6,"wins":53},"mistralai/mistral-large-4-0":{"draws":15,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":27,"losses":8,"wins":81},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":21},"moonshotai/kimi-k3":{"draws":44,"losses":52,"wins":86},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":59},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":16,"wins":84},"o3":{"draws":25,"losses":54,"wins":171},"openai/gpt-oss-120b":{"draws":53,"losses":8,"wins":107},"poolside/laguna-s-2.1":{"draws":41,"losses":20,"wins":107},"qwen/qwen3.7-max":{"draws":21,"losses":15,"wins":48},"qwen/qwen3.7-plus":{"draws":15,"losses":6,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":45,"wins":115},"qwen/qwen3.8-27b":{"draws":30,"losses":18,"wins":70},"qwen/qwen3.8-flash":{"draws":44,"losses":25,"wins":73},"qwen/qwen3.8-max":{"draws":51,"losses":53,"wins":108},"qwen/qwen3.8-max-0902":{"draws":36,"losses":30,"wins":72},"stealth/ox-alpha":{"draws":141,"losses":193,"wins":366},"stealth/space-bunny-alpha":{"draws":25,"losses":9,"wins":76},"stepfun/step-3.7-flash":{"draws":15,"losses":3,"wins":78},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":6},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":52},"tencent/hy4-preview":{"draws":39,"losses":43,"wins":126},"thinkingmachines/inkling":{"draws":44,"losses":25,"wins":141},"thinkingmachines/inkling-small":{"draws":43,"losses":21,"wins":136},"unbiased/pareto-26.10-preview":{"draws":4,"losses":37,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":32},"x-ai/grok-4.5":{"draws":38,"losses":47,"wins":103},"x-ai/grok-4.6":{"draws":49,"losses":76,"wins":97},"x-ai/grok-4.7":{"draws":16,"losses":72,"wins":32},"x-ai/grok-build-0.1":{"draws":13,"losses":1,"wins":34},"xiaomi/mimo-v2.5":{"draws":51,"losses":4,"wins":161},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":6,"wins":58},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":18,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":43},"z-ai/glm-5.2":{"draws":90,"losses":59,"wins":197},"z-ai/glm-5.3":{"draws":26,"losses":45,"wins":45},"z-ai/glm-5.3-flash":{"draws":53,"losses":57,"wins":104},"z-ai/glm-5.3-flashx":{"draws":27,"losses":33,"wins":78}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":66,"losses":37,"wins":111},"claude-fable-5":{"draws":44,"losses":124,"wins":80},"claude-fable-5-1":{"draws":24,"losses":238,"wins":30},"claude-haiku-5-5":{"draws":27,"losses":54,"wins":57},"claude-opus-4-5":{"draws":77,"losses":78,"wins":163},"claude-opus-4-8":{"draws":22,"losses":58,"wins":62},"claude-opus-5":{"draws":35,"losses":196,"wins":61},"claude-opus-5-5":{"draws":13,"losses":132,"wins":11},"claude-sonnet-5":{"draws":55,"losses":69,"wins":132},"claude-sonnet-5-5":{"draws":20,"losses":69,"wins":55},"cohere/north-mini-code":{"draws":12,"losses":8,"wins":36},"deepseek/deepseek-v4-flash":{"draws":97,"losses":49,"wins":154},"deepseek/deepseek-v4-pro":{"draws":58,"losses":65,"wins":105},"deepseek/deepseek-v4-pro-0813":{"draws":55,"losses":59,"wins":112},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":47,"wins":59},"fireworks/ember-1":{"draws":32,"losses":45,"wins":67},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":66},"google/gemini-3.1-flash-lite":{"draws":25,"losses":11,"wins":64},"google/gemini-3.5-flash":{"draws":67,"losses":96,"wins":127},"google/gemini-3.5-flash-lite":{"draws":122,"losses":69,"wins":235},"google/gemini-3.6-flash":{"draws":99,"losses":137,"wins":204},"google/gemini-3.8-flash":{"draws":53,"losses":114,"wins":91},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":8,"losses":12,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":38,"losses":30,"wins":68},"gpt-5.4":{"draws":51,"losses":105,"wins":90},"gpt-5.4-mini":{"draws":35,"losses":16,"wins":51},"gpt-5.4-nano":{"draws":29,"losses":36,"wins":79},"gpt-5.5":{"draws":33,"losses":45,"wins":60},"gpt-5.6-luna":{"draws":75,"losses":52,"wins":113},"gpt-5.6-sol":{"draws":46,"losses":132,"wins":90},"gpt-5.6-terra":{"draws":66,"losses":72,"wins":104},"gpt-6-astra":{"draws":32,"losses":209,"wins":15},"gpt-6-luna":{"draws":40,"losses":34,"wins":70},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":13,"losses":115,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":56,"losses":17,"wins":87},"inclusionai/ling-3.0-flash":{"draws":40,"losses":9,"wins":71},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":49,"losses":41,"wins":114},"meta/muse-glimmer-30b":{"draws":67,"losses":23,"wins":116},"meta/muse-spark-1.2":{"draws":33,"losses":78,"wins":93},"meta/muse-spark-1.3":{"draws":46,"losses":77,"wins":95},"meta/muse-wonder":{"draws":30,"losses":71,"wins":43},"minimax/minimax-m3":{"draws":20,"losses":14,"wins":44},"mistralai/mistral-large-4-0":{"draws":26,"losses":22,"wins":42},"mistralai/mistral-medium-3-5":{"draws":45,"losses":21,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":61,"losses":66,"wins":85},"nex-agi/nex-n2-pro":{"draws":19,"losses":6,"wins":49},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":29,"wins":56},"o3":{"draws":45,"losses":113,"wins":130},"openai/gpt-oss-120b":{"draws":61,"losses":19,"wins":112},"poolside/laguna-s-2.1":{"draws":67,"losses":29,"wins":94},"qwen/qwen3.7-max":{"draws":27,"losses":19,"wins":38},"qwen/qwen3.7-plus":{"draws":23,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":60,"losses":87,"wins":97},"qwen/qwen3.8-27b":{"draws":27,"losses":47,"wins":60},"qwen/qwen3.8-flash":{"draws":52,"losses":54,"wins":58},"qwen/qwen3.8-max":{"draws":70,"losses":89,"wins":87},"qwen/qwen3.8-max-0902":{"draws":43,"losses":49,"wins":52},"stealth/ox-alpha":{"draws":181,"losses":313,"wins":352},"stealth/space-bunny-alpha":{"draws":30,"losses":17,"wins":67},"stepfun/step-3.7-flash":{"draws":25,"losses":18,"wins":65},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":25,"losses":15,"wins":46},"tencent/hy4-preview":{"draws":55,"losses":81,"wins":100},"thinkingmachines/inkling":{"draws":57,"losses":37,"wins":140},"thinkingmachines/inkling-small":{"draws":81,"losses":39,"wins":128},"unbiased/pareto-26.10-preview":{"draws":3,"losses":39,"wins":6},"upstage/solar-mini4":{"draws":6,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":33,"losses":84,"wins":89},"x-ai/grok-4.6":{"draws":63,"losses":97,"wins":94},"x-ai/grok-4.7":{"draws":15,"losses":77,"wins":34},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":28},"xiaomi/mimo-v2.5":{"draws":67,"losses":35,"wins":126},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":16,"wins":52},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":27,"wins":41},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":126,"losses":79,"wins":193},"z-ai/glm-5.3":{"draws":53,"losses":104,"wins":57},"z-ai/glm-5.3-flash":{"draws":48,"losses":62,"wins":62},"z-ai/glm-5.3-flashx":{"draws":40,"losses":50,"wins":54}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":25,"wins":83},"claude-fable-5":{"draws":29,"losses":73,"wins":42},"claude-fable-5-1":{"draws":15,"losses":134,"wins":13},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":53,"losses":55,"wins":126},"claude-opus-4-8":{"draws":25,"losses":58,"wins":49},"claude-opus-5":{"draws":36,"losses":166,"wins":44},"claude-opus-5-5":{"draws":15,"losses":131,"wins":10},"claude-sonnet-5":{"draws":39,"losses":33,"wins":72},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":54},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":39},"deepseek/deepseek-v4-flash":{"draws":58,"losses":32,"wins":126},"deepseek/deepseek-v4-pro":{"draws":32,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":37,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":43,"wins":61},"fireworks/ember-1":{"draws":35,"losses":51,"wins":58},"gemini-3.1-pro-preview":{"draws":35,"losses":34,"wins":75},"google/gemini-3.1-flash-lite":{"draws":25,"losses":7,"wins":64},"google/gemini-3.5-flash":{"draws":48,"losses":43,"wins":89},"google/gemini-3.5-flash-lite":{"draws":67,"losses":47,"wins":138},"google/gemini-3.6-flash":{"draws":71,"losses":95,"wins":110},"google/gemini-3.8-flash":{"draws":29,"losses":64,"wins":51},"google/gemma-4-31b-it":{"draws":28,"losses":11,"wins":45},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":38,"losses":32,"wins":56},"gpt-5.4":{"draws":34,"losses":50,"wins":54},"gpt-5.4-mini":{"draws":27,"losses":13,"wins":56},"gpt-5.4-nano":{"draws":29,"losses":33,"wins":82},"gpt-5.5":{"draws":42,"losses":44,"wins":46},"gpt-5.6-luna":{"draws":42,"losses":29,"wins":73},"gpt-5.6-sol":{"draws":23,"losses":80,"wins":41},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":63},"gpt-6-astra":{"draws":14,"losses":121,"wins":9},"gpt-6-luna":{"draws":30,"losses":42,"wins":72},"gpt-6-sol":{"draws":20,"losses":87,"wins":37},"gpt-6.1-sol":{"draws":19,"losses":107,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":5,"wins":68},"inclusionai/ling-3.0-flash":{"draws":35,"losses":8,"wins":59},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":36,"losses":19,"wins":101},"meta/muse-glimmer-30b":{"draws":36,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":29,"losses":49,"wins":60},"meta/muse-spark-1.3":{"draws":28,"losses":59,"wins":57},"meta/muse-wonder":{"draws":34,"losses":73,"wins":37},"minimax/minimax-m3":{"draws":20,"losses":12,"wins":46},"mistralai/mistral-large-4-0":{"draws":29,"losses":27,"wins":34},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":12,"wins":12},"moonshotai/kimi-k3":{"draws":41,"losses":34,"wins":63},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":21,"wins":74},"o3":{"draws":21,"losses":59,"wins":118},"openai/gpt-oss-120b":{"draws":37,"losses":13,"wins":76},"poolside/laguna-s-2.1":{"draws":40,"losses":23,"wins":75},"qwen/qwen3.7-max":{"draws":22,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":10,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":45,"wins":61},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":32,"losses":22,"wins":42},"qwen/qwen3.8-max":{"draws":40,"losses":48,"wins":56},"qwen/qwen3.8-max-0902":{"draws":36,"losses":51,"wins":57},"stealth/ox-alpha":{"draws":85,"losses":168,"wins":221},"stealth/space-bunny-alpha":{"draws":33,"losses":22,"wins":59},"stepfun/step-3.7-flash":{"draws":17,"losses":14,"wins":71},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":14,"wins":46},"tencent/hy4-preview":{"draws":32,"losses":57,"wins":49},"thinkingmachines/inkling":{"draws":44,"losses":25,"wins":123},"thinkingmachines/inkling-small":{"draws":36,"losses":23,"wins":85},"unbiased/pareto-26.10-preview":{"draws":3,"losses":42,"wins":3},"upstage/solar-mini4":{"draws":5,"losses":4,"wins":27},"x-ai/grok-4.5":{"draws":25,"losses":59,"wins":60},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":52},"x-ai/grok-4.7":{"draws":15,"losses":84,"wins":27},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":30},"xiaomi/mimo-v2.5":{"draws":73,"losses":16,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":34,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":82,"losses":64,"wins":142},"z-ai/glm-5.3":{"draws":27,"losses":78,"wins":33},"z-ai/glm-5.3-flash":{"draws":40,"losses":54,"wins":50},"z-ai/glm-5.3-flashx":{"draws":32,"losses":32,"wins":32}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":16,"wins":19},"claude-fable-5":{"draws":15,"losses":55,"wins":8},"claude-fable-5-1":{"draws":5,"losses":77,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":43,"losses":45,"wins":20},"claude-opus-4-8":{"draws":14,"losses":24,"wins":6},"claude-opus-5":{"draws":9,"losses":66,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":30,"losses":40,"wins":16},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":40,"losses":31,"wins":41},"deepseek/deepseek-v4-pro":{"draws":17,"losses":36,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":29,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":17},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":35,"losses":42,"wins":21},"google/gemini-3.5-flash-lite":{"draws":74,"losses":35,"wins":51},"google/gemini-3.6-flash":{"draws":49,"losses":61,"wins":34},"google/gemini-3.8-flash":{"draws":25,"losses":41,"wins":12},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":21,"losses":16,"wins":11},"gpt-5.4":{"draws":22,"losses":37,"wins":15},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":15,"losses":16,"wins":17},"gpt-5.5":{"draws":26,"losses":15,"wins":11},"gpt-5.6-luna":{"draws":42,"losses":22,"wins":26},"gpt-5.6-sol":{"draws":14,"losses":50,"wins":14},"gpt-5.6-terra":{"draws":29,"losses":34,"wins":19},"gpt-6-astra":{"draws":4,"losses":65,"wins":3},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":14,"wins":22},"inclusionai/ling-3.0-flash":{"draws":23,"losses":5,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":13,"wins":33},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":26},"meta/muse-spark-1.2":{"draws":22,"losses":27,"wins":21},"meta/muse-spark-1.3":{"draws":25,"losses":35,"wins":12},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":22,"losses":8,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":27,"losses":34,"wins":13},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":14,"wins":15},"o3":{"draws":23,"losses":41,"wins":36},"openai/gpt-oss-120b":{"draws":35,"losses":13,"wins":32},"poolside/laguna-s-2.1":{"draws":38,"losses":11,"wins":21},"qwen/qwen3.7-max":{"draws":12,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":29,"wins":23},"qwen/qwen3.8-27b":{"draws":10,"losses":24,"wins":8},"qwen/qwen3.8-flash":{"draws":24,"losses":22,"wins":10},"qwen/qwen3.8-max":{"draws":33,"losses":29,"wins":28},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":76,"losses":142,"wins":58},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":32,"losses":45,"wins":11},"thinkingmachines/inkling":{"draws":35,"losses":13,"wins":38},"thinkingmachines/inkling-small":{"draws":42,"losses":18,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":23,"losses":43,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":54,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":32,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":58,"losses":44,"wins":44},"z-ai/glm-5.3":{"draws":18,"losses":43,"wins":7},"z-ai/glm-5.3-flash":{"draws":29,"losses":42,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":50},"claude-fable-5":{"draws":3,"losses":25,"wins":30},"claude-fable-5-1":{"draws":10,"losses":76,"wins":22},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":10,"losses":11,"wins":89},"claude-opus-4-8":{"draws":5,"losses":13,"wins":30},"claude-opus-5":{"draws":11,"losses":45,"wins":34},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":16,"losses":8,"wins":60},"claude-sonnet-5-5":{"draws":1,"losses":19,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":10,"losses":4,"wins":80},"deepseek/deepseek-v4-pro":{"draws":5,"losses":16,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":10,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":8,"wins":34},"fireworks/ember-1":{"draws":6,"losses":5,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":8,"wins":34},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":14,"losses":7,"wins":75},"google/gemini-3.5-flash-lite":{"draws":19,"losses":7,"wins":106},"google/gemini-3.6-flash":{"draws":21,"losses":26,"wins":93},"google/gemini-3.8-flash":{"draws":14,"losses":34,"wins":42},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":5,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":6,"losses":13,"wins":27},"gpt-5.4":{"draws":16,"losses":32,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":40},"gpt-5.5":{"draws":4,"losses":19,"wins":23},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":55},"gpt-5.6-sol":{"draws":12,"losses":29,"wins":53},"gpt-5.6-terra":{"draws":19,"losses":11,"wins":50},"gpt-6-astra":{"draws":9,"losses":70,"wins":17},"gpt-6-luna":{"draws":8,"losses":11,"wins":29},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":38},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":47},"meta/muse-glimmer-30b":{"draws":13,"losses":2,"wins":47},"meta/muse-spark-1.2":{"draws":2,"losses":12,"wins":52},"meta/muse-spark-1.3":{"draws":9,"losses":14,"wins":45},"meta/muse-wonder":{"draws":5,"losses":15,"wins":28},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":48},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":28},"o3":{"draws":11,"losses":18,"wins":63},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":46},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":43},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":55},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":37},"qwen/qwen3.8-flash":{"draws":15,"losses":6,"wins":33},"qwen/qwen3.8-max":{"draws":13,"losses":17,"wins":48},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":32},"stealth/ox-alpha":{"draws":43,"losses":39,"wins":200},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":17,"wins":49},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":63},"thinkingmachines/inkling-small":{"draws":11,"losses":2,"wins":55},"unbiased/pareto-26.10-preview":{"draws":3,"losses":9,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":3,"losses":18,"wins":51},"x-ai/grok-4.6":{"draws":20,"losses":26,"wins":46},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":17},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":19,"losses":13,"wins":86},"z-ai/glm-5.3":{"draws":15,"losses":18,"wins":43},"z-ai/glm-5.3-flash":{"draws":17,"losses":16,"wins":53},"z-ai/glm-5.3-flashx":{"draws":11,"losses":8,"wins":29}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":86},"claude-fable-5":{"draws":3,"losses":8,"wins":111},"claude-fable-5-1":{"draws":10,"losses":22,"wins":80},"claude-haiku-5-5":{"draws":4,"losses":0,"wins":58},"claude-opus-4-5":{"draws":2,"losses":4,"wins":138},"claude-opus-4-8":{"draws":0,"losses":3,"wins":55},"claude-opus-5":{"draws":8,"losses":20,"wins":88},"claude-opus-5-5":{"draws":8,"losses":32,"wins":30},"claude-sonnet-5":{"draws":0,"losses":2,"wins":118},"claude-sonnet-5-5":{"draws":2,"losses":12,"wins":52},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":122},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":95},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":101},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":59},"fireworks/ember-1":{"draws":0,"losses":1,"wins":65},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":63},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":41},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":122},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":169},"google/gemini-3.6-flash":{"draws":8,"losses":7,"wins":181},"google/gemini-3.8-flash":{"draws":8,"losses":6,"wins":110},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":37},"gpt-4.1":{"draws":0,"losses":0,"wins":22},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":0,"losses":0,"wins":58},"gpt-5.4":{"draws":1,"losses":6,"wins":107},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":44},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":58},"gpt-5.5":{"draws":0,"losses":3,"wins":59},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":95},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":114},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":110},"gpt-6-astra":{"draws":7,"losses":51,"wins":74},"gpt-6-luna":{"draws":1,"losses":1,"wins":64},"gpt-6-sol":{"draws":2,"losses":11,"wins":53},"gpt-6.1-sol":{"draws":2,"losses":23,"wins":41},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":60},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":48},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":79},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":74},"meta/muse-spark-1.2":{"draws":1,"losses":7,"wins":86},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":90},"meta/muse-wonder":{"draws":4,"losses":7,"wins":55},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":33},"mistralai/mistral-large-4-0":{"draws":0,"losses":4,"wins":38},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":92},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":50},"o3":{"draws":0,"losses":1,"wins":115},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":69},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":73},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":110},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":60},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":66},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":106},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":61},"stealth/ox-alpha":{"draws":22,"losses":9,"wins":387},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":53},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":31},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":101},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":100},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":97},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":91},"x-ai/grok-4.6":{"draws":3,"losses":13,"wins":108},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":49},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":37},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":157},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":92},"z-ai/glm-5.3-flash":{"draws":3,"losses":11,"wins":106},"z-ai/glm-5.3-flashx":{"draws":6,"losses":1,"wins":59}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":34},"claude-fable-5":{"draws":5,"losses":11,"wins":26},"claude-fable-5-1":{"draws":4,"losses":39,"wins":3},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":20},"claude-opus-4-5":{"draws":12,"losses":6,"wins":52},"claude-opus-4-8":{"draws":7,"losses":10,"wins":25},"claude-opus-5":{"draws":10,"losses":38,"wins":22},"claude-opus-5-5":{"draws":6,"losses":32,"wins":8},"claude-sonnet-5":{"draws":5,"losses":4,"wins":33},"claude-sonnet-5-5":{"draws":5,"losses":13,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":8,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":6,"losses":5,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":25},"fireworks/ember-1":{"draws":5,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":29},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":63},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":52},"google/gemini-3.8-flash":{"draws":7,"losses":9,"wins":26},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":23},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":4,"wins":29},"gpt-5.4":{"draws":2,"losses":9,"wins":29},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":39},"gpt-5.5":{"draws":5,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":35},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":33,"wins":5},"gpt-6-luna":{"draws":6,"losses":6,"wins":30},"gpt-6-sol":{"draws":12,"losses":15,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":30},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":34},"meta/muse-wonder":{"draws":9,"losses":16,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":9,"wins":29},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":32},"o3":{"draws":2,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":31},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":8,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":26},"stealth/ox-alpha":{"draws":17,"losses":21,"wins":80},"stealth/space-bunny-alpha":{"draws":6,"losses":5,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":9,"wins":27},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":40},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":6},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":25},"x-ai/grok-4.6":{"draws":4,"losses":11,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":9,"wins":70},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":3,"losses":9,"wins":30}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":10,"wins":50},"claude-fable-5":{"draws":17,"losses":64,"wins":15},"claude-fable-5-1":{"draws":6,"losses":92,"wins":6},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":32,"losses":39,"wins":35},"claude-opus-4-8":{"draws":15,"losses":29,"wins":16},"claude-opus-5":{"draws":19,"losses":136,"wins":11},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":61,"losses":26,"wins":55},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":32,"losses":19,"wins":59},"deepseek/deepseek-v4-pro":{"draws":24,"losses":27,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":32,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":13},"fireworks/ember-1":{"draws":16,"losses":16,"wins":16},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":28},"google/gemini-3.5-flash":{"draws":23,"losses":42,"wins":35},"google/gemini-3.5-flash-lite":{"draws":103,"losses":65,"wins":122},"google/gemini-3.6-flash":{"draws":75,"losses":126,"wins":79},"google/gemini-3.8-flash":{"draws":27,"losses":55,"wins":12},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":11,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":19,"losses":19,"wins":22},"gpt-5.4":{"draws":42,"losses":68,"wins":26},"gpt-5.4-mini":{"draws":15,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":20},"gpt-5.5":{"draws":20,"losses":28,"wins":14},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":59},"gpt-5.6-sol":{"draws":18,"losses":91,"wins":33},"gpt-5.6-terra":{"draws":28,"losses":20,"wins":34},"gpt-6-astra":{"draws":2,"losses":87,"wins":3},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":4,"wins":32},"inclusionai/ling-3.0-flash":{"draws":19,"losses":17,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":25,"losses":26,"wins":61},"meta/muse-glimmer-30b":{"draws":32,"losses":6,"wins":40},"meta/muse-spark-1.2":{"draws":25,"losses":49,"wins":28},"meta/muse-spark-1.3":{"draws":17,"losses":38,"wins":19},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":34,"losses":49,"wins":41},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":5,"wins":28},"o3":{"draws":31,"losses":41,"wins":110},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":47},"poolside/laguna-s-2.1":{"draws":48,"losses":11,"wins":55},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":34,"wins":21},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":18},"qwen/qwen3.8-flash":{"draws":16,"losses":23,"wins":19},"qwen/qwen3.8-max":{"draws":27,"losses":41,"wins":24},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"stealth/ox-alpha":{"draws":81,"losses":122,"wins":103},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":29},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":11,"wins":14},"tencent/hy4-preview":{"draws":26,"losses":38,"wins":26},"thinkingmachines/inkling":{"draws":33,"losses":10,"wins":69},"thinkingmachines/inkling-small":{"draws":41,"losses":18,"wins":37},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":46,"losses":65,"wins":33},"x-ai/grok-4.6":{"draws":26,"losses":50,"wins":16},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":32,"losses":12,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":13,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":45,"losses":36,"wins":61},"z-ai/glm-5.3":{"draws":17,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":21,"losses":45,"wins":22},"z-ai/glm-5.3-flashx":{"draws":17,"losses":19,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":5,"wins":31},"claude-fable-5":{"draws":7,"losses":15,"wins":22},"claude-fable-5-1":{"draws":3,"losses":34,"wins":9},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":19,"losses":22,"wins":91},"claude-opus-4-8":{"draws":4,"losses":9,"wins":37},"claude-opus-5":{"draws":37,"losses":90,"wins":55},"claude-opus-5-5":{"draws":9,"losses":28,"wins":9},"claude-sonnet-5":{"draws":8,"losses":5,"wins":29},"claude-sonnet-5-5":{"draws":10,"losses":11,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":60},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":24},"fireworks/ember-1":{"draws":10,"losses":6,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":28},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":46},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":45},"google/gemini-3.5-flash-lite":{"draws":8,"losses":6,"wins":78},"google/gemini-3.6-flash":{"draws":15,"losses":37,"wins":60},"google/gemini-3.8-flash":{"draws":8,"losses":13,"wins":27},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":12,"wins":58},"gpt-5.4":{"draws":4,"losses":16,"wins":26},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":31},"gpt-5.4-nano":{"draws":9,"losses":4,"wins":61},"gpt-5.5":{"draws":16,"losses":34,"wins":32},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":29},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":33},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":32},"gpt-6-astra":{"draws":7,"losses":33,"wins":4},"gpt-6-luna":{"draws":9,"losses":4,"wins":29},"gpt-6-sol":{"draws":8,"losses":19,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":28,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":25},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":5,"losses":7,"wins":30},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":24},"meta/muse-wonder":{"draws":7,"losses":14,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":34},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":23},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":61},"o3":{"draws":6,"losses":14,"wins":80},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":43},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":25},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":23},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":19},"qwen/qwen3.8-max":{"draws":1,"losses":11,"wins":34},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":29,"losses":24,"wins":75},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":22},"stepfun/step-3.7-flash":{"draws":1,"losses":6,"wins":37},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":10,"wins":32},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":29},"thinkingmachines/inkling":{"draws":10,"losses":2,"wins":68},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":15,"wins":39},"x-ai/grok-4.6":{"draws":8,"losses":15,"wins":23},"x-ai/grok-4.7":{"draws":7,"losses":19,"wins":12},"x-ai/grok-build-0.1":{"draws":0,"losses":5,"wins":17},"xiaomi/mimo-v2.5":{"draws":20,"losses":4,"wins":86},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":92},"z-ai/glm-5.3":{"draws":6,"losses":15,"wins":21},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":29},"z-ai/glm-5.3-flashx":{"draws":8,"losses":4,"wins":30}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":7,"wins":64},"claude-fable-5":{"draws":4,"losses":19,"wins":69},"claude-fable-5-1":{"draws":13,"losses":38,"wins":45},"claude-haiku-5-5":{"draws":1,"losses":11,"wins":62},"claude-opus-4-5":{"draws":11,"losses":19,"wins":190},"claude-opus-4-8":{"draws":9,"losses":31,"wins":98},"claude-opus-5":{"draws":31,"losses":108,"wins":209},"claude-opus-5-5":{"draws":5,"losses":44,"wins":37},"claude-sonnet-5":{"draws":3,"losses":6,"wins":69},"claude-sonnet-5-5":{"draws":3,"losses":17,"wins":58},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":27},"deepseek/deepseek-v4-flash":{"draws":3,"losses":9,"wins":112},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":68},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":7,"wins":62},"fireworks/ember-1":{"draws":3,"losses":14,"wins":61},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":69},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":66},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":87},"google/gemini-3.5-flash-lite":{"draws":7,"losses":8,"wins":161},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":160},"google/gemini-3.8-flash":{"draws":4,"losses":17,"wins":75},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":40},"gpt-4.1":{"draws":1,"losses":2,"wins":37},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":2,"losses":8,"wins":96},"gpt-5.4":{"draws":3,"losses":8,"wins":67},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":57},"gpt-5.4-nano":{"draws":3,"losses":11,"wins":86},"gpt-5.5":{"draws":6,"losses":19,"wins":101},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":72},"gpt-5.6-sol":{"draws":12,"losses":15,"wins":73},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":68},"gpt-6-astra":{"draws":13,"losses":45,"wins":30},"gpt-6-luna":{"draws":11,"losses":4,"wins":63},"gpt-6-sol":{"draws":7,"losses":24,"wins":47},"gpt-6.1-sol":{"draws":11,"losses":38,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":47},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":11,"wins":76},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":69},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":71},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":67},"meta/muse-wonder":{"draws":5,"losses":17,"wins":56},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":55},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":44},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":34},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":72},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":6,"wins":97},"o3":{"draws":2,"losses":9,"wins":133},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":59},"poolside/laguna-s-2.1":{"draws":1,"losses":7,"wins":92},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":49},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":73},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":50},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":53},"qwen/qwen3.8-max":{"draws":3,"losses":6,"wins":73},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":65},"stealth/ox-alpha":{"draws":22,"losses":24,"wins":260},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":57},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":56},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":5,"wins":63},"tencent/hy4-preview":{"draws":6,"losses":7,"wins":73},"thinkingmachines/inkling":{"draws":7,"losses":10,"wins":131},"thinkingmachines/inkling-small":{"draws":2,"losses":6,"wins":72},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":14},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":13},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":99},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":70},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":45},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":31},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":41},"z-ai/glm-5.2":{"draws":12,"losses":13,"wins":155},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":67},"z-ai/glm-5.3-flash":{"draws":7,"losses":12,"wins":77},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":64}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":2,"losses":3,"wins":43},"claude-fable-5-1":{"draws":4,"losses":8,"wins":42},"claude-haiku-5-5":{"draws":2,"losses":1,"wins":43},"claude-opus-4-5":{"draws":0,"losses":0,"wins":78},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":5,"losses":9,"wins":68},"claude-opus-5-5":{"draws":3,"losses":7,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":4,"losses":5,"wins":39},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":72},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":45},"fireworks/ember-1":{"draws":0,"losses":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":58},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":83},"google/gemini-3.6-flash":{"draws":1,"losses":3,"wins":88},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":45},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":42},"gpt-5.4":{"draws":0,"losses":4,"wins":42},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":30},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":45},"gpt-5.6-sol":{"draws":1,"losses":3,"wins":44},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":4,"losses":15,"wins":29},"gpt-6-luna":{"draws":1,"losses":0,"wins":47},"gpt-6-sol":{"draws":2,"losses":1,"wins":45},"gpt-6.1-sol":{"draws":8,"losses":7,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":52},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":42},"meta/muse-spark-1.3":{"draws":1,"losses":3,"wins":44},"meta/muse-wonder":{"draws":1,"losses":4,"wins":43},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":1,"losses":0,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":0,"losses":3,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"o3":{"draws":1,"losses":1,"wins":64},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":43},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":31},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":43},"stealth/ox-alpha":{"draws":2,"losses":1,"wins":155},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":45},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":3,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":44},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":42},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":43}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":7,"wins":45},"claude-fable-5":{"draws":14,"losses":45,"wins":23},"claude-fable-5-1":{"draws":4,"losses":89,"wins":3},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":23},"claude-opus-4-5":{"draws":45,"losses":44,"wins":51},"claude-opus-4-8":{"draws":10,"losses":14,"wins":20},"claude-opus-5":{"draws":10,"losses":67,"wins":17},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":26,"losses":11,"wins":55},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":15},"deepseek/deepseek-v4-flash":{"draws":30,"losses":12,"wins":62},"deepseek/deepseek-v4-pro":{"draws":16,"losses":21,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":26,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":35,"wins":38},"google/gemini-3.5-flash-lite":{"draws":44,"losses":31,"wins":137},"google/gemini-3.6-flash":{"draws":34,"losses":79,"wins":109},"google/gemini-3.8-flash":{"draws":18,"losses":33,"wins":35},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":32,"losses":52,"wins":42},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":31},"gpt-5.5":{"draws":12,"losses":23,"wins":15},"gpt-5.6-luna":{"draws":35,"losses":36,"wins":53},"gpt-5.6-sol":{"draws":22,"losses":95,"wins":27},"gpt-5.6-terra":{"draws":18,"losses":21,"wins":41},"gpt-6-astra":{"draws":3,"losses":73,"wins":10},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":8,"losses":31,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":3,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":64},"meta/muse-glimmer-30b":{"draws":14,"losses":9,"wins":39},"meta/muse-spark-1.2":{"draws":32,"losses":24,"wins":46},"meta/muse-spark-1.3":{"draws":13,"losses":29,"wins":28},"meta/muse-wonder":{"draws":11,"losses":23,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":12,"losses":9,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":26,"losses":42,"wins":36},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":21},"o3":{"draws":7,"losses":54,"wins":73},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":40},"poolside/laguna-s-2.1":{"draws":20,"losses":3,"wins":57},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":17},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":30,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":24},"qwen/qwen3.8-flash":{"draws":16,"losses":14,"wins":22},"qwen/qwen3.8-max":{"draws":13,"losses":28,"wins":45},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"stealth/ox-alpha":{"draws":66,"losses":105,"wins":111},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":15},"tencent/hy4-preview":{"draws":13,"losses":33,"wins":36},"thinkingmachines/inkling":{"draws":27,"losses":14,"wins":53},"thinkingmachines/inkling-small":{"draws":21,"losses":13,"wins":48},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":39,"losses":44,"wins":23},"x-ai/grok-4.6":{"draws":18,"losses":38,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":21,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":26,"losses":36,"wins":62},"z-ai/glm-5.3":{"draws":14,"losses":38,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":47,"wins":27},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":0,"wins":37},"claude-fable-5":{"draws":5,"losses":2,"wins":41},"claude-fable-5-1":{"draws":7,"losses":16,"wins":31},"claude-haiku-5-5":{"draws":5,"losses":2,"wins":39},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":5,"losses":1,"wins":38},"claude-opus-5":{"draws":6,"losses":16,"wins":60},"claude-opus-5-5":{"draws":10,"losses":17,"wins":25},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":1,"losses":1,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":69},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":41},"fireworks/ember-1":{"draws":5,"losses":0,"wins":43},"gemini-3.1-pro-preview":{"draws":0,"losses":3,"wins":45},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":3,"losses":2,"wins":55},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":10,"losses":5,"wins":77},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":0,"wins":39},"gpt-5.4":{"draws":9,"losses":1,"wins":36},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":4,"losses":1,"wins":39},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":3,"wins":42},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":42},"gpt-6-astra":{"draws":7,"losses":16,"wins":25},"gpt-6-luna":{"draws":8,"losses":1,"wins":39},"gpt-6-sol":{"draws":7,"losses":6,"wins":35},"gpt-6.1-sol":{"draws":2,"losses":14,"wins":32},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":43},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":44},"meta/muse-wonder":{"draws":5,"losses":1,"wins":42},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"o3":{"draws":2,"losses":1,"wins":63},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":44},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":46},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":4,"wins":144},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":3,"losses":0,"wins":43},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":57},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":5,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":1,"wins":41},"x-ai/grok-4.6":{"draws":5,"losses":0,"wins":43},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":37},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":90},"z-ai/glm-5.3":{"draws":7,"losses":3,"wins":36},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":39}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":13,"wins":17},"claude-fable-5":{"draws":14,"losses":42,"wins":12},"claude-fable-5-1":{"draws":5,"losses":70,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":23,"losses":43,"wins":24},"claude-opus-4-8":{"draws":10,"losses":21,"wins":7},"claude-opus-5":{"draws":12,"losses":49,"wins":9},"claude-opus-5-5":{"draws":4,"losses":40,"wins":2},"claude-sonnet-5":{"draws":29,"losses":34,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":20,"losses":25,"wins":31},"deepseek/deepseek-v4-pro":{"draws":35,"losses":28,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":23,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":18,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":13,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":13},"google/gemini-3.5-flash":{"draws":33,"losses":28,"wins":23},"google/gemini-3.5-flash-lite":{"draws":54,"losses":51,"wins":31},"google/gemini-3.6-flash":{"draws":45,"losses":60,"wins":19},"google/gemini-3.8-flash":{"draws":18,"losses":41,"wins":13},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":9},"gpt-4.1":{"draws":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":14,"wins":9},"gpt-5.4":{"draws":30,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":13},"gpt-5.5":{"draws":16,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":42,"losses":14,"wins":24},"gpt-5.6-sol":{"draws":12,"losses":43,"wins":11},"gpt-5.6-terra":{"draws":29,"losses":23,"wins":20},"gpt-6-astra":{"draws":4,"losses":58,"wins":2},"gpt-6-luna":{"draws":19,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":4,"wins":18},"inclusionai/ling-3.0-flash":{"draws":19,"losses":12,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":46,"losses":10,"wins":14},"meta/muse-spark-1.2":{"draws":20,"losses":26,"wins":10},"meta/muse-spark-1.3":{"draws":18,"losses":34,"wins":8},"meta/muse-wonder":{"draws":8,"losses":25,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":29,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":21,"losses":21,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":12},"o3":{"draws":21,"losses":29,"wins":24},"openai/gpt-oss-120b":{"draws":36,"losses":24,"wins":8},"poolside/laguna-s-2.1":{"draws":30,"losses":14,"wins":12},"qwen/qwen3.7-max":{"draws":15,"losses":6,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":26,"wins":21},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":19,"losses":20,"wins":11},"qwen/qwen3.8-max":{"draws":27,"losses":33,"wins":12},"qwen/qwen3.8-max-0902":{"draws":19,"losses":15,"wins":8},"stealth/ox-alpha":{"draws":75,"losses":108,"wins":53},"stealth/space-bunny-alpha":{"draws":17,"losses":7,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":38,"losses":12,"wins":18},"thinkingmachines/inkling-small":{"draws":43,"losses":14,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":17,"losses":30,"wins":15},"x-ai/grok-4.6":{"draws":24,"losses":39,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":53,"losses":36,"wins":29},"z-ai/glm-5.3":{"draws":15,"losses":41,"wins":4},"z-ai/glm-5.3-flash":{"draws":27,"losses":31,"wins":12},"z-ai/glm-5.3-flashx":{"draws":16,"losses":19,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":38},"claude-fable-5":{"draws":21,"losses":47,"wins":18},"claude-fable-5-1":{"draws":7,"losses":91,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":33,"losses":33,"wins":42},"claude-opus-4-8":{"draws":11,"losses":22,"wins":17},"claude-opus-5":{"draws":13,"losses":70,"wins":9},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":28,"losses":35,"wins":21},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":38,"losses":20,"wins":48},"deepseek/deepseek-v4-pro":{"draws":20,"losses":14,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":26,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":14,"wins":18},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":12,"wins":21},"google/gemini-3.1-flash-lite":{"draws":13,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":31,"losses":33,"wins":36},"google/gemini-3.5-flash-lite":{"draws":53,"losses":34,"wins":65},"google/gemini-3.6-flash":{"draws":38,"losses":62,"wins":50},"google/gemini-3.8-flash":{"draws":32,"losses":42,"wins":16},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":8,"wins":20},"gpt-5.4":{"draws":37,"losses":30,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":27},"gpt-5.5":{"draws":21,"losses":22,"wins":7},"gpt-5.6-luna":{"draws":34,"losses":16,"wins":32},"gpt-5.6-sol":{"draws":13,"losses":48,"wins":23},"gpt-5.6-terra":{"draws":32,"losses":29,"wins":21},"gpt-6-astra":{"draws":8,"losses":76,"wins":4},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":8,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":6,"losses":41,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":11,"wins":34},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":32},"meta/muse-spark-1.2":{"draws":16,"losses":30,"wins":20},"meta/muse-spark-1.3":{"draws":17,"losses":39,"wins":18},"meta/muse-wonder":{"draws":14,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":17,"losses":0,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":15,"losses":29,"wins":24},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":19},"o3":{"draws":21,"losses":27,"wins":54},"openai/gpt-oss-120b":{"draws":30,"losses":15,"wins":27},"poolside/laguna-s-2.1":{"draws":25,"losses":17,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":35,"wins":25},"qwen/qwen3.8-27b":{"draws":10,"losses":22,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":19},"qwen/qwen3.8-max":{"draws":25,"losses":34,"wins":25},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":13},"stealth/ox-alpha":{"draws":80,"losses":127,"wins":77},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":12,"losses":5,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":24,"losses":37,"wins":23},"thinkingmachines/inkling":{"draws":26,"losses":11,"wins":45},"thinkingmachines/inkling-small":{"draws":38,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":17,"losses":28,"wins":33},"x-ai/grok-4.6":{"draws":26,"losses":42,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":36,"losses":10,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":53,"losses":45,"wins":42},"z-ai/glm-5.3":{"draws":19,"losses":37,"wins":14},"z-ai/glm-5.3-flash":{"draws":31,"losses":34,"wins":27},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"wins":19}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":11,"wins":46},"claude-fable-5":{"draws":18,"losses":45,"wins":21},"claude-fable-5-1":{"draws":4,"losses":92,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":21,"wins":14},"claude-opus-4-5":{"draws":21,"losses":27,"wins":60},"claude-opus-4-8":{"draws":14,"losses":13,"wins":19},"claude-opus-5":{"draws":7,"losses":75,"wins":10},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":27,"losses":20,"wins":43},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":36,"losses":12,"wins":56},"deepseek/deepseek-v4-pro":{"draws":20,"losses":24,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":20,"wins":13},"fireworks/ember-1":{"draws":12,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":20},"google/gemini-3.5-flash":{"draws":32,"losses":27,"wins":41},"google/gemini-3.5-flash-lite":{"draws":51,"losses":13,"wins":78},"google/gemini-3.6-flash":{"draws":36,"losses":59,"wins":67},"google/gemini-3.8-flash":{"draws":18,"losses":32,"wins":38},"google/gemma-4-31b-it":{"draws":12,"losses":0,"wins":16},"gpt-4.1":{"draws":7,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":12,"wins":24},"gpt-5.4":{"draws":24,"losses":25,"wins":27},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":27},"gpt-5.5":{"draws":9,"losses":22,"wins":13},"gpt-5.6-luna":{"draws":31,"losses":13,"wins":40},"gpt-5.6-sol":{"draws":12,"losses":49,"wins":25},"gpt-5.6-terra":{"draws":27,"losses":18,"wins":37},"gpt-6-astra":{"draws":10,"losses":74,"wins":0},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":23,"losses":4,"wins":33},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":9,"wins":43},"meta/muse-glimmer-30b":{"draws":26,"losses":9,"wins":35},"meta/muse-spark-1.2":{"draws":17,"losses":19,"wins":34},"meta/muse-spark-1.3":{"draws":22,"losses":23,"wins":29},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":19,"losses":3,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":8},"moonshotai/kimi-k3":{"draws":22,"losses":10,"wins":32},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":5,"wins":22},"o3":{"draws":16,"losses":15,"wins":59},"openai/gpt-oss-120b":{"draws":29,"losses":9,"wins":30},"poolside/laguna-s-2.1":{"draws":23,"losses":8,"wins":33},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":28,"wins":36},"qwen/qwen3.8-27b":{"draws":8,"losses":16,"wins":20},"qwen/qwen3.8-flash":{"draws":18,"losses":20,"wins":22},"qwen/qwen3.8-max":{"draws":22,"losses":26,"wins":40},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":20},"stealth/ox-alpha":{"draws":60,"losses":87,"wins":131},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":35,"wins":39},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":47},"thinkingmachines/inkling-small":{"draws":25,"losses":13,"wins":40},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":23,"wins":28},"x-ai/grok-4.6":{"draws":25,"losses":39,"wins":24},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":7,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":19,"wins":11},"z-ai/glm-5.2":{"draws":37,"losses":42,"wins":57},"z-ai/glm-5.3":{"draws":13,"losses":36,"wins":25},"z-ai/glm-5.3-flash":{"draws":19,"losses":45,"wins":22},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":11,"losses":17,"wins":20},"claude-fable-5-1":{"draws":6,"losses":42,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":15,"losses":12,"wins":51},"claude-opus-4-8":{"draws":7,"losses":11,"wins":26},"claude-opus-5":{"draws":9,"losses":55,"wins":18},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":13,"losses":7,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":1,"wins":56},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":17},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":27},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":7,"wins":38},"google/gemini-3.5-flash-lite":{"draws":16,"losses":6,"wins":62},"google/gemini-3.6-flash":{"draws":19,"losses":23,"wins":50},"google/gemini-3.8-flash":{"draws":9,"losses":10,"wins":29},"google/gemma-4-31b-it":{"draws":7,"losses":1,"wins":20},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":4,"wins":25},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":38},"gpt-5.5":{"draws":11,"losses":8,"wins":25},"gpt-5.6-luna":{"draws":12,"losses":3,"wins":33},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":23},"gpt-5.6-terra":{"draws":15,"losses":4,"wins":27},"gpt-6-astra":{"draws":7,"losses":38,"wins":3},"gpt-6-luna":{"draws":11,"losses":7,"wins":30},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":26},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":27},"meta/muse-wonder":{"draws":12,"losses":17,"wins":19},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":27},"o3":{"draws":10,"losses":13,"wins":43},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":33},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":9,"wins":28},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":26},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"stealth/ox-alpha":{"draws":31,"losses":41,"wins":86},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":24},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":1,"losses":23,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":18,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":23,"losses":10,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":24},"z-ai/glm-5.3-flashx":{"draws":13,"losses":12,"wins":23}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":4,"wins":31},"claude-fable-5":{"draws":5,"losses":27,"wins":16},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":18,"losses":13,"wins":47},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":8,"losses":50,"wins":24},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":20,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":6,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":9,"wins":26},"fireworks/ember-1":{"draws":8,"losses":5,"wins":19},"gemini-3.1-pro-preview":{"draws":9,"losses":10,"wins":29},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":27,"wins":49},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":22},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":7,"wins":30},"gpt-5.4":{"draws":8,"losses":14,"wins":24},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":34},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":29},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":18},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":35},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":11,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":18,"wins":22},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":8,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":29},"o3":{"draws":7,"losses":6,"wins":53},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":10,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":17},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":12,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"stealth/ox-alpha":{"draws":23,"losses":44,"wins":91},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":12,"losses":2,"wins":50},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":20,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":23},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":3,"losses":26,"wins":19},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":26},"claude-opus-4-5":{"draws":10,"losses":19,"wins":49},"claude-opus-4-8":{"draws":8,"losses":10,"wins":26},"claude-opus-5":{"draws":5,"losses":52,"wins":25},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":7,"losses":12,"wins":29},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":14,"wins":27},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":22},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":36},"google/gemini-3.5-flash-lite":{"draws":13,"losses":11,"wins":60},"google/gemini-3.6-flash":{"draws":10,"losses":24,"wins":58},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":4,"losses":5,"wins":33},"gpt-5.4":{"draws":3,"losses":16,"wins":27},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":5,"losses":18,"wins":21},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":31},"gpt-5.6-sol":{"draws":4,"losses":20,"wins":24},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":28},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":5,"losses":7,"wins":36},"gpt-6-sol":{"draws":6,"losses":25,"wins":17},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":23},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":39},"meta/muse-glimmer-30b":{"draws":7,"losses":2,"wins":33},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":28},"meta/muse-spark-1.3":{"draws":4,"losses":21,"wins":23},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"mistralai/mistral-large-4-0":{"draws":5,"losses":6,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":25},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":30},"o3":{"draws":2,"losses":16,"wins":48},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":31},"poolside/laguna-s-2.1":{"draws":6,"losses":3,"wins":37},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":14,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":19},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"stealth/ox-alpha":{"draws":23,"losses":45,"wins":90},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":2,"losses":15,"wins":29},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":43},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":35},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":16,"wins":25},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":12,"losses":19,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":23},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":23}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":14,"wins":7},"claude-fable-5":{"draws":5,"losses":26,"wins":1},"claude-fable-5-1":{"draws":2,"losses":34,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":4},"claude-opus-4-5":{"draws":21,"losses":61,"wins":6},"claude-opus-4-8":{"draws":13,"losses":43,"wins":4},"claude-opus-5":{"draws":10,"losses":68,"wins":2},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":11,"losses":3,"wins":16},"deepseek/deepseek-v4-flash":{"draws":19,"losses":25,"wins":22},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"fireworks/ember-1":{"draws":8,"losses":21,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":8},"google/gemini-3.1-flash-lite":{"draws":2,"losses":13,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":4},"google/gemini-3.5-flash-lite":{"draws":27,"losses":32,"wins":13},"google/gemini-3.6-flash":{"draws":19,"losses":53,"wins":4},"google/gemini-3.8-flash":{"draws":8,"losses":22,"wins":4},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":8,"losses":8,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":25,"wins":1},"gpt-5.4":{"draws":11,"losses":17,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":17,"wins":5},"gpt-5.4-nano":{"draws":10,"losses":40,"wins":12},"gpt-5.5":{"draws":14,"losses":34,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":19,"wins":4},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":8,"losses":18,"wins":4},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":20,"losses":6,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":23,"wins":17},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":8,"losses":22,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":21,"wins":4},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":6,"losses":10,"wins":10},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":18,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":17,"wins":10},"o3":{"draws":14,"losses":54,"wins":8},"openai/gpt-oss-120b":{"draws":10,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":10},"qwen/qwen3.7-max":{"draws":5,"losses":15,"wins":4},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":1},"qwen/qwen3.8-max-0902":{"draws":9,"losses":19,"wins":2},"stealth/ox-alpha":{"draws":23,"losses":59,"wins":8},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":9,"losses":22,"wins":1},"thinkingmachines/inkling":{"draws":18,"losses":28,"wins":16},"thinkingmachines/inkling-small":{"draws":11,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":7,"losses":29,"wins":2},"x-ai/grok-4.6":{"draws":5,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":41,"losses":30,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":23,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":23,"losses":45,"wins":12},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":17,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":8,"wins":43},"claude-fable-5":{"draws":14,"losses":49,"wins":25},"claude-fable-5-1":{"draws":8,"losses":88,"wins":12},"claude-haiku-5-5":{"draws":12,"losses":14,"wins":20},"claude-opus-4-5":{"draws":29,"losses":16,"wins":67},"claude-opus-4-8":{"draws":15,"losses":19,"wins":18},"claude-opus-5":{"draws":17,"losses":67,"wins":14},"claude-opus-5-5":{"draws":5,"losses":40,"wins":7},"claude-sonnet-5":{"draws":25,"losses":20,"wins":39},"claude-sonnet-5-5":{"draws":5,"losses":24,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":14,"wins":68},"deepseek/deepseek-v4-pro":{"draws":13,"losses":28,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":14,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":12,"wins":25},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":16,"losses":7,"wins":45},"google/gemini-3.5-flash-lite":{"draws":34,"losses":16,"wins":88},"google/gemini-3.6-flash":{"draws":29,"losses":35,"wins":84},"google/gemini-3.8-flash":{"draws":12,"losses":36,"wins":42},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":17},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":9,"wins":22},"gpt-5.4":{"draws":16,"losses":34,"wins":36},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":37},"gpt-5.5":{"draws":16,"losses":13,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":16,"wins":47},"gpt-5.6-sol":{"draws":11,"losses":41,"wins":40},"gpt-5.6-terra":{"draws":31,"losses":22,"wins":33},"gpt-6-astra":{"draws":14,"losses":78,"wins":4},"gpt-6-luna":{"draws":9,"losses":13,"wins":26},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":36},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":33},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":16,"losses":4,"wins":52},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":45},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":37},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":34},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":24,"wins":35},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"o3":{"draws":11,"losses":20,"wins":65},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":45},"poolside/laguna-s-2.1":{"draws":11,"losses":5,"wins":50},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":27,"wins":45},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":21},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":36},"qwen/qwen3.8-max":{"draws":29,"losses":19,"wins":36},"qwen/qwen3.8-max-0902":{"draws":12,"losses":19,"wins":17},"stealth/ox-alpha":{"draws":64,"losses":93,"wins":135},"stealth/space-bunny-alpha":{"draws":8,"losses":3,"wins":27},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":14,"losses":41,"wins":27},"thinkingmachines/inkling":{"draws":16,"losses":5,"wins":59},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":50},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":15,"losses":25,"wins":36},"x-ai/grok-4.6":{"draws":23,"losses":38,"wins":29},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":21,"losses":32,"wins":77},"z-ai/glm-5.3":{"draws":16,"losses":38,"wins":22},"z-ai/glm-5.3-flash":{"draws":12,"losses":35,"wins":45},"z-ai/glm-5.3-flashx":{"draws":12,"losses":18,"wins":18}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":44,"losses":45,"wins":47},"claude-fable-5":{"draws":22,"losses":76,"wins":20},"claude-fable-5-1":{"draws":9,"losses":125,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":48,"wins":11},"claude-opus-4-5":{"draws":67,"losses":111,"wins":72},"claude-opus-4-8":{"draws":16,"losses":58,"wins":14},"claude-opus-5":{"draws":16,"losses":137,"wins":13},"claude-opus-5-5":{"draws":8,"losses":74,"wins":0},"claude-sonnet-5":{"draws":56,"losses":97,"wins":61},"claude-sonnet-5-5":{"draws":16,"losses":48,"wins":14},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":52,"losses":55,"wins":71},"deepseek/deepseek-v4-pro":{"draws":33,"losses":67,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":58,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":34,"wins":21},"fireworks/ember-1":{"draws":29,"losses":35,"wins":14},"gemini-3.1-pro-preview":{"draws":17,"losses":37,"wins":24},"google/gemini-3.1-flash-lite":{"draws":16,"losses":16,"wins":36},"google/gemini-3.5-flash":{"draws":40,"losses":72,"wins":42},"google/gemini-3.5-flash-lite":{"draws":113,"losses":143,"wins":152},"google/gemini-3.6-flash":{"draws":107,"losses":229,"wins":98},"google/gemini-3.8-flash":{"draws":18,"losses":85,"wins":13},"google/gemma-4-31b-it":{"draws":15,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":29,"losses":38,"wins":21},"gpt-5.4":{"draws":41,"losses":116,"wins":47},"gpt-5.4-mini":{"draws":18,"losses":20,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":27,"wins":39},"gpt-5.5":{"draws":31,"losses":45,"wins":18},"gpt-5.6-luna":{"draws":68,"losses":75,"wins":79},"gpt-5.6-sol":{"draws":35,"losses":150,"wins":15},"gpt-5.6-terra":{"draws":37,"losses":62,"wins":33},"gpt-6-astra":{"draws":9,"losses":101,"wins":2},"gpt-6-luna":{"draws":22,"losses":40,"wins":16},"gpt-6-sol":{"draws":11,"losses":63,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":74,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":40,"losses":17,"wins":53},"inclusionai/ling-3.0-flash":{"draws":31,"losses":24,"wins":51},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":57,"wins":89},"meta/muse-glimmer-30b":{"draws":42,"losses":37,"wins":55},"meta/muse-spark-1.2":{"draws":36,"losses":83,"wins":41},"meta/muse-spark-1.3":{"draws":21,"losses":71,"wins":22},"meta/muse-wonder":{"draws":10,"losses":59,"wins":9},"minimax/minimax-m3":{"draws":12,"losses":17,"wins":19},"mistralai/mistral-large-4-0":{"draws":14,"losses":21,"wins":13},"mistralai/mistral-medium-3-5":{"draws":25,"losses":19,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":53,"losses":92,"wins":57},"nex-agi/nex-n2-pro":{"draws":11,"losses":10,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":32,"wins":27},"o3":{"draws":30,"losses":166,"wins":92},"openai/gpt-oss-120b":{"draws":42,"losses":34,"wins":56},"poolside/laguna-s-2.1":{"draws":68,"losses":53,"wins":57},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":18},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":66,"wins":35},"qwen/qwen3.8-27b":{"draws":10,"losses":42,"wins":14},"qwen/qwen3.8-flash":{"draws":32,"losses":42,"wins":16},"qwen/qwen3.8-max":{"draws":48,"losses":62,"wins":26},"qwen/qwen3.8-max-0902":{"draws":20,"losses":43,"wins":15},"stealth/ox-alpha":{"draws":83,"losses":248,"wins":115},"stealth/space-bunny-alpha":{"draws":13,"losses":30,"wins":21},"stepfun/step-3.7-flash":{"draws":15,"losses":22,"wins":33},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":21,"wins":15},"tencent/hy4-preview":{"draws":29,"losses":76,"wins":33},"thinkingmachines/inkling":{"draws":53,"losses":55,"wins":90},"thinkingmachines/inkling-small":{"draws":49,"losses":59,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":25,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":9},"x-ai/grok-4.5":{"draws":48,"losses":98,"wins":50},"x-ai/grok-4.6":{"draws":30,"losses":68,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.5":{"draws":40,"losses":38,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":20,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":33,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":9},"z-ai/glm-5.2":{"draws":60,"losses":87,"wins":83},"z-ai/glm-5.3":{"draws":19,"losses":80,"wins":11},"z-ai/glm-5.3-flash":{"draws":32,"losses":79,"wins":19},"z-ai/glm-5.3-flashx":{"draws":16,"losses":45,"wins":17}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":19,"wins":72},"claude-fable-5":{"draws":16,"losses":69,"wins":67},"claude-fable-5-1":{"draws":11,"losses":140,"wins":17},"claude-haiku-5-5":{"draws":22,"losses":24,"wins":46},"claude-opus-4-5":{"draws":60,"losses":62,"wins":156},"claude-opus-4-8":{"draws":18,"losses":44,"wins":52},"claude-opus-5":{"draws":40,"losses":156,"wins":46},"claude-opus-5-5":{"draws":15,"losses":82,"wins":7},"claude-sonnet-5":{"draws":28,"losses":49,"wins":139},"claude-sonnet-5-5":{"draws":21,"losses":34,"wins":41},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":27},"deepseek/deepseek-v4-flash":{"draws":33,"losses":7,"wins":148},"deepseek/deepseek-v4-pro":{"draws":30,"losses":35,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":25,"wins":81},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":25,"wins":47},"fireworks/ember-1":{"draws":24,"losses":24,"wins":48},"gemini-3.1-pro-preview":{"draws":18,"losses":24,"wins":54},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":61},"google/gemini-3.5-flash":{"draws":40,"losses":54,"wins":82},"google/gemini-3.5-flash-lite":{"draws":105,"losses":46,"wins":271},"google/gemini-3.6-flash":{"draws":62,"losses":114,"wins":212},"google/gemini-3.8-flash":{"draws":32,"losses":58,"wins":68},"google/gemma-4-31b-it":{"draws":15,"losses":2,"wins":39},"gpt-4.1":{"draws":7,"losses":5,"wins":20},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":9},"gpt-5":{"draws":16,"losses":33,"wins":63},"gpt-5.4":{"draws":38,"losses":92,"wins":88},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":42},"gpt-5.4-nano":{"draws":17,"losses":12,"wins":67},"gpt-5.5":{"draws":27,"losses":36,"wins":49},"gpt-5.6-luna":{"draws":45,"losses":52,"wins":117},"gpt-5.6-sol":{"draws":25,"losses":96,"wins":101},"gpt-5.6-terra":{"draws":34,"losses":26,"wins":80},"gpt-6-astra":{"draws":10,"losses":119,"wins":21},"gpt-6-luna":{"draws":28,"losses":13,"wins":55},"gpt-6-sol":{"draws":15,"losses":54,"wins":27},"gpt-6.1-sol":{"draws":9,"losses":74,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":27,"losses":7,"wins":56},"inclusionai/ling-3.0-flash":{"draws":39,"losses":6,"wins":63},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":40,"losses":19,"wins":131},"meta/muse-glimmer-30b":{"draws":34,"losses":9,"wins":79},"meta/muse-spark-1.2":{"draws":26,"losses":52,"wins":90},"meta/muse-spark-1.3":{"draws":16,"losses":53,"wins":65},"meta/muse-wonder":{"draws":21,"losses":44,"wins":31},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":35},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":32},"mistralai/mistral-medium-3-5":{"draws":22,"losses":4,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":1,"wins":16},"moonshotai/kimi-k3":{"draws":46,"losses":39,"wins":125},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":37},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":12,"wins":69},"o3":{"draws":41,"losses":56,"wins":193},"openai/gpt-oss-120b":{"draws":30,"losses":8,"wins":80},"poolside/laguna-s-2.1":{"draws":49,"losses":13,"wins":100},"qwen/qwen3.7-max":{"draws":20,"losses":9,"wins":29},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":41,"wins":80},"qwen/qwen3.8-27b":{"draws":19,"losses":17,"wins":44},"qwen/qwen3.8-flash":{"draws":35,"losses":15,"wins":50},"qwen/qwen3.8-max":{"draws":38,"losses":37,"wins":80},"qwen/qwen3.8-max-0902":{"draws":27,"losses":34,"wins":35},"stealth/ox-alpha":{"draws":83,"losses":145,"wins":256},"stealth/space-bunny-alpha":{"draws":15,"losses":8,"wins":53},"stepfun/step-3.7-flash":{"draws":11,"losses":5,"wins":65},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":18,"wins":41},"tencent/hy4-preview":{"draws":29,"losses":39,"wins":80},"thinkingmachines/inkling":{"draws":52,"losses":27,"wins":127},"thinkingmachines/inkling-small":{"draws":35,"losses":11,"wins":86},"unbiased/pareto-26.10-preview":{"draws":2,"losses":25,"wins":5},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":19},"x-ai/grok-4.5":{"draws":31,"losses":70,"wins":117},"x-ai/grok-4.6":{"draws":27,"losses":53,"wins":76},"x-ai/grok-4.7":{"draws":8,"losses":55,"wins":21},"x-ai/grok-build-0.1":{"draws":9,"losses":1,"wins":22},"xiaomi/mimo-v2.5":{"draws":42,"losses":8,"wins":102},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":20,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":30,"wins":23},"z-ai/glm-5.2":{"draws":59,"losses":36,"wins":141},"z-ai/glm-5.3":{"draws":23,"losses":56,"wins":51},"z-ai/glm-5.3-flash":{"draws":36,"losses":55,"wins":57},"z-ai/glm-5.3-flashx":{"draws":29,"losses":32,"wins":35}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":48},"claude-fable-5":{"draws":11,"losses":43,"wins":36},"claude-fable-5-1":{"draws":11,"losses":84,"wins":13},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":16,"losses":25,"wins":67},"claude-opus-4-8":{"draws":6,"losses":14,"wins":26},"claude-opus-5":{"draws":4,"losses":82,"wins":24},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":11,"losses":22,"wins":51},"claude-sonnet-5-5":{"draws":4,"losses":22,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":81},"deepseek/deepseek-v4-pro":{"draws":16,"losses":14,"wins":52},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":24,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":17,"wins":23},"fireworks/ember-1":{"draws":5,"losses":17,"wins":26},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":34},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":18,"losses":13,"wins":67},"google/gemini-3.5-flash-lite":{"draws":14,"losses":9,"wins":103},"google/gemini-3.6-flash":{"draws":18,"losses":39,"wins":89},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":25},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":8,"losses":9,"wins":27},"gpt-5.4":{"draws":13,"losses":38,"wins":33},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":32},"gpt-5.5":{"draws":9,"losses":21,"wins":18},"gpt-5.6-luna":{"draws":12,"losses":16,"wins":46},"gpt-5.6-sol":{"draws":8,"losses":40,"wins":48},"gpt-5.6-terra":{"draws":20,"losses":24,"wins":36},"gpt-6-astra":{"draws":12,"losses":75,"wins":9},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":33},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":30},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":5,"wins":48},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":44},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":42},"meta/muse-spark-1.3":{"draws":13,"losses":27,"wins":28},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":4,"wins":22},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":45},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":28},"o3":{"draws":9,"losses":16,"wins":69},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":50},"poolside/laguna-s-2.1":{"draws":7,"losses":4,"wins":47},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":28,"wins":48},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":27},"qwen/qwen3.8-flash":{"draws":7,"losses":17,"wins":30},"qwen/qwen3.8-max":{"draws":18,"losses":31,"wins":33},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":24},"stealth/ox-alpha":{"draws":42,"losses":82,"wins":164},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":24},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":9,"losses":32,"wins":35},"thinkingmachines/inkling":{"draws":12,"losses":8,"wins":54},"thinkingmachines/inkling-small":{"draws":19,"losses":15,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":34,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":34,"wins":43},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":13,"losses":14,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":18,"losses":29,"wins":83},"z-ai/glm-5.3":{"draws":15,"losses":37,"wins":26},"z-ai/glm-5.3-flash":{"draws":18,"losses":27,"wins":43},"z-ai/glm-5.3-flashx":{"draws":9,"losses":15,"wins":24}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":9,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":14},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":58,"losses":29,"wins":39},"claude-opus-4-8":{"draws":24,"losses":42,"wins":20},"claude-opus-5":{"draws":14,"losses":130,"wins":14},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":17,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":36,"losses":5,"wins":51},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":11,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":16,"wins":10},"fireworks/ember-1":{"draws":15,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":19,"wins":13},"google/gemini-3.1-flash-lite":{"draws":20,"losses":4,"wins":36},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":27},"google/gemini-3.5-flash-lite":{"draws":47,"losses":20,"wins":43},"google/gemini-3.6-flash":{"draws":37,"losses":57,"wins":38},"google/gemini-3.8-flash":{"draws":12,"losses":23,"wins":17},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":10,"losses":11,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":5,"wins":25},"gpt-5.4":{"draws":12,"losses":22,"wins":14},"gpt-5.4-mini":{"draws":15,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":50},"gpt-5.5":{"draws":34,"losses":32,"wins":18},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":15,"wins":18},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":19,"losses":12,"wins":17},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":19,"losses":10,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":19,"wins":31},"meta/muse-glimmer-30b":{"draws":21,"losses":4,"wins":21},"meta/muse-spark-1.2":{"draws":17,"losses":18,"wins":17},"meta/muse-spark-1.3":{"draws":18,"losses":21,"wins":15},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":14,"losses":6,"wins":24},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":9},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":18},"nex-agi/nex-n2-pro":{"draws":17,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":4,"wins":39},"o3":{"draws":18,"losses":34,"wins":48},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":20},"poolside/laguna-s-2.1":{"draws":28,"losses":26,"wins":18},"qwen/qwen3.7-max":{"draws":21,"losses":6,"wins":17},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":16},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":24,"losses":11,"wins":13},"qwen/qwen3.8-max-0902":{"draws":15,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":43,"losses":74,"wins":49},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":14,"losses":6,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":19,"losses":15,"wins":16},"thinkingmachines/inkling":{"draws":33,"losses":16,"wins":47},"thinkingmachines/inkling-small":{"draws":20,"losses":5,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":37,"wins":19},"x-ai/grok-4.6":{"draws":17,"losses":26,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":59,"losses":17,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":12,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":55,"losses":35,"wins":54},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":9},"z-ai/glm-5.3-flash":{"draws":18,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":19,"losses":13,"wins":16}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":37},"claude-fable-5":{"draws":21,"losses":26,"wins":37},"claude-fable-5-1":{"draws":11,"losses":68,"wins":17},"claude-haiku-5-5":{"draws":6,"losses":12,"wins":22},"claude-opus-4-5":{"draws":19,"losses":17,"wins":84},"claude-opus-4-8":{"draws":5,"losses":14,"wins":25},"claude-opus-5":{"draws":8,"losses":51,"wins":17},"claude-opus-5-5":{"draws":4,"losses":36,"wins":6},"claude-sonnet-5":{"draws":17,"losses":21,"wins":78},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":7,"wins":63},"deepseek/deepseek-v4-pro":{"draws":17,"losses":12,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":12,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":27},"fireworks/ember-1":{"draws":5,"losses":9,"wins":28},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":28},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":7,"losses":12,"wins":65},"google/gemini-3.5-flash-lite":{"draws":22,"losses":17,"wins":151},"google/gemini-3.6-flash":{"draws":34,"losses":35,"wins":137},"google/gemini-3.8-flash":{"draws":5,"losses":24,"wins":53},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":19},"gpt-4.1":{"draws":4,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":33},"gpt-5.4":{"draws":17,"losses":6,"wins":68},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":36},"gpt-5.5":{"draws":9,"losses":9,"wins":22},"gpt-5.6-luna":{"draws":17,"losses":5,"wins":87},"gpt-5.6-sol":{"draws":27,"losses":45,"wins":62},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":58},"gpt-6-astra":{"draws":8,"losses":65,"wins":11},"gpt-6-luna":{"draws":8,"losses":8,"wins":26},"gpt-6-sol":{"draws":2,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":20},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":36},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":10,"losses":2,"wins":66},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":9,"losses":22,"wins":53},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":42},"meta/muse-wonder":{"draws":5,"losses":17,"wins":20},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":67},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":26},"o3":{"draws":2,"losses":12,"wins":114},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":36},"poolside/laguna-s-2.1":{"draws":12,"losses":3,"wins":55},"qwen/qwen3.7-max":{"draws":0,"losses":5,"wins":21},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":41},"qwen/qwen3.8-27b":{"draws":7,"losses":2,"wins":31},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":32},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":42},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":27},"stealth/ox-alpha":{"draws":75,"losses":50,"wins":139},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":52},"thinkingmachines/inkling":{"draws":19,"losses":14,"wins":55},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":37},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":16,"losses":17,"wins":62},"x-ai/grok-4.6":{"draws":17,"losses":18,"wins":47},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":12},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":25,"losses":19,"wins":70},"z-ai/glm-5.3":{"draws":4,"losses":26,"wins":34},"z-ai/glm-5.3-flash":{"draws":11,"losses":18,"wins":47},"z-ai/glm-5.3-flashx":{"draws":6,"losses":13,"wins":23}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":27},"claude-fable-5":{"draws":7,"losses":19,"wins":18},"claude-fable-5-1":{"draws":0,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":22},"claude-opus-4-5":{"draws":27,"losses":14,"wins":71},"claude-opus-4-8":{"draws":11,"losses":14,"wins":55},"claude-opus-5":{"draws":8,"losses":88,"wins":80},"claude-opus-5-5":{"draws":2,"losses":35,"wins":9},"claude-sonnet-5":{"draws":7,"losses":8,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":20,"losses":2,"wins":54},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":8,"wins":22},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":29},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":38},"google/gemini-3.5-flash":{"draws":14,"losses":9,"wins":35},"google/gemini-3.5-flash-lite":{"draws":26,"losses":10,"wins":62},"google/gemini-3.6-flash":{"draws":29,"losses":24,"wins":59},"google/gemini-3.8-flash":{"draws":12,"losses":7,"wins":27},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":17},"gpt-4.1":{"draws":2,"losses":2,"wins":18},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":17,"losses":9,"wins":50},"gpt-5.4":{"draws":15,"losses":12,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":55},"gpt-5.5":{"draws":24,"losses":10,"wins":24},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":9,"losses":6,"wins":25},"gpt-6-astra":{"draws":1,"losses":38,"wins":5},"gpt-6-luna":{"draws":15,"losses":3,"wins":24},"gpt-6-sol":{"draws":4,"losses":23,"wins":15},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":15,"losses":7,"wins":38},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":4,"losses":7,"wins":31},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":24},"meta/muse-wonder":{"draws":8,"losses":14,"wins":20},"minimax/minimax-m3":{"draws":9,"losses":3,"wins":22},"mistralai/mistral-large-4-0":{"draws":4,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":19},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":2,"wins":39},"o3":{"draws":8,"losses":9,"wins":77},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":11,"losses":5,"wins":40},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":29},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":8,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-flash":{"draws":7,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":23},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":22},"stealth/ox-alpha":{"draws":31,"losses":31,"wins":86},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":39},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":20,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":11,"wins":22},"thinkingmachines/inkling":{"draws":13,"losses":11,"wins":58},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":30},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":20,"losses":15,"wins":37},"x-ai/grok-4.6":{"draws":13,"losses":11,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":17,"wins":15},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":3,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":32,"losses":8,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":5,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":10,"losses":9,"wins":23}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":15,"wins":25},"claude-fable-5":{"draws":23,"losses":36,"wins":25},"claude-fable-5-1":{"draws":5,"losses":74,"wins":9},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":50,"losses":29,"wins":55},"claude-opus-4-8":{"draws":15,"losses":10,"wins":21},"claude-opus-5":{"draws":8,"losses":66,"wins":10},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":40,"losses":32,"wins":60},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":46,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":25,"losses":18,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":14,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":14,"wins":13},"fireworks/ember-1":{"draws":18,"losses":8,"wins":22},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":21},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":35,"losses":20,"wins":43},"google/gemini-3.5-flash-lite":{"draws":89,"losses":34,"wins":113},"google/gemini-3.6-flash":{"draws":63,"losses":71,"wins":90},"google/gemini-3.8-flash":{"draws":23,"losses":27,"wins":36},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":8,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":8,"wins":22},"gpt-5.4":{"draws":54,"losses":58,"wins":27},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":18,"losses":13,"wins":13},"gpt-5.6-luna":{"draws":41,"losses":13,"wins":35},"gpt-5.6-sol":{"draws":24,"losses":64,"wins":40},"gpt-5.6-terra":{"draws":32,"losses":13,"wins":41},"gpt-6-astra":{"draws":10,"losses":67,"wins":1},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":3,"wins":22},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":27},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":14,"wins":54},"meta/muse-glimmer-30b":{"draws":33,"losses":5,"wins":34},"meta/muse-spark-1.2":{"draws":19,"losses":42,"wins":35},"meta/muse-spark-1.3":{"draws":19,"losses":25,"wins":24},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":26,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":35,"losses":27,"wins":38},"nex-agi/nex-n2-pro":{"draws":10,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":22},"o3":{"draws":27,"losses":29,"wins":76},"openai/gpt-oss-120b":{"draws":38,"losses":8,"wins":28},"poolside/laguna-s-2.1":{"draws":43,"losses":11,"wins":40},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":14,"wins":35},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":15},"qwen/qwen3.8-flash":{"draws":21,"losses":22,"wins":17},"qwen/qwen3.8-max":{"draws":33,"losses":27,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":9,"wins":21},"stealth/ox-alpha":{"draws":76,"losses":93,"wins":103},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":34,"losses":18,"wins":28},"thinkingmachines/inkling":{"draws":34,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":38,"losses":12,"wins":32},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":18,"losses":25,"wins":63},"x-ai/grok-4.6":{"draws":23,"losses":35,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":3,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":55,"losses":36,"wins":41},"z-ai/glm-5.3":{"draws":16,"losses":38,"wins":18},"z-ai/glm-5.3-flash":{"draws":24,"losses":33,"wins":27},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":52},"claude-fable-5":{"draws":6,"losses":29,"wins":55},"claude-fable-5-1":{"draws":10,"losses":67,"wins":31},"claude-haiku-5-5":{"draws":7,"losses":5,"wins":34},"claude-opus-4-5":{"draws":8,"losses":29,"wins":99},"claude-opus-4-8":{"draws":7,"losses":5,"wins":34},"claude-opus-5":{"draws":9,"losses":53,"wins":34},"claude-opus-5-5":{"draws":6,"losses":31,"wins":15},"claude-sonnet-5":{"draws":0,"losses":9,"wins":131},"claude-sonnet-5-5":{"draws":2,"losses":15,"wins":31},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":87},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":2,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":39},"fireworks/ember-1":{"draws":5,"losses":7,"wins":36},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":5,"losses":15,"wins":72},"google/gemini-3.5-flash-lite":{"draws":10,"losses":3,"wins":193},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":158},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":63},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":0,"losses":3,"wins":39},"gpt-5.4":{"draws":9,"losses":32,"wins":91},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":29},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":5,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":6,"losses":16,"wins":100},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":85},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":66},"gpt-6-astra":{"draws":12,"losses":70,"wins":14},"gpt-6-luna":{"draws":9,"losses":2,"wins":37},"gpt-6-sol":{"draws":6,"losses":18,"wins":24},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":36},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":7,"wins":71},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":45},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":88},"meta/muse-spark-1.3":{"draws":9,"losses":11,"wins":50},"meta/muse-wonder":{"draws":2,"losses":16,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":1,"losses":9,"wins":94},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"o3":{"draws":1,"losses":21,"wins":104},"openai/gpt-oss-120b":{"draws":5,"losses":5,"wins":42},"poolside/laguna-s-2.1":{"draws":3,"losses":2,"wins":79},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":11,"wins":66},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":33},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":41},"qwen/qwen3.8-max":{"draws":5,"losses":6,"wins":69},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"stealth/ox-alpha":{"draws":24,"losses":31,"wins":227},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":24},"tencent/hy4-preview":{"draws":6,"losses":26,"wins":48},"thinkingmachines/inkling":{"draws":6,"losses":4,"wins":78},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":67},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":10,"losses":9,"wins":85},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":55},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":19},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":3,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":104},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":47},"z-ai/glm-5.3-flash":{"draws":9,"losses":20,"wins":59},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":9,"wins":39},"claude-fable-5":{"draws":26,"losses":41,"wins":21},"claude-fable-5-1":{"draws":6,"losses":84,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":32,"losses":35,"wins":37},"claude-opus-4-8":{"draws":6,"losses":21,"wins":21},"claude-opus-5":{"draws":11,"losses":67,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":29,"losses":21,"wins":34},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":30,"losses":17,"wins":63},"deepseek/deepseek-v4-pro":{"draws":18,"losses":25,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":21,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":20,"wins":9},"fireworks/ember-1":{"draws":15,"losses":14,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":27},"google/gemini-3.5-flash":{"draws":32,"losses":19,"wins":47},"google/gemini-3.5-flash-lite":{"draws":40,"losses":22,"wins":84},"google/gemini-3.6-flash":{"draws":47,"losses":55,"wins":46},"google/gemini-3.8-flash":{"draws":21,"losses":37,"wins":26},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":23,"losses":38,"wins":21},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":33},"gpt-5.5":{"draws":13,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":24,"losses":23,"wins":37},"gpt-5.6-sol":{"draws":15,"losses":52,"wins":21},"gpt-5.6-terra":{"draws":18,"losses":22,"wins":18},"gpt-6-astra":{"draws":5,"losses":76,"wins":3},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":11,"losses":29,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":6,"wins":27},"inclusionai/ling-3.0-flash":{"draws":11,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":15,"wins":40},"meta/muse-glimmer-30b":{"draws":28,"losses":13,"wins":33},"meta/muse-spark-1.2":{"draws":17,"losses":36,"wins":15},"meta/muse-spark-1.3":{"draws":17,"losses":31,"wins":22},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-large-4-0":{"draws":15,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":17,"losses":6,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":27,"losses":15,"wins":32},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":26},"o3":{"draws":11,"losses":31,"wins":54},"openai/gpt-oss-120b":{"draws":17,"losses":11,"wins":46},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":39},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":21},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":40,"wins":23},"qwen/qwen3.8-27b":{"draws":13,"losses":11,"wins":18},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":28},"qwen/qwen3.8-max":{"draws":32,"losses":32,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":66,"losses":100,"wins":104},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":4,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":17,"losses":30,"wins":33},"thinkingmachines/inkling":{"draws":20,"losses":10,"wins":50},"thinkingmachines/inkling-small":{"draws":26,"losses":10,"wins":50},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":34,"wins":26},"x-ai/grok-4.6":{"draws":26,"losses":50,"wins":14},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":25,"losses":4,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":55,"losses":29,"wins":58},"z-ai/glm-5.3":{"draws":24,"losses":31,"wins":19},"z-ai/glm-5.3-flash":{"draws":17,"losses":34,"wins":33},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":4,"wins":54},"claude-fable-5":{"draws":3,"losses":16,"wins":75},"claude-fable-5-1":{"draws":7,"losses":25,"wins":76},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":2,"losses":7,"wins":97},"claude-opus-4-8":{"draws":1,"losses":2,"wins":43},"claude-opus-5":{"draws":4,"losses":10,"wins":70},"claude-opus-5-5":{"draws":6,"losses":14,"wins":32},"claude-sonnet-5":{"draws":0,"losses":4,"wins":84},"claude-sonnet-5-5":{"draws":2,"losses":6,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":93},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":46},"fireworks/ember-1":{"draws":0,"losses":1,"wins":47},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":92},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":118},"google/gemini-3.6-flash":{"draws":4,"losses":5,"wins":133},"google/gemini-3.8-flash":{"draws":7,"losses":3,"wins":80},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":2,"losses":8,"wins":74},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":4,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":61},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":82},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":81},"gpt-6-astra":{"draws":1,"losses":14,"wins":49},"gpt-6-luna":{"draws":3,"losses":0,"wins":45},"gpt-6-sol":{"draws":6,"losses":4,"wins":38},"gpt-6.1-sol":{"draws":5,"losses":7,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":42},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":36},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":62},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":52},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":68},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":68},"meta/muse-wonder":{"draws":3,"losses":3,"wins":42},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":70},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":41},"o3":{"draws":1,"losses":2,"wins":87},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":52},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":56},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":83},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":49},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":78},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"stealth/ox-alpha":{"draws":10,"losses":8,"wins":264},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":0,"losses":6,"wins":76},"thinkingmachines/inkling":{"draws":0,"losses":2,"wins":68},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":64},"unbiased/pareto-26.10-preview":{"draws":3,"losses":5,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":68},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":88},"x-ai/grok-4.7":{"draws":3,"losses":3,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":28},"z-ai/glm-5.2":{"draws":2,"losses":1,"wins":117},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":64},"z-ai/glm-5.3-flash":{"draws":8,"losses":2,"wins":74},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":45}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":26,"wins":13},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":20,"wins":21},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":7,"losses":17,"wins":20},"claude-opus-5":{"draws":11,"losses":61,"wins":10},"claude-opus-5-5":{"draws":8,"losses":43,"wins":1},"claude-sonnet-5":{"draws":8,"losses":14,"wins":26},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":13,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":21},"fireworks/ember-1":{"draws":6,"losses":21,"wins":21},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":23},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":29},"google/gemini-3.5-flash-lite":{"draws":12,"losses":19,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":39},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":19},"gpt-4.1":{"draws":2,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":14,"wins":23},"gpt-5.4":{"draws":11,"losses":18,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":3,"losses":13,"wins":32},"gpt-5.5":{"draws":9,"losses":18,"wins":17},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":11,"losses":26,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":9,"losses":36,"wins":3},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":6,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":8,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":26,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"mistralai/mistral-large-4-0":{"draws":5,"losses":9,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":16,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":9,"wins":31},"o3":{"draws":2,"losses":20,"wins":44},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":14,"wins":28},"qwen/qwen3.7-max":{"draws":2,"losses":8,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":21},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"stealth/ox-alpha":{"draws":31,"losses":57,"wins":70},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":20},"thinkingmachines/inkling":{"draws":8,"losses":11,"wins":45},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":19},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":29,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":14,"losses":14,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":21,"losses":26,"wins":49},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":36},"claude-fable-5":{"draws":4,"losses":10,"wins":34},"claude-fable-5-1":{"draws":4,"losses":23,"wins":27},"claude-haiku-5-5":{"draws":5,"losses":8,"wins":33},"claude-opus-4-5":{"draws":3,"losses":12,"wins":63},"claude-opus-4-8":{"draws":3,"losses":9,"wins":32},"claude-opus-5":{"draws":12,"losses":24,"wins":46},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":5,"losses":10,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":7,"wins":61},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":6,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":35},"fireworks/ember-1":{"draws":3,"losses":5,"wins":40},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":35},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":48},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":7,"losses":16,"wins":69},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":26},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":6,"wins":36},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":1,"losses":4,"wins":27},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":3,"losses":7,"wins":34},"gpt-5.6-luna":{"draws":1,"losses":6,"wins":41},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":38},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":37},"gpt-6-astra":{"draws":4,"losses":32,"wins":12},"gpt-6-luna":{"draws":6,"losses":4,"wins":38},"gpt-6-sol":{"draws":3,"losses":8,"wins":21},"gpt-6.1-sol":{"draws":5,"losses":23,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"inclusionai/ling-3.0-flash":{"draws":3,"losses":5,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":40},"meta/muse-wonder":{"draws":2,"losses":8,"wins":38},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":21},"mistralai/mistral-large-4-0":{"draws":3,"losses":5,"wins":22},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":0,"losses":5,"wins":41},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":36},"o3":{"draws":0,"losses":9,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":6,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":26},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":40},"qwen/qwen3.8-max-0902":{"draws":0,"losses":9,"wins":39},"stealth/ox-alpha":{"draws":14,"losses":20,"wins":124},"stealth/space-bunny-alpha":{"draws":0,"losses":4,"wins":34},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":22},"tencent/hy4-preview":{"draws":4,"losses":7,"wins":35},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":45},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":38},"x-ai/grok-4.6":{"draws":2,"losses":5,"wins":41},"x-ai/grok-4.7":{"draws":5,"losses":15,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":5,"losses":13,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":36}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":44},"claude-fable-5":{"draws":3,"losses":5,"wins":40},"claude-fable-5-1":{"draws":6,"losses":16,"wins":32},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":0,"losses":2,"wins":76},"claude-opus-4-8":{"draws":1,"losses":1,"wins":42},"claude-opus-5":{"draws":5,"losses":14,"wins":63},"claude-opus-5-5":{"draws":5,"losses":22,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":7,"wins":39},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":71},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":42},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":46},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":55},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":82},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":42},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":41},"gpt-5.4":{"draws":3,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":5,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":8,"wins":38},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":44},"gpt-6-astra":{"draws":8,"losses":16,"wins":24},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":4,"wins":39},"gpt-6.1-sol":{"draws":2,"losses":7,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":51},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":0,"wins":46},"meta/muse-wonder":{"draws":4,"losses":4,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":42},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":40},"o3":{"draws":0,"losses":2,"wins":64},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":30},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"stealth/ox-alpha":{"draws":3,"losses":4,"wins":151},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":38},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":26},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":6,"wins":9},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":46},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":36},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":27},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":93},"z-ai/glm-5.3":{"draws":6,"losses":3,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":42}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":18,"wins":14},"claude-fable-5":{"draws":16,"losses":34,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":27,"wins":0},"claude-opus-4-5":{"draws":37,"losses":41,"wins":2},"claude-opus-4-8":{"draws":10,"losses":26,"wins":2},"claude-opus-5":{"draws":11,"losses":45,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":23,"losses":42,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":2},"deepseek/deepseek-v4-flash":{"draws":40,"losses":39,"wins":7},"deepseek/deepseek-v4-pro":{"draws":26,"losses":28,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":28,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":2},"fireworks/ember-1":{"draws":15,"losses":20,"wins":1},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":5},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":32,"losses":35,"wins":1},"google/gemini-3.5-flash-lite":{"draws":61,"losses":53,"wins":6},"google/gemini-3.6-flash":{"draws":49,"losses":55,"wins":6},"google/gemini-3.8-flash":{"draws":17,"losses":40,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":8},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":16,"wins":1},"gpt-5.4":{"draws":24,"losses":26,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":6},"gpt-5.5":{"draws":13,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":34,"losses":18,"wins":12},"gpt-5.6-sol":{"draws":11,"losses":43,"wins":0},"gpt-5.6-terra":{"draws":24,"losses":34,"wins":4},"gpt-6-astra":{"draws":5,"losses":41,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":2},"gpt-6-sol":{"draws":4,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":21,"losses":16,"wins":9},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":23,"wins":8},"meta/muse-glimmer-30b":{"draws":32,"losses":20,"wins":8},"meta/muse-spark-1.2":{"draws":20,"losses":32,"wins":2},"meta/muse-spark-1.3":{"draws":19,"losses":27,"wins":6},"meta/muse-wonder":{"draws":8,"losses":28,"wins":0},"minimax/minimax-m3":{"draws":12,"losses":9,"wins":1},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":20,"losses":12,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":10},"o3":{"draws":16,"losses":56,"wins":2},"openai/gpt-oss-120b":{"draws":28,"losses":18,"wins":14},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":5},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":22,"losses":20,"wins":4},"qwen/qwen3.8-max":{"draws":34,"losses":26,"wins":4},"qwen/qwen3.8-max-0902":{"draws":17,"losses":16,"wins":3},"stealth/ox-alpha":{"draws":57,"losses":85,"wins":16},"stealth/space-bunny-alpha":{"draws":16,"losses":11,"wins":1},"stepfun/step-3.7-flash":{"draws":14,"losses":15,"wins":3},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":3},"tencent/hy4-preview":{"draws":25,"losses":28,"wins":3},"thinkingmachines/inkling":{"draws":25,"losses":24,"wins":7},"thinkingmachines/inkling-small":{"draws":35,"losses":27,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":19,"losses":33,"wins":0},"x-ai/grok-4.6":{"draws":19,"losses":26,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":27,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":10,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":47,"losses":48,"wins":9},"z-ai/glm-5.3":{"draws":18,"losses":29,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":34,"wins":3},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":2}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":14,"wins":29},"claude-fable-5":{"draws":16,"losses":44,"wins":4},"claude-fable-5-1":{"draws":4,"losses":58,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":17,"wins":8},"claude-opus-4-5":{"draws":38,"losses":37,"wins":15},"claude-opus-4-8":{"draws":14,"losses":21,"wins":9},"claude-opus-5":{"draws":8,"losses":66,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":30,"losses":33,"wins":17},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":12},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":51,"losses":17,"wins":30},"deepseek/deepseek-v4-pro":{"draws":27,"losses":27,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":30,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":14,"wins":9},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":8},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":30,"losses":29,"wins":21},"google/gemini-3.5-flash-lite":{"draws":56,"losses":41,"wins":41},"google/gemini-3.6-flash":{"draws":55,"losses":52,"wins":33},"google/gemini-3.8-flash":{"draws":21,"losses":39,"wins":10},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":20,"losses":17,"wins":9},"gpt-5.4":{"draws":26,"losses":32,"wins":12},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":15},"gpt-5.5":{"draws":23,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":40,"losses":18,"wins":22},"gpt-5.6-sol":{"draws":12,"losses":41,"wins":9},"gpt-5.6-terra":{"draws":40,"losses":25,"wins":9},"gpt-6-astra":{"draws":4,"losses":56,"wins":0},"gpt-6-luna":{"draws":17,"losses":17,"wins":8},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":6,"wins":19},"inclusionai/ling-3.0-flash":{"draws":28,"losses":8,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":27,"losses":10,"wins":27},"meta/muse-glimmer-30b":{"draws":28,"losses":4,"wins":18},"meta/muse-spark-1.2":{"draws":20,"losses":26,"wins":14},"meta/muse-spark-1.3":{"draws":24,"losses":22,"wins":12},"meta/muse-wonder":{"draws":12,"losses":25,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":5,"wins":9},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":28,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":24,"losses":23,"wins":13},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":14},"o3":{"draws":19,"losses":38,"wins":21},"openai/gpt-oss-120b":{"draws":34,"losses":15,"wins":23},"poolside/laguna-s-2.1":{"draws":30,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":2,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":20,"wins":17},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":21,"losses":12,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":26,"wins":22},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":6},"stealth/ox-alpha":{"draws":65,"losses":124,"wins":49},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":3,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":4},"tencent/hy4-preview":{"draws":30,"losses":28,"wins":12},"thinkingmachines/inkling":{"draws":30,"losses":16,"wins":32},"thinkingmachines/inkling-small":{"draws":42,"losses":5,"wins":33},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":30,"wins":10},"x-ai/grok-4.6":{"draws":20,"losses":40,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":11,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":5,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":58,"losses":42,"wins":24},"z-ai/glm-5.3":{"draws":18,"losses":33,"wins":7},"z-ai/glm-5.3-flash":{"draws":22,"losses":38,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":10}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":29},"claude-fable-5":{"draws":8,"losses":26,"wins":14},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":18,"losses":18,"wins":42},"claude-opus-4-8":{"draws":8,"losses":14,"wins":22},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":21,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":21},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":24},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":17,"wins":33},"google/gemini-3.5-flash-lite":{"draws":16,"losses":15,"wins":53},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":18,"wins":23},"google/gemma-4-31b-it":{"draws":5,"losses":5,"wins":18},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":6,"losses":5,"wins":31},"gpt-5.4":{"draws":9,"losses":20,"wins":17},"gpt-5.4-mini":{"draws":7,"losses":7,"wins":18},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":27},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":24},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":11,"losses":11,"wins":26},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":15},"meta/muse-spark-1.3":{"draws":6,"losses":21,"wins":21},"meta/muse-wonder":{"draws":9,"losses":21,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":23},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":26},"o3":{"draws":6,"losses":21,"wins":39},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":21},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":24},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":25},"stealth/ox-alpha":{"draws":30,"losses":57,"wins":71},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":24},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":9,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":11,"losses":20,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":16},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":7,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":52},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":19,"wins":19}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":33},"claude-fable-5":{"draws":6,"losses":21,"wins":21},"claude-fable-5-1":{"draws":4,"losses":41,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":12,"losses":11,"wins":55},"claude-opus-4-8":{"draws":7,"losses":10,"wins":27},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":1,"losses":42,"wins":9},"claude-sonnet-5":{"draws":6,"losses":8,"wins":34},"claude-sonnet-5-5":{"draws":5,"losses":19,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":62},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":11,"wins":29},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":31},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":11,"losses":21,"wins":60},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":22},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":2,"wins":31},"gpt-5.4":{"draws":11,"losses":13,"wins":22},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":6,"losses":12,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":28},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":31},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":6,"losses":6,"wins":36},"gpt-6-sol":{"draws":8,"losses":27,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":27},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":31},"meta/muse-spark-1.2":{"draws":6,"losses":11,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":24},"meta/muse-wonder":{"draws":8,"losses":21,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":28},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":34},"o3":{"draws":3,"losses":9,"wins":54},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":33},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":12,"wins":30},"qwen/qwen3.8-max-0902":{"draws":11,"losses":15,"wins":22},"stealth/ox-alpha":{"draws":23,"losses":31,"wins":104},"stealth/space-bunny-alpha":{"draws":7,"losses":2,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":4,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":6,"losses":11,"wins":29},"thinkingmachines/inkling":{"draws":5,"losses":6,"wins":53},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":42},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":24,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":10,"losses":15,"wins":71},"z-ai/glm-5.3":{"draws":10,"losses":16,"wins":20},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":29}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":35},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":5,"losses":35,"wins":14},"claude-haiku-5-5":{"draws":6,"losses":6,"wins":34},"claude-opus-4-5":{"draws":9,"losses":9,"wins":60},"claude-opus-4-8":{"draws":9,"losses":8,"wins":27},"claude-opus-5":{"draws":11,"losses":34,"wins":37},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":6,"losses":5,"wins":37},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":62},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":5,"wins":31},"fireworks/ember-1":{"draws":12,"losses":5,"wins":31},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":47},"google/gemini-3.5-flash-lite":{"draws":8,"losses":5,"wins":71},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":73},"google/gemini-3.8-flash":{"draws":9,"losses":12,"wins":27},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":2,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":43},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":7,"losses":5,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":13,"wins":30},"gpt-5.6-terra":{"draws":10,"losses":5,"wins":31},"gpt-6-astra":{"draws":6,"losses":33,"wins":9},"gpt-6-luna":{"draws":7,"losses":5,"wins":36},"gpt-6-sol":{"draws":4,"losses":23,"wins":21},"gpt-6.1-sol":{"draws":9,"losses":26,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":35},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":36},"meta/muse-wonder":{"draws":6,"losses":7,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":34},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"o3":{"draws":3,"losses":7,"wins":56},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":42},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":26},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":32},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":25},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":7,"wins":32},"stealth/ox-alpha":{"draws":21,"losses":21,"wins":116},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":32},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":40},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":33},"x-ai/grok-4.6":{"draws":14,"losses":7,"wins":27},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":28},"z-ai/glm-5.3-flash":{"draws":11,"losses":10,"wins":27},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":33}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":23},"claude-fable-5":{"draws":8,"losses":25,"wins":15},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":22,"losses":22,"wins":34},"claude-opus-4-8":{"draws":7,"losses":14,"wins":23},"claude-opus-5":{"draws":13,"losses":57,"wins":12},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":14,"losses":18,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":14,"wins":19},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":26},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash-lite":{"draws":17,"losses":14,"wins":53},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":48},"google/gemini-3.8-flash":{"draws":14,"losses":15,"wins":19},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":6,"wins":25},"gpt-5.4":{"draws":15,"losses":18,"wins":13},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":10,"wins":31},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":24,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":17},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":14,"losses":15,"wins":19},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":8,"losses":35,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":6,"wins":33},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":21,"wins":20},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":21},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":23},"qwen/qwen3.7-max":{"draws":8,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":20},"qwen/qwen3.8-27b":{"draws":8,"losses":8,"wins":18},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":11,"wins":22},"qwen/qwen3.8-max-0902":{"draws":15,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":50,"losses":53,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":2,"wins":23},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":39},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":31},"unbiased/pareto-26.10-preview":{"draws":3,"losses":10,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":16,"losses":17,"wins":15},"x-ai/grok-4.7":{"draws":9,"losses":20,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":18,"wins":49},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":18}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":19,"wins":20},"claude-fable-5":{"draws":25,"losses":30,"wins":7},"claude-fable-5-1":{"draws":3,"losses":54,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":26,"losses":52,"wins":12},"claude-opus-4-8":{"draws":13,"losses":26,"wins":3},"claude-opus-5":{"draws":12,"losses":54,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":37,"losses":26,"wins":15},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":39,"losses":30,"wins":29},"deepseek/deepseek-v4-pro":{"draws":21,"losses":39,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":32,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":22,"wins":6},"fireworks/ember-1":{"draws":14,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":18,"losses":16,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":11,"wins":14},"google/gemini-3.5-flash":{"draws":28,"losses":38,"wins":16},"google/gemini-3.5-flash-lite":{"draws":59,"losses":50,"wins":33},"google/gemini-3.6-flash":{"draws":45,"losses":61,"wins":18},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":17,"wins":9},"gpt-5.4":{"draws":28,"losses":30,"wins":8},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":20,"wins":13},"gpt-5.5":{"draws":16,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":36,"losses":34,"wins":8},"gpt-5.6-sol":{"draws":17,"losses":46,"wins":3},"gpt-5.6-terra":{"draws":26,"losses":38,"wins":10},"gpt-6-astra":{"draws":4,"losses":48,"wins":0},"gpt-6-luna":{"draws":15,"losses":22,"wins":5},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":14,"wins":22},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":23,"wins":21},"meta/muse-glimmer-30b":{"draws":36,"losses":26,"wins":10},"meta/muse-spark-1.2":{"draws":19,"losses":30,"wins":13},"meta/muse-spark-1.3":{"draws":19,"losses":38,"wins":5},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":12,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":29,"wins":13},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":11,"wins":8},"o3":{"draws":18,"losses":53,"wins":15},"openai/gpt-oss-120b":{"draws":36,"losses":14,"wins":22},"poolside/laguna-s-2.1":{"draws":26,"losses":23,"wins":17},"qwen/qwen3.7-max":{"draws":14,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":43,"wins":4},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":21,"losses":19,"wins":6},"qwen/qwen3.8-max":{"draws":29,"losses":34,"wins":9},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":67,"losses":125,"wins":50},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":31,"losses":30,"wins":7},"thinkingmachines/inkling":{"draws":26,"losses":26,"wins":20},"thinkingmachines/inkling-small":{"draws":38,"losses":34,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":1},"x-ai/grok-4.5":{"draws":18,"losses":38,"wins":8},"x-ai/grok-4.6":{"draws":27,"losses":37,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":52,"losses":48,"wins":22},"z-ai/glm-5.3":{"draws":15,"losses":39,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":12},"z-ai/glm-5.3-flashx":{"draws":14,"losses":24,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":17},"claude-fable-5":{"draws":6,"losses":24,"wins":12},"claude-fable-5-1":{"draws":0,"losses":41,"wins":7},"claude-haiku-5-5":{"draws":10,"losses":16,"wins":14},"claude-opus-4-5":{"draws":19,"losses":23,"wins":26},"claude-opus-4-8":{"draws":8,"losses":17,"wins":13},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":2,"losses":41,"wins":3},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":15},"cohere/north-mini-code":{"draws":7,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":27},"deepseek/deepseek-v4-pro":{"draws":10,"losses":11,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":21,"wins":13},"fireworks/ember-1":{"draws":13,"losses":14,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":19},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":16,"losses":32,"wins":32},"google/gemini-3.8-flash":{"draws":8,"losses":18,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":15,"wins":18},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":16},"gpt-5.5":{"draws":9,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":17},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":12,"losses":9,"wins":21},"gpt-6-sol":{"draws":4,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":7,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":6,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":15},"meta/muse-wonder":{"draws":6,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":16,"wins":12},"o3":{"draws":9,"losses":21,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":12},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":17,"wins":16},"qwen/qwen3.8-max-0902":{"draws":7,"losses":24,"wins":11},"stealth/ox-alpha":{"draws":30,"losses":50,"wins":62},"stealth/space-bunny-alpha":{"draws":8,"losses":6,"wins":20},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":12},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":19,"wins":17},"x-ai/grok-4.6":{"draws":7,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":22,"losses":12,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":5},"z-ai/glm-5.2":{"draws":24,"losses":24,"wins":36},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":15},"z-ai/glm-5.3-flash":{"draws":11,"losses":17,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":15}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":14,"wins":15},"claude-fable-5":{"draws":14,"losses":39,"wins":1},"claude-fable-5-1":{"draws":4,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":16,"losses":31,"wins":7},"claude-opus-4-5":{"draws":69,"losses":72,"wins":17},"claude-opus-4-8":{"draws":29,"losses":55,"wins":12},"claude-opus-5":{"draws":22,"losses":114,"wins":2},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":28,"losses":24,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":9},"cohere/north-mini-code":{"draws":14,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":61,"losses":26,"wins":27},"deepseek/deepseek-v4-pro":{"draws":21,"losses":21,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":23,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":21,"wins":10},"fireworks/ember-1":{"draws":26,"losses":24,"wins":4},"gemini-3.1-pro-preview":{"draws":26,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":31,"losses":14,"wins":34},"google/gemini-3.5-flash":{"draws":31,"losses":30,"wins":17},"google/gemini-3.5-flash-lite":{"draws":53,"losses":36,"wins":35},"google/gemini-3.6-flash":{"draws":48,"losses":61,"wins":11},"google/gemini-3.8-flash":{"draws":23,"losses":30,"wins":3},"google/gemma-4-31b-it":{"draws":21,"losses":7,"wins":6},"gpt-4.1":{"draws":18,"losses":8,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":40,"losses":34,"wins":8},"gpt-5.4":{"draws":20,"losses":29,"wins":1},"gpt-5.4-mini":{"draws":38,"losses":16,"wins":8},"gpt-5.4-nano":{"draws":37,"losses":35,"wins":26},"gpt-5.5":{"draws":40,"losses":41,"wins":1},"gpt-5.6-luna":{"draws":27,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":27,"losses":24,"wins":5},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":19,"losses":28,"wins":7},"gpt-6-sol":{"draws":6,"losses":46,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":49,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":31,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":14,"wins":30},"meta/muse-glimmer-30b":{"draws":28,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":15,"losses":32,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":38,"wins":3},"meta/muse-wonder":{"draws":20,"losses":33,"wins":1},"minimax/minimax-m3":{"draws":27,"losses":13,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":17,"wins":5},"mistralai/mistral-medium-3-5":{"draws":19,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":15,"wins":1},"moonshotai/kimi-k3":{"draws":22,"losses":21,"wins":9},"nex-agi/nex-n2-pro":{"draws":25,"losses":7,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":24,"wins":8},"o3":{"draws":39,"losses":66,"wins":19},"openai/gpt-oss-120b":{"draws":27,"losses":9,"wins":12},"poolside/laguna-s-2.1":{"draws":37,"losses":20,"wins":13},"qwen/qwen3.7-max":{"draws":41,"losses":10,"wins":7},"qwen/qwen3.7-plus":{"draws":29,"losses":15,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":20,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":27,"losses":25,"wins":4},"qwen/qwen3.8-max-0902":{"draws":28,"losses":22,"wins":4},"stealth/ox-alpha":{"draws":58,"losses":84,"wins":12},"stealth/space-bunny-alpha":{"draws":20,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":24,"losses":18,"wins":14},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":40,"losses":20,"wins":10},"tencent/hy4-preview":{"draws":20,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":45,"losses":31,"wins":46},"thinkingmachines/inkling-small":{"draws":31,"losses":13,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":18,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":24,"losses":46,"wins":2},"x-ai/grok-4.6":{"draws":26,"losses":25,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":22,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":95,"losses":30,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":15,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":20,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":82,"losses":54,"wins":18},"z-ai/glm-5.3":{"draws":14,"losses":38,"wins":4},"z-ai/glm-5.3-flash":{"draws":24,"losses":21,"wins":9},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":63,"wins":102},"claude-fable-5":{"draws":11,"losses":150,"wins":33},"claude-fable-5-1":{"draws":0,"losses":190,"wins":12},"claude-haiku-5-5":{"draws":11,"losses":57,"wins":44},"claude-opus-4-5":{"draws":42,"losses":258,"wins":118},"claude-opus-4-8":{"draws":7,"losses":97,"wins":44},"claude-opus-5":{"draws":6,"losses":222,"wins":14},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":23,"losses":138,"wins":163},"claude-sonnet-5-5":{"draws":4,"losses":83,"wins":27},"cohere/north-mini-code":{"draws":8,"losses":11,"wins":39},"deepseek/deepseek-v4-flash":{"draws":31,"losses":87,"wins":154},"deepseek/deepseek-v4-pro":{"draws":19,"losses":100,"wins":75},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":101,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":53,"wins":39},"fireworks/ember-1":{"draws":10,"losses":68,"wins":36},"gemini-3.1-pro-preview":{"draws":13,"losses":44,"wins":57},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":99},"google/gemini-3.5-flash":{"draws":23,"losses":134,"wins":77},"google/gemini-3.5-flash-lite":{"draws":88,"losses":197,"wins":427},"google/gemini-3.6-flash":{"draws":75,"losses":366,"wins":241},"google/gemini-3.8-flash":{"draws":19,"losses":129,"wins":56},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":46},"gpt-4.1":{"draws":4,"losses":21,"wins":19},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":13,"losses":77,"wins":52},"gpt-5.4":{"draws":24,"losses":218,"wins":66},"gpt-5.4-mini":{"draws":12,"losses":17,"wins":49},"gpt-5.4-nano":{"draws":7,"losses":70,"wins":77},"gpt-5.5":{"draws":18,"losses":84,"wins":30},"gpt-5.6-luna":{"draws":42,"losses":124,"wins":156},"gpt-5.6-sol":{"draws":13,"losses":234,"wins":61},"gpt-5.6-terra":{"draws":24,"losses":88,"wins":86},"gpt-6-astra":{"draws":5,"losses":181,"wins":2},"gpt-6-luna":{"draws":15,"losses":62,"wins":37},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":107,"wins":7},"inception/mercury-2.5-preview":{"draws":21,"losses":17,"wins":100},"inclusionai/ling-3.0-flash":{"draws":14,"losses":29,"wins":109},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":25,"losses":78,"wins":185},"meta/muse-glimmer-30b":{"draws":32,"losses":29,"wins":113},"meta/muse-spark-1.2":{"draws":15,"losses":87,"wins":130},"meta/muse-spark-1.3":{"draws":8,"losses":102,"wins":62},"meta/muse-wonder":{"draws":4,"losses":86,"wins":24},"minimax/minimax-m3":{"draws":5,"losses":20,"wins":49},"mistralai/mistral-large-4-0":{"draws":10,"losses":34,"wins":24},"mistralai/mistral-medium-3-5":{"draws":16,"losses":14,"wins":86},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":13,"wins":19},"moonshotai/kimi-k3":{"draws":32,"losses":113,"wins":141},"nex-agi/nex-n2-pro":{"draws":7,"losses":13,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":31,"wins":93},"o3":{"draws":29,"losses":204,"wins":211},"openai/gpt-oss-120b":{"draws":25,"losses":33,"wins":120},"poolside/laguna-s-2.1":{"draws":43,"losses":69,"wins":112},"qwen/qwen3.7-max":{"draws":12,"losses":29,"wins":35},"qwen/qwen3.7-plus":{"draws":4,"losses":17,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":112,"wins":73},"qwen/qwen3.8-27b":{"draws":7,"losses":62,"wins":47},"qwen/qwen3.8-flash":{"draws":24,"losses":55,"wins":55},"qwen/qwen3.8-max":{"draws":30,"losses":112,"wins":74},"qwen/qwen3.8-max-0902":{"draws":15,"losses":54,"wins":45},"stealth/ox-alpha":{"draws":58,"losses":286,"wins":268},"stealth/space-bunny-alpha":{"draws":7,"losses":36,"wins":49},"stepfun/step-3.7-flash":{"draws":17,"losses":42,"wins":79},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":38,"wins":42},"tencent/hy4-preview":{"draws":25,"losses":114,"wins":71},"thinkingmachines/inkling":{"draws":30,"losses":65,"wins":195},"thinkingmachines/inkling-small":{"draws":41,"losses":55,"wins":117},"unbiased/pareto-26.10-preview":{"draws":0,"losses":35,"wins":3},"upstage/solar-mini4":{"draws":4,"losses":9,"wins":25},"x-ai/grok-4.5":{"draws":14,"losses":184,"wins":98},"x-ai/grok-4.6":{"draws":29,"losses":110,"wins":59},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":23},"xiaomi/mimo-v2.5":{"draws":23,"losses":32,"wins":135},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":39,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":44,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":51,"wins":21},"z-ai/glm-5.2":{"draws":40,"losses":126,"wins":156},"z-ai/glm-5.3":{"draws":11,"losses":114,"wins":43},"z-ai/glm-5.3-flash":{"draws":20,"losses":90,"wins":88},"z-ai/glm-5.3-flashx":{"draws":7,"losses":68,"wins":39}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":24,"wins":19},"claude-fable-5":{"draws":19,"losses":32,"wins":13},"claude-fable-5-1":{"draws":4,"losses":60,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":26,"wins":4},"claude-opus-4-5":{"draws":21,"losses":39,"wins":24},"claude-opus-4-8":{"draws":13,"losses":17,"wins":8},"claude-opus-5":{"draws":13,"losses":59,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":22,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":41,"losses":23,"wins":28},"deepseek/deepseek-v4-pro":{"draws":30,"losses":21,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":25,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":11},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":12},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":31,"losses":29,"wins":22},"google/gemini-3.5-flash-lite":{"draws":51,"losses":38,"wins":39},"google/gemini-3.6-flash":{"draws":45,"losses":65,"wins":20},"google/gemini-3.8-flash":{"draws":13,"losses":39,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":15,"wins":9},"gpt-5.4":{"draws":27,"losses":25,"wins":14},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":15},"gpt-5.5":{"draws":15,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":40,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":15,"losses":43,"wins":10},"gpt-5.6-terra":{"draws":31,"losses":28,"wins":15},"gpt-6-astra":{"draws":6,"losses":50,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":9},"gpt-6-sol":{"draws":7,"losses":34,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":25,"wins":20},"meta/muse-glimmer-30b":{"draws":28,"losses":15,"wins":17},"meta/muse-spark-1.2":{"draws":19,"losses":27,"wins":14},"meta/muse-spark-1.3":{"draws":13,"losses":40,"wins":9},"meta/muse-wonder":{"draws":9,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":13},"o3":{"draws":19,"losses":44,"wins":21},"openai/gpt-oss-120b":{"draws":21,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":34,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":31,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-max":{"draws":21,"losses":44,"wins":7},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":60,"losses":107,"wins":57},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":13,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":27,"wins":14},"thinkingmachines/inkling":{"draws":20,"losses":21,"wins":23},"thinkingmachines/inkling-small":{"draws":38,"losses":19,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":18,"losses":37,"wins":7},"x-ai/grok-4.6":{"draws":18,"losses":33,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":12,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":48,"losses":46,"wins":26},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":23,"losses":34,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":26,"wins":3}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":2,"wins":43},"claude-fable-5":{"draws":22,"losses":24,"wins":42},"claude-fable-5-1":{"draws":11,"losses":86,"wins":11},"claude-haiku-5-5":{"draws":10,"losses":11,"wins":25},"claude-opus-4-5":{"draws":29,"losses":11,"wins":64},"claude-opus-4-8":{"draws":8,"losses":5,"wins":31},"claude-opus-5":{"draws":18,"losses":66,"wins":20},"claude-opus-5-5":{"draws":4,"losses":37,"wins":11},"claude-sonnet-5":{"draws":25,"losses":10,"wins":45},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":20,"losses":9,"wins":67},"deepseek/deepseek-v4-pro":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":9,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":24},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":20,"losses":17,"wins":55},"google/gemini-3.5-flash-lite":{"draws":30,"losses":8,"wins":90},"google/gemini-3.6-flash":{"draws":38,"losses":33,"wins":73},"google/gemini-3.8-flash":{"draws":21,"losses":28,"wins":41},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":9,"wins":28},"gpt-5.4":{"draws":12,"losses":22,"wins":50},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":2,"wins":43},"gpt-5.5":{"draws":13,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":42},"gpt-5.6-sol":{"draws":17,"losses":34,"wins":43},"gpt-5.6-terra":{"draws":26,"losses":12,"wins":46},"gpt-6-astra":{"draws":2,"losses":84,"wins":10},"gpt-6-luna":{"draws":12,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":33,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":26},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":14,"losses":4,"wins":42},"meta/muse-spark-1.2":{"draws":20,"losses":15,"wins":33},"meta/muse-spark-1.3":{"draws":14,"losses":16,"wins":46},"meta/muse-wonder":{"draws":8,"losses":16,"wins":24},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":12,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":24,"losses":15,"wins":33},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":30},"o3":{"draws":4,"losses":20,"wins":68},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":41},"poolside/laguna-s-2.1":{"draws":16,"losses":2,"wins":40},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":10,"wins":34},"qwen/qwen3.8-27b":{"draws":15,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":30},"qwen/qwen3.8-max":{"draws":24,"losses":16,"wins":42},"qwen/qwen3.8-max-0902":{"draws":14,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":67,"losses":72,"wins":145},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":20,"losses":24,"wins":34},"thinkingmachines/inkling":{"draws":23,"losses":3,"wins":46},"thinkingmachines/inkling-small":{"draws":23,"losses":8,"wins":41},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":16,"wins":36},"x-ai/grok-4.6":{"draws":20,"losses":25,"wins":47},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":15},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":3,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":37,"losses":20,"wins":65},"z-ai/glm-5.3":{"draws":20,"losses":28,"wins":26},"z-ai/glm-5.3-flash":{"draws":16,"losses":22,"wins":48},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":12,"wins":36},"claude-fable-5":{"draws":6,"losses":39,"wins":21},"claude-fable-5-1":{"draws":3,"losses":69,"wins":2},"claude-haiku-5-5":{"draws":4,"losses":14,"wins":18},"claude-opus-4-5":{"draws":11,"losses":22,"wins":51},"claude-opus-4-8":{"draws":5,"losses":13,"wins":18},"claude-opus-5":{"draws":6,"losses":52,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":20,"wins":34},"claude-sonnet-5-5":{"draws":3,"losses":18,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":5,"losses":23,"wins":52},"deepseek/deepseek-v4-pro":{"draws":3,"losses":21,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":19,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":20,"wins":13},"fireworks/ember-1":{"draws":3,"losses":11,"wins":22},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":15,"wins":43},"google/gemini-3.5-flash-lite":{"draws":10,"losses":15,"wins":81},"google/gemini-3.6-flash":{"draws":13,"losses":42,"wins":55},"google/gemini-3.8-flash":{"draws":8,"losses":26,"wins":30},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":16},"gpt-4.1":{"draws":2,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":12,"wins":24},"gpt-5.4":{"draws":10,"losses":34,"wins":20},"gpt-5.4-mini":{"draws":1,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":4,"losses":13,"wins":25},"gpt-5.5":{"draws":3,"losses":22,"wins":15},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":31},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":24},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":28},"gpt-6-astra":{"draws":0,"losses":68,"wins":0},"gpt-6-luna":{"draws":4,"losses":13,"wins":19},"gpt-6-sol":{"draws":5,"losses":23,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":31,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":3,"wins":34},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":44},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":4,"losses":17,"wins":33},"meta/muse-spark-1.3":{"draws":6,"losses":17,"wins":31},"meta/muse-wonder":{"draws":3,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":7,"losses":28,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":24},"o3":{"draws":6,"losses":29,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":8,"wins":40},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":33},"qwen/qwen3.7-max":{"draws":1,"losses":10,"wins":17},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":25,"wins":22},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":22},"qwen/qwen3.8-max":{"draws":14,"losses":24,"wins":24},"qwen/qwen3.8-max-0902":{"draws":6,"losses":13,"wins":17},"stealth/ox-alpha":{"draws":31,"losses":68,"wins":93},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":1,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":20},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":28},"thinkingmachines/inkling":{"draws":2,"losses":10,"wins":46},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":56},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":0,"losses":36,"wins":20},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":29},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":9},"z-ai/glm-5.2":{"draws":18,"losses":28,"wins":52},"z-ai/glm-5.3":{"draws":12,"losses":33,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":20,"wins":36},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":17}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":24,"wins":33},"claude-fable-5":{"draws":16,"losses":50,"wins":18},"claude-fable-5-1":{"draws":5,"losses":95,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":35,"losses":25,"wins":54},"claude-opus-4-8":{"draws":5,"losses":23,"wins":18},"claude-opus-5":{"draws":7,"losses":67,"wins":12},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":18,"losses":27,"wins":41},"claude-sonnet-5-5":{"draws":7,"losses":23,"wins":18},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-flash":{"draws":27,"losses":24,"wins":57},"deepseek/deepseek-v4-pro":{"draws":21,"losses":21,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":23,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":27,"losses":37,"wins":30},"google/gemini-3.5-flash-lite":{"draws":40,"losses":23,"wins":85},"google/gemini-3.6-flash":{"draws":30,"losses":62,"wins":64},"google/gemini-3.8-flash":{"draws":27,"losses":41,"wins":20},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":8,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":14,"wins":15},"gpt-5.4":{"draws":23,"losses":28,"wins":31},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":12,"wins":30},"gpt-5.5":{"draws":13,"losses":17,"wins":18},"gpt-5.6-luna":{"draws":17,"losses":16,"wins":44},"gpt-5.6-sol":{"draws":19,"losses":55,"wins":16},"gpt-5.6-terra":{"draws":36,"losses":19,"wins":27},"gpt-6-astra":{"draws":10,"losses":80,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":21,"losses":0,"wins":35},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":50},"meta/muse-glimmer-30b":{"draws":21,"losses":16,"wins":29},"meta/muse-spark-1.2":{"draws":18,"losses":26,"wins":21},"meta/muse-spark-1.3":{"draws":18,"losses":35,"wins":23},"meta/muse-wonder":{"draws":9,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":15,"losses":3,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":26,"wins":29},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":7,"wins":21},"o3":{"draws":15,"losses":36,"wins":50},"openai/gpt-oss-120b":{"draws":19,"losses":4,"wins":45},"poolside/laguna-s-2.1":{"draws":23,"losses":12,"wins":31},"qwen/qwen3.7-max":{"draws":14,"losses":8,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":34,"wins":25},"qwen/qwen3.8-27b":{"draws":12,"losses":8,"wins":24},"qwen/qwen3.8-flash":{"draws":18,"losses":12,"wins":26},"qwen/qwen3.8-max":{"draws":20,"losses":27,"wins":36},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"stealth/ox-alpha":{"draws":75,"losses":119,"wins":104},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":2,"wins":12},"tencent/hy4-preview":{"draws":18,"losses":34,"wins":30},"thinkingmachines/inkling":{"draws":26,"losses":10,"wins":42},"thinkingmachines/inkling-small":{"draws":44,"losses":25,"wins":59},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":29},"x-ai/grok-4.6":{"draws":27,"losses":33,"wins":34},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":8,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":45,"losses":41,"wins":48},"z-ai/glm-5.3":{"draws":9,"losses":45,"wins":20},"z-ai/glm-5.3-flash":{"draws":28,"losses":22,"wins":42},"z-ai/glm-5.3-flashx":{"draws":17,"losses":15,"wins":16}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":33},"claude-fable-5":{"draws":10,"losses":16,"wins":22},"claude-fable-5-1":{"draws":3,"losses":37,"wins":14},"claude-haiku-5-5":{"draws":10,"losses":9,"wins":27},"claude-opus-4-5":{"draws":14,"losses":12,"wins":52},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":8,"losses":44,"wins":30},"claude-opus-5-5":{"draws":8,"losses":35,"wins":9},"claude-sonnet-5":{"draws":12,"losses":7,"wins":29},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":53},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":9,"wins":26},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":6,"wins":30},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":41},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":67},"google/gemini-3.6-flash":{"draws":19,"losses":15,"wins":58},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":22},"gpt-4.1":{"draws":5,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":10,"losses":4,"wins":28},"gpt-5.4":{"draws":12,"losses":13,"wins":21},"gpt-5.4-mini":{"draws":11,"losses":1,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":14,"losses":9,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":7,"wins":32},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":8,"wins":29},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":31},"meta/muse-wonder":{"draws":13,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":31},"o3":{"draws":8,"losses":14,"wins":44},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":8,"losses":2,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":7,"wins":28},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":27},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":9,"losses":10,"wins":29},"qwen/qwen3.8-max-0902":{"draws":9,"losses":2,"wins":21},"stealth/ox-alpha":{"draws":32,"losses":40,"wins":86},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":8,"wins":28},"thinkingmachines/inkling":{"draws":11,"losses":4,"wins":49},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10-preview":{"draws":2,"losses":9,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":26},"x-ai/grok-4.6":{"draws":15,"losses":14,"wins":19},"x-ai/grok-4.7":{"draws":6,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":22,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":7,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":19,"losses":12,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":19,"wins":18},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":34,"wins":156},"claude-fable-5":{"draws":36,"losses":154,"wins":88},"claude-fable-5-1":{"draws":40,"losses":268,"wins":36},"claude-haiku-5-5":{"draws":17,"losses":43,"wins":80},"claude-opus-4-5":{"draws":44,"losses":70,"wins":224},"claude-opus-4-8":{"draws":22,"losses":36,"wins":80},"claude-opus-5":{"draws":41,"losses":206,"wins":59},"claude-opus-5-5":{"draws":12,"losses":127,"wins":23},"claude-sonnet-5":{"draws":28,"losses":63,"wins":185},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":74},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":50},"deepseek/deepseek-v4-flash":{"draws":21,"losses":31,"wins":250},"deepseek/deepseek-v4-pro":{"draws":28,"losses":61,"wins":143},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":63,"wins":139},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":42,"wins":90},"fireworks/ember-1":{"draws":23,"losses":34,"wins":93},"gemini-3.1-pro-preview":{"draws":15,"losses":39,"wins":96},"google/gemini-3.1-flash-lite":{"draws":8,"losses":8,"wins":80},"google/gemini-3.5-flash":{"draws":31,"losses":76,"wins":187},"google/gemini-3.5-flash-lite":{"draws":36,"losses":48,"wins":306},"google/gemini-3.6-flash":{"draws":52,"losses":143,"wins":263},"google/gemini-3.8-flash":{"draws":30,"losses":111,"wins":147},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":9,"wins":33},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":14},"gpt-5":{"draws":12,"losses":29,"wins":95},"gpt-5.4":{"draws":47,"losses":90,"wins":127},"gpt-5.4-mini":{"draws":15,"losses":11,"wins":76},"gpt-5.4-nano":{"draws":6,"losses":39,"wins":103},"gpt-5.5":{"draws":18,"losses":43,"wins":85},"gpt-5.6-luna":{"draws":35,"losses":40,"wins":153},"gpt-5.6-sol":{"draws":31,"losses":140,"wins":125},"gpt-5.6-terra":{"draws":40,"losses":74,"wins":136},"gpt-6-astra":{"draws":43,"losses":225,"wins":32},"gpt-6-luna":{"draws":21,"losses":28,"wins":101},"gpt-6-sol":{"draws":18,"losses":92,"wins":40},"gpt-6.1-sol":{"draws":17,"losses":116,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":21,"losses":17,"wins":96},"inclusionai/ling-3.0-flash":{"draws":9,"losses":7,"wins":102},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":21,"losses":29,"wins":154},"meta/muse-glimmer-30b":{"draws":15,"losses":11,"wins":150},"meta/muse-spark-1.2":{"draws":29,"losses":42,"wins":149},"meta/muse-spark-1.3":{"draws":28,"losses":79,"wins":125},"meta/muse-wonder":{"draws":12,"losses":76,"wins":62},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":64},"mistralai/mistral-large-4-0":{"draws":15,"losses":24,"wins":55},"mistralai/mistral-medium-3-5":{"draws":16,"losses":13,"wins":85},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":22},"moonshotai/kimi-k3":{"draws":34,"losses":59,"wins":139},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":65},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":19,"wins":86},"o3":{"draws":12,"losses":70,"wins":208},"openai/gpt-oss-120b":{"draws":17,"losses":10,"wins":153},"poolside/laguna-s-2.1":{"draws":25,"losses":22,"wins":147},"qwen/qwen3.7-max":{"draws":6,"losses":13,"wins":69},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":61},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":82,"wins":153},"qwen/qwen3.8-27b":{"draws":13,"losses":33,"wins":92},"qwen/qwen3.8-flash":{"draws":22,"losses":46,"wins":108},"qwen/qwen3.8-max":{"draws":36,"losses":66,"wins":164},"qwen/qwen3.8-max-0902":{"draws":21,"losses":42,"wins":87},"stealth/ox-alpha":{"draws":130,"losses":252,"wins":578},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":91},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":95},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":14,"losses":14,"wins":54},"tencent/hy4-preview":{"draws":36,"losses":89,"wins":133},"thinkingmachines/inkling":{"draws":24,"losses":28,"wins":188},"thinkingmachines/inkling-small":{"draws":29,"losses":13,"wins":192},"unbiased/pareto-26.10-preview":{"draws":10,"losses":35,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":33},"x-ai/grok-4.5":{"draws":21,"losses":104,"wins":101},"x-ai/grok-4.6":{"draws":51,"losses":112,"wins":121},"x-ai/grok-4.7":{"draws":12,"losses":77,"wins":39},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":46},"xiaomi/mimo-v2.5":{"draws":22,"losses":17,"wins":185},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":16,"wins":68},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":65},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":46},"z-ai/glm-5.2":{"draws":45,"losses":71,"wins":268},"z-ai/glm-5.3":{"draws":28,"losses":95,"wins":107},"z-ai/glm-5.3-flash":{"draws":33,"losses":84,"wins":157},"z-ai/glm-5.3-flashx":{"draws":18,"losses":49,"wins":83}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":8,"wins":15},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":1,"losses":37,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":18,"losses":27,"wins":15},"claude-opus-4-8":{"draws":8,"losses":15,"wins":13},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":6,"losses":13,"wins":17},"claude-sonnet-5-5":{"draws":3,"losses":19,"wins":14},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":14,"wins":8},"fireworks/ember-1":{"draws":8,"losses":16,"wins":12},"gemini-3.1-pro-preview":{"draws":7,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":15},"google/gemini-3.5-flash-lite":{"draws":16,"losses":16,"wins":34},"google/gemini-3.6-flash":{"draws":14,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":8},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":6,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":13,"wins":13},"gpt-5.4":{"draws":6,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":11,"losses":15,"wins":8},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":8,"losses":13,"wins":13},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":1,"losses":27,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":15},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":14,"wins":12},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":6,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":14,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":9},"stealth/ox-alpha":{"draws":22,"losses":45,"wins":35},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":13,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":8,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":24,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":21,"wins":9},"claude-fable-5":{"draws":2,"losses":29,"wins":3},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":22,"wins":5},"claude-opus-4-5":{"draws":8,"losses":59,"wins":15},"claude-opus-4-8":{"draws":4,"losses":37,"wins":9},"claude-opus-5":{"draws":1,"losses":60,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":5,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":0,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":15,"losses":30,"wins":25},"deepseek/deepseek-v4-pro":{"draws":6,"losses":22,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":18,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":2},"fireworks/ember-1":{"draws":4,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":15,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":38},"google/gemini-3.5-flash":{"draws":9,"losses":26,"wins":11},"google/gemini-3.5-flash-lite":{"draws":16,"losses":37,"wins":19},"google/gemini-3.6-flash":{"draws":11,"losses":58,"wins":6},"google/gemini-3.8-flash":{"draws":6,"losses":27,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":12,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":38,"wins":2},"gpt-5.4":{"draws":6,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":6,"losses":32,"wins":22},"gpt-5.5":{"draws":7,"losses":38,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":14,"wins":11},"gpt-5.6-sol":{"draws":0,"losses":28,"wins":4},"gpt-5.6-terra":{"draws":8,"losses":17,"wins":5},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":3,"losses":20,"wins":7},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":8,"losses":9,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":22,"wins":17},"meta/muse-glimmer-30b":{"draws":6,"losses":19,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":2,"losses":34,"wins":0},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":17,"wins":4},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":1},"mistralai/mistral-medium-3-5":{"draws":4,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":3,"losses":22,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":13,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":22,"wins":22},"o3":{"draws":16,"losses":61,"wins":21},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":12},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":13},"qwen/qwen3.7-max":{"draws":8,"losses":20,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":20,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":1,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":6,"losses":27,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":17,"wins":6},"stealth/ox-alpha":{"draws":9,"losses":72,"wins":15},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":4,"losses":24,"wins":2},"thinkingmachines/inkling":{"draws":12,"losses":19,"wins":37},"thinkingmachines/inkling-small":{"draws":7,"losses":13,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":37,"wins":3},"x-ai/grok-4.6":{"draws":4,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":20,"losses":41,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":19,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":45,"wins":20},"z-ai/glm-5.3":{"draws":2,"losses":26,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":21,"wins":5}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":14},"claude-fable-5":{"draws":13,"losses":24,"wins":5},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":13},"claude-opus-4-5":{"draws":42,"losses":48,"wins":26},"claude-opus-4-8":{"draws":15,"losses":36,"wins":17},"claude-opus-5":{"draws":17,"losses":108,"wins":5},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":23,"losses":32,"wins":33},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":11},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":14},"google/gemini-3.1-flash-lite":{"draws":18,"losses":17,"wins":29},"google/gemini-3.5-flash":{"draws":16,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":24,"losses":23,"wins":37},"google/gemini-3.6-flash":{"draws":27,"losses":54,"wins":25},"google/gemini-3.8-flash":{"draws":16,"losses":24,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":16,"losses":14,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":20,"losses":27,"wins":31},"gpt-5.4":{"draws":13,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":15,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":32},"gpt-5.5":{"draws":37,"losses":30,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":12},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":8,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":9,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":22,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-1.3":{"draws":5,"losses":29,"wins":10},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":16,"wins":33},"o3":{"draws":18,"losses":36,"wins":42},"openai/gpt-oss-120b":{"draws":12,"losses":12,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":24},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":8},"qwen/qwen3.7-plus":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":12},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":38,"losses":58,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":15,"wins":22},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":13},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":35},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":45,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.5":{"draws":35,"losses":35,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":20,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":34,"losses":40,"wins":42},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":7},"z-ai/glm-5.3-flashx":{"draws":6,"losses":27,"wins":9}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":4,"wins":38},"claude-fable-5":{"draws":21,"losses":37,"wins":32},"claude-fable-5-1":{"draws":6,"losses":85,"wins":17},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":29,"losses":21,"wins":60},"claude-opus-4-8":{"draws":15,"losses":13,"wins":26},"claude-opus-5":{"draws":14,"losses":77,"wins":15},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":28,"losses":8,"wins":50},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":8,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":32,"losses":8,"wins":60},"deepseek/deepseek-v4-pro":{"draws":21,"losses":16,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":10,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"fireworks/ember-1":{"draws":14,"losses":7,"wins":27},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":25,"losses":10,"wins":65},"google/gemini-3.5-flash-lite":{"draws":49,"losses":11,"wins":74},"google/gemini-3.6-flash":{"draws":39,"losses":43,"wins":72},"google/gemini-3.8-flash":{"draws":21,"losses":26,"wins":41},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":17},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":19,"losses":7,"wins":18},"gpt-5.4":{"draws":24,"losses":30,"wins":30},"gpt-5.4-mini":{"draws":13,"losses":1,"wins":18},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":33},"gpt-5.5":{"draws":14,"losses":11,"wins":21},"gpt-5.6-luna":{"draws":28,"losses":10,"wins":38},"gpt-5.6-sol":{"draws":12,"losses":42,"wins":40},"gpt-5.6-terra":{"draws":27,"losses":12,"wins":41},"gpt-6-astra":{"draws":11,"losses":75,"wins":10},"gpt-6-luna":{"draws":13,"losses":8,"wins":27},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":26,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":20,"losses":0,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":9,"wins":36},"meta/muse-glimmer-30b":{"draws":29,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":7,"losses":22,"wins":41},"meta/muse-spark-1.3":{"draws":20,"losses":26,"wins":28},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":21},"mistralai/mistral-large-4-0":{"draws":11,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":14,"losses":1,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":18,"losses":14,"wins":40},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"o3":{"draws":20,"losses":23,"wins":51},"openai/gpt-oss-120b":{"draws":30,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":30,"losses":7,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":22},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":46},"qwen/qwen3.8-27b":{"draws":13,"losses":9,"wins":22},"qwen/qwen3.8-flash":{"draws":18,"losses":15,"wins":21},"qwen/qwen3.8-max":{"draws":21,"losses":20,"wins":43},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"stealth/ox-alpha":{"draws":75,"losses":51,"wins":164},"stealth/space-bunny-alpha":{"draws":10,"losses":4,"wins":24},"stepfun/step-3.7-flash":{"draws":10,"losses":4,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":11,"wins":27},"thinkingmachines/inkling":{"draws":24,"losses":9,"wins":41},"thinkingmachines/inkling-small":{"draws":27,"losses":4,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":22,"wins":43},"x-ai/grok-4.6":{"draws":34,"losses":30,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":30,"losses":0,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":2,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":37,"losses":11,"wins":78},"z-ai/glm-5.3":{"draws":14,"losses":39,"wins":23},"z-ai/glm-5.3-flash":{"draws":28,"losses":35,"wins":27},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":51,"wins":31},"claude-fable-5":{"draws":23,"losses":86,"wins":5},"claude-fable-5-1":{"draws":6,"losses":112,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":9},"claude-opus-4-5":{"draws":69,"losses":126,"wins":33},"claude-opus-4-8":{"draws":23,"losses":57,"wins":12},"claude-opus-5":{"draws":22,"losses":137,"wins":13},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":58,"losses":103,"wins":25},"claude-sonnet-5-5":{"draws":19,"losses":47,"wins":18},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":63,"losses":48,"wins":63},"deepseek/deepseek-v4-pro":{"draws":44,"losses":58,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":43,"losses":48,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":43,"wins":14},"fireworks/ember-1":{"draws":28,"losses":45,"wins":11},"gemini-3.1-pro-preview":{"draws":29,"losses":35,"wins":20},"google/gemini-3.1-flash-lite":{"draws":20,"losses":10,"wins":38},"google/gemini-3.5-flash":{"draws":43,"losses":67,"wins":38},"google/gemini-3.5-flash-lite":{"draws":134,"losses":143,"wins":127},"google/gemini-3.6-flash":{"draws":107,"losses":204,"wins":61},"google/gemini-3.8-flash":{"draws":42,"losses":61,"wins":11},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":19},"gpt-4.1":{"draws":8,"losses":10,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":24,"losses":43,"wins":29},"gpt-5.4":{"draws":42,"losses":89,"wins":31},"gpt-5.4-mini":{"draws":23,"losses":16,"wins":19},"gpt-5.4-nano":{"draws":29,"losses":28,"wins":35},"gpt-5.5":{"draws":32,"losses":50,"wins":16},"gpt-5.6-luna":{"draws":73,"losses":73,"wins":40},"gpt-5.6-sol":{"draws":31,"losses":120,"wins":17},"gpt-5.6-terra":{"draws":39,"losses":60,"wins":23},"gpt-6-astra":{"draws":7,"losses":93,"wins":2},"gpt-6-luna":{"draws":23,"losses":41,"wins":20},"gpt-6-sol":{"draws":8,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":74,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":47,"losses":18,"wins":29},"inclusionai/ling-3.0-flash":{"draws":49,"losses":19,"wins":32},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":44,"losses":50,"wins":78},"meta/muse-glimmer-30b":{"draws":44,"losses":40,"wins":38},"meta/muse-spark-1.2":{"draws":47,"losses":80,"wins":15},"meta/muse-spark-1.3":{"draws":23,"losses":76,"wins":11},"meta/muse-wonder":{"draws":24,"losses":52,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":19,"losses":25,"wins":10},"mistralai/mistral-medium-3-5":{"draws":28,"losses":13,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":61,"losses":85,"wins":28},"nex-agi/nex-n2-pro":{"draws":12,"losses":15,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":30,"wins":29},"o3":{"draws":43,"losses":139,"wins":64},"openai/gpt-oss-120b":{"draws":39,"losses":29,"wins":50},"poolside/laguna-s-2.1":{"draws":63,"losses":61,"wins":44},"qwen/qwen3.7-max":{"draws":16,"losses":29,"wins":11},"qwen/qwen3.7-plus":{"draws":15,"losses":17,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":64,"wins":13},"qwen/qwen3.8-27b":{"draws":19,"losses":34,"wins":15},"qwen/qwen3.8-flash":{"draws":32,"losses":35,"wins":17},"qwen/qwen3.8-max":{"draws":38,"losses":53,"wins":27},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"stealth/ox-alpha":{"draws":109,"losses":230,"wins":77},"stealth/space-bunny-alpha":{"draws":21,"losses":23,"wins":22},"stepfun/step-3.7-flash":{"draws":23,"losses":22,"wins":29},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":17,"losses":23,"wins":14},"tencent/hy4-preview":{"draws":35,"losses":64,"wins":21},"thinkingmachines/inkling":{"draws":27,"losses":38,"wins":43},"thinkingmachines/inkling-small":{"draws":54,"losses":23,"wins":61},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":53,"losses":93,"wins":20},"x-ai/grok-4.6":{"draws":39,"losses":62,"wins":11},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":15,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":45,"losses":41,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":24,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":63,"losses":90,"wins":65},"z-ai/glm-5.3":{"draws":27,"losses":65,"wins":12},"z-ai/glm-5.3-flash":{"draws":35,"losses":68,"wins":21},"z-ai/glm-5.3-flashx":{"draws":22,"losses":50,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":32,"wins":21},"claude-fable-5":{"draws":14,"losses":51,"wins":9},"claude-fable-5-1":{"draws":5,"losses":85,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":41,"losses":41,"wins":28},"claude-opus-4-8":{"draws":15,"losses":25,"wins":6},"claude-opus-5":{"draws":11,"losses":72,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":22,"losses":38,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":39,"losses":45,"wins":32},"deepseek/deepseek-v4-pro":{"draws":35,"losses":34,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":40,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":22,"wins":8},"fireworks/ember-1":{"draws":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":15,"losses":16,"wins":17},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":23},"google/gemini-3.5-flash":{"draws":26,"losses":49,"wins":21},"google/gemini-3.5-flash-lite":{"draws":51,"losses":39,"wins":71},"google/gemini-3.6-flash":{"draws":53,"losses":73,"wins":25},"google/gemini-3.8-flash":{"draws":24,"losses":49,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":19,"wins":7},"gpt-5.4":{"draws":23,"losses":43,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":21,"losses":13,"wins":22},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":40,"losses":19,"wins":33},"gpt-5.6-sol":{"draws":12,"losses":61,"wins":10},"gpt-5.6-terra":{"draws":24,"losses":39,"wins":21},"gpt-6-astra":{"draws":8,"losses":66,"wins":0},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":10,"wins":25},"inclusionai/ling-3.0-flash":{"draws":19,"losses":8,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":16,"wins":30},"meta/muse-glimmer-30b":{"draws":38,"losses":24,"wins":20},"meta/muse-spark-1.2":{"draws":24,"losses":34,"wins":16},"meta/muse-spark-1.3":{"draws":24,"losses":43,"wins":9},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":9,"losses":16,"wins":5},"mistralai/mistral-medium-3-5":{"draws":23,"losses":4,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":27,"losses":32,"wins":14},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":20},"o3":{"draws":26,"losses":44,"wins":32},"openai/gpt-oss-120b":{"draws":36,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":29,"losses":26,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":34,"wins":16},"qwen/qwen3.8-27b":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-flash":{"draws":31,"losses":14,"wins":15},"qwen/qwen3.8-max":{"draws":44,"losses":38,"wins":45},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":79,"losses":161,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":9,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":33,"losses":45,"wins":10},"thinkingmachines/inkling":{"draws":28,"losses":20,"wins":34},"thinkingmachines/inkling-small":{"draws":34,"losses":15,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":15,"losses":43,"wins":18},"x-ai/grok-4.6":{"draws":32,"losses":41,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":17,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":18,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":23,"wins":4},"z-ai/glm-5.2":{"draws":56,"losses":48,"wins":36},"z-ai/glm-5.3":{"draws":14,"losses":48,"wins":8},"z-ai/glm-5.3-flash":{"draws":36,"losses":38,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":10},"claude-fable-5":{"draws":0,"losses":14,"wins":4},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":16,"wins":2},"claude-opus-4-5":{"draws":0,"losses":20,"wins":10},"claude-opus-4-8":{"draws":0,"losses":15,"wins":3},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":0,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":0,"losses":13,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":0,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":14,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":15,"wins":3},"fireworks/ember-1":{"draws":0,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":0,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":15},"google/gemini-3.5-flash":{"draws":0,"losses":15,"wins":9},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":22},"google/gemini-3.6-flash":{"draws":1,"losses":28,"wins":7},"google/gemini-3.8-flash":{"draws":0,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":9},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":13,"wins":3},"gpt-5.4":{"draws":0,"losses":16,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":11,"wins":11},"gpt-5.5":{"draws":0,"losses":11,"wins":5},"gpt-5.6-luna":{"draws":1,"losses":8,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":0,"losses":9,"wins":9},"gpt-6-sol":{"draws":0,"losses":17,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":9,"wins":14},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":8},"meta/muse-spark-1.2":{"draws":0,"losses":13,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":14,"wins":4},"meta/muse-wonder":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"mistralai/mistral-large-4-0":{"draws":0,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":10},"o3":{"draws":2,"losses":22,"wins":12},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":14,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":0,"losses":8,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":11,"wins":7},"qwen/qwen3.8-max-0902":{"draws":0,"losses":15,"wins":3},"stealth/ox-alpha":{"draws":0,"losses":40,"wins":12},"stealth/space-bunny-alpha":{"draws":0,"losses":9,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":10,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":15,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":5,"wins":19},"thinkingmachines/inkling-small":{"draws":0,"losses":3,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":13,"wins":5},"x-ai/grok-4.6":{"draws":0,"losses":14,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":0,"losses":5,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":7,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":12,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":18,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":15,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":2,"wins":52},"claude-fable-5":{"draws":9,"losses":34,"wins":45},"claude-fable-5-1":{"draws":3,"losses":81,"wins":10},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":46,"losses":37,"wins":87},"claude-opus-4-8":{"draws":17,"losses":23,"wins":22},"claude-opus-5":{"draws":17,"losses":88,"wins":25},"claude-opus-5-5":{"draws":9,"losses":38,"wins":5},"claude-sonnet-5":{"draws":27,"losses":32,"wins":81},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":15,"losses":17,"wins":70},"deepseek/deepseek-v4-pro":{"draws":23,"losses":17,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":32},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":52},"google/gemini-3.5-flash-lite":{"draws":42,"losses":66,"wins":154},"google/gemini-3.6-flash":{"draws":37,"losses":105,"wins":142},"google/gemini-3.8-flash":{"draws":10,"losses":27,"wins":47},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":13,"wins":34},"gpt-5.4":{"draws":28,"losses":49,"wins":58},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":30},"gpt-5.5":{"draws":14,"losses":20,"wins":24},"gpt-5.6-luna":{"draws":22,"losses":39,"wins":65},"gpt-5.6-sol":{"draws":17,"losses":62,"wins":57},"gpt-5.6-terra":{"draws":20,"losses":12,"wins":58},"gpt-6-astra":{"draws":1,"losses":71,"wins":12},"gpt-6-luna":{"draws":6,"losses":15,"wins":27},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":39},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":52},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":30,"losses":9,"wins":89},"meta/muse-glimmer-30b":{"draws":12,"losses":12,"wins":42},"meta/muse-spark-1.2":{"draws":17,"losses":20,"wins":63},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":40},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":22,"losses":29,"wins":77},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":39},"o3":{"draws":16,"losses":32,"wins":112},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":50},"poolside/laguna-s-2.1":{"draws":31,"losses":13,"wins":76},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":26,"wins":44},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":29},"qwen/qwen3.8-flash":{"draws":8,"losses":16,"wins":28},"qwen/qwen3.8-max":{"draws":15,"losses":24,"wins":47},"qwen/qwen3.8-max-0902":{"draws":8,"losses":16,"wins":24},"stealth/ox-alpha":{"draws":58,"losses":76,"wins":138},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":35},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":32},"tencent/hy4-preview":{"draws":15,"losses":28,"wins":41},"thinkingmachines/inkling":{"draws":34,"losses":17,"wins":63},"thinkingmachines/inkling-small":{"draws":9,"losses":14,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":33,"losses":18,"wins":39},"x-ai/grok-4.6":{"draws":15,"losses":31,"wins":44},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":26,"losses":22,"wins":80},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":25},"z-ai/glm-5.3-flash":{"draws":11,"losses":31,"wins":36},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":38},"claude-fable-5":{"draws":23,"losses":33,"wins":38},"claude-fable-5-1":{"draws":7,"losses":75,"wins":26},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":23,"losses":24,"wins":57},"claude-opus-4-8":{"draws":10,"losses":18,"wins":22},"claude-opus-5":{"draws":10,"losses":52,"wins":27},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":17,"losses":13,"wins":54},"claude-sonnet-5-5":{"draws":4,"losses":19,"wins":25},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":31,"losses":7,"wins":66},"deepseek/deepseek-v4-pro":{"draws":17,"losses":21,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":19,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":13,"wins":27},"fireworks/ember-1":{"draws":12,"losses":12,"wins":24},"gemini-3.1-pro-preview":{"draws":9,"losses":7,"wins":32},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":30,"losses":14,"wins":54},"google/gemini-3.5-flash-lite":{"draws":37,"losses":17,"wins":82},"google/gemini-3.6-flash":{"draws":30,"losses":56,"wins":66},"google/gemini-3.8-flash":{"draws":25,"losses":24,"wins":41},"google/gemma-4-31b-it":{"draws":9,"losses":0,"wins":19},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":15,"losses":5,"wins":26},"gpt-5.4":{"draws":27,"losses":26,"wins":37},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":17,"losses":8,"wins":27},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":52},"gpt-5.6-sol":{"draws":15,"losses":30,"wins":49},"gpt-5.6-terra":{"draws":18,"losses":8,"wins":66},"gpt-6-astra":{"draws":9,"losses":71,"wins":16},"gpt-6-luna":{"draws":10,"losses":11,"wins":27},"gpt-6-sol":{"draws":2,"losses":36,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":32},"inclusionai/ling-3.0-flash":{"draws":16,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":19,"losses":3,"wins":50},"meta/muse-glimmer-30b":{"draws":18,"losses":14,"wins":36},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":40},"meta/muse-spark-1.3":{"draws":15,"losses":26,"wins":29},"meta/muse-wonder":{"draws":11,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":20,"wins":37},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":20},"o3":{"draws":22,"losses":24,"wins":46},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":40},"poolside/laguna-s-2.1":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.7-plus":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":34,"wins":39},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":26},"qwen/qwen3.8-flash":{"draws":22,"losses":8,"wins":26},"qwen/qwen3.8-max":{"draws":12,"losses":32,"wins":44},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":86,"losses":81,"wins":123},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":8,"losses":2,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":16},"tencent/hy4-preview":{"draws":30,"losses":18,"wins":36},"thinkingmachines/inkling":{"draws":24,"losses":8,"wins":40},"thinkingmachines/inkling-small":{"draws":30,"losses":9,"wins":41},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":20,"losses":25,"wins":35},"x-ai/grok-4.6":{"draws":23,"losses":11,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":4,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":82},"z-ai/glm-5.3":{"draws":18,"losses":26,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":32,"wins":34},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":1,"losses":12,"wins":29},"claude-fable-5-1":{"draws":1,"losses":28,"wins":17},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":36},"claude-opus-4-5":{"draws":1,"losses":5,"wins":62},"claude-opus-4-8":{"draws":3,"losses":7,"wins":28},"claude-opus-5":{"draws":4,"losses":30,"wins":36},"claude-opus-5-5":{"draws":0,"losses":32,"wins":14},"claude-sonnet-5":{"draws":0,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"fireworks/ember-1":{"draws":3,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":4,"wins":36},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":48},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":66},"google/gemini-3.8-flash":{"draws":4,"losses":6,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":3,"wins":32},"gpt-5.4":{"draws":2,"losses":8,"wins":30},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":43},"gpt-5.5":{"draws":3,"losses":9,"wins":26},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":37},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":28},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":34},"gpt-6-astra":{"draws":4,"losses":30,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":36},"gpt-6-sol":{"draws":1,"losses":12,"wins":29},"gpt-6.1-sol":{"draws":1,"losses":24,"wins":17},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":45},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":34},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":35},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":34},"meta/muse-wonder":{"draws":5,"losses":10,"wins":27},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":35},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":36},"o3":{"draws":1,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":41},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":6,"losses":14,"wins":120},"stealth/space-bunny-alpha":{"draws":0,"losses":5,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":32},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":35},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":28},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":1,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":4,"losses":8,"wins":72},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":30},"z-ai/glm-5.3-flash":{"draws":2,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"wins":33}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":7,"wins":6},"claude-fable-5":{"draws":10,"losses":20,"wins":0},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":1},"claude-opus-4-5":{"draws":52,"losses":26,"wins":6},"claude-opus-4-8":{"draws":22,"losses":22,"wins":4},"claude-opus-5":{"draws":13,"losses":58,"wins":5},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":16,"losses":11,"wins":3},"claude-sonnet-5-5":{"draws":11,"losses":17,"wins":2},"cohere/north-mini-code":{"draws":10,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":35,"losses":12,"wins":11},"deepseek/deepseek-v4-pro":{"draws":19,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":9,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":12,"wins":1},"fireworks/ember-1":{"draws":17,"losses":8,"wins":5},"gemini-3.1-pro-preview":{"draws":15,"losses":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":29,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":22,"losses":14,"wins":6},"google/gemini-3.5-flash-lite":{"draws":36,"losses":14,"wins":10},"google/gemini-3.6-flash":{"draws":33,"losses":23,"wins":8},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":3},"gpt-4.1":{"draws":14,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":34,"losses":11,"wins":7},"gpt-5.4":{"draws":12,"losses":15,"wins":1},"gpt-5.4-mini":{"draws":27,"losses":4,"wins":11},"gpt-5.4-nano":{"draws":27,"losses":24,"wins":11},"gpt-5.5":{"draws":22,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":3},"gpt-5.6-sol":{"draws":10,"losses":20,"wins":4},"gpt-5.6-terra":{"draws":19,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":30,"wins":0},"gpt-6-luna":{"draws":18,"losses":11,"wins":1},"gpt-6-sol":{"draws":6,"losses":22,"wins":2},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":31,"losses":3,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":11,"wins":7},"meta/muse-glimmer-30b":{"draws":21,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":4},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":0},"meta/muse-wonder":{"draws":9,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":13,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":15,"losses":0,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":6,"wins":8},"o3":{"draws":20,"losses":19,"wins":7},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":3},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":2},"qwen/qwen3.7-max":{"draws":22,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":16,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":9,"wins":3},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":3},"qwen/qwen3.8-flash":{"draws":16,"losses":4,"wins":0},"qwen/qwen3.8-max":{"draws":18,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":18,"losses":8,"wins":4},"stealth/ox-alpha":{"draws":39,"losses":40,"wins":11},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":15,"losses":6,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":38,"losses":8,"wins":10},"thinkingmachines/inkling-small":{"draws":23,"losses":4,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":16,"losses":20,"wins":4},"x-ai/grok-4.6":{"draws":14,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":20,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":51,"losses":28,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":58,"losses":25,"wins":13},"z-ai/glm-5.3":{"draws":11,"losses":19,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":2},"z-ai/glm-5.3-flashx":{"draws":16,"losses":13,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":22,"wins":22},"claude-fable-5":{"draws":20,"losses":42,"wins":14},"claude-fable-5-1":{"draws":6,"losses":73,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":25,"losses":48,"wins":31},"claude-opus-4-8":{"draws":16,"losses":22,"wins":12},"claude-opus-5":{"draws":23,"losses":63,"wins":4},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":18,"losses":37,"wins":35},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":36,"losses":32,"wins":40},"deepseek/deepseek-v4-pro":{"draws":19,"losses":26,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":30,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":20,"wins":12},"fireworks/ember-1":{"draws":13,"losses":19,"wins":16},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":26,"losses":42,"wins":26},"google/gemini-3.5-flash-lite":{"draws":52,"losses":31,"wins":55},"google/gemini-3.6-flash":{"draws":35,"losses":68,"wins":37},"google/gemini-3.8-flash":{"draws":22,"losses":41,"wins":15},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":18,"losses":16,"wins":12},"gpt-5.4":{"draws":25,"losses":44,"wins":9},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":21,"wins":23},"gpt-5.5":{"draws":13,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":25,"losses":19,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":61,"wins":9},"gpt-5.6-terra":{"draws":44,"losses":37,"wins":7},"gpt-6-astra":{"draws":8,"losses":64,"wins":2},"gpt-6-luna":{"draws":18,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":14,"wins":26},"inclusionai/ling-3.0-flash":{"draws":21,"losses":8,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":24,"wins":23},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":30},"meta/muse-spark-1.2":{"draws":15,"losses":33,"wins":20},"meta/muse-spark-1.3":{"draws":11,"losses":43,"wins":14},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":18,"losses":10,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":27,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":7,"wins":15},"o3":{"draws":20,"losses":49,"wins":31},"openai/gpt-oss-120b":{"draws":26,"losses":12,"wins":38},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":31},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":27,"wins":25},"qwen/qwen3.8-27b":{"draws":12,"losses":13,"wins":19},"qwen/qwen3.8-flash":{"draws":19,"losses":20,"wins":11},"qwen/qwen3.8-max":{"draws":32,"losses":29,"wins":19},"qwen/qwen3.8-max-0902":{"draws":15,"losses":27,"wins":6},"stealth/ox-alpha":{"draws":84,"losses":125,"wins":59},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":9},"tencent/hy4-preview":{"draws":25,"losses":32,"wins":17},"thinkingmachines/inkling":{"draws":22,"losses":25,"wins":35},"thinkingmachines/inkling-small":{"draws":32,"losses":20,"wins":34},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":15,"losses":39,"wins":16},"x-ai/grok-4.6":{"draws":27,"losses":37,"wins":18},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":37,"losses":15,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":35,"wins":34},"z-ai/glm-5.3":{"draws":19,"losses":30,"wins":17},"z-ai/glm-5.3-flash":{"draws":27,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":34},"claude-fable-5":{"draws":4,"losses":7,"wins":31},"claude-fable-5-1":{"draws":2,"losses":35,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":32},"claude-opus-4-5":{"draws":5,"losses":4,"wins":59},"claude-opus-4-8":{"draws":5,"losses":5,"wins":28},"claude-opus-5":{"draws":6,"losses":25,"wins":39},"claude-opus-5-5":{"draws":2,"losses":32,"wins":12},"claude-sonnet-5":{"draws":5,"losses":2,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":57},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":37},"fireworks/ember-1":{"draws":3,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":6,"losses":5,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":43},"google/gemini-3.5-flash-lite":{"draws":4,"losses":1,"wins":69},"google/gemini-3.6-flash":{"draws":9,"losses":8,"wins":63},"google/gemini-3.8-flash":{"draws":7,"losses":5,"wins":30},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":21},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":3,"wins":33},"gpt-5.4":{"draws":5,"losses":2,"wins":33},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":26},"gpt-5.4-nano":{"draws":4,"losses":1,"wins":35},"gpt-5.5":{"draws":3,"losses":3,"wins":32},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":6,"wins":31},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":31},"gpt-6-astra":{"draws":8,"losses":27,"wins":7},"gpt-6-luna":{"draws":5,"losses":1,"wins":36},"gpt-6-sol":{"draws":7,"losses":17,"wins":18},"gpt-6.1-sol":{"draws":8,"losses":23,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":28},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":44},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":27},"meta/muse-spark-1.2":{"draws":5,"losses":3,"wins":32},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":29},"meta/muse-wonder":{"draws":5,"losses":8,"wins":29},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":17},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":6,"wins":29},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"o3":{"draws":1,"losses":1,"wins":54},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":33},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":3,"wins":38},"qwen/qwen3.8-27b":{"draws":3,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":36},"qwen/qwen3.8-max-0902":{"draws":8,"losses":5,"wins":29},"stealth/ox-alpha":{"draws":15,"losses":12,"wins":115},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":29},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":20},"tencent/hy4-preview":{"draws":3,"losses":3,"wins":34},"thinkingmachines/inkling":{"draws":6,"losses":3,"wins":45},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":6,"losses":4,"wins":32},"x-ai/grok-4.6":{"draws":5,"losses":6,"wins":31},"x-ai/grok-4.7":{"draws":5,"losses":13,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":5,"wins":17},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":70},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":5,"wins":31},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":35}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":16,"wins":39},"claude-fable-5":{"draws":13,"losses":33,"wins":36},"claude-fable-5-1":{"draws":10,"losses":74,"wins":14},"claude-haiku-5-5":{"draws":7,"losses":17,"wins":22},"claude-opus-4-5":{"draws":19,"losses":22,"wins":63},"claude-opus-4-8":{"draws":8,"losses":20,"wins":24},"claude-opus-5":{"draws":11,"losses":64,"wins":25},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":11,"losses":24,"wins":49},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":21,"losses":18,"wins":55},"deepseek/deepseek-v4-pro":{"draws":10,"losses":22,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"fireworks/ember-1":{"draws":7,"losses":17,"wins":24},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":22},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":20,"losses":30,"wins":42},"google/gemini-3.5-flash-lite":{"draws":34,"losses":18,"wins":86},"google/gemini-3.6-flash":{"draws":25,"losses":42,"wins":77},"google/gemini-3.8-flash":{"draws":13,"losses":35,"wins":36},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"gpt-5":{"draws":11,"losses":6,"wins":27},"gpt-5.4":{"draws":11,"losses":28,"wins":37},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":15,"wins":28},"gpt-5.5":{"draws":8,"losses":15,"wins":25},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":44},"gpt-5.6-sol":{"draws":12,"losses":42,"wins":36},"gpt-5.6-terra":{"draws":17,"losses":23,"wins":40},"gpt-6-astra":{"draws":7,"losses":75,"wins":2},"gpt-6-luna":{"draws":11,"losses":11,"wins":26},"gpt-6-sol":{"draws":5,"losses":34,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":11,"wins":26},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":38},"meta/muse-glimmer-30b":{"draws":15,"losses":3,"wins":46},"meta/muse-spark-1.2":{"draws":7,"losses":26,"wins":39},"meta/muse-spark-1.3":{"draws":12,"losses":22,"wins":40},"meta/muse-wonder":{"draws":7,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":9,"losses":9,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":16,"losses":20,"wins":34},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":9,"wins":20},"o3":{"draws":13,"losses":44,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":41},"poolside/laguna-s-2.1":{"draws":19,"losses":5,"wins":40},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":27,"wins":45},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":24},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":25},"qwen/qwen3.8-max":{"draws":23,"losses":30,"wins":33},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"stealth/ox-alpha":{"draws":55,"losses":87,"wins":138},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":17,"losses":17,"wins":46},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":50},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":45},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":34},"x-ai/grok-4.6":{"draws":13,"losses":37,"wins":36},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":15},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":16,"losses":16,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":32,"wins":69},"z-ai/glm-5.3":{"draws":16,"losses":34,"wins":22},"z-ai/glm-5.3-flash":{"draws":17,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":13,"losses":14,"wins":21}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":31},"claude-fable-5":{"draws":8,"losses":16,"wins":24},"claude-fable-5-1":{"draws":8,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":7,"losses":12,"wins":27},"claude-opus-4-5":{"draws":9,"losses":13,"wins":56},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":7,"losses":19,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":31},"fireworks/ember-1":{"draws":6,"losses":10,"wins":32},"gemini-3.1-pro-preview":{"draws":9,"losses":9,"wins":30},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":13,"losses":8,"wins":39},"google/gemini-3.5-flash-lite":{"draws":20,"losses":8,"wins":56},"google/gemini-3.6-flash":{"draws":21,"losses":20,"wins":51},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":30},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":5,"wins":26},"gpt-5.4":{"draws":7,"losses":10,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":34},"gpt-5.5":{"draws":10,"losses":12,"wins":22},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":19,"wins":24},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":28},"gpt-6-astra":{"draws":3,"losses":39,"wins":6},"gpt-6-luna":{"draws":7,"losses":10,"wins":31},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"gpt-6.1-sol":{"draws":10,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":27},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":4,"wins":39},"meta/muse-glimmer-30b":{"draws":11,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-wonder":{"draws":11,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":8,"wins":31},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"o3":{"draws":5,"losses":13,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":27},"stealth/ox-alpha":{"draws":18,"losses":34,"wins":106},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"thinkingmachines/inkling":{"draws":7,"losses":9,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":32},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":26},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":5,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":20,"losses":15,"wins":61},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":12,"losses":14,"wins":22},"z-ai/glm-5.3-flashx":{"draws":10,"losses":5,"wins":17}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":13,"wins":22},"claude-fable-5":{"draws":11,"losses":35,"wins":16},"claude-fable-5-1":{"draws":2,"losses":62,"wins":4},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":17},"claude-opus-4-5":{"draws":27,"losses":36,"wins":33},"claude-opus-4-8":{"draws":11,"losses":15,"wins":16},"claude-opus-5":{"draws":14,"losses":54,"wins":12},"claude-opus-5-5":{"draws":2,"losses":39,"wins":5},"claude-sonnet-5":{"draws":27,"losses":30,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":29,"losses":29,"wins":34},"deepseek/deepseek-v4-pro":{"draws":24,"losses":27,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":28,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"fireworks/ember-1":{"draws":10,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":9,"losses":7,"wins":16},"google/gemini-3.5-flash":{"draws":20,"losses":28,"wins":26},"google/gemini-3.5-flash-lite":{"draws":41,"losses":35,"wins":58},"google/gemini-3.6-flash":{"draws":32,"losses":60,"wins":38},"google/gemini-3.8-flash":{"draws":15,"losses":30,"wins":19},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":8,"losses":10,"wins":18},"gpt-5.4":{"draws":14,"losses":22,"wins":20},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":13,"wins":26},"gpt-5.5":{"draws":14,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":15,"wins":36},"gpt-5.6-sol":{"draws":13,"losses":43,"wins":12},"gpt-5.6-terra":{"draws":21,"losses":28,"wins":17},"gpt-6-astra":{"draws":5,"losses":41,"wins":10},"gpt-6-luna":{"draws":11,"losses":15,"wins":16},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":33,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":20,"wins":14},"inclusionai/ling-3.0-flash":{"draws":12,"losses":7,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":31},"meta/muse-glimmer-30b":{"draws":19,"losses":17,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":20,"wins":26},"meta/muse-spark-1.3":{"draws":14,"losses":28,"wins":16},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":12},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":14,"losses":13,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":14,"losses":29,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":17},"o3":{"draws":10,"losses":34,"wins":30},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":27},"poolside/laguna-s-2.1":{"draws":21,"losses":17,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":28,"wins":20},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":14},"qwen/qwen3.8-flash":{"draws":11,"losses":19,"wins":22},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":28},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":9},"stealth/ox-alpha":{"draws":53,"losses":110,"wins":63},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":38,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":31},"thinkingmachines/inkling-small":{"draws":23,"losses":16,"wins":37},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":17,"losses":32,"wins":9},"x-ai/grok-4.6":{"draws":22,"losses":30,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":39,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":19},"z-ai/glm-5.3-flash":{"draws":14,"losses":33,"wins":19},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":14,"wins":37},"claude-fable-5":{"draws":12,"losses":19,"wins":29},"claude-fable-5-1":{"draws":2,"losses":82,"wins":16},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":24,"losses":13,"wins":71},"claude-opus-4-8":{"draws":13,"losses":8,"wins":25},"claude-opus-5":{"draws":13,"losses":67,"wins":28},"claude-opus-5-5":{"draws":5,"losses":38,"wins":9},"claude-sonnet-5":{"draws":13,"losses":16,"wins":55},"claude-sonnet-5-5":{"draws":10,"losses":16,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":22,"losses":6,"wins":68},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":20,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":13,"wins":23},"fireworks/ember-1":{"draws":11,"losses":7,"wins":30},"gemini-3.1-pro-preview":{"draws":10,"losses":8,"wins":30},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":53},"google/gemini-3.5-flash-lite":{"draws":24,"losses":26,"wins":76},"google/gemini-3.6-flash":{"draws":21,"losses":54,"wins":67},"google/gemini-3.8-flash":{"draws":9,"losses":25,"wins":52},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":18},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":10,"wins":29},"gpt-5.4":{"draws":21,"losses":23,"wins":44},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":37},"gpt-5.5":{"draws":11,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":20,"losses":13,"wins":39},"gpt-5.6-sol":{"draws":6,"losses":42,"wins":42},"gpt-5.6-terra":{"draws":25,"losses":10,"wins":53},"gpt-6-astra":{"draws":6,"losses":69,"wins":19},"gpt-6-luna":{"draws":12,"losses":7,"wins":29},"gpt-6-sol":{"draws":8,"losses":24,"wins":16},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":27},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":45},"meta/muse-glimmer-30b":{"draws":10,"losses":10,"wins":36},"meta/muse-spark-1.2":{"draws":15,"losses":15,"wins":36},"meta/muse-spark-1.3":{"draws":16,"losses":21,"wins":33},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":51},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":30},"o3":{"draws":7,"losses":12,"wins":75},"openai/gpt-oss-120b":{"draws":19,"losses":11,"wins":32},"poolside/laguna-s-2.1":{"draws":10,"losses":16,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":19,"wins":37},"qwen/qwen3.8-27b":{"draws":10,"losses":7,"wins":27},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":28,"wins":43},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"stealth/ox-alpha":{"draws":61,"losses":68,"wins":145},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":18},"tencent/hy4-preview":{"draws":16,"losses":12,"wins":50},"thinkingmachines/inkling":{"draws":18,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":14,"losses":15,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":14,"losses":27,"wins":33},"x-ai/grok-4.6":{"draws":24,"losses":36,"wins":30},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":2,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":17},"z-ai/glm-5.2":{"draws":28,"losses":21,"wins":77},"z-ai/glm-5.3":{"draws":8,"losses":36,"wins":28},"z-ai/glm-5.3-flash":{"draws":16,"losses":22,"wins":46},"z-ai/glm-5.3-flashx":{"draws":10,"losses":15,"wins":23}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":56},"claude-fable-5":{"draws":7,"losses":17,"wins":66},"claude-fable-5-1":{"draws":5,"losses":47,"wins":24},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":42},"claude-opus-4-5":{"draws":6,"losses":5,"wins":97},"claude-opus-4-8":{"draws":4,"losses":5,"wins":35},"claude-opus-5":{"draws":10,"losses":40,"wins":38},"claude-opus-5-5":{"draws":6,"losses":35,"wins":11},"claude-sonnet-5":{"draws":6,"losses":4,"wins":76},"claude-sonnet-5-5":{"draws":3,"losses":10,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":9,"losses":1,"wins":88},"deepseek/deepseek-v4-pro":{"draws":6,"losses":2,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"fireworks/ember-1":{"draws":0,"losses":5,"wins":43},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":42},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":7,"wins":80},"google/gemini-3.5-flash-lite":{"draws":14,"losses":0,"wins":104},"google/gemini-3.6-flash":{"draws":11,"losses":19,"wins":110},"google/gemini-3.8-flash":{"draws":8,"losses":9,"wins":73},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":2,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":0,"wins":38},"gpt-5.4":{"draws":11,"losses":11,"wins":62},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":3,"losses":9,"wins":36},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":56},"gpt-5.6-sol":{"draws":9,"losses":16,"wins":69},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":66},"gpt-6-astra":{"draws":9,"losses":70,"wins":17},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":6,"losses":12,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":29,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":38},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":1,"wins":55},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":45},"meta/muse-spark-1.2":{"draws":7,"losses":4,"wins":57},"meta/muse-spark-1.3":{"draws":4,"losses":8,"wins":54},"meta/muse-wonder":{"draws":3,"losses":14,"wins":31},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":60},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"o3":{"draws":3,"losses":7,"wins":80},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":50},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":51},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":10,"wins":70},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":41},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":45},"qwen/qwen3.8-max":{"draws":5,"losses":3,"wins":72},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"stealth/ox-alpha":{"draws":19,"losses":25,"wins":240},"stealth/space-bunny-alpha":{"draws":1,"losses":2,"wins":35},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":12,"wins":65},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":64},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":60},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":11,"wins":60},"x-ai/grok-4.6":{"draws":6,"losses":19,"wins":67},"x-ai/grok-4.7":{"draws":1,"losses":17,"wins":24},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":13,"losses":4,"wins":101},"z-ai/glm-5.3":{"draws":6,"losses":15,"wins":53},"z-ai/glm-5.3-flash":{"draws":4,"losses":14,"wins":66},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":36}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":26},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":2,"losses":47,"wins":5},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":9},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":15,"losses":56,"wins":11},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":19,"losses":8,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":6,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":11,"wins":20},"fireworks/ember-1":{"draws":14,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":13,"wins":54},"google/gemini-3.6-flash":{"draws":25,"losses":32,"wins":35},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":15},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":11,"losses":19,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":24},"gpt-5.5":{"draws":19,"losses":10,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":17,"losses":11,"wins":20},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":8,"losses":38,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":37},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":23},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":23},"o3":{"draws":14,"losses":15,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":8,"wins":19},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":25},"qwen/qwen3.8-max-0902":{"draws":15,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":36,"losses":60,"wins":62},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":26},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":13,"losses":16,"wins":17},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":43},"thinkingmachines/inkling-small":{"draws":9,"losses":5,"wins":34},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":9,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":24,"losses":21,"wins":51},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":16,"wins":20}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":16,"wins":42},"claude-fable-5":{"draws":12,"losses":60,"wins":10},"claude-fable-5-1":{"draws":5,"losses":94,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":32,"losses":28,"wins":52},"claude-opus-4-8":{"draws":20,"losses":26,"wins":22},"claude-opus-5":{"draws":24,"losses":90,"wins":20},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":31,"losses":29,"wins":72},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":22},"deepseek/deepseek-v4-flash":{"draws":25,"losses":23,"wins":60},"deepseek/deepseek-v4-pro":{"draws":13,"losses":28,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":29,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"fireworks/ember-1":{"draws":16,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":34},"google/gemini-3.5-flash":{"draws":25,"losses":42,"wins":33},"google/gemini-3.5-flash-lite":{"draws":69,"losses":48,"wins":141},"google/gemini-3.6-flash":{"draws":60,"losses":109,"wins":89},"google/gemini-3.8-flash":{"draws":20,"losses":46,"wins":26},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":7,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":19,"wins":24},"gpt-5.4":{"draws":28,"losses":64,"wins":26},"gpt-5.4-mini":{"draws":18,"losses":11,"wins":21},"gpt-5.4-nano":{"draws":19,"losses":18,"wins":45},"gpt-5.5":{"draws":31,"losses":27,"wins":14},"gpt-5.6-luna":{"draws":42,"losses":33,"wins":49},"gpt-5.6-sol":{"draws":21,"losses":86,"wins":25},"gpt-5.6-terra":{"draws":24,"losses":22,"wins":32},"gpt-6-astra":{"draws":12,"losses":72,"wins":6},"gpt-6-luna":{"draws":16,"losses":11,"wins":21},"gpt-6-sol":{"draws":9,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":34},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":43},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":26,"losses":17,"wins":69},"meta/muse-glimmer-30b":{"draws":17,"losses":14,"wins":37},"meta/muse-spark-1.2":{"draws":24,"losses":46,"wins":28},"meta/muse-spark-1.3":{"draws":12,"losses":37,"wins":25},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":26},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k3":{"draws":45,"losses":37,"wins":38},"nex-agi/nex-n2-pro":{"draws":10,"losses":2,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":26},"o3":{"draws":18,"losses":57,"wins":109},"openai/gpt-oss-120b":{"draws":16,"losses":6,"wins":44},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":59},"qwen/qwen3.7-max":{"draws":13,"losses":8,"wins":25},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":32,"wins":26},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":15},"qwen/qwen3.8-flash":{"draws":18,"losses":13,"wins":23},"qwen/qwen3.8-max":{"draws":20,"losses":42,"wins":25},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":15},"stealth/ox-alpha":{"draws":83,"losses":104,"wins":89},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":40,"wins":25},"thinkingmachines/inkling":{"draws":24,"losses":21,"wins":59},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":59},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":42,"losses":57,"wins":43},"x-ai/grok-4.6":{"draws":22,"losses":44,"wins":18},"x-ai/grok-4.7":{"draws":2,"losses":30,"wins":10},"x-ai/grok-build-0.1":{"draws":10,"losses":6,"wins":18},"xiaomi/mimo-v2.5":{"draws":39,"losses":17,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":16,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":15,"wins":6},"z-ai/glm-5.2":{"draws":43,"losses":35,"wins":56},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":14},"z-ai/glm-5.3-flash":{"draws":20,"losses":42,"wins":26},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":7,"wins":20},"claude-fable-5":{"draws":16,"losses":28,"wins":10},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":41,"losses":42,"wins":47},"claude-opus-4-8":{"draws":13,"losses":33,"wins":14},"claude-opus-5":{"draws":19,"losses":102,"wins":7},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":18,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":15,"losses":6,"wins":19},"deepseek/deepseek-v4-flash":{"draws":37,"losses":13,"wins":36},"deepseek/deepseek-v4-pro":{"draws":19,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":18,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":19,"wins":11},"fireworks/ember-1":{"draws":19,"losses":16,"wins":13},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":22,"losses":3,"wins":39},"google/gemini-3.5-flash":{"draws":25,"losses":18,"wins":23},"google/gemini-3.5-flash-lite":{"draws":44,"losses":10,"wins":50},"google/gemini-3.6-flash":{"draws":39,"losses":50,"wins":33},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":13},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":16,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":27,"losses":20,"wins":29},"gpt-5.4":{"draws":16,"losses":18,"wins":14},"gpt-5.4-mini":{"draws":25,"losses":21,"wins":16},"gpt-5.4-nano":{"draws":26,"losses":27,"wins":41},"gpt-5.5":{"draws":34,"losses":26,"wins":20},"gpt-5.6-luna":{"draws":21,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":14,"losses":31,"wins":13},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":16},"gpt-6-astra":{"draws":1,"losses":48,"wins":3},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":45,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":17},"inclusionai/ling-3.0-flash":{"draws":33,"losses":0,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":19,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":19},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":18},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":20,"losses":11,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":8},"moonshotai/kimi-k3":{"draws":18,"losses":19,"wins":17},"nex-agi/nex-n2-pro":{"draws":27,"losses":0,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":13,"wins":26},"o3":{"draws":22,"losses":20,"wins":42},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":36,"losses":10,"wins":34},"qwen/qwen3.7-max":{"draws":30,"losses":9,"wins":21},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":23,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":20,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":17,"losses":19,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"stealth/ox-alpha":{"draws":48,"losses":74,"wins":48},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":10,"wins":9},"tencent/hy4-preview":{"draws":19,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":30,"losses":17,"wins":35},"thinkingmachines/inkling-small":{"draws":23,"losses":3,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":29,"wins":21},"x-ai/grok-4.6":{"draws":19,"losses":22,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":21},"xiaomi/mimo-v2.5":{"draws":60,"losses":13,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":9,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":63,"losses":29,"wins":58},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":17},"z-ai/glm-5.3-flashx":{"draws":11,"losses":22,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":5,"wins":59},"claude-fable-5":{"draws":9,"losses":27,"wins":62},"claude-fable-5-1":{"draws":6,"losses":69,"wins":21},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":51},"claude-opus-4-5":{"draws":45,"losses":18,"wins":195},"claude-opus-4-8":{"draws":29,"losses":27,"wins":88},"claude-opus-5":{"draws":43,"losses":161,"wins":130},"claude-opus-5-5":{"draws":6,"losses":61,"wins":25},"claude-sonnet-5":{"draws":13,"losses":11,"wins":66},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":45},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":34},"deepseek/deepseek-v4-flash":{"draws":17,"losses":2,"wins":129},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":64},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":12,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":16,"wins":56},"fireworks/ember-1":{"draws":9,"losses":15,"wins":60},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":61},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":58},"google/gemini-3.5-flash":{"draws":18,"losses":7,"wins":97},"google/gemini-3.5-flash-lite":{"draws":34,"losses":14,"wins":138},"google/gemini-3.6-flash":{"draws":21,"losses":36,"wins":163},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":74},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":35},"gpt-4.1":{"draws":4,"losses":5,"wins":47},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":9,"wins":105},"gpt-5.4":{"draws":10,"losses":15,"wins":57},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":71},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":102},"gpt-5.5":{"draws":19,"losses":49,"wins":96},"gpt-5.6-luna":{"draws":9,"losses":13,"wins":66},"gpt-5.6-sol":{"draws":17,"losses":21,"wins":60},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":62},"gpt-6-astra":{"draws":6,"losses":61,"wins":19},"gpt-6-luna":{"draws":16,"losses":8,"wins":60},"gpt-6-sol":{"draws":12,"losses":32,"wins":40},"gpt-6.1-sol":{"draws":6,"losses":49,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":40},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":62},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":17,"losses":16,"wins":105},"meta/muse-glimmer-30b":{"draws":4,"losses":10,"wins":66},"meta/muse-spark-1.2":{"draws":12,"losses":15,"wins":63},"meta/muse-spark-1.3":{"draws":10,"losses":20,"wins":62},"meta/muse-wonder":{"draws":9,"losses":32,"wins":43},"minimax/minimax-m3":{"draws":6,"losses":11,"wins":59},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":40},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":44},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":82},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":53},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":1,"wins":97},"o3":{"draws":9,"losses":10,"wins":121},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":70},"poolside/laguna-s-2.1":{"draws":9,"losses":8,"wins":119},"qwen/qwen3.7-max":{"draws":16,"losses":9,"wins":77},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":13,"wins":65},"qwen/qwen3.8-27b":{"draws":10,"losses":6,"wins":40},"qwen/qwen3.8-flash":{"draws":12,"losses":5,"wins":49},"qwen/qwen3.8-max":{"draws":13,"losses":5,"wins":70},"qwen/qwen3.8-max-0902":{"draws":14,"losses":14,"wins":56},"stealth/ox-alpha":{"draws":40,"losses":34,"wins":234},"stealth/space-bunny-alpha":{"draws":14,"losses":4,"wins":50},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":55},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":14,"losses":11,"wins":59},"tencent/hy4-preview":{"draws":6,"losses":13,"wins":69},"thinkingmachines/inkling":{"draws":28,"losses":6,"wins":110},"thinkingmachines/inkling-small":{"draws":15,"losses":4,"wins":65},"unbiased/pareto-26.10-preview":{"draws":2,"losses":18,"wins":8},"upstage/solar-mini4":{"draws":4,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":17,"losses":28,"wins":85},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":56},"x-ai/grok-4.7":{"draws":7,"losses":41,"wins":28},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":28},"xiaomi/mimo-v2.5":{"draws":45,"losses":13,"wins":142},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":1,"wins":60},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":16,"wins":31},"z-ai/glm-5.2":{"draws":35,"losses":18,"wins":179},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":47},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":69},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":59}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":3,"wins":48},"claude-fable-5-1":{"draws":5,"losses":18,"wins":37},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":50},"claude-opus-4-5":{"draws":4,"losses":0,"wins":84},"claude-opus-4-8":{"draws":2,"losses":1,"wins":47},"claude-opus-5":{"draws":4,"losses":19,"wins":71},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":1,"wins":53},"claude-sonnet-5-5":{"draws":5,"losses":8,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":79},"deepseek/deepseek-v4-pro":{"draws":3,"losses":0,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"fireworks/ember-1":{"draws":0,"losses":0,"wins":54},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":49},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":36},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":67},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":93},"google/gemini-3.6-flash":{"draws":3,"losses":7,"wins":92},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":48},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":32},"gpt-4.1":{"draws":0,"losses":0,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":1,"wins":47},"gpt-5.4":{"draws":1,"losses":3,"wins":48},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":55},"gpt-5.5":{"draws":4,"losses":0,"wins":46},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":50},"gpt-5.6-sol":{"draws":1,"losses":6,"wins":47},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":50},"gpt-6-astra":{"draws":5,"losses":25,"wins":24},"gpt-6-luna":{"draws":2,"losses":0,"wins":52},"gpt-6-sol":{"draws":3,"losses":12,"wins":39},"gpt-6.1-sol":{"draws":3,"losses":20,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":38},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":40},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":57},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":48},"meta/muse-spark-1.2":{"draws":0,"losses":1,"wins":51},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":54},"meta/muse-wonder":{"draws":2,"losses":7,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":30},"mistralai/mistral-large-4-0":{"draws":2,"losses":3,"wins":29},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":51},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":50},"o3":{"draws":2,"losses":1,"wins":73},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":48},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":0,"wins":53},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":34},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":48},"stealth/ox-alpha":{"draws":8,"losses":5,"wins":161},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":41},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":38},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":28},"tencent/hy4-preview":{"draws":1,"losses":4,"wins":47},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":68},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":12},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":2,"wins":49},"x-ai/grok-4.6":{"draws":2,"losses":1,"wins":51},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":34},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":108},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":45},"z-ai/glm-5.3-flash":{"draws":4,"losses":4,"wins":46},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":50}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":10,"wins":44},"claude-fable-5":{"draws":17,"losses":61,"wins":10},"claude-fable-5-1":{"draws":5,"losses":95,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":42,"losses":62,"wins":34},"claude-opus-4-8":{"draws":13,"losses":21,"wins":10},"claude-opus-5":{"draws":13,"losses":60,"wins":13},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":26,"losses":41,"wins":21},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":38,"losses":20,"wins":58},"deepseek/deepseek-v4-pro":{"draws":32,"losses":28,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":35,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":16,"wins":13},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":34,"losses":39,"wins":27},"google/gemini-3.5-flash-lite":{"draws":80,"losses":62,"wins":102},"google/gemini-3.6-flash":{"draws":75,"losses":103,"wins":48},"google/gemini-3.8-flash":{"draws":26,"losses":45,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":10,"wins":19},"gpt-5.4":{"draws":41,"losses":72,"wins":21},"gpt-5.4-mini":{"draws":18,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":18,"wins":22},"gpt-5.5":{"draws":21,"losses":21,"wins":4},"gpt-5.6-luna":{"draws":47,"losses":34,"wins":59},"gpt-5.6-sol":{"draws":20,"losses":110,"wins":21},"gpt-5.6-terra":{"draws":39,"losses":24,"wins":15},"gpt-6-astra":{"draws":5,"losses":83,"wins":4},"gpt-6-luna":{"draws":14,"losses":17,"wins":17},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":8,"wins":30},"inclusionai/ling-3.0-flash":{"draws":24,"losses":6,"wins":32},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":14,"wins":46},"meta/muse-glimmer-30b":{"draws":36,"losses":10,"wins":36},"meta/muse-spark-1.2":{"draws":29,"losses":45,"wins":26},"meta/muse-spark-1.3":{"draws":23,"losses":35,"wins":16},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":28,"losses":6,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":40,"losses":47,"wins":19},"nex-agi/nex-n2-pro":{"draws":14,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":7,"wins":19},"o3":{"draws":24,"losses":70,"wins":46},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":42},"poolside/laguna-s-2.1":{"draws":44,"losses":13,"wins":37},"qwen/qwen3.7-max":{"draws":12,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":35,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":22,"wins":9},"qwen/qwen3.8-flash":{"draws":26,"losses":18,"wins":18},"qwen/qwen3.8-max":{"draws":34,"losses":36,"wins":23},"qwen/qwen3.8-max-0902":{"draws":17,"losses":22,"wins":9},"stealth/ox-alpha":{"draws":71,"losses":168,"wins":63},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":37,"losses":41,"wins":12},"thinkingmachines/inkling":{"draws":34,"losses":15,"wins":53},"thinkingmachines/inkling-small":{"draws":33,"losses":14,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":28,"losses":56,"wins":26},"x-ai/grok-4.6":{"draws":25,"losses":47,"wins":18},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":10,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":51,"losses":42,"wins":53},"z-ai/glm-5.3":{"draws":13,"losses":52,"wins":5},"z-ai/glm-5.3-flash":{"draws":27,"losses":47,"wins":16},"z-ai/glm-5.3-flashx":{"draws":15,"losses":26,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":11,"losses":28,"wins":9},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":22,"losses":21,"wins":35},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":8,"losses":61,"wins":13},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":21},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":12,"losses":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":24,"losses":17,"wins":43},"google/gemini-3.6-flash":{"draws":23,"losses":39,"wins":30},"google/gemini-3.8-flash":{"draws":6,"losses":24,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":3,"wins":34},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":16,"losses":13,"wins":17},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":16,"wins":19},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":41,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":12,"wins":30},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":13,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":16},"meta/muse-wonder":{"draws":11,"losses":21,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":9,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":24},"o3":{"draws":7,"losses":15,"wins":44},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":23},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":16,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":5,"wins":26},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":8,"losses":26,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":29,"losses":22,"wins":45},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":15,"wins":12},"claude-fable-5":{"draws":6,"losses":32,"wins":2},"claude-fable-5-1":{"draws":0,"losses":42,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":7},"claude-opus-4-5":{"draws":13,"losses":58,"wins":13},"claude-opus-4-8":{"draws":15,"losses":35,"wins":6},"claude-opus-5":{"draws":9,"losses":59,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":6,"losses":24,"wins":10},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":24,"losses":23,"wins":27},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":6},"fireworks/ember-1":{"draws":8,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":19,"losses":21,"wins":20},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":10},"google/gemini-3.5-flash-lite":{"draws":36,"losses":29,"wins":27},"google/gemini-3.6-flash":{"draws":29,"losses":54,"wins":11},"google/gemini-3.8-flash":{"draws":7,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":5},"gpt-4.1":{"draws":9,"losses":13,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":39,"wins":10},"gpt-5.4":{"draws":8,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":15,"losses":22,"wins":9},"gpt-5.4-nano":{"draws":19,"losses":36,"wins":15},"gpt-5.5":{"draws":21,"losses":31,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":20,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":24,"wins":8},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":6},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":20,"losses":20,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":36,"wins":15},"meta/muse-glimmer-30b":{"draws":16,"losses":11,"wins":9},"meta/muse-spark-1.2":{"draws":3,"losses":25,"wins":12},"meta/muse-spark-1.3":{"draws":2,"losses":34,"wins":2},"meta/muse-wonder":{"draws":3,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":9,"losses":18,"wins":17},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":10,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":11},"nex-agi/nex-n2-pro":{"draws":19,"losses":19,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":16,"wins":23},"o3":{"draws":16,"losses":43,"wins":17},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":10},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":26},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":29,"wins":3},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":6,"losses":25,"wins":5},"stealth/ox-alpha":{"draws":28,"losses":82,"wins":22},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":15,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":15,"wins":8},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":22,"wins":19},"thinkingmachines/inkling-small":{"draws":15,"losses":15,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":36,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":10,"losses":15,"wins":7},"xiaomi/mimo-v2.5":{"draws":41,"losses":28,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":17,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":42,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":48,"losses":62,"wins":54},"claude-fable-5":{"draws":31,"losses":128,"wins":9},"claude-fable-5-1":{"draws":5,"losses":174,"wins":1},"claude-haiku-5-5":{"draws":33,"losses":75,"wins":20},"claude-opus-4-5":{"draws":90,"losses":143,"wins":53},"claude-opus-4-8":{"draws":46,"losses":98,"wins":16},"claude-opus-5":{"draws":29,"losses":243,"wins":14},"claude-opus-5-5":{"draws":6,"losses":134,"wins":4},"claude-sonnet-5":{"draws":55,"losses":96,"wins":35},"claude-sonnet-5-5":{"draws":28,"losses":86,"wins":18},"cohere/north-mini-code":{"draws":22,"losses":28,"wins":22},"deepseek/deepseek-v4-flash":{"draws":73,"losses":77,"wins":76},"deepseek/deepseek-v4-pro":{"draws":44,"losses":82,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":59,"losses":77,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":74,"wins":15},"fireworks/ember-1":{"draws":41,"losses":73,"wins":18},"gemini-3.1-pro-preview":{"draws":39,"losses":64,"wins":29},"google/gemini-3.1-flash-lite":{"draws":42,"losses":50,"wins":78},"google/gemini-3.5-flash":{"draws":53,"losses":120,"wins":41},"google/gemini-3.5-flash-lite":{"draws":100,"losses":93,"wins":113},"google/gemini-3.6-flash":{"draws":91,"losses":195,"wins":56},"google/gemini-3.8-flash":{"draws":36,"losses":113,"wins":19},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":32,"losses":32,"wins":12},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":63,"losses":66,"wins":29},"gpt-5.4":{"draws":53,"losses":99,"wins":16},"gpt-5.4-mini":{"draws":58,"losses":50,"wins":36},"gpt-5.4-nano":{"draws":51,"losses":71,"wins":78},"gpt-5.5":{"draws":74,"losses":79,"wins":13},"gpt-5.6-luna":{"draws":68,"losses":67,"wins":37},"gpt-5.6-sol":{"draws":22,"losses":140,"wins":10},"gpt-5.6-terra":{"draws":60,"losses":92,"wins":24},"gpt-6-astra":{"draws":4,"losses":156,"wins":4},"gpt-6-luna":{"draws":35,"losses":71,"wins":26},"gpt-6-sol":{"draws":18,"losses":105,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":122,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":53,"losses":23,"wins":50},"inclusionai/ling-3.0-flash":{"draws":68,"losses":34,"wins":54},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":62,"losses":68,"wins":78},"meta/muse-glimmer-30b":{"draws":62,"losses":30,"wins":56},"meta/muse-spark-1.2":{"draws":39,"losses":87,"wins":26},"meta/muse-spark-1.3":{"draws":31,"losses":102,"wins":27},"meta/muse-wonder":{"draws":23,"losses":93,"wins":16},"minimax/minimax-m3":{"draws":39,"losses":41,"wins":44},"mistralai/mistral-large-4-0":{"draws":28,"losses":43,"wins":11},"mistralai/mistral-medium-3-5":{"draws":40,"losses":22,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":23,"wins":14},"moonshotai/kimi-k3":{"draws":48,"losses":83,"wins":27},"nex-agi/nex-n2-pro":{"draws":30,"losses":41,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":79,"losses":47,"wins":60},"o3":{"draws":37,"losses":147,"wins":62},"openai/gpt-oss-120b":{"draws":59,"losses":39,"wins":54},"poolside/laguna-s-2.1":{"draws":80,"losses":56,"wins":58},"qwen/qwen3.7-max":{"draws":49,"losses":40,"wins":29},"qwen/qwen3.7-plus":{"draws":34,"losses":41,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":97,"wins":26},"qwen/qwen3.8-27b":{"draws":25,"losses":56,"wins":27},"qwen/qwen3.8-flash":{"draws":40,"losses":45,"wins":27},"qwen/qwen3.8-max":{"draws":60,"losses":83,"wins":31},"qwen/qwen3.8-max-0902":{"draws":38,"losses":78,"wins":16},"stealth/ox-alpha":{"draws":143,"losses":311,"wins":88},"stealth/space-bunny-alpha":{"draws":36,"losses":51,"wins":17},"stepfun/step-3.7-flash":{"draws":31,"losses":46,"wins":41},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":39,"losses":44,"wins":33},"tencent/hy4-preview":{"draws":46,"losses":88,"wins":26},"thinkingmachines/inkling":{"draws":67,"losses":89,"wins":72},"thinkingmachines/inkling-small":{"draws":74,"losses":36,"wins":70},"unbiased/pareto-26.10-preview":{"draws":0,"losses":44,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":10,"wins":18},"x-ai/grok-4.5":{"draws":31,"losses":125,"wins":26},"x-ai/grok-4.6":{"draws":52,"losses":108,"wins":14},"x-ai/grok-4.7":{"draws":12,"losses":98,"wins":8},"x-ai/grok-build-0.1":{"draws":29,"losses":19,"wins":28},"xiaomi/mimo-v2.5":{"draws":124,"losses":125,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":37,"losses":48,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":52,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":128,"losses":156,"wins":80},"z-ai/glm-5.3":{"draws":37,"losses":103,"wins":8},"z-ai/glm-5.3-flash":{"draws":43,"losses":92,"wins":27},"z-ai/glm-5.3-flashx":{"draws":34,"losses":78,"wins":20}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":16,"wins":51},"claude-fable-5":{"draws":16,"losses":47,"wins":29},"claude-fable-5-1":{"draws":6,"losses":86,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":23,"losses":27,"wins":54},"claude-opus-4-8":{"draws":12,"losses":18,"wins":18},"claude-opus-5":{"draws":9,"losses":62,"wins":15},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":27,"losses":23,"wins":40},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":14},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":25,"losses":29,"wins":54},"deepseek/deepseek-v4-pro":{"draws":14,"losses":18,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":29,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"wins":17},"fireworks/ember-1":{"draws":12,"losses":19,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":23,"losses":42,"wins":35},"google/gemini-3.5-flash-lite":{"draws":27,"losses":42,"wins":85},"google/gemini-3.6-flash":{"draws":28,"losses":51,"wins":75},"google/gemini-3.8-flash":{"draws":11,"losses":49,"wins":26},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":24},"gpt-5.4":{"draws":11,"losses":45,"wins":32},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":11,"wins":28},"gpt-5.5":{"draws":8,"losses":21,"wins":17},"gpt-5.6-luna":{"draws":26,"losses":21,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":53,"wins":26},"gpt-5.6-terra":{"draws":18,"losses":26,"wins":44},"gpt-6-astra":{"draws":4,"losses":64,"wins":16},"gpt-6-luna":{"draws":10,"losses":20,"wins":18},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":3,"wins":37},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":5,"wins":50},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":38},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":34},"meta/muse-spark-1.3":{"draws":7,"losses":35,"wins":30},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":17,"losses":29,"wins":22},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":5,"wins":25},"o3":{"draws":8,"losses":38,"wins":56},"openai/gpt-oss-120b":{"draws":19,"losses":12,"wins":41},"poolside/laguna-s-2.1":{"draws":15,"losses":13,"wins":42},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":19},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":25},"qwen/qwen3.8-27b":{"draws":10,"losses":10,"wins":26},"qwen/qwen3.8-flash":{"draws":13,"losses":25,"wins":20},"qwen/qwen3.8-max":{"draws":22,"losses":37,"wins":31},"qwen/qwen3.8-max-0902":{"draws":11,"losses":23,"wins":14},"stealth/ox-alpha":{"draws":70,"losses":107,"wins":105},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":19},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":18,"losses":35,"wins":31},"thinkingmachines/inkling":{"draws":25,"losses":11,"wins":46},"thinkingmachines/inkling-small":{"draws":26,"losses":12,"wins":50},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":35,"wins":25},"x-ai/grok-4.6":{"draws":12,"losses":48,"wins":30},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":22,"losses":9,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":37,"losses":31,"wins":64},"z-ai/glm-5.3":{"draws":12,"losses":41,"wins":21},"z-ai/glm-5.3-flash":{"draws":10,"losses":39,"wins":31},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":35},"claude-fable-5":{"draws":9,"losses":56,"wins":17},"claude-fable-5-1":{"draws":2,"losses":90,"wins":4},"claude-haiku-5-5":{"draws":10,"losses":24,"wins":12},"claude-opus-4-5":{"draws":32,"losses":34,"wins":38},"claude-opus-4-8":{"draws":11,"losses":19,"wins":18},"claude-opus-5":{"draws":11,"losses":66,"wins":11},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":27,"losses":21,"wins":38},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":35,"losses":36,"wins":45},"deepseek/deepseek-v4-pro":{"draws":21,"losses":33,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":36,"losses":42,"wins":26},"google/gemini-3.5-flash-lite":{"draws":50,"losses":29,"wins":71},"google/gemini-3.6-flash":{"draws":42,"losses":78,"wins":34},"google/gemini-3.8-flash":{"draws":26,"losses":35,"wins":19},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":17,"wins":14},"gpt-5.4":{"draws":18,"losses":40,"wins":20},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":17},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":25},"gpt-5.5":{"draws":14,"losses":15,"wins":17},"gpt-5.6-luna":{"draws":28,"losses":37,"wins":23},"gpt-5.6-sol":{"draws":15,"losses":56,"wins":15},"gpt-5.6-terra":{"draws":20,"losses":40,"wins":26},"gpt-6-astra":{"draws":3,"losses":79,"wins":0},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":5,"losses":35,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":12,"wins":32},"inclusionai/ling-3.0-flash":{"draws":21,"losses":6,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":28,"losses":17,"wins":31},"meta/muse-glimmer-30b":{"draws":28,"losses":12,"wins":40},"meta/muse-spark-1.2":{"draws":22,"losses":33,"wins":19},"meta/muse-spark-1.3":{"draws":17,"losses":36,"wins":21},"meta/muse-wonder":{"draws":13,"losses":27,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":24},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":21,"losses":32,"wins":21},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":23},"o3":{"draws":16,"losses":38,"wins":46},"openai/gpt-oss-120b":{"draws":17,"losses":18,"wins":33},"poolside/laguna-s-2.1":{"draws":20,"losses":23,"wins":29},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":28,"wins":25},"qwen/qwen3.8-27b":{"draws":14,"losses":17,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":20,"wins":13},"qwen/qwen3.8-max":{"draws":40,"losses":31,"wins":17},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":74,"losses":118,"wins":92},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":22,"losses":35,"wins":23},"thinkingmachines/inkling":{"draws":27,"losses":20,"wins":35},"thinkingmachines/inkling-small":{"draws":24,"losses":16,"wins":50},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":21,"losses":35,"wins":28},"x-ai/grok-4.6":{"draws":24,"losses":44,"wins":22},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":13,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":55,"losses":36,"wins":47},"z-ai/glm-5.3":{"draws":22,"losses":32,"wins":16},"z-ai/glm-5.3-flash":{"draws":15,"losses":44,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":6,"wins":22},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":8,"losses":41,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":18,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":11,"losses":11,"wins":22},"claude-opus-5":{"draws":17,"losses":52,"wins":13},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":11,"losses":15,"wins":22},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":29,"losses":6,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":13,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":10,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":13},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":16,"losses":12,"wins":20},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":22,"losses":15,"wins":23},"google/gemini-3.5-flash-lite":{"draws":38,"losses":7,"wins":39},"google/gemini-3.6-flash":{"draws":29,"losses":33,"wins":30},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":14,"losses":3,"wins":11},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":16,"losses":9,"wins":17},"gpt-5.4":{"draws":17,"losses":15,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":10,"wins":20},"gpt-5.5":{"draws":14,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":22,"losses":6,"wins":20},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":16,"losses":10,"wins":22},"gpt-6-sol":{"draws":9,"losses":27,"wins":12},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":13},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":28},"meta/muse-glimmer-30b":{"draws":18,"losses":4,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":13,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-wonder":{"draws":16,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":12,"wins":18},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"o3":{"draws":17,"losses":16,"wins":33},"openai/gpt-oss-120b":{"draws":16,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":22,"losses":5,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":20,"losses":11,"wins":17},"stealth/ox-alpha":{"draws":37,"losses":58,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":20,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":6,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":11,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":13,"losses":16,"wins":19},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":16}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":5,"wins":25},"claude-fable-5":{"draws":14,"losses":29,"wins":5},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":30,"losses":21,"wins":27},"claude-opus-4-8":{"draws":17,"losses":16,"wins":11},"claude-opus-5":{"draws":9,"losses":58,"wins":15},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":23,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":25,"losses":10,"wins":37},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"fireworks/ember-1":{"draws":11,"losses":7,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":19,"losses":17,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":9,"wins":41},"google/gemini-3.6-flash":{"draws":31,"losses":29,"wins":32},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":20},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":9,"wins":21},"gpt-5.4":{"draws":14,"losses":20,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":15,"losses":9,"wins":24},"gpt-5.5":{"draws":19,"losses":14,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":11},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":0,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":5,"wins":33},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":19},"meta/muse-spark-1.3":{"draws":21,"losses":16,"wins":11},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":17},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":19},"o3":{"draws":13,"losses":18,"wins":35},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":7,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":13,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":17,"losses":11,"wins":20},"qwen/qwen3.8-max-0902":{"draws":19,"losses":18,"wins":11},"stealth/ox-alpha":{"draws":50,"losses":50,"wins":58},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":24,"losses":3,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":24},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":16},"x-ai/grok-4.6":{"draws":16,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":12,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":19,"wins":43},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":9},"z-ai/glm-5.3-flash":{"draws":12,"losses":22,"wins":14},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":13,"losses":25,"wins":10},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":27,"losses":34,"wins":17},"claude-opus-4-8":{"draws":16,"losses":22,"wins":6},"claude-opus-5":{"draws":10,"losses":65,"wins":7},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":19,"losses":15,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":30,"losses":16,"wins":26},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":14},"fireworks/ember-1":{"draws":16,"losses":23,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":17,"losses":29,"wins":14},"google/gemini-3.5-flash-lite":{"draws":35,"losses":23,"wins":26},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":24},"google/gemini-3.8-flash":{"draws":12,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":9},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":12,"wins":13},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":18},"gpt-5.5":{"draws":15,"losses":20,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":12,"wins":16},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":18,"losses":16,"wins":14},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":2,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":23},"meta/muse-glimmer-30b":{"draws":20,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":12},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":7,"losses":14,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":24,"wins":10},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":8},"o3":{"draws":17,"losses":28,"wins":21},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":15,"losses":22,"wins":11},"stealth/ox-alpha":{"draws":45,"losses":71,"wins":42},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":16,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":9,"losses":25,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":37,"losses":14,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":21,"wins":4},"z-ai/glm-5.2":{"draws":35,"losses":35,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":30,"wins":7},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":16,"losses":25,"wins":7}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":16,"wins":8},"claude-fable-5":{"draws":3,"losses":31,"wins":2},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":4},"claude-opus-4-5":{"draws":23,"losses":74,"wins":3},"claude-opus-4-8":{"draws":21,"losses":44,"wins":5},"claude-opus-5":{"draws":11,"losses":61,"wins":6},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":16,"losses":24,"wins":2},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":6},"cohere/north-mini-code":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-flash":{"draws":20,"losses":42,"wins":18},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":8,"losses":25,"wins":3},"gemini-3.1-pro-preview":{"draws":7,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":17,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":26,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":34,"wins":28},"google/gemini-3.6-flash":{"draws":18,"losses":53,"wins":9},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":7},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":30,"wins":4},"gpt-5.4":{"draws":7,"losses":28,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":32,"wins":8},"gpt-5.4-nano":{"draws":21,"losses":52,"wins":21},"gpt-5.5":{"draws":18,"losses":29,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":33,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":25,"wins":5},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":11,"losses":22,"wins":3},"gpt-6-sol":{"draws":6,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":35,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":14,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":34,"wins":1},"meta/muse-wonder":{"draws":5,"losses":30,"wins":1},"minimax/minimax-m3":{"draws":15,"losses":21,"wins":18},"mistralai/mistral-large-4-0":{"draws":7,"losses":15,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":7,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":21,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":13,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":21,"wins":28},"o3":{"draws":17,"losses":51,"wins":4},"openai/gpt-oss-120b":{"draws":9,"losses":19,"wins":6},"poolside/laguna-s-2.1":{"draws":10,"losses":24,"wins":16},"qwen/qwen3.7-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.7-plus":{"draws":10,"losses":22,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":27,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":0},"stealth/ox-alpha":{"draws":21,"losses":70,"wins":15},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":23,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":31,"wins":20},"thinkingmachines/inkling-small":{"draws":13,"losses":12,"wins":13},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":14,"losses":38,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":21,"wins":3},"xiaomi/mimo-v2.5":{"draws":45,"losses":46,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":29,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":25,"losses":65,"wins":16},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":3}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":38},"claude-fable-5":{"draws":20,"losses":46,"wins":20},"claude-fable-5-1":{"draws":11,"losses":91,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":19},"claude-opus-4-5":{"draws":28,"losses":25,"wins":53},"claude-opus-4-8":{"draws":9,"losses":18,"wins":25},"claude-opus-5":{"draws":8,"losses":75,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":19,"losses":17,"wins":50},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":19},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":34,"losses":12,"wins":54},"deepseek/deepseek-v4-pro":{"draws":21,"losses":13,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":17,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":11,"losses":16,"wins":21},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":24},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":22,"wins":31},"google/gemini-3.5-flash-lite":{"draws":31,"losses":21,"wins":78},"google/gemini-3.6-flash":{"draws":36,"losses":46,"wins":64},"google/gemini-3.8-flash":{"draws":22,"losses":40,"wins":32},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":10,"wins":24},"gpt-5.4":{"draws":15,"losses":38,"wins":29},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":28},"gpt-5.5":{"draws":11,"losses":18,"wins":15},"gpt-5.6-luna":{"draws":33,"losses":13,"wins":36},"gpt-5.6-sol":{"draws":12,"losses":54,"wins":22},"gpt-5.6-terra":{"draws":23,"losses":27,"wins":30},"gpt-6-astra":{"draws":9,"losses":76,"wins":5},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":6,"losses":34,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":39,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":2,"wins":28},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":36},"meta/muse-glimmer-30b":{"draws":21,"losses":9,"wins":34},"meta/muse-spark-1.2":{"draws":16,"losses":19,"wins":31},"meta/muse-spark-1.3":{"draws":16,"losses":33,"wins":21},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":8,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":12,"losses":8,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":26,"losses":16,"wins":32},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":26},"o3":{"draws":13,"losses":20,"wins":57},"openai/gpt-oss-120b":{"draws":22,"losses":8,"wins":36},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":7,"losses":1,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":23,"wins":39},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":22},"qwen/qwen3.8-flash":{"draws":19,"losses":14,"wins":23},"qwen/qwen3.8-max":{"draws":20,"losses":28,"wins":32},"qwen/qwen3.8-max-0902":{"draws":14,"losses":19,"wins":15},"stealth/ox-alpha":{"draws":65,"losses":83,"wins":134},"stealth/space-bunny-alpha":{"draws":12,"losses":3,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":39,"wins":31},"thinkingmachines/inkling":{"draws":24,"losses":9,"wins":43},"thinkingmachines/inkling-small":{"draws":20,"losses":13,"wins":39},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":26,"wins":33},"x-ai/grok-4.6":{"draws":26,"losses":42,"wins":18},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":35,"losses":31,"wins":64},"z-ai/glm-5.3":{"draws":16,"losses":30,"wins":28},"z-ai/glm-5.3-flash":{"draws":27,"losses":29,"wins":36},"z-ai/glm-5.3-flashx":{"draws":20,"losses":15,"wins":13}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":56,"losses":57,"wins":35},"claude-fable-5":{"draws":30,"losses":86,"wins":10},"claude-fable-5-1":{"draws":8,"losses":101,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":102,"losses":155,"wins":19},"claude-opus-4-8":{"draws":39,"losses":62,"wins":1},"claude-opus-5":{"draws":30,"losses":142,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":63,"losses":129,"wins":32},"claude-sonnet-5-5":{"draws":15,"losses":57,"wins":12},"cohere/north-mini-code":{"draws":23,"losses":23,"wins":6},"deepseek/deepseek-v4-flash":{"draws":71,"losses":79,"wins":42},"deepseek/deepseek-v4-pro":{"draws":45,"losses":59,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":55,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":41,"wins":8},"fireworks/ember-1":{"draws":34,"losses":42,"wins":8},"gemini-3.1-pro-preview":{"draws":32,"losses":37,"wins":15},"google/gemini-3.1-flash-lite":{"draws":29,"losses":21,"wins":32},"google/gemini-3.5-flash":{"draws":45,"losses":79,"wins":34},"google/gemini-3.5-flash-lite":{"draws":155,"losses":150,"wins":123},"google/gemini-3.6-flash":{"draws":165,"losses":227,"wins":57},"google/gemini-3.8-flash":{"draws":32,"losses":84,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":14,"wins":14},"gpt-4.1":{"draws":13,"losses":16,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":40,"losses":34,"wins":20},"gpt-5.4":{"draws":70,"losses":120,"wins":16},"gpt-5.4-mini":{"draws":37,"losses":37,"wins":12},"gpt-5.4-nano":{"draws":32,"losses":37,"wins":39},"gpt-5.5":{"draws":51,"losses":45,"wins":6},"gpt-5.6-luna":{"draws":77,"losses":115,"wins":40},"gpt-5.6-sol":{"draws":32,"losses":163,"wins":9},"gpt-5.6-terra":{"draws":47,"losses":76,"wins":11},"gpt-6-astra":{"draws":7,"losses":103,"wins":0},"gpt-6-luna":{"draws":28,"losses":39,"wins":17},"gpt-6-sol":{"draws":14,"losses":61,"wins":9},"gpt-6.1-sol":{"draws":5,"losses":78,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":45,"losses":34,"wins":31},"inclusionai/ling-3.0-flash":{"draws":47,"losses":37,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":63,"losses":95,"wins":54},"meta/muse-glimmer-30b":{"draws":66,"losses":33,"wins":43},"meta/muse-spark-1.2":{"draws":40,"losses":104,"wins":18},"meta/muse-spark-1.3":{"draws":27,"losses":79,"wins":14},"meta/muse-wonder":{"draws":15,"losses":63,"wins":6},"minimax/minimax-m3":{"draws":21,"losses":19,"wins":28},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":40,"losses":25,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":11,"wins":9},"moonshotai/kimi-k3":{"draws":82,"losses":103,"wins":19},"nex-agi/nex-n2-pro":{"draws":22,"losses":16,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":32,"wins":20},"o3":{"draws":56,"losses":226,"wins":26},"openai/gpt-oss-120b":{"draws":55,"losses":48,"wins":31},"poolside/laguna-s-2.1":{"draws":89,"losses":87,"wins":34},"qwen/qwen3.7-max":{"draws":23,"losses":28,"wins":13},"qwen/qwen3.7-plus":{"draws":26,"losses":20,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":74,"wins":9},"qwen/qwen3.8-27b":{"draws":15,"losses":45,"wins":12},"qwen/qwen3.8-flash":{"draws":41,"losses":43,"wins":4},"qwen/qwen3.8-max":{"draws":52,"losses":67,"wins":22},"qwen/qwen3.8-max-0902":{"draws":27,"losses":52,"wins":5},"stealth/ox-alpha":{"draws":131,"losses":273,"wins":60},"stealth/space-bunny-alpha":{"draws":20,"losses":35,"wins":11},"stepfun/step-3.7-flash":{"draws":21,"losses":30,"wins":11},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":23,"losses":20,"wins":7},"tencent/hy4-preview":{"draws":45,"losses":72,"wins":19},"thinkingmachines/inkling":{"draws":59,"losses":77,"wins":64},"thinkingmachines/inkling-small":{"draws":61,"losses":46,"wins":62},"unbiased/pareto-26.10-preview":{"draws":0,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":8,"losses":12,"wins":2},"x-ai/grok-4.5":{"draws":63,"losses":138,"wins":15},"x-ai/grok-4.6":{"draws":51,"losses":78,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":25,"losses":22,"wins":5},"xiaomi/mimo-v2.5":{"draws":68,"losses":62,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":30,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":35,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":44,"wins":6},"z-ai/glm-5.2":{"draws":103,"losses":100,"wins":43},"z-ai/glm-5.3":{"draws":31,"losses":74,"wins":5},"z-ai/glm-5.3-flash":{"draws":44,"losses":66,"wins":20},"z-ai/glm-5.3-flashx":{"draws":23,"losses":52,"wins":9}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":21,"wins":68},"claude-fable-5":{"draws":22,"losses":71,"wins":45},"claude-fable-5-1":{"draws":10,"losses":126,"wins":14},"claude-haiku-5-5":{"draws":15,"losses":29,"wins":36},"claude-opus-4-5":{"draws":66,"losses":57,"wins":133},"claude-opus-4-8":{"draws":33,"losses":32,"wins":55},"claude-opus-5":{"draws":20,"losses":134,"wins":52},"claude-opus-5-5":{"draws":7,"losses":70,"wins":11},"claude-sonnet-5":{"draws":48,"losses":55,"wins":87},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":38},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":36},"deepseek/deepseek-v4-flash":{"draws":43,"losses":27,"wins":116},"deepseek/deepseek-v4-pro":{"draws":27,"losses":43,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":31,"wins":72},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":25,"wins":39},"fireworks/ember-1":{"draws":21,"losses":29,"wins":34},"gemini-3.1-pro-preview":{"draws":14,"losses":27,"wins":43},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":61},"google/gemini-3.5-flash":{"draws":33,"losses":52,"wins":71},"google/gemini-3.5-flash-lite":{"draws":105,"losses":64,"wins":230},"google/gemini-3.6-flash":{"draws":72,"losses":112,"wins":166},"google/gemini-3.8-flash":{"draws":25,"losses":59,"wins":50},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":11,"losses":5,"wins":22},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":21,"losses":21,"wins":56},"gpt-5.4":{"draws":45,"losses":85,"wins":68},"gpt-5.4-mini":{"draws":23,"losses":18,"wins":50},"gpt-5.4-nano":{"draws":23,"losses":16,"wins":77},"gpt-5.5":{"draws":31,"losses":39,"wins":44},"gpt-5.6-luna":{"draws":42,"losses":33,"wins":109},"gpt-5.6-sol":{"draws":31,"losses":97,"wins":68},"gpt-5.6-terra":{"draws":37,"losses":30,"wins":61},"gpt-6-astra":{"draws":14,"losses":112,"wins":8},"gpt-6-luna":{"draws":21,"losses":21,"wins":42},"gpt-6-sol":{"draws":9,"losses":51,"wins":24},"gpt-6.1-sol":{"draws":4,"losses":66,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":8,"wins":47},"inclusionai/ling-3.0-flash":{"draws":38,"losses":6,"wins":68},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":50,"losses":20,"wins":118},"meta/muse-glimmer-30b":{"draws":32,"losses":15,"wins":67},"meta/muse-spark-1.2":{"draws":30,"losses":50,"wins":72},"meta/muse-spark-1.3":{"draws":17,"losses":52,"wins":47},"meta/muse-wonder":{"draws":13,"losses":43,"wins":28},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":41},"mistralai/mistral-large-4-0":{"draws":10,"losses":19,"wins":23},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":4,"wins":21},"moonshotai/kimi-k3":{"draws":48,"losses":55,"wins":97},"nex-agi/nex-n2-pro":{"draws":8,"losses":8,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":52},"o3":{"draws":30,"losses":58,"wins":178},"openai/gpt-oss-120b":{"draws":31,"losses":11,"wins":62},"poolside/laguna-s-2.1":{"draws":45,"losses":27,"wins":96},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":46},"qwen/qwen3.7-plus":{"draws":20,"losses":6,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":45,"wins":59},"qwen/qwen3.8-27b":{"draws":10,"losses":23,"wins":41},"qwen/qwen3.8-flash":{"draws":26,"losses":23,"wins":41},"qwen/qwen3.8-max":{"draws":36,"losses":41,"wins":59},"qwen/qwen3.8-max-0902":{"draws":18,"losses":30,"wins":36},"stealth/ox-alpha":{"draws":93,"losses":158,"wins":203},"stealth/space-bunny-alpha":{"draws":19,"losses":10,"wins":39},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":45},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":19,"losses":14,"wins":23},"tencent/hy4-preview":{"draws":30,"losses":45,"wins":63},"thinkingmachines/inkling":{"draws":42,"losses":27,"wins":107},"thinkingmachines/inkling-small":{"draws":32,"losses":16,"wins":79},"unbiased/pareto-26.10-preview":{"draws":3,"losses":22,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":51,"losses":75,"wins":98},"x-ai/grok-4.6":{"draws":35,"losses":51,"wins":48},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":22},"x-ai/grok-build-0.1":{"draws":13,"losses":0,"wins":29},"xiaomi/mimo-v2.5":{"draws":70,"losses":17,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":8,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":18,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":18,"wins":24},"z-ai/glm-5.2":{"draws":60,"losses":66,"wins":104},"z-ai/glm-5.3":{"draws":21,"losses":59,"wins":32},"z-ai/glm-5.3-flash":{"draws":12,"losses":63,"wins":49},"z-ai/glm-5.3-flashx":{"draws":15,"losses":30,"wins":39}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":10,"wins":33},"claude-fable-5":{"draws":15,"losses":28,"wins":43},"claude-fable-5-1":{"draws":4,"losses":86,"wins":12},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":44,"losses":15,"wins":55},"claude-opus-4-8":{"draws":14,"losses":14,"wins":22},"claude-opus-5":{"draws":12,"losses":57,"wins":23},"claude-opus-5-5":{"draws":7,"losses":41,"wins":4},"claude-sonnet-5":{"draws":28,"losses":23,"wins":37},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":30,"losses":13,"wins":61},"deepseek/deepseek-v4-pro":{"draws":29,"losses":20,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":14,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"fireworks/ember-1":{"draws":17,"losses":13,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":9,"wins":25},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":21},"google/gemini-3.5-flash":{"draws":26,"losses":27,"wins":47},"google/gemini-3.5-flash-lite":{"draws":46,"losses":5,"wins":83},"google/gemini-3.6-flash":{"draws":43,"losses":45,"wins":61},"google/gemini-3.8-flash":{"draws":17,"losses":19,"wins":26},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":7,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":15,"wins":20},"gpt-5.4":{"draws":27,"losses":33,"wins":28},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":17},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":27},"gpt-5.5":{"draws":25,"losses":12,"wins":9},"gpt-5.6-luna":{"draws":23,"losses":13,"wins":48},"gpt-5.6-sol":{"draws":16,"losses":48,"wins":24},"gpt-5.6-terra":{"draws":27,"losses":18,"wins":35},"gpt-6-astra":{"draws":7,"losses":79,"wins":4},"gpt-6-luna":{"draws":14,"losses":12,"wins":22},"gpt-6-sol":{"draws":9,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":31,"losses":5,"wins":30},"meta/muse-spark-1.2":{"draws":17,"losses":38,"wins":15},"meta/muse-spark-1.3":{"draws":21,"losses":22,"wins":27},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":10,"losses":0,"wins":18},"mistralai/mistral-large-4-0":{"draws":11,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":18,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":4},"moonshotai/kimi-k3":{"draws":24,"losses":14,"wins":34},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":1,"wins":26},"o3":{"draws":19,"losses":26,"wins":53},"openai/gpt-oss-120b":{"draws":27,"losses":7,"wins":32},"poolside/laguna-s-2.1":{"draws":25,"losses":9,"wins":28},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":25,"wins":37},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":26},"qwen/qwen3.8-flash":{"draws":21,"losses":12,"wins":27},"qwen/qwen3.8-max":{"draws":24,"losses":26,"wins":34},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":19},"stealth/ox-alpha":{"draws":70,"losses":80,"wins":140},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":24,"losses":26,"wins":32},"thinkingmachines/inkling":{"draws":29,"losses":4,"wins":41},"thinkingmachines/inkling-small":{"draws":31,"losses":4,"wins":39},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":23},"x-ai/grok-4.6":{"draws":33,"losses":31,"wins":22},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":4,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":42,"losses":20,"wins":66},"z-ai/glm-5.3":{"draws":15,"losses":34,"wins":27},"z-ai/glm-5.3-flash":{"draws":21,"losses":28,"wins":41},"z-ai/glm-5.3-flashx":{"draws":12,"losses":14,"wins":22}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":13,"wins":17},"claude-fable-5":{"draws":11,"losses":30,"wins":7},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":28,"wins":6},"claude-opus-4-5":{"draws":28,"losses":37,"wins":13},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":13,"losses":62,"wins":7},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":10},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":24,"wins":14},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":19,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":31,"wins":24},"google/gemini-3.6-flash":{"draws":28,"losses":49,"wins":15},"google/gemini-3.8-flash":{"draws":10,"losses":31,"wins":7},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":6},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":17,"wins":8},"gpt-5.4":{"draws":17,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":13,"wins":6},"gpt-5.4-nano":{"draws":17,"losses":20,"wins":11},"gpt-5.5":{"draws":19,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":38,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":5,"losses":41,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":19,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":10},"o3":{"draws":15,"losses":34,"wins":17},"openai/gpt-oss-120b":{"draws":17,"losses":17,"wins":8},"poolside/laguna-s-2.1":{"draws":18,"losses":14,"wins":14},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":16,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":21,"losses":22,"wins":5},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":91,"wins":35},"stealth/space-bunny-alpha":{"draws":14,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":12,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":9},"thinkingmachines/inkling":{"draws":25,"losses":17,"wins":22},"thinkingmachines/inkling-small":{"draws":19,"losses":13,"wins":16},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.5":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":34,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":43,"losses":31,"wins":22},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":15,"losses":24,"wins":9}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":16,"wins":16},"claude-fable-5":{"draws":9,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":28,"losses":49,"wins":37},"claude-opus-4-8":{"draws":17,"losses":38,"wins":23},"claude-opus-5":{"draws":17,"losses":82,"wins":9},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":13,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":26,"wins":9},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":25},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"fireworks/ember-1":{"draws":11,"losses":21,"wins":10},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":12},"google/gemini-3.1-flash-lite":{"draws":19,"losses":0,"wins":33},"google/gemini-3.5-flash":{"draws":18,"losses":27,"wins":17},"google/gemini-3.5-flash-lite":{"draws":32,"losses":31,"wins":31},"google/gemini-3.6-flash":{"draws":13,"losses":52,"wins":31},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":11},"gpt-4.1":{"draws":7,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":25,"wins":6},"gpt-5.4":{"draws":11,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":21,"losses":19,"wins":18},"gpt-5.4-nano":{"draws":14,"losses":35,"wins":25},"gpt-5.5":{"draws":18,"losses":32,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":11},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":10,"losses":19,"wins":13},"gpt-6-sol":{"draws":2,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":15},"inclusionai/ling-3.0-flash":{"draws":21,"losses":20,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":13,"wins":47},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":10,"losses":24,"wins":12},"meta/muse-spark-1.3":{"draws":7,"losses":28,"wins":9},"meta/muse-wonder":{"draws":7,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":10,"losses":16,"wins":18},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":3},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":7,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":24,"wins":21},"o3":{"draws":17,"losses":27,"wins":40},"openai/gpt-oss-120b":{"draws":9,"losses":9,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":24,"wins":21},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":23},"qwen/qwen3.7-plus":{"draws":10,"losses":12,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":25,"wins":8},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":11},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":9,"losses":27,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":36,"losses":62,"wins":50},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":15,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":21,"losses":17,"wins":40},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":13,"losses":33,"wins":18},"x-ai/grok-4.6":{"draws":12,"losses":29,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":21},"xiaomi/mimo-v2.5":{"draws":45,"losses":36,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":12,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":41,"losses":39,"wins":42},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":16,"wins":31},"claude-fable-5":{"draws":27,"losses":35,"wins":26},"claude-fable-5-1":{"draws":2,"losses":78,"wins":12},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":15},"claude-opus-4-5":{"draws":46,"losses":19,"wins":67},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":6,"losses":71,"wins":13},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":55,"losses":27,"wins":54},"claude-sonnet-5-5":{"draws":17,"losses":20,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":40,"losses":14,"wins":56},"deepseek/deepseek-v4-pro":{"draws":23,"losses":22,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":19,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":13,"wins":14},"fireworks/ember-1":{"draws":16,"losses":14,"wins":18},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":24,"losses":34,"wins":40},"google/gemini-3.5-flash-lite":{"draws":79,"losses":32,"wins":117},"google/gemini-3.6-flash":{"draws":71,"losses":77,"wins":84},"google/gemini-3.8-flash":{"draws":29,"losses":28,"wins":31},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":10,"wins":19},"gpt-5.4":{"draws":30,"losses":28,"wins":41},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":12,"wins":28},"gpt-5.5":{"draws":16,"losses":18,"wins":12},"gpt-5.6-luna":{"draws":55,"losses":20,"wins":65},"gpt-5.6-sol":{"draws":23,"losses":78,"wins":41},"gpt-5.6-terra":{"draws":35,"losses":16,"wins":35},"gpt-6-astra":{"draws":9,"losses":62,"wins":13},"gpt-6-luna":{"draws":15,"losses":12,"wins":21},"gpt-6-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":16,"losses":14,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":13,"wins":50},"meta/muse-glimmer-30b":{"draws":32,"losses":6,"wins":34},"meta/muse-spark-1.2":{"draws":33,"losses":22,"wins":45},"meta/muse-spark-1.3":{"draws":25,"losses":20,"wins":27},"meta/muse-wonder":{"draws":15,"losses":20,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":15},"mistralai/mistral-large-4-0":{"draws":12,"losses":5,"wins":13},"mistralai/mistral-medium-3-5":{"draws":20,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":24,"losses":27,"wins":57},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":2,"wins":22},"o3":{"draws":20,"losses":22,"wins":92},"openai/gpt-oss-120b":{"draws":38,"losses":10,"wins":26},"poolside/laguna-s-2.1":{"draws":31,"losses":10,"wins":45},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":38,"wins":28},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":24},"qwen/qwen3.8-flash":{"draws":16,"losses":15,"wins":25},"qwen/qwen3.8-max":{"draws":36,"losses":29,"wins":29},"qwen/qwen3.8-max-0902":{"draws":16,"losses":15,"wins":17},"stealth/ox-alpha":{"draws":89,"losses":78,"wins":109},"stealth/space-bunny-alpha":{"draws":15,"losses":6,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":3,"wins":11},"tencent/hy4-preview":{"draws":27,"losses":26,"wins":31},"thinkingmachines/inkling":{"draws":27,"losses":16,"wins":49},"thinkingmachines/inkling-small":{"draws":44,"losses":7,"wins":40},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":27,"losses":37,"wins":44},"x-ai/grok-4.6":{"draws":35,"losses":25,"wins":28},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":29,"losses":5,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":8,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":48,"losses":23,"wins":55},"z-ai/glm-5.3":{"draws":21,"losses":33,"wins":22},"z-ai/glm-5.3-flash":{"draws":20,"losses":34,"wins":30},"z-ai/glm-5.3-flashx":{"draws":13,"losses":20,"wins":15}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":20},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":39,"losses":54,"wins":49},"claude-opus-4-8":{"draws":20,"losses":30,"wins":36},"claude-opus-5":{"draws":20,"losses":106,"wins":16},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":18,"losses":13,"wins":23},"claude-sonnet-5-5":{"draws":8,"losses":27,"wins":13},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":24},"deepseek/deepseek-v4-flash":{"draws":33,"losses":13,"wins":48},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":18,"wins":15},"fireworks/ember-1":{"draws":14,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":15,"wins":18},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":36},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":27},"google/gemini-3.5-flash-lite":{"draws":38,"losses":13,"wins":61},"google/gemini-3.6-flash":{"draws":23,"losses":59,"wins":33},"google/gemini-3.8-flash":{"draws":10,"losses":33,"wins":17},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":14,"losses":7,"wins":15},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":19,"losses":15,"wins":44},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":22,"losses":39,"wins":39},"gpt-5.5":{"draws":41,"losses":26,"wins":13},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":13},"gpt-5.6-terra":{"draws":20,"losses":13,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":17,"wins":10},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":14,"wins":47},"meta/muse-glimmer-30b":{"draws":19,"losses":0,"wins":23},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":12},"meta/muse-wonder":{"draws":10,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":25,"losses":8,"wins":33},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":13,"wins":11},"moonshotai/kimi-k3":{"draws":20,"losses":15,"wins":27},"nex-agi/nex-n2-pro":{"draws":18,"losses":4,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":17,"wins":31},"o3":{"draws":13,"losses":34,"wins":37},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":30,"losses":12,"wins":42},"qwen/qwen3.7-max":{"draws":17,"losses":21,"wins":20},"qwen/qwen3.7-plus":{"draws":18,"losses":16,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":25,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":19,"losses":22,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":21,"wins":13},"stealth/ox-alpha":{"draws":36,"losses":77,"wins":53},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":16,"losses":21,"wins":13},"thinkingmachines/inkling":{"draws":31,"losses":18,"wins":35},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":19,"losses":36,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":14},"x-ai/grok-4.7":{"draws":7,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":12,"losses":10,"wins":22},"xiaomi/mimo-v2.5":{"draws":53,"losses":25,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":13,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":59,"losses":43,"wins":38},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":16,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":28,"wins":28},"claude-fable-5":{"draws":8,"losses":54,"wins":12},"claude-fable-5-1":{"draws":0,"losses":80,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":54,"losses":77,"wins":75},"claude-opus-4-8":{"draws":23,"losses":72,"wins":33},"claude-opus-5":{"draws":17,"losses":141,"wins":32},"claude-opus-5-5":{"draws":2,"losses":76,"wins":2},"claude-sonnet-5":{"draws":11,"losses":38,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":52,"wins":11},"cohere/north-mini-code":{"draws":16,"losses":11,"wins":31},"deepseek/deepseek-v4-flash":{"draws":35,"losses":46,"wins":53},"deepseek/deepseek-v4-pro":{"draws":10,"losses":37,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":32,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":37,"wins":21},"fireworks/ember-1":{"draws":16,"losses":35,"wins":21},"gemini-3.1-pro-preview":{"draws":14,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":22,"losses":19,"wins":73},"google/gemini-3.5-flash":{"draws":20,"losses":52,"wins":38},"google/gemini-3.5-flash-lite":{"draws":22,"losses":76,"wins":54},"google/gemini-3.6-flash":{"draws":31,"losses":96,"wins":39},"google/gemini-3.8-flash":{"draws":14,"losses":46,"wins":18},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":26},"gpt-4.1":{"draws":5,"losses":17,"wins":20},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":18,"losses":47,"wins":45},"gpt-5.4":{"draws":12,"losses":39,"wins":21},"gpt-5.4-mini":{"draws":16,"losses":29,"wins":55},"gpt-5.4-nano":{"draws":15,"losses":51,"wins":60},"gpt-5.5":{"draws":29,"losses":59,"wins":38},"gpt-5.6-luna":{"draws":14,"losses":33,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":56,"wins":10},"gpt-5.6-terra":{"draws":10,"losses":37,"wins":25},"gpt-6-astra":{"draws":1,"losses":70,"wins":1},"gpt-6-luna":{"draws":14,"losses":30,"wins":28},"gpt-6-sol":{"draws":12,"losses":56,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":67,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":7,"wins":33},"inclusionai/ling-3.0-flash":{"draws":25,"losses":25,"wins":30},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":42,"wins":81},"meta/muse-glimmer-30b":{"draws":13,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":32,"wins":26},"meta/muse-spark-1.3":{"draws":15,"losses":38,"wins":19},"meta/muse-wonder":{"draws":7,"losses":55,"wins":10},"minimax/minimax-m3":{"draws":20,"losses":24,"wins":42},"mistralai/mistral-large-4-0":{"draws":8,"losses":23,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":9,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":21,"wins":18},"moonshotai/kimi-k3":{"draws":23,"losses":39,"wins":24},"nex-agi/nex-n2-pro":{"draws":10,"losses":16,"wins":44},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":48,"wins":46},"o3":{"draws":12,"losses":66,"wins":76},"openai/gpt-oss-120b":{"draws":13,"losses":28,"wins":27},"poolside/laguna-s-2.1":{"draws":22,"losses":44,"wins":42},"qwen/qwen3.7-max":{"draws":17,"losses":35,"wins":32},"qwen/qwen3.7-plus":{"draws":20,"losses":37,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":44,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":25,"wins":21},"qwen/qwen3.8-flash":{"draws":13,"losses":22,"wins":17},"qwen/qwen3.8-max":{"draws":19,"losses":40,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":36,"wins":20},"stealth/ox-alpha":{"draws":34,"losses":111,"wins":69},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":11,"losses":18,"wins":41},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":23,"wins":20},"tencent/hy4-preview":{"draws":9,"losses":43,"wins":22},"thinkingmachines/inkling":{"draws":18,"losses":36,"wins":62},"thinkingmachines/inkling-small":{"draws":25,"losses":22,"wins":31},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":13},"x-ai/grok-4.5":{"draws":17,"losses":51,"wins":36},"x-ai/grok-4.6":{"draws":9,"losses":51,"wins":12},"x-ai/grok-4.7":{"draws":7,"losses":50,"wins":9},"x-ai/grok-build-0.1":{"draws":12,"losses":15,"wins":29},"xiaomi/mimo-v2.5":{"draws":60,"losses":74,"wins":108},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":32,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":25,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":31,"wins":11},"z-ai/glm-5.2":{"draws":45,"losses":79,"wins":92},"z-ai/glm-5.3":{"draws":7,"losses":51,"wins":14},"z-ai/glm-5.3-flash":{"draws":14,"losses":36,"wins":22},"z-ai/glm-5.3-flashx":{"draws":12,"losses":41,"wins":19}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":10,"wins":16},"claude-fable-5":{"draws":11,"losses":24,"wins":15},"claude-fable-5-1":{"draws":3,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":20,"losses":19,"wins":7},"claude-opus-4-5":{"draws":62,"losses":33,"wins":41},"claude-opus-4-8":{"draws":29,"losses":25,"wins":36},"claude-opus-5":{"draws":23,"losses":108,"wins":23},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":23,"losses":7,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":20},"deepseek/deepseek-v4-flash":{"draws":36,"losses":13,"wins":43},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":22},"google/gemini-3.1-flash-lite":{"draws":18,"losses":8,"wins":32},"google/gemini-3.5-flash":{"draws":20,"losses":19,"wins":29},"google/gemini-3.5-flash-lite":{"draws":46,"losses":12,"wins":44},"google/gemini-3.6-flash":{"draws":35,"losses":41,"wins":38},"google/gemini-3.8-flash":{"draws":18,"losses":20,"wins":12},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":11,"losses":7,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":25,"losses":21,"wins":34},"gpt-5.4":{"draws":15,"losses":16,"wins":15},"gpt-5.4-mini":{"draws":35,"losses":11,"wins":22},"gpt-5.4-nano":{"draws":31,"losses":43,"wins":32},"gpt-5.5":{"draws":22,"losses":20,"wins":20},"gpt-5.6-luna":{"draws":19,"losses":9,"wins":20},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":2,"losses":41,"wins":5},"gpt-6-luna":{"draws":21,"losses":9,"wins":18},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":7,"wins":14},"inclusionai/ling-3.0-flash":{"draws":26,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":27,"losses":20,"wins":39},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":17,"losses":4,"wins":31},"mistralai/mistral-large-4-0":{"draws":11,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":19,"losses":22,"wins":19},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":6,"wins":42},"o3":{"draws":21,"losses":24,"wins":35},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":28,"losses":17,"wins":27},"qwen/qwen3.7-max":{"draws":21,"losses":10,"wins":25},"qwen/qwen3.7-plus":{"draws":24,"losses":6,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":9,"wins":17},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"stealth/ox-alpha":{"draws":47,"losses":71,"wins":48},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":19,"losses":4,"wins":21},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":25,"losses":24,"wins":37},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":34,"wins":27},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":24,"losses":9,"wins":7},"xiaomi/mimo-v2.5":{"draws":56,"losses":17,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":12,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":13},"z-ai/glm-5.2":{"draws":59,"losses":29,"wins":48},"z-ai/glm-5.3":{"draws":17,"losses":24,"wins":9},"z-ai/glm-5.3-flash":{"draws":13,"losses":18,"wins":19},"z-ai/glm-5.3-flashx":{"draws":14,"losses":19,"wins":15}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":26,"wins":30},"claude-fable-5":{"draws":22,"losses":58,"wins":4},"claude-fable-5-1":{"draws":8,"losses":78,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":50,"losses":51,"wins":37},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":66,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":53,"losses":50,"wins":33},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":39,"losses":30,"wins":45},"deepseek/deepseek-v4-pro":{"draws":30,"losses":28,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":36,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":22,"wins":7},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":16,"losses":16,"wins":16},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":36,"losses":44,"wins":22},"google/gemini-3.5-flash-lite":{"draws":80,"losses":53,"wins":103},"google/gemini-3.6-flash":{"draws":70,"losses":108,"wins":52},"google/gemini-3.8-flash":{"draws":24,"losses":51,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":17,"wins":10},"gpt-5.4":{"draws":47,"losses":68,"wins":19},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":16,"losses":13,"wins":23},"gpt-5.5":{"draws":18,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":42,"losses":21,"wins":32},"gpt-5.6-sol":{"draws":25,"losses":91,"wins":16},"gpt-5.6-terra":{"draws":24,"losses":34,"wins":28},"gpt-6-astra":{"draws":10,"losses":63,"wins":1},"gpt-6-luna":{"draws":18,"losses":18,"wins":12},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":44,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":4,"wins":29},"inclusionai/ling-3.0-flash":{"draws":24,"losses":12,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":18,"wins":48},"meta/muse-glimmer-30b":{"draws":36,"losses":12,"wins":34},"meta/muse-spark-1.2":{"draws":30,"losses":45,"wins":27},"meta/muse-spark-1.3":{"draws":20,"losses":37,"wins":17},"meta/muse-wonder":{"draws":9,"losses":34,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":3,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":2},"mistralai/mistral-medium-3-5":{"draws":20,"losses":2,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":34,"losses":51,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":14},"o3":{"draws":29,"losses":52,"wins":57},"openai/gpt-oss-120b":{"draws":36,"losses":16,"wins":30},"poolside/laguna-s-2.1":{"draws":36,"losses":14,"wins":42},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":37,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":13},"qwen/qwen3.8-flash":{"draws":17,"losses":20,"wins":23},"qwen/qwen3.8-max":{"draws":33,"losses":33,"wins":19},"qwen/qwen3.8-max-0902":{"draws":19,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":100,"losses":114,"wins":70},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":47,"wins":10},"thinkingmachines/inkling":{"draws":37,"losses":20,"wins":45},"thinkingmachines/inkling-small":{"draws":42,"losses":19,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":29,"losses":46,"wins":27},"x-ai/grok-4.6":{"draws":28,"losses":45,"wins":9},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":9,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":50,"losses":45,"wins":43},"z-ai/glm-5.3":{"draws":17,"losses":44,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":43,"wins":15},"z-ai/glm-5.3-flashx":{"draws":16,"losses":22,"wins":10}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":16,"wins":46},"claude-fable-5":{"draws":14,"losses":37,"wins":33},"claude-fable-5-1":{"draws":10,"losses":87,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":29,"losses":27,"wins":84},"claude-opus-4-8":{"draws":3,"losses":24,"wins":25},"claude-opus-5":{"draws":19,"losses":70,"wins":21},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":19,"losses":25,"wins":101},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":19},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":70},"deepseek/deepseek-v4-pro":{"draws":5,"losses":17,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"fireworks/ember-1":{"draws":7,"losses":12,"wins":29},"gemini-3.1-pro-preview":{"draws":3,"losses":17,"wins":28},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":9,"losses":24,"wins":55},"google/gemini-3.5-flash-lite":{"draws":20,"losses":26,"wins":158},"google/gemini-3.6-flash":{"draws":29,"losses":68,"wins":113},"google/gemini-3.8-flash":{"draws":10,"losses":39,"wins":39},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":25,"losses":37,"wins":64},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":39},"gpt-5.5":{"draws":11,"losses":15,"wins":22},"gpt-5.6-luna":{"draws":12,"losses":23,"wins":83},"gpt-5.6-sol":{"draws":20,"losses":64,"wins":18},"gpt-5.6-terra":{"draws":23,"losses":13,"wins":48},"gpt-6-astra":{"draws":12,"losses":73,"wins":5},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":43},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":42},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":12,"wins":61},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":44},"meta/muse-spark-1.2":{"draws":10,"losses":30,"wins":62},"meta/muse-spark-1.3":{"draws":15,"losses":22,"wins":33},"meta/muse-wonder":{"draws":10,"losses":22,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":27,"losses":27,"wins":50},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":33},"o3":{"draws":16,"losses":20,"wins":94},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":48},"poolside/laguna-s-2.1":{"draws":14,"losses":3,"wins":71},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":50},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":27},"qwen/qwen3.8-flash":{"draws":9,"losses":11,"wins":32},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":38},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":29},"stealth/ox-alpha":{"draws":42,"losses":71,"wins":169},"stealth/space-bunny-alpha":{"draws":7,"losses":6,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":29},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":23,"wins":48},"thinkingmachines/inkling":{"draws":15,"losses":12,"wins":65},"thinkingmachines/inkling-small":{"draws":10,"losses":15,"wins":49},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":13,"losses":41,"wins":56},"x-ai/grok-4.6":{"draws":16,"losses":38,"wins":34},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":12,"losses":8,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":13,"losses":18,"wins":93},"z-ai/glm-5.3":{"draws":17,"losses":19,"wins":36},"z-ai/glm-5.3-flash":{"draws":19,"losses":32,"wins":35},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":26}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":19,"wins":34},"claude-fable-5":{"draws":19,"losses":58,"wins":17},"claude-fable-5-1":{"draws":9,"losses":87,"wins":4},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":35,"losses":33,"wins":38},"claude-opus-4-8":{"draws":14,"losses":21,"wins":13},"claude-opus-5":{"draws":5,"losses":80,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":26,"losses":26,"wins":34},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":40,"losses":19,"wins":45},"deepseek/deepseek-v4-pro":{"draws":33,"losses":26,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":27,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":14,"wins":16},"fireworks/ember-1":{"draws":13,"losses":20,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":16,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":21,"losses":28,"wins":43},"google/gemini-3.5-flash-lite":{"draws":44,"losses":29,"wins":73},"google/gemini-3.6-flash":{"draws":36,"losses":71,"wins":47},"google/gemini-3.8-flash":{"draws":26,"losses":29,"wins":33},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":13,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":26},"gpt-5.4":{"draws":29,"losses":39,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":27},"gpt-5.5":{"draws":14,"losses":18,"wins":12},"gpt-5.6-luna":{"draws":30,"losses":32,"wins":28},"gpt-5.6-sol":{"draws":22,"losses":51,"wins":17},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":19},"gpt-6-astra":{"draws":7,"losses":79,"wins":4},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":6,"losses":37,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":43,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":23,"losses":2,"wins":31},"inclusionai/ling-3.0-flash":{"draws":14,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":18,"wins":44},"meta/muse-glimmer-30b":{"draws":28,"losses":10,"wins":36},"meta/muse-spark-1.2":{"draws":21,"losses":25,"wins":28},"meta/muse-spark-1.3":{"draws":14,"losses":36,"wins":22},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":18},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":36,"wins":27},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":21},"o3":{"draws":18,"losses":39,"wins":45},"openai/gpt-oss-120b":{"draws":26,"losses":12,"wins":40},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":36},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":42,"wins":18},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":20},"qwen/qwen3.8-flash":{"draws":18,"losses":24,"wins":12},"qwen/qwen3.8-max":{"draws":36,"losses":28,"wins":24},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":13},"stealth/ox-alpha":{"draws":81,"losses":113,"wins":82},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":17,"losses":40,"wins":21},"thinkingmachines/inkling":{"draws":25,"losses":14,"wins":41},"thinkingmachines/inkling-small":{"draws":27,"losses":16,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":17,"losses":42,"wins":21},"x-ai/grok-4.6":{"draws":27,"losses":44,"wins":23},"x-ai/grok-4.7":{"draws":6,"losses":28,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":7},"xiaomi/mimo-v2.5":{"draws":27,"losses":4,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":55,"losses":33,"wins":56},"z-ai/glm-5.3":{"draws":17,"losses":46,"wins":11},"z-ai/glm-5.3-flash":{"draws":18,"losses":36,"wins":28},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":53},"claude-fable-5":{"draws":7,"losses":16,"wins":67},"claude-fable-5-1":{"draws":10,"losses":37,"wins":61},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":9,"losses":2,"wins":95},"claude-opus-4-8":{"draws":2,"losses":2,"wins":42},"claude-opus-5":{"draws":11,"losses":27,"wins":52},"claude-opus-5-5":{"draws":4,"losses":24,"wins":24},"claude-sonnet-5":{"draws":2,"losses":0,"wins":84},"claude-sonnet-5-5":{"draws":6,"losses":9,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":2,"wins":87},"deepseek/deepseek-v4-pro":{"draws":0,"losses":7,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":3,"wins":41},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":5,"losses":2,"wins":41},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":9,"losses":8,"wins":77},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":115},"google/gemini-3.6-flash":{"draws":10,"losses":13,"wins":117},"google/gemini-3.8-flash":{"draws":9,"losses":4,"wins":81},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":28},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":1,"wins":37},"gpt-5.4":{"draws":5,"losses":10,"wins":69},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":2,"losses":3,"wins":41},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":64},"gpt-5.6-sol":{"draws":10,"losses":15,"wins":69},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":74},"gpt-6-astra":{"draws":8,"losses":42,"wins":14},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":6,"losses":7,"wins":35},"gpt-6.1-sol":{"draws":7,"losses":19,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":34},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":35},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":56},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":45},"meta/muse-spark-1.2":{"draws":6,"losses":1,"wins":61},"meta/muse-spark-1.3":{"draws":11,"losses":4,"wins":55},"meta/muse-wonder":{"draws":3,"losses":6,"wins":39},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":9,"losses":6,"wins":57},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"o3":{"draws":3,"losses":0,"wins":93},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":46},"poolside/laguna-s-2.1":{"draws":5,"losses":0,"wins":55},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":26},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":4,"wins":75},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":43},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":46},"qwen/qwen3.8-max":{"draws":10,"losses":0,"wins":70},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"stealth/ox-alpha":{"draws":40,"losses":16,"wins":226},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":70},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":67},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":61},"unbiased/pareto-26.10-preview":{"draws":3,"losses":8,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":8,"wins":65},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":71},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":29},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":1,"wins":26},"z-ai/glm-5.2":{"draws":8,"losses":3,"wins":105},"z-ai/glm-5.3":{"draws":11,"losses":6,"wins":57},"z-ai/glm-5.3-flash":{"draws":11,"losses":4,"wins":71},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":41}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":23,"wins":9},"claude-opus-4-5":{"draws":31,"losses":33,"wins":14},"claude-opus-4-8":{"draws":11,"losses":22,"wins":11},"claude-opus-5":{"draws":19,"losses":57,"wins":6},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":14,"losses":22,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":32,"losses":13,"wins":27},"deepseek/deepseek-v4-pro":{"draws":16,"losses":10,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":17,"losses":21,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":26,"wins":15},"google/gemini-3.5-flash-lite":{"draws":31,"losses":21,"wins":32},"google/gemini-3.6-flash":{"draws":30,"losses":51,"wins":11},"google/gemini-3.8-flash":{"draws":19,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":15,"wins":10},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":22,"losses":17,"wins":5},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":9,"losses":13,"wins":10},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":4,"losses":44,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":16,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":16,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":11,"wins":14},"o3":{"draws":16,"losses":19,"wins":31},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-27b":{"draws":11,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":38,"losses":76,"wins":44},"stealth/space-bunny-alpha":{"draws":15,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":23},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":6,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.6":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":32,"losses":9,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":23,"wins":29},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":16,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":7,"losses":13,"wins":28},"claude-fable-5-1":{"draws":7,"losses":37,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":5,"wins":28},"claude-opus-4-5":{"draws":18,"losses":5,"wins":55},"claude-opus-4-8":{"draws":10,"losses":7,"wins":27},"claude-opus-5":{"draws":11,"losses":36,"wins":35},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":26},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":5,"losses":2,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":7,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":29},"fireworks/ember-1":{"draws":7,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":39},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":3,"wins":44},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":57},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":63},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":32},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":32},"gpt-5.4":{"draws":7,"losses":7,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":10,"losses":5,"wins":33},"gpt-5.5":{"draws":7,"losses":9,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":27},"gpt-5.6-terra":{"draws":10,"losses":4,"wins":32},"gpt-6-astra":{"draws":8,"losses":30,"wins":10},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":6,"losses":12,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":31,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":45},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":11,"losses":6,"wins":31},"meta/muse-wonder":{"draws":4,"losses":16,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":7,"losses":7,"wins":32},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"o3":{"draws":6,"losses":3,"wins":57},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":35},"poolside/laguna-s-2.1":{"draws":11,"losses":2,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":9,"wins":34},"qwen/qwen3.8-27b":{"draws":9,"losses":4,"wins":21},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":35},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":35},"stealth/ox-alpha":{"draws":23,"losses":19,"wins":116},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":6,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":4,"wins":51},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":9,"wins":33},"x-ai/grok-4.6":{"draws":7,"losses":9,"wins":32},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":15,"losses":3,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":17,"losses":6,"wins":73},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":7,"losses":10,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":4,"losses":9,"wins":35},"claude-fable-5-1":{"draws":3,"losses":21,"wins":30},"claude-haiku-5-5":{"draws":5,"losses":4,"wins":37},"claude-opus-4-5":{"draws":2,"losses":5,"wins":71},"claude-opus-4-8":{"draws":2,"losses":5,"wins":37},"claude-opus-5":{"draws":11,"losses":26,"wins":45},"claude-opus-5-5":{"draws":3,"losses":28,"wins":21},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":65},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"fireworks/ember-1":{"draws":0,"losses":8,"wins":40},"gemini-3.1-pro-preview":{"draws":4,"losses":3,"wins":41},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":51},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":7,"wins":79},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":38},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":2,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":29},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":45},"gpt-5.5":{"draws":1,"losses":6,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":5,"losses":26,"wins":17},"gpt-6-luna":{"draws":1,"losses":1,"wins":46},"gpt-6-sol":{"draws":5,"losses":10,"wins":33},"gpt-6.1-sol":{"draws":2,"losses":16,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":38},"meta/muse-wonder":{"draws":7,"losses":11,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":23},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":38},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"o3":{"draws":1,"losses":0,"wins":65},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":41},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":7,"wins":38},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":0,"losses":3,"wins":29},"qwen/qwen3.8-max":{"draws":5,"losses":4,"wins":39},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":45},"stealth/ox-alpha":{"draws":14,"losses":8,"wins":136},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":23},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":42},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":40},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":21},"z-ai/glm-5.2":{"draws":11,"losses":5,"wins":80},"z-ai/glm-5.3":{"draws":8,"losses":7,"wins":31},"z-ai/glm-5.3-flash":{"draws":5,"losses":5,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":4,"wins":1},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":9,"losses":1,"wins":0},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":4,"losses":6,"wins":2},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":9,"losses":3,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":2},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":0},"gpt-5.5":{"draws":3,"losses":1,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":2},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":0},"o3":{"draws":4,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":8,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":1},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":22,"wins":14},"claude-fable-5":{"draws":14,"losses":32,"wins":0},"claude-fable-5-1":{"draws":4,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":26,"losses":51,"wins":1},"claude-opus-4-8":{"draws":11,"losses":24,"wins":1},"claude-opus-5":{"draws":7,"losses":49,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":27,"losses":33,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":9,"wins":6},"deepseek/deepseek-v4-flash":{"draws":38,"losses":35,"wins":9},"deepseek/deepseek-v4-pro":{"draws":26,"losses":30,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":26,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":16,"losses":20,"wins":0},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":10,"wins":10},"google/gemini-3.5-flash":{"draws":21,"losses":40,"wins":7},"google/gemini-3.5-flash-lite":{"draws":53,"losses":56,"wins":15},"google/gemini-3.6-flash":{"draws":39,"losses":61,"wins":4},"google/gemini-3.8-flash":{"draws":22,"losses":27,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":2},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":24,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":26,"wins":3},"gpt-5.5":{"draws":14,"losses":16,"wins":2},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":10},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":0},"gpt-5.6-terra":{"draws":30,"losses":30,"wins":0},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":5,"losses":30,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":18,"losses":11,"wins":5},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":23,"wins":15},"meta/muse-glimmer-30b":{"draws":32,"losses":20,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":29,"wins":5},"meta/muse-spark-1.3":{"draws":16,"losses":33,"wins":1},"meta/muse-wonder":{"draws":10,"losses":25,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":1},"mistralai/mistral-medium-3-5":{"draws":23,"losses":14,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":26,"losses":30,"wins":0},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":12,"wins":7},"o3":{"draws":19,"losses":50,"wins":7},"openai/gpt-oss-120b":{"draws":26,"losses":26,"wins":6},"poolside/laguna-s-2.1":{"draws":24,"losses":11,"wins":11},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":20,"wins":2},"qwen/qwen3.8-flash":{"draws":22,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":24,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":15,"losses":16,"wins":5},"stealth/ox-alpha":{"draws":50,"losses":98,"wins":10},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":21,"losses":27,"wins":6},"thinkingmachines/inkling":{"draws":24,"losses":23,"wins":11},"thinkingmachines/inkling-small":{"draws":31,"losses":25,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":18,"losses":33,"wins":1},"x-ai/grok-4.6":{"draws":14,"losses":39,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":29,"losses":25,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":15,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":38,"losses":55,"wins":7},"z-ai/glm-5.3":{"draws":19,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":20,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":2}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":24,"wins":12},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":2,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":1},"claude-opus-4-5":{"draws":38,"losses":54,"wins":28},"claude-opus-4-8":{"draws":18,"losses":26,"wins":0},"claude-opus-5":{"draws":15,"losses":46,"wins":3},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":32,"losses":61,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":15},"deepseek/deepseek-v4-flash":{"draws":29,"losses":33,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":34,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":24,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":3},"fireworks/ember-1":{"draws":13,"losses":19,"wins":4},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":43,"wins":11},"google/gemini-3.5-flash-lite":{"draws":63,"losses":116,"wins":51},"google/gemini-3.6-flash":{"draws":77,"losses":107,"wins":36},"google/gemini-3.8-flash":{"draws":10,"losses":41,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":8},"gpt-4.1":{"draws":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":22,"wins":4},"gpt-5.4":{"draws":18,"losses":52,"wins":18},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":16},"gpt-5.5":{"draws":11,"losses":21,"wins":6},"gpt-5.6-luna":{"draws":31,"losses":33,"wins":36},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":37,"wins":8},"gpt-6-astra":{"draws":3,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":6},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":10,"wins":22},"inclusionai/ling-3.0-flash":{"draws":8,"losses":16,"wins":16},"meituan/longcat-2.0":{"draws":32,"losses":45,"wins":39},"meta/muse-glimmer-30b":{"draws":28,"losses":20,"wins":12},"meta/muse-spark-1.2":{"draws":28,"losses":30,"wins":16},"meta/muse-spark-1.3":{"draws":5,"losses":39,"wins":8},"meta/muse-wonder":{"draws":9,"losses":27,"wins":0},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":17,"losses":9,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":24,"losses":52,"wins":20},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":15},"o3":{"draws":4,"losses":101,"wins":29},"openai/gpt-oss-120b":{"draws":16,"losses":32,"wins":12},"poolside/laguna-s-2.1":{"draws":25,"losses":33,"wins":10},"qwen/qwen3.7-max":{"draws":13,"losses":25,"wins":2},"qwen/qwen3.7-plus":{"draws":11,"losses":12,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":34,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":25,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":24,"wins":9},"qwen/qwen3.8-max":{"draws":26,"losses":27,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"stealth/ox-alpha":{"draws":33,"losses":103,"wins":30},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":16,"wins":7},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":13,"losses":40,"wins":7},"thinkingmachines/inkling":{"draws":40,"losses":30,"wins":22},"thinkingmachines/inkling-small":{"draws":26,"losses":30,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":33,"losses":67,"wins":10},"x-ai/grok-4.6":{"draws":18,"losses":34,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":13,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":26,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":21,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":2},"z-ai/glm-5.2":{"draws":28,"losses":43,"wins":25},"z-ai/glm-5.3":{"draws":9,"losses":39,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":39,"wins":3},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":50,"wins":32},"claude-fable-5":{"draws":22,"losses":68,"wins":20},"claude-fable-5-1":{"draws":6,"losses":98,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":44,"wins":11},"claude-opus-4-5":{"draws":57,"losses":138,"wins":45},"claude-opus-4-8":{"draws":21,"losses":46,"wins":13},"claude-opus-5":{"draws":22,"losses":116,"wins":18},"claude-opus-5-5":{"draws":6,"losses":69,"wins":5},"claude-sonnet-5":{"draws":57,"losses":114,"wins":23},"claude-sonnet-5-5":{"draws":9,"losses":46,"wins":17},"cohere/north-mini-code":{"draws":12,"losses":12,"wins":26},"deepseek/deepseek-v4-flash":{"draws":49,"losses":65,"wins":38},"deepseek/deepseek-v4-pro":{"draws":33,"losses":64,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":58,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":41,"wins":14},"fireworks/ember-1":{"draws":17,"losses":41,"wins":14},"gemini-3.1-pro-preview":{"draws":13,"losses":36,"wins":23},"google/gemini-3.1-flash-lite":{"draws":13,"losses":17,"wins":38},"google/gemini-3.5-flash":{"draws":36,"losses":82,"wins":24},"google/gemini-3.5-flash-lite":{"draws":102,"losses":178,"wins":172},"google/gemini-3.6-flash":{"draws":101,"losses":237,"wins":58},"google/gemini-3.8-flash":{"draws":29,"losses":61,"wins":18},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":10,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":24,"losses":37,"wins":11},"gpt-5.4":{"draws":50,"losses":101,"wins":27},"gpt-5.4-mini":{"draws":21,"losses":26,"wins":19},"gpt-5.4-nano":{"draws":14,"losses":49,"wins":27},"gpt-5.5":{"draws":22,"losses":53,"wins":15},"gpt-5.6-luna":{"draws":58,"losses":84,"wins":58},"gpt-5.6-sol":{"draws":33,"losses":131,"wins":22},"gpt-5.6-terra":{"draws":35,"losses":59,"wins":30},"gpt-6-astra":{"draws":5,"losses":91,"wins":4},"gpt-6-luna":{"draws":15,"losses":40,"wins":17},"gpt-6-sol":{"draws":4,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":64,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":23,"wins":41},"inclusionai/ling-3.0-flash":{"draws":42,"losses":27,"wins":47},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":38,"wins":42},"meta/muse-glimmer-30b":{"draws":36,"losses":42,"wins":36},"meta/muse-spark-1.2":{"draws":36,"losses":72,"wins":44},"meta/muse-spark-1.3":{"draws":27,"losses":61,"wins":14},"meta/muse-wonder":{"draws":11,"losses":51,"wins":10},"minimax/minimax-m3":{"draws":9,"losses":19,"wins":24},"mistralai/mistral-large-4-0":{"draws":16,"losses":19,"wins":9},"mistralai/mistral-medium-3-5":{"draws":32,"losses":17,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":6},"moonshotai/kimi-k3":{"draws":52,"losses":112,"wins":24},"nex-agi/nex-n2-pro":{"draws":11,"losses":18,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":24,"wins":28},"o3":{"draws":28,"losses":172,"wins":70},"openai/gpt-oss-120b":{"draws":42,"losses":24,"wins":48},"poolside/laguna-s-2.1":{"draws":55,"losses":42,"wins":65},"qwen/qwen3.7-max":{"draws":14,"losses":35,"wins":7},"qwen/qwen3.7-plus":{"draws":12,"losses":17,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":71,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":42,"wins":11},"qwen/qwen3.8-flash":{"draws":29,"losses":35,"wins":18},"qwen/qwen3.8-max":{"draws":41,"losses":70,"wins":18},"qwen/qwen3.8-max-0902":{"draws":11,"losses":52,"wins":9},"stealth/ox-alpha":{"draws":93,"losses":221,"wins":56},"stealth/space-bunny-alpha":{"draws":18,"losses":24,"wins":18},"stepfun/step-3.7-flash":{"draws":16,"losses":26,"wins":10},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":13},"tencent/hy4-preview":{"draws":38,"losses":65,"wins":15},"thinkingmachines/inkling":{"draws":45,"losses":68,"wins":55},"thinkingmachines/inkling-small":{"draws":35,"losses":44,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":8,"wins":7},"x-ai/grok-4.5":{"draws":45,"losses":129,"wins":34},"x-ai/grok-4.6":{"draws":29,"losses":66,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":56,"wins":3},"x-ai/grok-build-0.1":{"draws":14,"losses":16,"wins":10},"xiaomi/mimo-v2.5":{"draws":50,"losses":40,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":16,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":24,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":38,"wins":5},"z-ai/glm-5.2":{"draws":52,"losses":90,"wins":58},"z-ai/glm-5.3":{"draws":26,"losses":63,"wins":11},"z-ai/glm-5.3-flash":{"draws":24,"losses":65,"wins":23},"z-ai/glm-5.3-flashx":{"draws":20,"losses":45,"wins":7}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":28,"wins":24},"claude-fable-5":{"draws":18,"losses":40,"wins":4},"claude-fable-5-1":{"draws":5,"losses":55,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":28,"wins":4},"claude-opus-4-5":{"draws":37,"losses":49,"wins":16},"claude-opus-4-8":{"draws":13,"losses":26,"wins":5},"claude-opus-5":{"draws":4,"losses":71,"wins":9},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":33,"losses":40,"wins":11},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":57,"losses":41,"wins":14},"deepseek/deepseek-v4-pro":{"draws":26,"losses":38,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":43,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":31,"wins":3},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":20,"losses":24,"wins":4},"google/gemini-3.1-flash-lite":{"draws":14,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":30,"losses":50,"wins":12},"google/gemini-3.5-flash-lite":{"draws":77,"losses":62,"wins":27},"google/gemini-3.6-flash":{"draws":51,"losses":82,"wins":13},"google/gemini-3.8-flash":{"draws":21,"losses":41,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":21,"wins":9},"gpt-5.4":{"draws":21,"losses":35,"wins":12},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":22,"wins":17},"gpt-5.5":{"draws":14,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":36,"losses":34,"wins":18},"gpt-5.6-sol":{"draws":11,"losses":48,"wins":3},"gpt-5.6-terra":{"draws":28,"losses":40,"wins":14},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":16,"losses":27,"wins":5},"gpt-6-sol":{"draws":10,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":34,"losses":18,"wins":16},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":23,"wins":23},"meta/muse-glimmer-30b":{"draws":25,"losses":11,"wins":12},"meta/muse-spark-1.2":{"draws":18,"losses":34,"wins":14},"meta/muse-spark-1.3":{"draws":24,"losses":37,"wins":7},"meta/muse-wonder":{"draws":8,"losses":34,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":12,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":26,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":20,"losses":41,"wins":9},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":14,"wins":7},"o3":{"draws":22,"losses":67,"wins":7},"openai/gpt-oss-120b":{"draws":40,"losses":26,"wins":14},"poolside/laguna-s-2.1":{"draws":37,"losses":22,"wins":13},"qwen/qwen3.7-max":{"draws":11,"losses":15,"wins":4},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":50,"wins":4},"qwen/qwen3.8-27b":{"draws":12,"losses":24,"wins":4},"qwen/qwen3.8-flash":{"draws":22,"losses":18,"wins":12},"qwen/qwen3.8-max":{"draws":24,"losses":37,"wins":15},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"stealth/ox-alpha":{"draws":72,"losses":150,"wins":26},"stealth/space-bunny-alpha":{"draws":14,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":23,"losses":48,"wins":5},"thinkingmachines/inkling":{"draws":30,"losses":27,"wins":25},"thinkingmachines/inkling-small":{"draws":42,"losses":26,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":16,"losses":45,"wins":7},"x-ai/grok-4.6":{"draws":24,"losses":38,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":24,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":16,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":58,"losses":50,"wins":22},"z-ai/glm-5.3":{"draws":13,"losses":40,"wins":7},"z-ai/glm-5.3-flash":{"draws":26,"losses":43,"wins":9},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":19,"wins":28},"claude-fable-5":{"draws":13,"losses":43,"wins":24},"claude-fable-5-1":{"draws":3,"losses":75,"wins":10},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":32,"losses":22,"wins":68},"claude-opus-4-8":{"draws":10,"losses":16,"wins":16},"claude-opus-5":{"draws":13,"losses":62,"wins":15},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":39,"losses":33,"wins":48},"claude-sonnet-5-5":{"draws":14,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":29,"losses":8,"wins":49},"deepseek/deepseek-v4-pro":{"draws":10,"losses":27,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":17,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":11,"wins":18},"fireworks/ember-1":{"draws":11,"losses":12,"wins":19},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":19},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":21,"losses":24,"wins":43},"google/gemini-3.5-flash-lite":{"draws":51,"losses":26,"wins":121},"google/gemini-3.6-flash":{"draws":33,"losses":52,"wins":113},"google/gemini-3.8-flash":{"draws":10,"losses":23,"wins":41},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":15,"losses":11,"wins":22},"gpt-5.4":{"draws":28,"losses":43,"wins":41},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":26},"gpt-5.5":{"draws":9,"losses":15,"wins":16},"gpt-5.6-luna":{"draws":36,"losses":17,"wins":65},"gpt-5.6-sol":{"draws":13,"losses":71,"wins":40},"gpt-5.6-terra":{"draws":33,"losses":16,"wins":31},"gpt-6-astra":{"draws":8,"losses":68,"wins":2},"gpt-6-luna":{"draws":15,"losses":7,"wins":20},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":31,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":24,"losses":13,"wins":45},"meta/muse-glimmer-30b":{"draws":17,"losses":4,"wins":41},"meta/muse-spark-1.2":{"draws":15,"losses":12,"wins":29},"meta/muse-spark-1.3":{"draws":15,"losses":18,"wins":29},"meta/muse-wonder":{"draws":8,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":10,"losses":8,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":20,"losses":33,"wins":35},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":2,"wins":23},"o3":{"draws":16,"losses":40,"wins":56},"openai/gpt-oss-120b":{"draws":22,"losses":4,"wins":38},"poolside/laguna-s-2.1":{"draws":27,"losses":9,"wins":46},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":23},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":26,"wins":28},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":11},"qwen/qwen3.8-flash":{"draws":18,"losses":13,"wins":19},"qwen/qwen3.8-max":{"draws":25,"losses":25,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":16},"stealth/ox-alpha":{"draws":68,"losses":107,"wins":77},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":16},"tencent/hy4-preview":{"draws":16,"losses":28,"wins":26},"thinkingmachines/inkling":{"draws":24,"losses":8,"wins":52},"thinkingmachines/inkling-small":{"draws":28,"losses":6,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":22,"losses":44,"wins":32},"x-ai/grok-4.6":{"draws":21,"losses":37,"wins":24},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":15},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":22,"losses":33,"wins":65},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":24},"z-ai/glm-5.3-flash":{"draws":13,"losses":29,"wins":32},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":11,"wins":42},"claude-fable-5":{"draws":16,"losses":42,"wins":32},"claude-fable-5-1":{"draws":7,"losses":90,"wins":11},"claude-haiku-5-5":{"draws":4,"losses":19,"wins":23},"claude-opus-4-5":{"draws":18,"losses":18,"wins":74},"claude-opus-4-8":{"draws":8,"losses":15,"wins":25},"claude-opus-5":{"draws":16,"losses":57,"wins":27},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":22,"losses":17,"wins":45},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":11,"wins":74},"deepseek/deepseek-v4-pro":{"draws":8,"losses":15,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":23},"fireworks/ember-1":{"draws":11,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":10,"losses":19,"wins":71},"google/gemini-3.5-flash-lite":{"draws":16,"losses":20,"wins":88},"google/gemini-3.6-flash":{"draws":24,"losses":49,"wins":73},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":50},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":5,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":8,"losses":8,"wins":34},"gpt-5.4":{"draws":13,"losses":33,"wins":36},"gpt-5.4-mini":{"draws":5,"losses":5,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":48},"gpt-5.6-sol":{"draws":19,"losses":40,"wins":35},"gpt-5.6-terra":{"draws":24,"losses":17,"wins":45},"gpt-6-astra":{"draws":11,"losses":77,"wins":8},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":8,"losses":33,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":34,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":6,"wins":28},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":52},"meta/muse-glimmer-30b":{"draws":14,"losses":1,"wins":41},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":35},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":21},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":23},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":15,"wins":51},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":32},"o3":{"draws":5,"losses":18,"wins":75},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":43},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":41},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":2,"losses":10,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":36,"wins":39},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":26},"qwen/qwen3.8-flash":{"draws":15,"losses":12,"wins":31},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":50},"qwen/qwen3.8-max-0902":{"draws":9,"losses":14,"wins":25},"stealth/ox-alpha":{"draws":50,"losses":86,"wins":144},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":23},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":44},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":60},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":28,"wins":42},"x-ai/grok-4.6":{"draws":15,"losses":39,"wins":36},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":14,"losses":1,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":25,"losses":24,"wins":73},"z-ai/glm-5.3":{"draws":9,"losses":35,"wins":30},"z-ai/glm-5.3-flash":{"draws":16,"losses":33,"wins":39},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":9,"losses":16,"wins":23},"claude-fable-5-1":{"draws":4,"losses":44,"wins":6},"claude-haiku-5-5":{"draws":8,"losses":11,"wins":27},"claude-opus-4-5":{"draws":11,"losses":22,"wins":45},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":7,"losses":53,"wins":22},"claude-opus-5-5":{"draws":5,"losses":37,"wins":10},"claude-sonnet-5":{"draws":8,"losses":13,"wins":27},"claude-sonnet-5-5":{"draws":6,"losses":23,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"fireworks/ember-1":{"draws":8,"losses":15,"wins":25},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":40},"google/gemini-3.5-flash-lite":{"draws":15,"losses":10,"wins":59},"google/gemini-3.6-flash":{"draws":16,"losses":29,"wins":47},"google/gemini-3.8-flash":{"draws":10,"losses":10,"wins":28},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":19},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":36},"gpt-5.5":{"draws":11,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":21},"gpt-5.6-terra":{"draws":3,"losses":16,"wins":27},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":9,"losses":14,"wins":25},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":33,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-wonder":{"draws":5,"losses":13,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":18},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":26},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":28},"o3":{"draws":2,"losses":14,"wins":50},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":13,"losses":12,"wins":23},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":27},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":82},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":20},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":8,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":6,"wins":31},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.6":{"draws":11,"losses":15,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":12,"losses":9,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":15,"wins":14},"z-ai/glm-5.2":{"draws":23,"losses":15,"wins":58},"z-ai/glm-5.3":{"draws":9,"losses":17,"wins":20},"z-ai/glm-5.3-flash":{"draws":8,"losses":12,"wins":28},"z-ai/glm-5.3-flashx":{"draws":11,"losses":13,"wins":24}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":15,"wins":9},"claude-fable-5":{"draws":10,"losses":31,"wins":1},"claude-fable-5-1":{"draws":1,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":34,"losses":62,"wins":6},"claude-opus-4-8":{"draws":25,"losses":37,"wins":4},"claude-opus-5":{"draws":9,"losses":76,"wins":5},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":13,"losses":28,"wins":5},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":2},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":12},"deepseek/deepseek-v4-flash":{"draws":37,"losses":36,"wins":27},"deepseek/deepseek-v4-pro":{"draws":11,"losses":26,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":32,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":12,"losses":29,"wins":1},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":7},"google/gemini-3.1-flash-lite":{"draws":19,"losses":40,"wins":23},"google/gemini-3.5-flash":{"draws":22,"losses":28,"wins":8},"google/gemini-3.5-flash-lite":{"draws":31,"losses":46,"wins":19},"google/gemini-3.6-flash":{"draws":28,"losses":53,"wins":11},"google/gemini-3.8-flash":{"draws":15,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":7},"gpt-4.1":{"draws":14,"losses":12,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":26,"losses":30,"wins":12},"gpt-5.4":{"draws":13,"losses":25,"wins":2},"gpt-5.4-mini":{"draws":22,"losses":32,"wins":16},"gpt-5.4-nano":{"draws":27,"losses":56,"wins":17},"gpt-5.5":{"draws":25,"losses":31,"wins":6},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":24,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":13,"losses":24,"wins":5},"gpt-6-sol":{"draws":7,"losses":33,"wins":2},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":36,"losses":15,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":41,"wins":22},"meta/muse-glimmer-30b":{"draws":16,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":33,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":33,"wins":2},"meta/muse-wonder":{"draws":8,"losses":30,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":2},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":11,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":17,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":26,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":13,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":27,"wins":13},"o3":{"draws":19,"losses":49,"wins":12},"openai/gpt-oss-120b":{"draws":16,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":32,"losses":30,"wins":10},"qwen/qwen3.7-max":{"draws":21,"losses":24,"wins":13},"qwen/qwen3.7-plus":{"draws":11,"losses":22,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":11,"losses":14,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":30,"losses":87,"wins":9},"stealth/space-bunny-alpha":{"draws":11,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":24,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":27,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":37,"wins":14},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":46,"wins":2},"x-ai/grok-4.6":{"draws":15,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":16,"losses":18,"wins":4},"xiaomi/mimo-v2.5":{"draws":62,"losses":55,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":24,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":47,"losses":60,"wins":9},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":5},"z-ai/glm-5.3-flashx":{"draws":14,"losses":26,"wins":2}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":16},"claude-fable-5":{"draws":9,"losses":21,"wins":8},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":29,"losses":50,"wins":29},"claude-opus-4-8":{"draws":16,"losses":32,"wins":14},"claude-opus-5":{"draws":13,"losses":112,"wins":7},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":10,"losses":9,"wins":17},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":12},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"fireworks/ember-1":{"draws":12,"losses":13,"wins":11},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":36},"google/gemini-3.5-flash":{"draws":13,"losses":16,"wins":19},"google/gemini-3.5-flash-lite":{"draws":18,"losses":21,"wins":33},"google/gemini-3.6-flash":{"draws":26,"losses":43,"wins":19},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":16},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":11,"losses":8,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":21,"wins":24},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":16,"losses":11,"wins":25},"gpt-5.4-nano":{"draws":14,"losses":28,"wins":28},"gpt-5.5":{"draws":30,"losses":17,"wins":19},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":12},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":12,"losses":14,"wins":10},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":10,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":15},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":25},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":12,"wins":20},"nex-agi/nex-n2-pro":{"draws":12,"losses":1,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":7,"wins":33},"o3":{"draws":7,"losses":29,"wins":34},"openai/gpt-oss-120b":{"draws":9,"losses":8,"wins":17},"poolside/laguna-s-2.1":{"draws":17,"losses":28,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":16,"wins":12},"qwen/qwen3.7-plus":{"draws":21,"losses":4,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":25,"losses":50,"wins":31},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":12,"losses":10,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":8},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":34},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":24,"wins":8},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":22},"xiaomi/mimo-v2.5":{"draws":50,"losses":22,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":5,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":23,"losses":43,"wins":42},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":37},"claude-fable-5":{"draws":25,"losses":55,"wins":2},"claude-fable-5-1":{"draws":10,"losses":80,"wins":4},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":60,"losses":56,"wins":44},"claude-opus-4-8":{"draws":15,"losses":20,"wins":17},"claude-opus-5":{"draws":20,"losses":81,"wins":9},"claude-opus-5-5":{"draws":2,"losses":44,"wins":6},"claude-sonnet-5":{"draws":52,"losses":37,"wins":51},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":33,"losses":23,"wins":52},"deepseek/deepseek-v4-pro":{"draws":24,"losses":24,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":28,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":15,"wins":13},"fireworks/ember-1":{"draws":19,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":39,"losses":36,"wins":27},"google/gemini-3.5-flash-lite":{"draws":102,"losses":60,"wins":132},"google/gemini-3.6-flash":{"draws":94,"losses":118,"wins":78},"google/gemini-3.8-flash":{"draws":35,"losses":48,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":17,"wins":14},"gpt-5.4":{"draws":41,"losses":80,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":12,"wins":16},"gpt-5.4-nano":{"draws":16,"losses":18,"wins":30},"gpt-5.5":{"draws":26,"losses":17,"wins":15},"gpt-5.6-luna":{"draws":52,"losses":33,"wins":51},"gpt-5.6-sol":{"draws":24,"losses":86,"wins":24},"gpt-5.6-terra":{"draws":33,"losses":26,"wins":27},"gpt-6-astra":{"draws":3,"losses":76,"wins":7},"gpt-6-luna":{"draws":18,"losses":15,"wins":15},"gpt-6-sol":{"draws":6,"losses":34,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":38,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":4,"wins":30},"inclusionai/ling-3.0-flash":{"draws":18,"losses":12,"wins":42},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":40,"losses":10,"wins":66},"meta/muse-glimmer-30b":{"draws":30,"losses":14,"wins":28},"meta/muse-spark-1.2":{"draws":24,"losses":37,"wins":39},"meta/muse-spark-1.3":{"draws":19,"losses":39,"wins":18},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":17},"mistralai/mistral-large-4-0":{"draws":14,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":25,"losses":5,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":11,"wins":3},"moonshotai/kimi-k3":{"draws":31,"losses":26,"wins":19},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":10,"wins":19},"o3":{"draws":26,"losses":76,"wins":64},"openai/gpt-oss-120b":{"draws":28,"losses":10,"wins":36},"poolside/laguna-s-2.1":{"draws":43,"losses":9,"wins":58},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":10,"losses":10,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":36,"wins":22},"qwen/qwen3.8-27b":{"draws":14,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":25,"losses":9,"wins":26},"qwen/qwen3.8-max":{"draws":32,"losses":27,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":77,"losses":122,"wins":91},"stealth/space-bunny-alpha":{"draws":16,"losses":7,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":28,"losses":30,"wins":26},"thinkingmachines/inkling":{"draws":39,"losses":15,"wins":60},"thinkingmachines/inkling-small":{"draws":34,"losses":8,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":38,"losses":65,"wins":29},"x-ai/grok-4.6":{"draws":39,"losses":32,"wins":15},"x-ai/grok-4.7":{"draws":7,"losses":29,"wins":6},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":15,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":48,"losses":37,"wins":45},"z-ai/glm-5.3":{"draws":17,"losses":37,"wins":18},"z-ai/glm-5.3-flash":{"draws":28,"losses":26,"wins":32},"z-ai/glm-5.3-flashx":{"draws":17,"losses":22,"wins":9}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":24,"wins":4},"claude-fable-5":{"draws":3,"losses":27,"wins":0},"claude-fable-5-1":{"draws":1,"losses":33,"wins":0},"claude-haiku-5-5":{"draws":1,"losses":24,"wins":3},"claude-opus-4-5":{"draws":6,"losses":64,"wins":4},"claude-opus-4-8":{"draws":8,"losses":36,"wins":0},"claude-opus-5":{"draws":0,"losses":59,"wins":1},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":9,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":3,"losses":24,"wins":3},"cohere/north-mini-code":{"draws":13,"losses":16,"wins":9},"deepseek/deepseek-v4-flash":{"draws":5,"losses":37,"wins":30},"deepseek/deepseek-v4-pro":{"draws":2,"losses":23,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":27,"wins":2},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":21,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":24,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":32,"wins":8},"google/gemini-3.5-flash-lite":{"draws":9,"losses":43,"wins":14},"google/gemini-3.6-flash":{"draws":2,"losses":60,"wins":4},"google/gemini-3.8-flash":{"draws":1,"losses":27,"wins":2},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":14,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":3,"losses":37,"wins":10},"gpt-5.4":{"draws":4,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":19,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":38,"wins":23},"gpt-5.5":{"draws":2,"losses":49,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":21,"wins":5},"gpt-5.6-sol":{"draws":1,"losses":30,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":26,"wins":1},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":23,"wins":5},"gpt-6-sol":{"draws":0,"losses":29,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":21,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":49,"wins":22},"meta/muse-glimmer-30b":{"draws":7,"losses":20,"wins":3},"meta/muse-spark-1.2":{"draws":1,"losses":29,"wins":2},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-wonder":{"draws":1,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":25,"wins":10},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":14,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":30,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":39,"wins":12},"o3":{"draws":3,"losses":59,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":15,"wins":9},"poolside/laguna-s-2.1":{"draws":16,"losses":31,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":26,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":16,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":25,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":4,"losses":22,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":24,"wins":2},"stealth/ox-alpha":{"draws":14,"losses":88,"wins":12},"stealth/space-bunny-alpha":{"draws":3,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":13,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":2,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":27,"wins":15},"thinkingmachines/inkling-small":{"draws":5,"losses":20,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":6,"wins":1},"x-ai/grok-4.5":{"draws":7,"losses":35,"wins":2},"x-ai/grok-4.6":{"draws":4,"losses":28,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":15,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":55,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":27,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":18,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":47,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":29,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":26,"wins":3},"z-ai/glm-5.3-flashx":{"draws":2,"losses":27,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":8},"claude-fable-5":{"draws":5,"losses":22,"wins":3},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":16,"wins":7},"claude-opus-4-5":{"draws":33,"losses":25,"wins":20},"claude-opus-4-8":{"draws":10,"losses":37,"wins":1},"claude-opus-5":{"draws":6,"losses":65,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":11,"losses":12,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":26,"losses":16,"wins":20},"deepseek/deepseek-v4-pro":{"draws":8,"losses":16,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":6},"fireworks/ember-1":{"draws":11,"losses":13,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":7,"wins":23},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":6},"google/gemini-3.5-flash-lite":{"draws":24,"losses":18,"wins":20},"google/gemini-3.6-flash":{"draws":19,"losses":36,"wins":11},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":4},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":20,"wins":13},"gpt-5.4":{"draws":9,"losses":18,"wins":3},"gpt-5.4-mini":{"draws":22,"losses":10,"wins":14},"gpt-5.4-nano":{"draws":26,"losses":24,"wins":30},"gpt-5.5":{"draws":18,"losses":26,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":10},"gpt-6-astra":{"draws":3,"losses":26,"wins":1},"gpt-6-luna":{"draws":13,"losses":11,"wins":6},"gpt-6-sol":{"draws":2,"losses":26,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":24,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":11},"inclusionai/ling-3.0-flash":{"draws":18,"losses":14,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":13,"wins":21},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":7},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":7},"meta/muse-wonder":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":15,"losses":13,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":8,"wins":13},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":6,"wins":12},"o3":{"draws":15,"losses":30,"wins":9},"openai/gpt-oss-120b":{"draws":11,"losses":11,"wins":4},"poolside/laguna-s-2.1":{"draws":28,"losses":12,"wins":8},"qwen/qwen3.7-max":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":2},"stealth/ox-alpha":{"draws":22,"losses":40,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":9,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":14,"losses":17,"wins":13},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":27,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":18,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":46,"losses":28,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":21,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":25,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":17,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":11},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":9}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":11,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":4},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":25,"wins":7},"claude-opus-4-5":{"draws":31,"losses":55,"wins":28},"claude-opus-4-8":{"draws":15,"losses":33,"wins":16},"claude-opus-5":{"draws":9,"losses":77,"wins":8},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":11,"losses":16,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":17},"deepseek/deepseek-v4-flash":{"draws":15,"losses":18,"wins":37},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":10},"fireworks/ember-1":{"draws":13,"losses":16,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":12,"wins":17},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":35},"google/gemini-3.5-flash":{"draws":13,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":55},"google/gemini-3.6-flash":{"draws":26,"losses":41,"wins":31},"google/gemini-3.8-flash":{"draws":5,"losses":25,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":13},"gpt-4.1":{"draws":8,"losses":4,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":24,"wins":14},"gpt-5.4":{"draws":11,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":21,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":30,"wins":39},"gpt-5.5":{"draws":24,"losses":31,"wins":9},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":7},"gpt-6-astra":{"draws":1,"losses":39,"wins":0},"gpt-6-luna":{"draws":7,"losses":16,"wins":13},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":17,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":9},"meta/muse-wonder":{"draws":2,"losses":29,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":26},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":14,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":14},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":10,"wins":18},"o3":{"draws":9,"losses":24,"wins":21},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":35},"qwen/qwen3.7-max":{"draws":15,"losses":15,"wins":20},"qwen/qwen3.7-plus":{"draws":8,"losses":11,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":3,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":20,"losses":65,"wins":29},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":7},"thinkingmachines/inkling":{"draws":14,"losses":16,"wins":34},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":18},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":21},"xiaomi/mimo-v2.5":{"draws":41,"losses":9,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":4},"z-ai/glm-5.2":{"draws":24,"losses":42,"wins":40},"z-ai/glm-5.3":{"draws":5,"losses":28,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":15,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":22,"wins":11}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":26,"wins":24},"claude-fable-5":{"draws":21,"losses":45,"wins":2},"claude-fable-5-1":{"draws":7,"losses":60,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":31,"wins":3},"claude-opus-4-5":{"draws":34,"losses":59,"wins":9},"claude-opus-4-8":{"draws":16,"losses":29,"wins":1},"claude-opus-5":{"draws":12,"losses":67,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":33,"losses":44,"wins":13},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":47,"losses":35,"wins":30},"deepseek/deepseek-v4-pro":{"draws":26,"losses":39,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":29,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":26,"wins":8},"fireworks/ember-1":{"draws":19,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":23,"wins":9},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":17},"google/gemini-3.5-flash":{"draws":29,"losses":47,"wins":16},"google/gemini-3.5-flash-lite":{"draws":56,"losses":63,"wins":43},"google/gemini-3.6-flash":{"draws":52,"losses":72,"wins":20},"google/gemini-3.8-flash":{"draws":19,"losses":49,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":7,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":22,"wins":5},"gpt-5.4":{"draws":36,"losses":36,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":20},"gpt-5.5":{"draws":21,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":40,"losses":36,"wins":16},"gpt-5.6-sol":{"draws":10,"losses":59,"wins":3},"gpt-5.6-terra":{"draws":32,"losses":48,"wins":4},"gpt-6-astra":{"draws":3,"losses":57,"wins":0},"gpt-6-luna":{"draws":16,"losses":23,"wins":9},"gpt-6-sol":{"draws":6,"losses":39,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":31,"losses":14,"wins":21},"inclusionai/ling-3.0-flash":{"draws":20,"losses":7,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":31,"wins":16},"meta/muse-glimmer-30b":{"draws":38,"losses":22,"wins":24},"meta/muse-spark-1.2":{"draws":22,"losses":39,"wins":7},"meta/muse-spark-1.3":{"draws":20,"losses":44,"wins":6},"meta/muse-wonder":{"draws":10,"losses":36,"wins":2},"minimax/minimax-m3":{"draws":11,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-medium-3-5":{"draws":25,"losses":14,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":24,"losses":40,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":13,"wins":14},"o3":{"draws":17,"losses":69,"wins":8},"openai/gpt-oss-120b":{"draws":20,"losses":18,"wins":10},"poolside/laguna-s-2.1":{"draws":30,"losses":25,"wins":15},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":25,"wins":8},"qwen/qwen3.8-flash":{"draws":23,"losses":21,"wins":10},"qwen/qwen3.8-max":{"draws":37,"losses":41,"wins":4},"qwen/qwen3.8-max-0902":{"draws":16,"losses":31,"wins":1},"stealth/ox-alpha":{"draws":77,"losses":162,"wins":25},"stealth/space-bunny-alpha":{"draws":14,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":31,"losses":35,"wins":10},"thinkingmachines/inkling":{"draws":28,"losses":29,"wins":25},"thinkingmachines/inkling-small":{"draws":39,"losses":27,"wins":30},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":4,"wins":5},"x-ai/grok-4.5":{"draws":24,"losses":45,"wins":3},"x-ai/grok-4.6":{"draws":30,"losses":39,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":26,"losses":25,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":21,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":2},"z-ai/glm-5.2":{"draws":50,"losses":58,"wins":28},"z-ai/glm-5.3":{"draws":17,"losses":43,"wins":4},"z-ai/glm-5.3-flash":{"draws":16,"losses":51,"wins":9},"z-ai/glm-5.3-flashx":{"draws":11,"losses":29,"wins":8}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":39,"wins":25},"claude-fable-5":{"draws":31,"losses":59,"wins":12},"claude-fable-5-1":{"draws":8,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":19,"losses":31,"wins":12},"claude-opus-4-5":{"draws":88,"losses":110,"wins":16},"claude-opus-4-8":{"draws":31,"losses":36,"wins":5},"claude-opus-5":{"draws":18,"losses":132,"wins":10},"claude-opus-5-5":{"draws":5,"losses":69,"wins":0},"claude-sonnet-5":{"draws":69,"losses":96,"wins":15},"claude-sonnet-5-5":{"draws":15,"losses":40,"wins":11},"cohere/north-mini-code":{"draws":18,"losses":14,"wins":4},"deepseek/deepseek-v4-flash":{"draws":81,"losses":48,"wins":31},"deepseek/deepseek-v4-pro":{"draws":49,"losses":40,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":32,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":25,"wins":9},"fireworks/ember-1":{"draws":30,"losses":27,"wins":9},"gemini-3.1-pro-preview":{"draws":27,"losses":28,"wins":11},"google/gemini-3.1-flash-lite":{"draws":17,"losses":11,"wins":24},"google/gemini-3.5-flash":{"draws":51,"losses":61,"wins":20},"google/gemini-3.5-flash-lite":{"draws":208,"losses":110,"wins":118},"google/gemini-3.6-flash":{"draws":169,"losses":173,"wins":38},"google/gemini-3.8-flash":{"draws":31,"losses":63,"wins":6},"google/gemma-4-31b-it":{"draws":20,"losses":10,"wins":8},"gpt-4.1":{"draws":13,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":1},"gpt-5":{"draws":34,"losses":25,"wins":11},"gpt-5.4":{"draws":64,"losses":85,"wins":11},"gpt-5.4-mini":{"draws":34,"losses":24,"wins":10},"gpt-5.4-nano":{"draws":32,"losses":28,"wins":28},"gpt-5.5":{"draws":29,"losses":32,"wins":13},"gpt-5.6-luna":{"draws":82,"losses":67,"wins":41},"gpt-5.6-sol":{"draws":34,"losses":144,"wins":2},"gpt-5.6-terra":{"draws":49,"losses":50,"wins":7},"gpt-6-astra":{"draws":13,"losses":83,"wins":0},"gpt-6-luna":{"draws":25,"losses":34,"wins":7},"gpt-6-sol":{"draws":12,"losses":51,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":61,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":50,"losses":20,"wins":20},"inclusionai/ling-3.0-flash":{"draws":58,"losses":12,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":74,"losses":65,"wins":53},"meta/muse-glimmer-30b":{"draws":63,"losses":20,"wins":33},"meta/muse-spark-1.2":{"draws":43,"losses":84,"wins":11},"meta/muse-spark-1.3":{"draws":37,"losses":48,"wins":13},"meta/muse-wonder":{"draws":12,"losses":48,"wins":6},"minimax/minimax-m3":{"draws":22,"losses":12,"wins":16},"mistralai/mistral-large-4-0":{"draws":19,"losses":19,"wins":4},"mistralai/mistral-medium-3-5":{"draws":44,"losses":14,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":14,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":75,"losses":99,"wins":2},"nex-agi/nex-n2-pro":{"draws":19,"losses":8,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":17,"wins":9},"o3":{"draws":51,"losses":100,"wins":49},"openai/gpt-oss-120b":{"draws":67,"losses":29,"wins":20},"poolside/laguna-s-2.1":{"draws":63,"losses":39,"wins":30},"qwen/qwen3.7-max":{"draws":25,"losses":20,"wins":11},"qwen/qwen3.7-plus":{"draws":25,"losses":10,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":55,"wins":10},"qwen/qwen3.8-27b":{"draws":16,"losses":29,"wins":7},"qwen/qwen3.8-flash":{"draws":38,"losses":27,"wins":9},"qwen/qwen3.8-max":{"draws":50,"losses":45,"wins":19},"qwen/qwen3.8-max-0902":{"draws":26,"losses":35,"wins":5},"stealth/ox-alpha":{"draws":127,"losses":200,"wins":45},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":12},"stepfun/step-3.7-flash":{"draws":20,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":8},"tencent/hy4-preview":{"draws":43,"losses":50,"wins":17},"thinkingmachines/inkling":{"draws":73,"losses":48,"wins":59},"thinkingmachines/inkling-small":{"draws":67,"losses":19,"wins":47},"unbiased/pareto-26.10-preview":{"draws":0,"losses":22,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":68,"losses":96,"wins":22},"x-ai/grok-4.6":{"draws":37,"losses":63,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":46,"wins":5},"x-ai/grok-build-0.1":{"draws":25,"losses":13,"wins":8},"xiaomi/mimo-v2.5":{"draws":56,"losses":28,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":17,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":26,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":105,"losses":57,"wins":32},"z-ai/glm-5.3":{"draws":32,"losses":54,"wins":10},"z-ai/glm-5.3-flash":{"draws":46,"losses":52,"wins":14},"z-ai/glm-5.3-flashx":{"draws":27,"losses":31,"wins":8}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":6,"wins":19},"claude-fable-5":{"draws":7,"losses":28,"wins":7},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":12},"claude-opus-4-5":{"draws":49,"losses":51,"wins":34},"claude-opus-4-8":{"draws":27,"losses":31,"wins":24},"claude-opus-5":{"draws":12,"losses":90,"wins":20},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":11},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":12,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":39,"losses":13,"wins":26},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":13,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":12,"wins":12},"fireworks/ember-1":{"draws":13,"losses":17,"wins":12},"gemini-3.1-pro-preview":{"draws":14,"losses":12,"wins":16},"google/gemini-3.1-flash-lite":{"draws":25,"losses":6,"wins":23},"google/gemini-3.5-flash":{"draws":24,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":34,"losses":29,"wins":33},"google/gemini-3.6-flash":{"draws":28,"losses":44,"wins":24},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":18,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":30,"losses":26,"wins":14},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":18,"losses":14,"wins":20},"gpt-5.4-nano":{"draws":25,"losses":27,"wins":40},"gpt-5.5":{"draws":28,"losses":35,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":29,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":23,"wins":12},"gpt-6-astra":{"draws":5,"losses":38,"wins":1},"gpt-6-luna":{"draws":11,"losses":19,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":28,"losses":6,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":9,"wins":42},"meta/muse-glimmer-30b":{"draws":16,"losses":12,"wins":14},"meta/muse-spark-1.2":{"draws":5,"losses":32,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":13},"meta/muse-wonder":{"draws":6,"losses":33,"wins":3},"minimax/minimax-m3":{"draws":19,"losses":15,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":14,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":13,"losses":23,"wins":12},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":15,"wins":23},"o3":{"draws":24,"losses":25,"wins":33},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":26,"losses":8,"wins":26},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":13,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":36,"losses":58,"wins":32},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":9,"wins":15},"tencent/hy4-preview":{"draws":8,"losses":25,"wins":11},"thinkingmachines/inkling":{"draws":28,"losses":10,"wins":42},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":19,"losses":28,"wins":17},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":18,"losses":10,"wins":10},"xiaomi/mimo-v2.5":{"draws":58,"losses":25,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":12,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":37,"losses":53,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":20,"wins":11},"z-ai/glm-5.3-flash":{"draws":16,"losses":14,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":13},"claude-fable-5":{"draws":7,"losses":24,"wins":5},"claude-fable-5-1":{"draws":0,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":22,"wins":7},"claude-opus-4-5":{"draws":23,"losses":36,"wins":33},"claude-opus-4-8":{"draws":15,"losses":38,"wins":15},"claude-opus-5":{"draws":16,"losses":71,"wins":1},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":11,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":16},"deepseek/deepseek-v4-flash":{"draws":24,"losses":25,"wins":27},"deepseek/deepseek-v4-pro":{"draws":8,"losses":16,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":18,"wins":5},"fireworks/ember-1":{"draws":11,"losses":16,"wins":9},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":30},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":13},"google/gemini-3.5-flash-lite":{"draws":29,"losses":13,"wins":38},"google/gemini-3.6-flash":{"draws":22,"losses":46,"wins":22},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":9},"gpt-4.1":{"draws":10,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":20,"losses":23,"wins":15},"gpt-5.4":{"draws":8,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":28},"gpt-5.4-nano":{"draws":18,"losses":23,"wins":47},"gpt-5.5":{"draws":31,"losses":25,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":8,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":16,"losses":10,"wins":10},"gpt-6-astra":{"draws":2,"losses":36,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":10},"gpt-6-sol":{"draws":3,"losses":27,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":30,"wins":4},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":23,"losses":4,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":16,"wins":36},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":11},"meta/muse-spark-1.2":{"draws":6,"losses":34,"wins":8},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":11},"meta/muse-wonder":{"draws":11,"losses":25,"wins":0},"minimax/minimax-m3":{"draws":11,"losses":12,"wins":23},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":1},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":15},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":16,"wins":26},"o3":{"draws":13,"losses":33,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":15},"poolside/laguna-s-2.1":{"draws":32,"losses":18,"wins":14},"qwen/qwen3.7-max":{"draws":17,"losses":19,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":11,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":22,"losses":66,"wins":20},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":6},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":13,"losses":7,"wins":34},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":8,"losses":37,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":10,"losses":2,"wins":18},"xiaomi/mimo-v2.5":{"draws":42,"losses":9,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":12,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":37,"losses":43,"wins":28},"z-ai/glm-5.3":{"draws":7,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":18,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":9}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":24,"wins":26},"claude-fable-5":{"draws":25,"losses":51,"wins":8},"claude-fable-5-1":{"draws":12,"losses":76,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":22,"wins":8},"claude-opus-4-5":{"draws":54,"losses":37,"wins":17},"claude-opus-4-8":{"draws":23,"losses":20,"wins":9},"claude-opus-5":{"draws":10,"losses":66,"wins":12},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":39,"losses":38,"wins":17},"claude-sonnet-5-5":{"draws":14,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":48,"losses":29,"wins":35},"deepseek/deepseek-v4-pro":{"draws":29,"losses":33,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":38,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":22,"wins":10},"fireworks/ember-1":{"draws":27,"losses":19,"wins":2},"gemini-3.1-pro-preview":{"draws":15,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":31,"losses":45,"wins":26},"google/gemini-3.5-flash-lite":{"draws":61,"losses":38,"wins":53},"google/gemini-3.6-flash":{"draws":49,"losses":69,"wins":36},"google/gemini-3.8-flash":{"draws":25,"losses":43,"wins":14},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":10,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":19,"losses":14,"wins":9},"gpt-5.4":{"draws":27,"losses":43,"wins":14},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":20,"losses":17,"wins":19},"gpt-5.5":{"draws":19,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":45,"losses":18,"wins":25},"gpt-5.6-sol":{"draws":15,"losses":61,"wins":12},"gpt-5.6-terra":{"draws":44,"losses":22,"wins":24},"gpt-6-astra":{"draws":5,"losses":73,"wins":2},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":6,"losses":37,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":24,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":15,"wins":36},"meta/muse-glimmer-30b":{"draws":46,"losses":4,"wins":30},"meta/muse-spark-1.2":{"draws":22,"losses":31,"wins":15},"meta/muse-spark-1.3":{"draws":24,"losses":42,"wins":10},"meta/muse-wonder":{"draws":9,"losses":33,"wins":6},"minimax/minimax-m3":{"draws":11,"losses":4,"wins":13},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":25,"losses":2,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":24,"losses":38,"wins":14},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":9,"wins":11},"o3":{"draws":23,"losses":44,"wins":35},"openai/gpt-oss-120b":{"draws":45,"losses":7,"wins":30},"poolside/laguna-s-2.1":{"draws":29,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":17,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":26,"wins":11},"qwen/qwen3.8-27b":{"draws":18,"losses":13,"wins":11},"qwen/qwen3.8-flash":{"draws":24,"losses":19,"wins":13},"qwen/qwen3.8-max":{"draws":38,"losses":25,"wins":23},"qwen/qwen3.8-max-0902":{"draws":20,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":97,"losses":126,"wins":61},"stealth/space-bunny-alpha":{"draws":18,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":27,"losses":36,"wins":23},"thinkingmachines/inkling":{"draws":30,"losses":14,"wins":40},"thinkingmachines/inkling-small":{"draws":38,"losses":12,"wins":42},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":43,"wins":13},"x-ai/grok-4.6":{"draws":27,"losses":42,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":41,"losses":19,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":66,"losses":39,"wins":31},"z-ai/glm-5.3":{"draws":16,"losses":44,"wins":10},"z-ai/glm-5.3-flash":{"draws":22,"losses":44,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":26,"wins":12}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":16},"claude-fable-5":{"draws":12,"losses":27,"wins":3},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":9},"claude-opus-4-5":{"draws":26,"losses":14,"wins":28},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":14,"losses":51,"wins":5},"claude-opus-5-5":{"draws":2,"losses":39,"wins":1},"claude-sonnet-5":{"draws":14,"losses":14,"wins":14},"claude-sonnet-5-5":{"draws":6,"losses":28,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":14},"fireworks/ember-1":{"draws":14,"losses":13,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":13,"losses":25,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":17,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":39,"wins":21},"google/gemini-3.8-flash":{"draws":6,"losses":30,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":13},"gpt-5.4":{"draws":10,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":20},"gpt-5.5":{"draws":17,"losses":13,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":18},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":6},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":5,"losses":32,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":10},"meta/muse-wonder":{"draws":10,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":16},"o3":{"draws":7,"losses":20,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":16},"poolside/laguna-s-2.1":{"draws":14,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":15,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"stealth/ox-alpha":{"draws":40,"losses":61,"wins":41},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":12},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":15,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":8,"wins":29},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":16,"losses":17,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":7,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":27,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":6}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":8,"wins":40},"claude-fable-5":{"draws":28,"losses":32,"wins":26},"claude-fable-5-1":{"draws":3,"losses":90,"wins":7},"claude-haiku-5-5":{"draws":15,"losses":14,"wins":17},"claude-opus-4-5":{"draws":33,"losses":19,"wins":52},"claude-opus-4-8":{"draws":21,"losses":12,"wins":17},"claude-opus-5":{"draws":14,"losses":70,"wins":12},"claude-opus-5-5":{"draws":6,"losses":44,"wins":2},"claude-sonnet-5":{"draws":24,"losses":17,"wins":41},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":40,"losses":8,"wins":54},"deepseek/deepseek-v4-pro":{"draws":18,"losses":14,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":11,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":15,"wins":15},"fireworks/ember-1":{"draws":17,"losses":10,"wins":21},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":14,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":38,"losses":22,"wins":42},"google/gemini-3.5-flash-lite":{"draws":52,"losses":8,"wins":70},"google/gemini-3.6-flash":{"draws":51,"losses":45,"wins":58},"google/gemini-3.8-flash":{"draws":25,"losses":21,"wins":40},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":13},"gpt-4.1":{"draws":6,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":20,"losses":8,"wins":22},"gpt-5.4":{"draws":22,"losses":30,"wins":30},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":27},"gpt-5.5":{"draws":16,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":28,"losses":11,"wins":45},"gpt-5.6-sol":{"draws":25,"losses":41,"wins":24},"gpt-5.6-terra":{"draws":33,"losses":15,"wins":34},"gpt-6-astra":{"draws":13,"losses":72,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":28,"wins":13},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":28,"losses":0,"wins":28},"inclusionai/ling-3.0-flash":{"draws":19,"losses":3,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":10,"wins":35},"meta/muse-glimmer-30b":{"draws":25,"losses":16,"wins":21},"meta/muse-spark-1.2":{"draws":19,"losses":21,"wins":32},"meta/muse-spark-1.3":{"draws":24,"losses":22,"wins":32},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":24},"mistralai/mistral-large-4-0":{"draws":11,"losses":3,"wins":16},"mistralai/mistral-medium-3-5":{"draws":18,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":22,"losses":12,"wins":38},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":4,"wins":19},"o3":{"draws":17,"losses":22,"wins":59},"openai/gpt-oss-120b":{"draws":28,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":29,"losses":2,"wins":31},"qwen/qwen3.7-max":{"draws":11,"losses":3,"wins":22},"qwen/qwen3.7-plus":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":22,"wins":44},"qwen/qwen3.8-27b":{"draws":13,"losses":10,"wins":19},"qwen/qwen3.8-flash":{"draws":16,"losses":0,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":23,"wins":34},"qwen/qwen3.8-max-0902":{"draws":17,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":82,"losses":67,"wins":127},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":18},"tencent/hy4-preview":{"draws":26,"losses":17,"wins":39},"thinkingmachines/inkling":{"draws":25,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":39,"losses":7,"wins":32},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":19,"losses":28,"wins":23},"x-ai/grok-4.6":{"draws":33,"losses":31,"wins":24},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":4,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":5,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":48,"losses":13,"wins":63},"z-ai/glm-5.3":{"draws":25,"losses":31,"wins":20},"z-ai/glm-5.3-flash":{"draws":18,"losses":24,"wins":46},"z-ai/glm-5.3-flashx":{"draws":13,"losses":16,"wins":19}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":16,"wins":33},"claude-fable-5":{"draws":8,"losses":54,"wins":22},"claude-fable-5-1":{"draws":7,"losses":85,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":27,"wins":12},"claude-opus-4-5":{"draws":31,"losses":25,"wins":55},"claude-opus-4-8":{"draws":15,"losses":23,"wins":16},"claude-opus-5":{"draws":17,"losses":67,"wins":8},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":27,"losses":23,"wins":38},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":29,"losses":17,"wins":56},"deepseek/deepseek-v4-pro":{"draws":21,"losses":21,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":22,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":18,"wins":13},"fireworks/ember-1":{"draws":19,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":28,"losses":43,"wins":27},"google/gemini-3.5-flash-lite":{"draws":50,"losses":30,"wins":60},"google/gemini-3.6-flash":{"draws":54,"losses":68,"wins":45},"google/gemini-3.8-flash":{"draws":24,"losses":34,"wins":28},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":9,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":8,"wins":20},"gpt-5.4":{"draws":25,"losses":40,"wins":23},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":13,"losses":10,"wins":27},"gpt-5.5":{"draws":16,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":35,"losses":18,"wins":29},"gpt-5.6-sol":{"draws":15,"losses":47,"wins":26},"gpt-5.6-terra":{"draws":36,"losses":27,"wins":23},"gpt-6-astra":{"draws":14,"losses":68,"wins":2},"gpt-6-luna":{"draws":15,"losses":14,"wins":19},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":6,"wins":23},"inclusionai/ling-3.0-flash":{"draws":22,"losses":8,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":19,"wins":34},"meta/muse-glimmer-30b":{"draws":22,"losses":15,"wins":27},"meta/muse-spark-1.2":{"draws":22,"losses":18,"wins":34},"meta/muse-spark-1.3":{"draws":20,"losses":42,"wins":14},"meta/muse-wonder":{"draws":11,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":10,"losses":1,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":25,"losses":25,"wins":26},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":22},"o3":{"draws":17,"losses":30,"wins":58},"openai/gpt-oss-120b":{"draws":28,"losses":6,"wins":36},"poolside/laguna-s-2.1":{"draws":25,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":21,"wins":36},"qwen/qwen3.8-27b":{"draws":12,"losses":19,"wins":11},"qwen/qwen3.8-flash":{"draws":27,"losses":19,"wins":12},"qwen/qwen3.8-max":{"draws":28,"losses":21,"wins":36},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":66,"losses":104,"wins":100},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":36,"wins":24},"thinkingmachines/inkling":{"draws":21,"losses":17,"wins":38},"thinkingmachines/inkling-small":{"draws":39,"losses":41,"wins":53},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":19,"losses":39,"wins":20},"x-ai/grok-4.6":{"draws":21,"losses":41,"wins":24},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":43,"losses":33,"wins":50},"z-ai/glm-5.3":{"draws":25,"losses":29,"wins":16},"z-ai/glm-5.3-flash":{"draws":23,"losses":33,"wins":22},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":12,"wins":22},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":11},"claude-opus-4-5":{"draws":23,"losses":39,"wins":16},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":16,"losses":57,"wins":9},"claude-opus-5-5":{"draws":6,"losses":45,"wins":1},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":24,"losses":14,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":25,"wins":19},"google/gemini-3.5-flash-lite":{"draws":32,"losses":20,"wins":32},"google/gemini-3.6-flash":{"draws":22,"losses":49,"wins":21},"google/gemini-3.8-flash":{"draws":13,"losses":30,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":15,"wins":14},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":14},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":31},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":15,"losses":23,"wins":10},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":18},"o3":{"draws":13,"losses":28,"wins":25},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":13,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":13,"losses":19,"wins":16},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"stealth/ox-alpha":{"draws":37,"losses":75,"wins":46},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":10,"losses":24,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":28,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":29,"losses":16,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":22,"wins":7},"z-ai/glm-5.2":{"draws":34,"losses":29,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":53,"losses":62,"wins":129},"claude-fable-5":{"draws":67,"losses":149,"wins":58},"claude-fable-5-1":{"draws":23,"losses":299,"wins":10},"claude-haiku-5-5":{"draws":31,"losses":59,"wins":52},"claude-opus-4-5":{"draws":106,"losses":110,"wins":126},"claude-opus-4-8":{"draws":36,"losses":50,"wins":52},"claude-opus-5":{"draws":53,"losses":206,"wins":49},"claude-opus-5-5":{"draws":21,"losses":140,"wins":7},"claude-sonnet-5":{"draws":71,"losses":82,"wins":131},"claude-sonnet-5-5":{"draws":37,"losses":70,"wins":49},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":45},"deepseek/deepseek-v4-flash":{"draws":87,"losses":77,"wins":170},"deepseek/deepseek-v4-pro":{"draws":61,"losses":83,"wins":100},"deepseek/deepseek-v4-pro-0813":{"draws":62,"losses":91,"wins":95},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":62,"wins":52},"fireworks/ember-1":{"draws":41,"losses":61,"wins":54},"gemini-3.1-pro-preview":{"draws":37,"losses":47,"wins":72},"google/gemini-3.1-flash-lite":{"draws":20,"losses":14,"wins":56},"google/gemini-3.5-flash":{"draws":74,"losses":102,"wins":126},"google/gemini-3.5-flash-lite":{"draws":106,"losses":99,"wins":259},"google/gemini-3.6-flash":{"draws":117,"losses":206,"wins":157},"google/gemini-3.8-flash":{"draws":65,"losses":136,"wins":81},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":51},"gpt-4.1":{"draws":14,"losses":9,"wins":31},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":34,"losses":48,"wins":70},"gpt-5.4":{"draws":75,"losses":103,"wins":84},"gpt-5.4-mini":{"draws":31,"losses":21,"wins":58},"gpt-5.4-nano":{"draws":31,"losses":35,"wins":78},"gpt-5.5":{"draws":46,"losses":57,"wins":51},"gpt-5.6-luna":{"draws":84,"losses":58,"wins":114},"gpt-5.6-sol":{"draws":41,"losses":197,"wins":52},"gpt-5.6-terra":{"draws":82,"losses":67,"wins":115},"gpt-6-astra":{"draws":27,"losses":244,"wins":11},"gpt-6-luna":{"draws":38,"losses":56,"wins":62},"gpt-6-sol":{"draws":24,"losses":115,"wins":17},"gpt-6.1-sol":{"draws":16,"losses":133,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":58,"losses":27,"wins":87},"inclusionai/ling-3.0-flash":{"draws":27,"losses":14,"wins":91},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":45,"losses":33,"wins":142},"meta/muse-glimmer-30b":{"draws":52,"losses":41,"wins":139},"meta/muse-spark-1.2":{"draws":53,"losses":87,"wins":94},"meta/muse-spark-1.3":{"draws":53,"losses":96,"wins":81},"meta/muse-wonder":{"draws":37,"losses":76,"wins":43},"minimax/minimax-m3":{"draws":21,"losses":19,"wins":48},"mistralai/mistral-large-4-0":{"draws":33,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":33,"losses":32,"wins":91},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":16},"moonshotai/kimi-k3":{"draws":64,"losses":101,"wins":75},"nex-agi/nex-n2-pro":{"draws":21,"losses":14,"wins":61},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":17,"wins":71},"o3":{"draws":35,"losses":118,"wins":133},"openai/gpt-oss-120b":{"draws":54,"losses":42,"wins":138},"poolside/laguna-s-2.1":{"draws":55,"losses":41,"wins":124},"qwen/qwen3.7-max":{"draws":23,"losses":22,"wins":45},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":85,"losses":109,"wins":88},"qwen/qwen3.8-27b":{"draws":29,"losses":57,"wins":50},"qwen/qwen3.8-flash":{"draws":48,"losses":62,"wins":64},"qwen/qwen3.8-max":{"draws":88,"losses":87,"wins":95},"qwen/qwen3.8-max-0902":{"draws":35,"losses":72,"wins":49},"stealth/ox-alpha":{"draws":209,"losses":477,"wins":380},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":59},"stepfun/step-3.7-flash":{"draws":15,"losses":22,"wins":73},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":31,"losses":15,"wins":40},"tencent/hy4-preview":{"draws":58,"losses":126,"wins":80},"thinkingmachines/inkling":{"draws":62,"losses":57,"wins":149},"thinkingmachines/inkling-small":{"draws":79,"losses":64,"wins":125},"unbiased/pareto-26.10-preview":{"draws":0,"losses":50,"wins":2},"upstage/solar-mini4":{"draws":5,"losses":7,"wins":18},"x-ai/grok-4.5":{"draws":53,"losses":107,"wins":72},"x-ai/grok-4.6":{"draws":73,"losses":118,"wins":89},"x-ai/grok-4.7":{"draws":17,"losses":98,"wins":17},"x-ai/grok-build-0.1":{"draws":15,"losses":5,"wins":36},"xiaomi/mimo-v2.5":{"draws":64,"losses":30,"wins":124},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":24,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":35,"wins":42},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":51,"wins":37},"z-ai/glm-5.2":{"draws":112,"losses":106,"wins":198},"z-ai/glm-5.3":{"draws":53,"losses":125,"wins":54},"z-ai/glm-5.3-flash":{"draws":61,"losses":128,"wins":89},"z-ai/glm-5.3-flashx":{"draws":24,"losses":78,"wins":54}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":6},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":18,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":11,"losses":22,"wins":5},"claude-opus-5":{"draws":8,"losses":57,"wins":5},"claude-opus-5-5":{"draws":1,"losses":41,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":9,"losses":29,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":9,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"wins":10},"fireworks/ember-1":{"draws":14,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":16,"losses":28,"wins":30},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":16},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":15},"gpt-5.4":{"draws":11,"losses":23,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":10,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":13},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":17,"losses":20,"wins":5},"gpt-6-sol":{"draws":9,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":36,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":10,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":18,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":31,"wins":4},"meta/muse-wonder":{"draws":14,"losses":21,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":8},"o3":{"draws":6,"losses":26,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":31,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":17,"wins":22},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":18,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":11},"z-ai/glm-5.2":{"draws":33,"losses":28,"wins":23},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":27,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":13},"claude-fable-5":{"draws":2,"losses":30,"wins":4},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":4,"losses":23,"wins":7},"claude-opus-4-5":{"draws":10,"losses":32,"wins":16},"claude-opus-4-8":{"draws":3,"losses":19,"wins":10},"claude-opus-5":{"draws":2,"losses":54,"wins":2},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":7,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":23,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":13,"losses":24,"wins":19},"deepseek/deepseek-v4-pro":{"draws":6,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":19,"wins":9},"fireworks/ember-1":{"draws":5,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":29,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":23,"wins":28},"google/gemini-3.6-flash":{"draws":9,"losses":45,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":9},"gpt-4.1":{"draws":1,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":25,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":22,"wins":12},"gpt-5.5":{"draws":8,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":14,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":19,"wins":7},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":6,"losses":21,"wins":9},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":7,"wins":11},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":14},"meta/muse-spark-1.2":{"draws":0,"losses":27,"wins":7},"meta/muse-spark-1.3":{"draws":3,"losses":24,"wins":9},"meta/muse-wonder":{"draws":1,"losses":32,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":20,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":13,"wins":9},"o3":{"draws":10,"losses":32,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":24,"wins":8},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":17,"losses":88,"wins":19},"stealth/space-bunny-alpha":{"draws":4,"losses":15,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":7},"thinkingmachines/inkling":{"draws":11,"losses":19,"wins":20},"thinkingmachines/inkling-small":{"draws":10,"losses":11,"wins":15},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":0,"losses":27,"wins":9},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":27,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":12,"losses":16,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":37,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":6,"losses":24,"wins":6}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":4},"claude-fable-5":{"draws":0,"losses":1,"wins":5},"claude-fable-5-1":{"draws":0,"losses":4,"wins":2},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":10},"claude-opus-4-8":{"draws":0,"losses":2,"wins":4},"claude-opus-5":{"draws":0,"losses":5,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":4},"claude-sonnet-5":{"draws":0,"losses":0,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":4,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":5},"fireworks/ember-1":{"draws":0,"losses":2,"wins":4},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":0,"losses":1,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":0,"losses":0,"wins":6},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":3,"wins":3},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":6},"gpt-6-astra":{"draws":0,"losses":2,"wins":4},"gpt-6-luna":{"draws":0,"losses":1,"wins":5},"gpt-6-sol":{"draws":1,"losses":2,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":4,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":5},"meta/muse-wonder":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-large-4-0":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"o3":{"draws":0,"losses":0,"wins":10},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":1,"wins":5},"stealth/ox-alpha":{"draws":0,"losses":1,"wins":15},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":4},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":11},"z-ai/glm-5.3":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":6}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":44},"claude-fable-5":{"draws":6,"losses":50,"wins":22},"claude-fable-5-1":{"draws":1,"losses":72,"wins":7},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":18,"losses":17,"wins":59},"claude-opus-4-8":{"draws":7,"losses":17,"wins":18},"claude-opus-5":{"draws":2,"losses":58,"wins":12},"claude-opus-5-5":{"draws":4,"losses":35,"wins":7},"claude-sonnet-5":{"draws":19,"losses":23,"wins":38},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":16},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":56},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":35,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"fireworks/ember-1":{"draws":8,"losses":15,"wins":19},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":10,"losses":25,"wins":47},"google/gemini-3.5-flash-lite":{"draws":19,"losses":34,"wins":85},"google/gemini-3.6-flash":{"draws":16,"losses":70,"wins":62},"google/gemini-3.8-flash":{"draws":13,"losses":25,"wins":32},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":14,"wins":19},"gpt-5.4":{"draws":8,"losses":35,"wins":37},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":9,"wins":35},"gpt-5.5":{"draws":10,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":18,"wins":38},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":36},"gpt-5.6-terra":{"draws":17,"losses":21,"wins":36},"gpt-6-astra":{"draws":5,"losses":65,"wins":4},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":3,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":28},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":44},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":42},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":31},"meta/muse-spark-1.3":{"draws":6,"losses":23,"wins":33},"meta/muse-wonder":{"draws":6,"losses":19,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"mistralai/mistral-large-4-0":{"draws":2,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":31,"wins":22},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":29},"o3":{"draws":7,"losses":19,"wins":72},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":37},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":34},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":31},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":21},"qwen/qwen3.8-flash":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max":{"draws":11,"losses":31,"wins":32},"qwen/qwen3.8-max-0902":{"draws":6,"losses":18,"wins":18},"stealth/ox-alpha":{"draws":53,"losses":91,"wins":102},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":17},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":18,"losses":6,"wins":48},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":51},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":31},"x-ai/grok-4.6":{"draws":14,"losses":38,"wins":24},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":25,"losses":33,"wins":60},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":30,"wins":34},"z-ai/glm-5.3-flashx":{"draws":5,"losses":18,"wins":19}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":24,"wins":2},"claude-opus-4-5":{"draws":18,"losses":37,"wins":3},"claude-opus-4-8":{"draws":6,"losses":25,"wins":1},"claude-opus-5":{"draws":10,"losses":43,"wins":5},"claude-opus-5-5":{"draws":5,"losses":31,"wins":0},"claude-sonnet-5":{"draws":10,"losses":23,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":26,"wins":13},"deepseek/deepseek-v4-pro":{"draws":13,"losses":21,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":1},"fireworks/ember-1":{"draws":8,"losses":27,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":11,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":36,"wins":3},"google/gemini-3.5-flash-lite":{"draws":16,"losses":32,"wins":18},"google/gemini-3.6-flash":{"draws":14,"losses":54,"wins":4},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":0},"google/gemma-4-31b-it":{"draws":5,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":23,"wins":2},"gpt-5.4":{"draws":9,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":10},"gpt-5.5":{"draws":13,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":9,"losses":21,"wins":6},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":22,"wins":3},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":10,"losses":24,"wins":2},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":8,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":23,"wins":7},"meta/muse-glimmer-30b":{"draws":9,"losses":17,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-wonder":{"draws":8,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":6},"o3":{"draws":5,"losses":46,"wins":3},"openai/gpt-oss-120b":{"draws":8,"losses":14,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.7-max":{"draws":3,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":28,"wins":1},"qwen/qwen3.8-27b":{"draws":6,"losses":19,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":8,"losses":28,"wins":0},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":77,"wins":15},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":17,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":25,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":19,"wins":8},"thinkingmachines/inkling-small":{"draws":11,"losses":13,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":27,"wins":1},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":43,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":31,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":1}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":32,"wins":22},"claude-fable-5":{"draws":22,"losses":46,"wins":8},"claude-fable-5-1":{"draws":5,"losses":71,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":31,"losses":68,"wins":10},"claude-opus-4-8":{"draws":14,"losses":26,"wins":4},"claude-opus-5":{"draws":12,"losses":66,"wins":6},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":27,"losses":48,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":55,"losses":40,"wins":21},"deepseek/deepseek-v4-pro":{"draws":24,"losses":50,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":38,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":25,"wins":9},"fireworks/ember-1":{"draws":17,"losses":26,"wins":5},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":25,"losses":44,"wins":21},"google/gemini-3.5-flash-lite":{"draws":67,"losses":76,"wins":30},"google/gemini-3.6-flash":{"draws":46,"losses":72,"wins":32},"google/gemini-3.8-flash":{"draws":28,"losses":34,"wins":16},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":5},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":16,"losses":19,"wins":9},"gpt-5.4":{"draws":38,"losses":33,"wins":4},"gpt-5.4-mini":{"draws":14,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":14,"losses":25,"wins":11},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":31,"losses":31,"wins":30},"gpt-5.6-sol":{"draws":8,"losses":56,"wins":12},"gpt-5.6-terra":{"draws":27,"losses":36,"wins":17},"gpt-6-astra":{"draws":5,"losses":65,"wins":0},"gpt-6-luna":{"draws":12,"losses":28,"wins":8},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":47,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":18,"wins":21},"inclusionai/ling-3.0-flash":{"draws":22,"losses":8,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":32,"wins":24},"meta/muse-glimmer-30b":{"draws":35,"losses":31,"wins":14},"meta/muse-spark-1.2":{"draws":17,"losses":40,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":47,"wins":9},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-large-4-0":{"draws":10,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":24,"losses":14,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":40,"wins":12},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":17,"wins":6},"o3":{"draws":22,"losses":62,"wins":20},"openai/gpt-oss-120b":{"draws":32,"losses":33,"wins":15},"poolside/laguna-s-2.1":{"draws":29,"losses":35,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":57,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":32,"wins":4},"qwen/qwen3.8-flash":{"draws":24,"losses":23,"wins":9},"qwen/qwen3.8-max":{"draws":45,"losses":69,"wins":23},"qwen/qwen3.8-max-0902":{"draws":16,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":89,"losses":144,"wins":41},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":26,"losses":48,"wins":8},"thinkingmachines/inkling":{"draws":26,"losses":43,"wins":13},"thinkingmachines/inkling-small":{"draws":35,"losses":34,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":19,"losses":48,"wins":11},"x-ai/grok-4.6":{"draws":25,"losses":45,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":32,"losses":24,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":15,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":50,"losses":59,"wins":31},"z-ai/glm-5.3":{"draws":14,"losses":43,"wins":11},"z-ai/glm-5.3-flash":{"draws":20,"losses":47,"wins":15},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":7,"wins":5},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":10,"wins":2},"claude-opus-4-5":{"draws":1,"losses":18,"wins":1},"claude-opus-4-8":{"draws":0,"losses":12,"wins":0},"claude-opus-5":{"draws":0,"losses":13,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":1,"losses":10,"wins":1},"claude-sonnet-5-5":{"draws":0,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":11,"wins":3},"deepseek/deepseek-v4-pro":{"draws":1,"losses":9,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":10,"wins":1},"fireworks/ember-1":{"draws":0,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":4,"wins":4},"google/gemini-3.5-flash":{"draws":1,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":3},"google/gemini-3.6-flash":{"draws":2,"losses":20,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":2},"gpt-4.1":{"draws":0,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":12,"wins":0},"gpt-5.4-mini":{"draws":1,"losses":6,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":11,"wins":3},"gpt-5.5":{"draws":0,"losses":9,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":8,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":12,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":11,"wins":1},"gpt-6-sol":{"draws":1,"losses":9,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":12,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":2},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":2,"losses":9,"wins":1},"meta/muse-wonder":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":8,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":7,"wins":3},"o3":{"draws":5,"losses":16,"wins":1},"openai/gpt-oss-120b":{"draws":3,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":3,"losses":26,"wins":3},"stealth/space-bunny-alpha":{"draws":0,"losses":7,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":2,"losses":10,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":10,"wins":3},"thinkingmachines/inkling-small":{"draws":0,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":4,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":10,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":10,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":22,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":33},"claude-fable-5":{"draws":5,"losses":26,"wins":17},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":21},"claude-opus-4-5":{"draws":34,"losses":31,"wins":57},"claude-opus-4-8":{"draws":15,"losses":30,"wins":41},"claude-opus-5":{"draws":22,"losses":111,"wins":33},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":12,"losses":11,"wins":25},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":18,"losses":11,"wins":69},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":14,"wins":21},"fireworks/ember-1":{"draws":12,"losses":15,"wins":21},"gemini-3.1-pro-preview":{"draws":10,"losses":11,"wins":27},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":36},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":35},"google/gemini-3.5-flash-lite":{"draws":23,"losses":21,"wins":82},"google/gemini-3.6-flash":{"draws":38,"losses":52,"wins":64},"google/gemini-3.8-flash":{"draws":9,"losses":17,"wins":32},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":18},"gpt-4.1":{"draws":8,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":13,"wins":45},"gpt-5.4":{"draws":15,"losses":19,"wins":18},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":32},"gpt-5.4-nano":{"draws":13,"losses":24,"wins":47},"gpt-5.5":{"draws":27,"losses":25,"wins":36},"gpt-5.6-luna":{"draws":15,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":16},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":29},"gpt-6-astra":{"draws":4,"losses":42,"wins":4},"gpt-6-luna":{"draws":11,"losses":13,"wins":24},"gpt-6-sol":{"draws":8,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":40,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":24},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":52},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":73},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":11,"losses":12,"wins":27},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":25},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":40},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":24,"losses":19,"wins":29},"nex-agi/nex-n2-pro":{"draws":13,"losses":1,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":49},"o3":{"draws":11,"losses":23,"wins":48},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":20,"losses":14,"wins":56},"qwen/qwen3.7-max":{"draws":18,"losses":11,"wins":19},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":24},"qwen/qwen3.8-flash":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"stealth/ox-alpha":{"draws":32,"losses":51,"wins":95},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":23},"tencent/hy4-preview":{"draws":11,"losses":13,"wins":22},"thinkingmachines/inkling":{"draws":26,"losses":9,"wins":53},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":16,"losses":15,"wins":23},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":7,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":14,"losses":0,"wins":26},"xiaomi/mimo-v2.5":{"draws":44,"losses":12,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":12,"wins":14},"z-ai/glm-5.2":{"draws":34,"losses":30,"wins":68},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":24},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":23}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":52},"claude-fable-5":{"draws":15,"losses":33,"wins":42},"claude-fable-5-1":{"draws":8,"losses":85,"wins":15},"claude-haiku-5-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-5":{"draws":25,"losses":13,"wins":72},"claude-opus-4-8":{"draws":11,"losses":9,"wins":26},"claude-opus-5":{"draws":12,"losses":57,"wins":25},"claude-opus-5-5":{"draws":8,"losses":37,"wins":7},"claude-sonnet-5":{"draws":17,"losses":14,"wins":53},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":16,"losses":5,"wins":75},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":7,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":11,"wins":25},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":16,"losses":12,"wins":70},"google/gemini-3.5-flash-lite":{"draws":15,"losses":9,"wins":94},"google/gemini-3.6-flash":{"draws":27,"losses":30,"wins":83},"google/gemini-3.8-flash":{"draws":21,"losses":24,"wins":45},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":6,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":3,"wins":29},"gpt-5.4":{"draws":22,"losses":22,"wins":40},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":5,"losses":0,"wins":43},"gpt-5.5":{"draws":8,"losses":13,"wins":23},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":46},"gpt-5.6-sol":{"draws":19,"losses":35,"wins":40},"gpt-5.6-terra":{"draws":21,"losses":15,"wins":48},"gpt-6-astra":{"draws":4,"losses":80,"wins":12},"gpt-6-luna":{"draws":8,"losses":2,"wins":38},"gpt-6-sol":{"draws":9,"losses":26,"wins":13},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":33},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":9,"losses":0,"wins":43},"meta/muse-spark-1.2":{"draws":12,"losses":8,"wins":46},"meta/muse-spark-1.3":{"draws":10,"losses":19,"wins":41},"meta/muse-wonder":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":38},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":0,"wins":33},"o3":{"draws":11,"losses":4,"wins":73},"openai/gpt-oss-120b":{"draws":10,"losses":1,"wins":39},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":47},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":17,"wins":45},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":29},"qwen/qwen3.8-flash":{"draws":17,"losses":8,"wins":31},"qwen/qwen3.8-max":{"draws":18,"losses":11,"wins":51},"qwen/qwen3.8-max-0902":{"draws":11,"losses":8,"wins":29},"stealth/ox-alpha":{"draws":54,"losses":55,"wins":179},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":20},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":48},"thinkingmachines/inkling":{"draws":22,"losses":3,"wins":45},"thinkingmachines/inkling-small":{"draws":12,"losses":2,"wins":54},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":14,"wins":36},"x-ai/grok-4.6":{"draws":18,"losses":15,"wins":25},"x-ai/grok-4.7":{"draws":6,"losses":19,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":21,"losses":2,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":2,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":16},"z-ai/glm-5.2":{"draws":30,"losses":12,"wins":82},"z-ai/glm-5.3":{"draws":14,"losses":30,"wins":32},"z-ai/glm-5.3-flash":{"draws":20,"losses":22,"wins":42},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":36},"claude-fable-5":{"draws":1,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":30,"wins":16},"claude-haiku-5-5":{"draws":2,"losses":2,"wins":36},"claude-opus-4-5":{"draws":3,"losses":3,"wins":62},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":7,"losses":27,"wins":46},"claude-opus-5-5":{"draws":6,"losses":28,"wins":12},"claude-sonnet-5":{"draws":3,"losses":4,"wins":35},"claude-sonnet-5-5":{"draws":3,"losses":15,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":4,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":28},"fireworks/ember-1":{"draws":2,"losses":4,"wins":36},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":32},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":1,"losses":7,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":7,"wins":59},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":71},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":38},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":22},"gpt-4.1":{"draws":1,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":0,"wins":37},"gpt-5.4":{"draws":2,"losses":5,"wins":33},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":34},"gpt-5.5":{"draws":0,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":29},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":35},"gpt-6-astra":{"draws":5,"losses":28,"wins":9},"gpt-6-luna":{"draws":3,"losses":1,"wins":38},"gpt-6-sol":{"draws":3,"losses":13,"wins":26},"gpt-6.1-sol":{"draws":2,"losses":25,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":36},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":33},"meta/muse-wonder":{"draws":1,"losses":10,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":21},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":10},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"o3":{"draws":3,"losses":2,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":36},"poolside/laguna-s-2.1":{"draws":1,"losses":2,"wins":39},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":36},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":24},"qwen/qwen3.8-max":{"draws":2,"losses":5,"wins":35},"qwen/qwen3.8-max-0902":{"draws":3,"losses":4,"wins":35},"stealth/ox-alpha":{"draws":14,"losses":13,"wins":115},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":1,"losses":8,"wins":31},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":51},"thinkingmachines/inkling-small":{"draws":2,"losses":1,"wins":39},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":7},"x-ai/grok-4.5":{"draws":4,"losses":4,"wins":34},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":34},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":13},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":21},"z-ai/glm-5.2":{"draws":3,"losses":5,"wins":76},"z-ai/glm-5.3":{"draws":2,"losses":9,"wins":29},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":34}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":10},"claude-fable-5":{"draws":11,"losses":31,"wins":8},"claude-fable-5-1":{"draws":0,"losses":53,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":47,"losses":65,"wins":18},"claude-opus-4-8":{"draws":24,"losses":50,"wins":14},"claude-opus-5":{"draws":22,"losses":84,"wins":8},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":21,"losses":28,"wins":3},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":40,"losses":38,"wins":26},"deepseek/deepseek-v4-pro":{"draws":18,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":27,"wins":5},"fireworks/ember-1":{"draws":18,"losses":24,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":18,"wins":13},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":38},"google/gemini-3.5-flash":{"draws":21,"losses":37,"wins":10},"google/gemini-3.5-flash-lite":{"draws":48,"losses":30,"wins":34},"google/gemini-3.6-flash":{"draws":35,"losses":66,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":8,"wins":9},"gpt-4.1":{"draws":14,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":27,"losses":33,"wins":16},"gpt-5.4":{"draws":12,"losses":29,"wins":7},"gpt-5.4-mini":{"draws":28,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":20,"losses":51,"wins":27},"gpt-5.5":{"draws":51,"losses":21,"wins":14},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":26,"wins":7},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":20,"losses":24,"wins":4},"gpt-6-sol":{"draws":8,"losses":38,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":8,"wins":8},"inclusionai/ling-3.0-flash":{"draws":26,"losses":4,"wins":36},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":28,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":33,"wins":11},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":8},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":20,"losses":17,"wins":25},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":16,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":22,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":31,"wins":6},"nex-agi/nex-n2-pro":{"draws":21,"losses":10,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":56,"losses":18,"wins":20},"o3":{"draws":22,"losses":51,"wins":13},"openai/gpt-oss-120b":{"draws":19,"losses":9,"wins":16},"poolside/laguna-s-2.1":{"draws":37,"losses":18,"wins":27},"qwen/qwen3.7-max":{"draws":27,"losses":15,"wins":22},"qwen/qwen3.7-plus":{"draws":17,"losses":22,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":19,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":21,"losses":20,"wins":9},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":44,"losses":107,"wins":19},"stealth/space-bunny-alpha":{"draws":12,"losses":16,"wins":10},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":21,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":25,"wins":6},"thinkingmachines/inkling":{"draws":32,"losses":22,"wins":32},"thinkingmachines/inkling-small":{"draws":22,"losses":14,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":23,"losses":46,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":69,"losses":37,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":26,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":47,"losses":48,"wins":23},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":28,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":36,"wins":13},"claude-fable-5":{"draws":21,"losses":68,"wins":3},"claude-fable-5-1":{"draws":6,"losses":93,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":52,"wins":10},"claude-opus-4-5":{"draws":115,"losses":123,"wins":38},"claude-opus-4-8":{"draws":59,"losses":84,"wins":13},"claude-opus-5":{"draws":39,"losses":175,"wins":20},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":44,"losses":41,"wins":15},"claude-sonnet-5-5":{"draws":23,"losses":56,"wins":11},"cohere/north-mini-code":{"draws":21,"losses":27,"wins":16},"deepseek/deepseek-v4-flash":{"draws":80,"losses":52,"wins":70},"deepseek/deepseek-v4-pro":{"draws":36,"losses":43,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":39,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":47,"wins":8},"fireworks/ember-1":{"draws":34,"losses":48,"wins":8},"gemini-3.1-pro-preview":{"draws":35,"losses":37,"wins":18},"google/gemini-3.1-flash-lite":{"draws":44,"losses":29,"wins":65},"google/gemini-3.5-flash":{"draws":45,"losses":59,"wins":20},"google/gemini-3.5-flash-lite":{"draws":78,"losses":55,"wins":61},"google/gemini-3.6-flash":{"draws":86,"losses":105,"wins":13},"google/gemini-3.8-flash":{"draws":32,"losses":55,"wins":7},"google/gemma-4-31b-it":{"draws":28,"losses":15,"wins":13},"gpt-4.1":{"draws":24,"losses":16,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":52,"losses":57,"wins":29},"gpt-5.4":{"draws":33,"losses":49,"wins":6},"gpt-5.4-mini":{"draws":53,"losses":47,"wins":18},"gpt-5.4-nano":{"draws":53,"losses":73,"wins":64},"gpt-5.5":{"draws":75,"losses":69,"wins":8},"gpt-5.6-luna":{"draws":41,"losses":35,"wins":18},"gpt-5.6-sol":{"draws":18,"losses":72,"wins":2},"gpt-5.6-terra":{"draws":38,"losses":53,"wins":5},"gpt-6-astra":{"draws":4,"losses":85,"wins":1},"gpt-6-luna":{"draws":38,"losses":39,"wins":13},"gpt-6-sol":{"draws":16,"losses":70,"wins":4},"gpt-6.1-sol":{"draws":8,"losses":80,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":38,"losses":10,"wins":24},"inclusionai/ling-3.0-flash":{"draws":42,"losses":25,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":61,"losses":50,"wins":51},"meta/muse-glimmer-30b":{"draws":34,"losses":30,"wins":22},"meta/muse-spark-1.2":{"draws":31,"losses":51,"wins":8},"meta/muse-spark-1.3":{"draws":28,"losses":58,"wins":8},"meta/muse-wonder":{"draws":26,"losses":60,"wins":4},"minimax/minimax-m3":{"draws":52,"losses":31,"wins":33},"mistralai/mistral-large-4-0":{"draws":24,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":29,"losses":8,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":29,"losses":36,"wins":7},"moonshotai/kimi-k3":{"draws":36,"losses":47,"wins":13},"nex-agi/nex-n2-pro":{"draws":17,"losses":25,"wins":34},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":72,"losses":56,"wins":26},"o3":{"draws":40,"losses":104,"wins":14},"openai/gpt-oss-120b":{"draws":32,"losses":24,"wins":24},"poolside/laguna-s-2.1":{"draws":46,"losses":43,"wins":37},"qwen/qwen3.7-max":{"draws":47,"losses":48,"wins":21},"qwen/qwen3.7-plus":{"draws":53,"losses":38,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":47,"wins":7},"qwen/qwen3.8-27b":{"draws":23,"losses":32,"wins":7},"qwen/qwen3.8-flash":{"draws":27,"losses":22,"wins":13},"qwen/qwen3.8-max":{"draws":41,"losses":42,"wins":11},"qwen/qwen3.8-max-0902":{"draws":32,"losses":46,"wins":12},"stealth/ox-alpha":{"draws":79,"losses":150,"wins":33},"stealth/space-bunny-alpha":{"draws":32,"losses":29,"wins":13},"stepfun/step-3.7-flash":{"draws":21,"losses":24,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":41,"losses":25,"wins":24},"tencent/hy4-preview":{"draws":29,"losses":47,"wins":8},"thinkingmachines/inkling":{"draws":60,"losses":39,"wins":63},"thinkingmachines/inkling-small":{"draws":41,"losses":29,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":30,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":3},"x-ai/grok-4.5":{"draws":47,"losses":76,"wins":7},"x-ai/grok-4.6":{"draws":35,"losses":55,"wins":6},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":33,"losses":21,"wins":14},"xiaomi/mimo-v2.5":{"draws":142,"losses":64,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":37,"losses":39,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":31,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":38,"wins":4},"z-ai/glm-5.2":{"draws":96,"losses":111,"wins":45},"z-ai/glm-5.3":{"draws":27,"losses":60,"wins":1},"z-ai/glm-5.3-flash":{"draws":32,"losses":49,"wins":13},"z-ai/glm-5.3-flashx":{"draws":35,"losses":50,"wins":5}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":11,"wins":19},"claude-fable-5":{"draws":3,"losses":37,"wins":2},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":10},"claude-opus-4-5":{"draws":24,"losses":43,"wins":47},"claude-opus-4-8":{"draws":14,"losses":43,"wins":19},"claude-opus-5":{"draws":19,"losses":70,"wins":5},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":3,"losses":22,"wins":23},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":14},"deepseek/deepseek-v4-flash":{"draws":20,"losses":17,"wins":35},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":12,"wins":15},"fireworks/ember-1":{"draws":10,"losses":14,"wins":12},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":15},"google/gemini-3.1-flash-lite":{"draws":13,"losses":6,"wins":45},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":24},"google/gemini-3.5-flash-lite":{"draws":27,"losses":21,"wins":50},"google/gemini-3.6-flash":{"draws":22,"losses":51,"wins":29},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":12},"gpt-4.1":{"draws":4,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":23,"wins":16},"gpt-5.4":{"draws":5,"losses":36,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":15,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":29,"wins":43},"gpt-5.5":{"draws":13,"losses":33,"wins":14},"gpt-5.6-luna":{"draws":9,"losses":16,"wins":21},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":23,"wins":10},"gpt-6-astra":{"draws":2,"losses":40,"wins":2},"gpt-6-luna":{"draws":8,"losses":16,"wins":12},"gpt-6-sol":{"draws":5,"losses":28,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":6,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":26},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":36},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":15},"meta/muse-spark-1.2":{"draws":2,"losses":26,"wins":20},"meta/muse-spark-1.3":{"draws":5,"losses":23,"wins":12},"meta/muse-wonder":{"draws":3,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":11,"losses":15,"wins":18},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":25},"nex-agi/nex-n2-pro":{"draws":6,"losses":9,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":13,"wins":32},"o3":{"draws":12,"losses":34,"wins":52},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":15,"losses":14,"wins":27},"qwen/qwen3.7-max":{"draws":13,"losses":23,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":16},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":14},"qwen/qwen3.8-max":{"draws":2,"losses":22,"wins":14},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":12},"stealth/ox-alpha":{"draws":16,"losses":57,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":15},"tencent/hy4-preview":{"draws":7,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":17},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":7,"losses":26,"wins":33},"x-ai/grok-4.6":{"draws":11,"losses":25,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":33,"losses":13,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":31,"losses":31,"wins":38},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":5},"z-ai/glm-5.3-flash":{"draws":5,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":12}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":32},"claude-fable-5":{"draws":6,"losses":24,"wins":18},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":9,"losses":20,"wins":17},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":6,"losses":12,"wins":26},"claude-opus-5":{"draws":8,"losses":63,"wins":11},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":7,"losses":9,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":12,"losses":12,"wins":48},"deepseek/deepseek-v4-pro":{"draws":11,"losses":10,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":20,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":5,"losses":18,"wins":25},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":18,"wins":33},"google/gemini-3.5-flash-lite":{"draws":14,"losses":10,"wins":60},"google/gemini-3.6-flash":{"draws":10,"losses":33,"wins":49},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":6,"losses":11,"wins":25},"gpt-5.4":{"draws":7,"losses":19,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":10,"wins":29},"gpt-5.5":{"draws":6,"losses":19,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":7,"losses":16,"wins":23},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":8,"losses":13,"wins":27},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":2,"wins":25},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":10,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":18},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":19},"meta/muse-wonder":{"draws":1,"losses":31,"wins":16},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":13,"wins":24},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":26},"o3":{"draws":9,"losses":15,"wins":42},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":16,"wins":24},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":17,"wins":25},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"stealth/ox-alpha":{"draws":22,"losses":61,"wins":75},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":30},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":22},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":13,"losses":1,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":26},"x-ai/grok-4.6":{"draws":8,"losses":19,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":12,"losses":20,"wins":64},"z-ai/glm-5.3":{"draws":7,"losses":28,"wins":11},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":21},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":38},"claude-fable-5":{"draws":2,"losses":15,"wins":31},"claude-fable-5-1":{"draws":9,"losses":38,"wins":7},"claude-haiku-5-5":{"draws":4,"losses":11,"wins":31},"claude-opus-4-5":{"draws":11,"losses":8,"wins":59},"claude-opus-4-8":{"draws":2,"losses":13,"wins":29},"claude-opus-5":{"draws":16,"losses":39,"wins":27},"claude-opus-5-5":{"draws":4,"losses":39,"wins":9},"claude-sonnet-5":{"draws":0,"losses":9,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":18,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":3,"losses":9,"wins":60},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":26},"fireworks/ember-1":{"draws":7,"losses":11,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":9,"wins":37},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":30},"google/gemini-3.5-flash":{"draws":9,"losses":11,"wins":40},"google/gemini-3.5-flash-lite":{"draws":0,"losses":12,"wins":72},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":64},"google/gemini-3.8-flash":{"draws":7,"losses":8,"wins":33},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":26},"gpt-4.1":{"draws":2,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":8,"wins":32},"gpt-5.4":{"draws":5,"losses":14,"wins":27},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":8,"wins":40},"gpt-5.5":{"draws":8,"losses":10,"wins":26},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":40},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":25},"gpt-5.6-terra":{"draws":9,"losses":7,"wins":30},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":21,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":27,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":30},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":43},"meta/muse-glimmer-30b":{"draws":0,"losses":7,"wins":35},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":35},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-wonder":{"draws":9,"losses":15,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":31},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":32},"o3":{"draws":1,"losses":8,"wins":57},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":40},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":13,"wins":27},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":24},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":36},"qwen/qwen3.8-max-0902":{"draws":4,"losses":11,"wins":33},"stealth/ox-alpha":{"draws":14,"losses":37,"wins":107},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":27},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":6,"losses":10,"wins":30},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":6,"losses":13,"wins":29},"x-ai/grok-4.6":{"draws":9,"losses":11,"wins":28},"x-ai/grok-4.7":{"draws":1,"losses":25,"wins":16},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":7,"losses":9,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":7,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":13},"z-ai/glm-5.2":{"draws":9,"losses":15,"wins":72},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":26},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":30}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":23,"wins":59},"claude-fable-5":{"draws":31,"losses":72,"wins":25},"claude-fable-5-1":{"draws":15,"losses":122,"wins":5},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":75,"losses":70,"wins":83},"claude-opus-4-8":{"draws":47,"losses":64,"wins":33},"claude-opus-5":{"draws":31,"losses":167,"wins":10},"claude-opus-5-5":{"draws":5,"losses":95,"wins":4},"claude-sonnet-5":{"draws":38,"losses":49,"wins":47},"claude-sonnet-5-5":{"draws":19,"losses":52,"wins":25},"cohere/north-mini-code":{"draws":20,"losses":11,"wins":17},"deepseek/deepseek-v4-flash":{"draws":83,"losses":38,"wins":81},"deepseek/deepseek-v4-pro":{"draws":58,"losses":36,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":45,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":23},"fireworks/ember-1":{"draws":33,"losses":40,"wins":23},"gemini-3.1-pro-preview":{"draws":32,"losses":29,"wins":35},"google/gemini-3.1-flash-lite":{"draws":27,"losses":7,"wins":50},"google/gemini-3.5-flash":{"draws":57,"losses":50,"wins":59},"google/gemini-3.5-flash-lite":{"draws":103,"losses":40,"wins":97},"google/gemini-3.6-flash":{"draws":63,"losses":94,"wins":85},"google/gemini-3.8-flash":{"draws":30,"losses":66,"wins":42},"google/gemma-4-31b-it":{"draws":25,"losses":8,"wins":23},"gpt-4.1":{"draws":18,"losses":9,"wins":21},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":47,"losses":36,"wins":39},"gpt-5.4":{"draws":45,"losses":45,"wins":34},"gpt-5.4-mini":{"draws":58,"losses":11,"wins":29},"gpt-5.4-nano":{"draws":43,"losses":37,"wins":50},"gpt-5.5":{"draws":57,"losses":50,"wins":21},"gpt-5.6-luna":{"draws":62,"losses":24,"wins":44},"gpt-5.6-sol":{"draws":17,"losses":77,"wins":34},"gpt-5.6-terra":{"draws":59,"losses":39,"wins":36},"gpt-6-astra":{"draws":12,"losses":106,"wins":8},"gpt-6-luna":{"draws":31,"losses":35,"wins":30},"gpt-6-sol":{"draws":14,"losses":71,"wins":11},"gpt-6.1-sol":{"draws":15,"losses":77,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":46,"losses":4,"wins":44},"inclusionai/ling-3.0-flash":{"draws":51,"losses":7,"wins":32},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":46,"losses":34,"wins":62},"meta/muse-glimmer-30b":{"draws":52,"losses":22,"wins":42},"meta/muse-spark-1.2":{"draws":27,"losses":55,"wins":34},"meta/muse-spark-1.3":{"draws":31,"losses":47,"wins":36},"meta/muse-wonder":{"draws":26,"losses":52,"wins":18},"minimax/minimax-m3":{"draws":25,"losses":12,"wins":31},"mistralai/mistral-large-4-0":{"draws":29,"losses":19,"wins":12},"mistralai/mistral-medium-3-5":{"draws":32,"losses":9,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":10,"wins":19},"moonshotai/kimi-k3":{"draws":45,"losses":34,"wins":33},"nex-agi/nex-n2-pro":{"draws":32,"losses":3,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":19,"wins":46},"o3":{"draws":34,"losses":61,"wins":81},"openai/gpt-oss-120b":{"draws":58,"losses":16,"wins":40},"poolside/laguna-s-2.1":{"draws":75,"losses":18,"wins":43},"qwen/qwen3.7-max":{"draws":27,"losses":14,"wins":35},"qwen/qwen3.7-plus":{"draws":24,"losses":9,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":55,"wins":39},"qwen/qwen3.8-27b":{"draws":23,"losses":23,"wins":30},"qwen/qwen3.8-flash":{"draws":31,"losses":30,"wins":25},"qwen/qwen3.8-max":{"draws":41,"losses":50,"wins":39},"qwen/qwen3.8-max-0902":{"draws":32,"losses":42,"wins":22},"stealth/ox-alpha":{"draws":122,"losses":192,"wins":122},"stealth/space-bunny-alpha":{"draws":31,"losses":19,"wins":26},"stepfun/step-3.7-flash":{"draws":22,"losses":8,"wins":42},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":20,"wins":22},"tencent/hy4-preview":{"draws":32,"losses":61,"wins":31},"thinkingmachines/inkling":{"draws":52,"losses":32,"wins":74},"thinkingmachines/inkling-small":{"draws":51,"losses":18,"wins":63},"unbiased/pareto-26.10-preview":{"draws":1,"losses":29,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":36,"losses":49,"wins":41},"x-ai/grok-4.6":{"draws":38,"losses":72,"wins":28},"x-ai/grok-4.7":{"draws":9,"losses":62,"wins":13},"x-ai/grok-build-0.1":{"draws":18,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":88,"losses":25,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":17,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":22,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":31,"wins":15},"z-ai/glm-5.2":{"draws":96,"losses":57,"wins":71},"z-ai/glm-5.3":{"draws":29,"losses":63,"wins":28},"z-ai/glm-5.3-flash":{"draws":50,"losses":55,"wins":33},"z-ai/glm-5.3-flashx":{"draws":31,"losses":40,"wins":25}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":44},"claude-fable-5":{"draws":14,"losses":32,"wins":44},"claude-fable-5-1":{"draws":8,"losses":77,"wins":23},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":28},"claude-opus-4-5":{"draws":22,"losses":14,"wins":76},"claude-opus-4-8":{"draws":8,"losses":12,"wins":28},"claude-opus-5":{"draws":16,"losses":60,"wins":16},"claude-opus-5-5":{"draws":3,"losses":36,"wins":13},"claude-sonnet-5":{"draws":10,"losses":12,"wins":60},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":26},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":19,"losses":3,"wins":74},"deepseek/deepseek-v4-pro":{"draws":10,"losses":15,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":15,"losses":17,"wins":66},"google/gemini-3.5-flash-lite":{"draws":18,"losses":4,"wins":100},"google/gemini-3.6-flash":{"draws":27,"losses":29,"wins":94},"google/gemini-3.8-flash":{"draws":17,"losses":20,"wins":53},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":30},"gpt-5.4":{"draws":10,"losses":24,"wins":48},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":9,"wins":38},"gpt-5.5":{"draws":15,"losses":12,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":58},"gpt-5.6-sol":{"draws":18,"losses":43,"wins":33},"gpt-5.6-terra":{"draws":27,"losses":8,"wins":47},"gpt-6-astra":{"draws":17,"losses":74,"wins":5},"gpt-6-luna":{"draws":10,"losses":7,"wins":31},"gpt-6-sol":{"draws":6,"losses":23,"wins":19},"gpt-6.1-sol":{"draws":12,"losses":29,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":36},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":3,"wins":45},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":47},"meta/muse-spark-1.2":{"draws":9,"losses":19,"wins":40},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":42},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":26,"wins":40},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":3,"wins":33},"o3":{"draws":10,"losses":14,"wins":74},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":41},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":22,"wins":49},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":22},"qwen/qwen3.8-flash":{"draws":13,"losses":7,"wins":38},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":49},"qwen/qwen3.8-max-0902":{"draws":10,"losses":7,"wins":31},"stealth/ox-alpha":{"draws":39,"losses":70,"wins":173},"stealth/space-bunny-alpha":{"draws":5,"losses":2,"wins":31},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":53},"thinkingmachines/inkling":{"draws":16,"losses":7,"wins":55},"thinkingmachines/inkling-small":{"draws":11,"losses":0,"wins":59},"unbiased/pareto-26.10-preview":{"draws":2,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":8,"losses":21,"wins":41},"x-ai/grok-4.6":{"draws":18,"losses":28,"wins":44},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":16,"losses":1,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":0,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":26,"losses":23,"wins":73},"z-ai/glm-5.3":{"draws":12,"losses":8,"wins":24},"z-ai/glm-5.3-flash":{"draws":20,"losses":19,"wins":47},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":30}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":11,"wins":34},"claude-fable-5":{"draws":13,"losses":42,"wins":31},"claude-fable-5-1":{"draws":9,"losses":85,"wins":10},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":28,"losses":19,"wins":59},"claude-opus-4-8":{"draws":8,"losses":15,"wins":23},"claude-opus-5":{"draws":8,"losses":67,"wins":23},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":17,"losses":12,"wins":55},"claude-sonnet-5-5":{"draws":5,"losses":24,"wins":19},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":26,"losses":9,"wins":63},"deepseek/deepseek-v4-pro":{"draws":21,"losses":25,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":16,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"fireworks/ember-1":{"draws":10,"losses":13,"wins":25},"gemini-3.1-pro-preview":{"draws":12,"losses":10,"wins":26},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":21,"losses":26,"wins":53},"google/gemini-3.5-flash-lite":{"draws":35,"losses":4,"wins":97},"google/gemini-3.6-flash":{"draws":32,"losses":37,"wins":79},"google/gemini-3.8-flash":{"draws":19,"losses":37,"wins":32},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":11,"wins":23},"gpt-5.4":{"draws":22,"losses":38,"wins":28},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":21},"gpt-5.6-luna":{"draws":19,"losses":16,"wins":43},"gpt-5.6-sol":{"draws":12,"losses":41,"wins":39},"gpt-5.6-terra":{"draws":22,"losses":25,"wins":35},"gpt-6-astra":{"draws":14,"losses":71,"wins":9},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":4,"wins":41},"meta/muse-glimmer-30b":{"draws":20,"losses":6,"wins":40},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":30},"meta/muse-spark-1.3":{"draws":18,"losses":22,"wins":34},"meta/muse-wonder":{"draws":7,"losses":23,"wins":18},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":18,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":30},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":4,"wins":23},"o3":{"draws":17,"losses":26,"wins":53},"openai/gpt-oss-120b":{"draws":22,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":22,"losses":9,"wins":33},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":29,"wins":31},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":22},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":21},"qwen/qwen3.8-max":{"draws":18,"losses":29,"wins":35},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":53,"losses":96,"wins":141},"stealth/space-bunny-alpha":{"draws":9,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":30,"wins":38},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":59},"thinkingmachines/inkling-small":{"draws":27,"losses":4,"wins":47},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":29,"wins":32},"x-ai/grok-4.6":{"draws":19,"losses":32,"wins":37},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":2,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":39,"losses":16,"wins":75},"z-ai/glm-5.3":{"draws":18,"losses":33,"wins":25},"z-ai/glm-5.3-flash":{"draws":15,"losses":8,"wins":37},"z-ai/glm-5.3-flashx":{"draws":12,"losses":13,"wins":23}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":12,"losses":27,"wins":9},"claude-fable-5-1":{"draws":4,"losses":45,"wins":5},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":13},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":21,"wins":14},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":10,"losses":15,"wins":23},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":27},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":19,"wins":26},"google/gemini-3.5-flash-lite":{"draws":15,"losses":26,"wins":43},"google/gemini-3.6-flash":{"draws":19,"losses":40,"wins":33},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":12},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":17,"wins":15},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":12,"losses":16,"wins":20},"gpt-6-sol":{"draws":4,"losses":34,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":20},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":11},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":15,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":26},"o3":{"draws":4,"losses":32,"wins":30},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"stealth/ox-alpha":{"draws":31,"losses":64,"wins":63},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":10,"losses":10,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":17},"x-ai/grok-4.6":{"draws":14,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":11,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":43},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":14,"losses":16,"wins":18},"z-ai/glm-5.3-flashx":{"draws":12,"losses":15,"wins":5}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":10},"claude-fable-5":{"draws":9,"losses":41,"wins":6},"claude-fable-5-1":{"draws":1,"losses":57,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":30,"wins":3},"claude-opus-4-5":{"draws":25,"losses":54,"wins":11},"claude-opus-4-8":{"draws":7,"losses":31,"wins":0},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":20,"losses":48,"wins":8},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":33,"losses":41,"wins":22},"deepseek/deepseek-v4-pro":{"draws":22,"losses":44,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":36,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":13,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":24,"wins":7},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":20,"losses":50,"wins":14},"google/gemini-3.5-flash-lite":{"draws":42,"losses":68,"wins":36},"google/gemini-3.6-flash":{"draws":34,"losses":80,"wins":16},"google/gemini-3.8-flash":{"draws":17,"losses":40,"wins":7},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":11,"losses":18,"wins":9},"gpt-5.4":{"draws":18,"losses":32,"wins":12},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":15},"gpt-5.5":{"draws":14,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":16,"losses":34,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":54,"wins":2},"gpt-5.6-terra":{"draws":18,"losses":45,"wins":7},"gpt-6-astra":{"draws":1,"losses":47,"wins":2},"gpt-6-luna":{"draws":13,"losses":22,"wins":7},"gpt-6-sol":{"draws":4,"losses":35,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":13,"wins":21},"inclusionai/ling-3.0-flash":{"draws":17,"losses":10,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":24,"wins":19},"meta/muse-glimmer-30b":{"draws":33,"losses":29,"wins":14},"meta/muse-spark-1.2":{"draws":16,"losses":36,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":43,"wins":7},"meta/muse-wonder":{"draws":5,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":22,"losses":14,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":32,"wins":14},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":10},"o3":{"draws":21,"losses":60,"wins":19},"openai/gpt-oss-120b":{"draws":22,"losses":29,"wins":17},"poolside/laguna-s-2.1":{"draws":22,"losses":24,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":43,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":22,"losses":24,"wins":4},"qwen/qwen3.8-max":{"draws":29,"losses":34,"wins":11},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":4},"stealth/ox-alpha":{"draws":47,"losses":152,"wins":37},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":6},"stepfun/step-3.7-flash":{"draws":10,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":26,"losses":39,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":30,"wins":24},"thinkingmachines/inkling-small":{"draws":31,"losses":22,"wins":29},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":6,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":45,"wins":8},"x-ai/grok-4.6":{"draws":20,"losses":37,"wins":9},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":24,"losses":24,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":18,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":55,"losses":45,"wins":20},"z-ai/glm-5.3":{"draws":13,"losses":38,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":36,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":29,"wins":6}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":8,"wins":44},"claude-fable-5":{"draws":9,"losses":32,"wins":17},"claude-fable-5-1":{"draws":3,"losses":84,"wins":7},"claude-haiku-5-5":{"draws":7,"losses":15,"wins":24},"claude-opus-4-5":{"draws":23,"losses":22,"wins":59},"claude-opus-4-8":{"draws":10,"losses":17,"wins":19},"claude-opus-5":{"draws":17,"losses":66,"wins":13},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":26,"losses":18,"wins":44},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":27,"losses":11,"wins":72},"deepseek/deepseek-v4-pro":{"draws":29,"losses":18,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":14,"losses":10,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":28,"losses":23,"wins":43},"google/gemini-3.5-flash-lite":{"draws":41,"losses":22,"wins":75},"google/gemini-3.6-flash":{"draws":35,"losses":52,"wins":65},"google/gemini-3.8-flash":{"draws":18,"losses":38,"wins":32},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":4,"wins":25},"gpt-5.4":{"draws":28,"losses":28,"wins":36},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":3,"wins":35},"gpt-5.5":{"draws":16,"losses":12,"wins":20},"gpt-5.6-luna":{"draws":31,"losses":12,"wins":39},"gpt-5.6-sol":{"draws":17,"losses":40,"wins":29},"gpt-5.6-terra":{"draws":24,"losses":19,"wins":47},"gpt-6-astra":{"draws":4,"losses":65,"wins":17},"gpt-6-luna":{"draws":11,"losses":10,"wins":27},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":1,"wins":23},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":40},"meta/muse-glimmer-30b":{"draws":25,"losses":2,"wins":37},"meta/muse-spark-1.2":{"draws":17,"losses":21,"wins":34},"meta/muse-spark-1.3":{"draws":14,"losses":23,"wins":31},"meta/muse-wonder":{"draws":11,"losses":22,"wins":15},"minimax/minimax-m3":{"draws":9,"losses":0,"wins":19},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":19,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":23,"losses":12,"wins":39},"nex-agi/nex-n2-pro":{"draws":7,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":4,"wins":31},"o3":{"draws":11,"losses":14,"wins":71},"openai/gpt-oss-120b":{"draws":24,"losses":6,"wins":36},"poolside/laguna-s-2.1":{"draws":21,"losses":10,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":19},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":26,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":19},"qwen/qwen3.8-flash":{"draws":17,"losses":12,"wins":25},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":40},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"stealth/ox-alpha":{"draws":68,"losses":81,"wins":129},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":28,"wins":42},"thinkingmachines/inkling":{"draws":21,"losses":4,"wins":51},"thinkingmachines/inkling-small":{"draws":26,"losses":9,"wins":43},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":32,"wins":30},"x-ai/grok-4.6":{"draws":20,"losses":28,"wins":40},"x-ai/grok-4.7":{"draws":1,"losses":28,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":20,"wins":10},"z-ai/glm-5.2":{"draws":41,"losses":27,"wins":58},"z-ai/glm-5.3":{"draws":12,"losses":43,"wins":19},"z-ai/glm-5.3-flash":{"draws":11,"losses":42,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":19,"wins":21}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":4,"wins":54},"claude-fable-5":{"draws":5,"losses":20,"wins":65},"claude-fable-5-1":{"draws":5,"losses":53,"wins":18},"claude-haiku-5-5":{"draws":2,"losses":6,"wins":38},"claude-opus-4-5":{"draws":7,"losses":2,"wins":97},"claude-opus-4-8":{"draws":4,"losses":3,"wins":37},"claude-opus-5":{"draws":14,"losses":26,"wins":48},"claude-opus-5-5":{"draws":2,"losses":28,"wins":22},"claude-sonnet-5":{"draws":9,"losses":3,"wins":72},"claude-sonnet-5-5":{"draws":4,"losses":12,"wins":32},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":89},"deepseek/deepseek-v4-pro":{"draws":7,"losses":2,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":2,"wins":36},"fireworks/ember-1":{"draws":4,"losses":2,"wins":42},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":45},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":33},"google/gemini-3.5-flash":{"draws":13,"losses":6,"wins":77},"google/gemini-3.5-flash-lite":{"draws":14,"losses":0,"wins":102},"google/gemini-3.6-flash":{"draws":15,"losses":6,"wins":119},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":74},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":1,"losses":0,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":1,"wins":38},"gpt-5.4":{"draws":7,"losses":16,"wins":61},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":49},"gpt-5.5":{"draws":2,"losses":6,"wins":36},"gpt-5.6-luna":{"draws":8,"losses":5,"wins":55},"gpt-5.6-sol":{"draws":13,"losses":15,"wins":66},"gpt-5.6-terra":{"draws":12,"losses":0,"wins":68},"gpt-6-astra":{"draws":11,"losses":65,"wins":20},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":6,"losses":15,"wins":27},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":31},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":36},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":55},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":5,"losses":1,"wins":62},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":57},"meta/muse-wonder":{"draws":6,"losses":10,"wins":32},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"mistralai/mistral-large-4-0":{"draws":1,"losses":1,"wins":28},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":3,"wins":61},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"o3":{"draws":2,"losses":6,"wins":82},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":51},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":54},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":29},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":3,"wins":70},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":38},"qwen/qwen3.8-flash":{"draws":5,"losses":3,"wins":46},"qwen/qwen3.8-max":{"draws":9,"losses":3,"wins":68},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":37,"losses":15,"wins":232},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":22},"tencent/hy4-preview":{"draws":7,"losses":10,"wins":63},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":65},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":64},"unbiased/pareto-26.10-preview":{"draws":1,"losses":10,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":62},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":71},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":6,"wins":21},"z-ai/glm-5.2":{"draws":12,"losses":5,"wins":101},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":51},"z-ai/glm-5.3-flash":{"draws":17,"losses":5,"wins":66},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":39}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":12,"wins":14},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":7},"claude-opus-4-5":{"draws":30,"losses":32,"wins":16},"claude-opus-4-8":{"draws":15,"losses":27,"wins":2},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":22,"wins":9},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":30,"losses":18,"wins":24},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":10},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":20,"losses":26,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":30,"losses":49,"wins":13},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":18,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":15,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":13},"gpt-5.5":{"draws":22,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":22,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":18,"wins":11},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":10,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":23,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-wonder":{"draws":11,"losses":36,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":12},"mistralai/mistral-large-4-0":{"draws":16,"losses":11,"wins":3},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":19,"wins":8},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":11,"wins":11},"o3":{"draws":16,"losses":35,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":17,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-27b":{"draws":12,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-max-0902":{"draws":19,"losses":23,"wins":6},"stealth/ox-alpha":{"draws":43,"losses":84,"wins":31},"stealth/space-bunny-alpha":{"draws":17,"losses":11,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":10,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":13,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":28,"losses":14,"wins":22},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":16,"losses":26,"wins":6},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":30,"losses":16,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":21,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":34,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":17,"wins":15},"claude-fable-5":{"draws":11,"losses":30,"wins":11},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":19,"wins":12},"claude-opus-4-5":{"draws":46,"losses":26,"wins":34},"claude-opus-4-8":{"draws":21,"losses":48,"wins":25},"claude-opus-5":{"draws":26,"losses":117,"wins":15},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":17,"losses":21,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":25,"losses":25,"wins":38},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":20,"wins":16},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":36},"google/gemini-3.5-flash":{"draws":20,"losses":26,"wins":20},"google/gemini-3.5-flash-lite":{"draws":45,"losses":24,"wins":39},"google/gemini-3.6-flash":{"draws":39,"losses":49,"wins":34},"google/gemini-3.8-flash":{"draws":20,"losses":24,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":16,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":24,"losses":13,"wins":17},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":29,"losses":16,"wins":21},"gpt-5.4-nano":{"draws":24,"losses":26,"wins":44},"gpt-5.5":{"draws":44,"losses":29,"wins":11},"gpt-5.6-luna":{"draws":21,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":34,"wins":8},"gpt-5.6-terra":{"draws":26,"losses":15,"wins":9},"gpt-6-astra":{"draws":3,"losses":41,"wins":6},"gpt-6-luna":{"draws":15,"losses":19,"wins":14},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":39,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":28,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":32,"losses":11,"wins":41},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":9},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":12,"losses":8,"wins":24},"mistralai/mistral-large-4-0":{"draws":10,"losses":6,"wins":14},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":6,"wins":13},"moonshotai/kimi-k3":{"draws":28,"losses":21,"wins":15},"nex-agi/nex-n2-pro":{"draws":11,"losses":8,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":10,"wins":37},"o3":{"draws":12,"losses":21,"wins":47},"openai/gpt-oss-120b":{"draws":17,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":32,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":9,"losses":19,"wins":26},"qwen/qwen3.7-plus":{"draws":16,"losses":10,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":19,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":9},"qwen/qwen3.8-flash":{"draws":15,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"stealth/ox-alpha":{"draws":54,"losses":81,"wins":39},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":25},"tencent/hy4-preview":{"draws":14,"losses":21,"wins":15},"thinkingmachines/inkling":{"draws":34,"losses":18,"wins":40},"thinkingmachines/inkling-small":{"draws":18,"losses":6,"wins":26},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":9},"x-ai/grok-4.5":{"draws":22,"losses":27,"wins":23},"x-ai/grok-4.6":{"draws":13,"losses":24,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":43,"losses":22,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":21,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":39,"losses":43,"wins":66},"z-ai/glm-5.3":{"draws":14,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":13,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":19},"claude-fable-5":{"draws":5,"losses":31,"wins":6},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":18,"wins":15},"claude-opus-4-5":{"draws":36,"losses":28,"wins":48},"claude-opus-4-8":{"draws":15,"losses":22,"wins":13},"claude-opus-5":{"draws":23,"losses":81,"wins":20},"claude-opus-5-5":{"draws":1,"losses":40,"wins":5},"claude-sonnet-5":{"draws":12,"losses":14,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":21,"losses":9,"wins":50},"deepseek/deepseek-v4-pro":{"draws":9,"losses":20,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"fireworks/ember-1":{"draws":15,"losses":15,"wins":12},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":36},"google/gemini-3.5-flash":{"draws":21,"losses":26,"wins":25},"google/gemini-3.5-flash-lite":{"draws":31,"losses":18,"wins":47},"google/gemini-3.6-flash":{"draws":29,"losses":49,"wins":26},"google/gemini-3.8-flash":{"draws":8,"losses":25,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":9,"losses":3,"wins":18},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":20,"wins":14},"gpt-5.4":{"draws":9,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":15,"losses":15,"wins":28},"gpt-5.4-nano":{"draws":17,"losses":28,"wins":45},"gpt-5.5":{"draws":21,"losses":39,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":13},"gpt-6-astra":{"draws":3,"losses":39,"wins":4},"gpt-6-luna":{"draws":9,"losses":16,"wins":17},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":15},"inclusionai/ling-3.0-flash":{"draws":24,"losses":0,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":8,"wins":40},"meta/muse-glimmer-30b":{"draws":13,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":15,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":12},"meta/muse-wonder":{"draws":8,"losses":22,"wins":12},"minimax/minimax-m3":{"draws":10,"losses":6,"wins":26},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":17,"losses":23,"wins":16},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":12,"wins":40},"o3":{"draws":8,"losses":34,"wins":30},"openai/gpt-oss-120b":{"draws":16,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":19,"losses":10,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":24,"wins":18},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":18,"wins":11},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":15},"stealth/ox-alpha":{"draws":23,"losses":70,"wins":37},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":9,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":22},"tencent/hy4-preview":{"draws":9,"losses":25,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":13,"wins":40},"thinkingmachines/inkling-small":{"draws":14,"losses":6,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":20,"losses":37,"wins":11},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":43,"losses":22,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":20,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":44,"losses":40,"wins":44},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":23,"wins":13}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":59},"claude-fable-5":{"draws":28,"losses":29,"wins":47},"claude-fable-5-1":{"draws":13,"losses":67,"wins":20},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":65,"losses":46,"wins":149},"claude-opus-4-8":{"draws":41,"losses":24,"wins":87},"claude-opus-5":{"draws":48,"losses":166,"wins":96},"claude-opus-5-5":{"draws":14,"losses":62,"wins":16},"claude-sonnet-5":{"draws":19,"losses":26,"wins":55},"claude-sonnet-5-5":{"draws":15,"losses":32,"wins":37},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":30},"deepseek/deepseek-v4-flash":{"draws":28,"losses":14,"wins":112},"deepseek/deepseek-v4-pro":{"draws":17,"losses":16,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":13,"wins":52},"fireworks/ember-1":{"draws":15,"losses":14,"wins":55},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":55},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":51},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":86},"google/gemini-3.5-flash-lite":{"draws":33,"losses":21,"wins":150},"google/gemini-3.6-flash":{"draws":50,"losses":55,"wins":137},"google/gemini-3.8-flash":{"draws":21,"losses":25,"wins":54},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":34},"gpt-4.1":{"draws":15,"losses":4,"wins":42},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":28,"losses":12,"wins":80},"gpt-5.4":{"draws":16,"losses":13,"wins":65},"gpt-5.4-mini":{"draws":32,"losses":10,"wins":54},"gpt-5.4-nano":{"draws":24,"losses":12,"wins":118},"gpt-5.5":{"draws":36,"losses":36,"wins":104},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":66},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":63},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":67},"gpt-6-astra":{"draws":11,"losses":63,"wins":16},"gpt-6-luna":{"draws":20,"losses":9,"wins":55},"gpt-6-sol":{"draws":14,"losses":37,"wins":33},"gpt-6.1-sol":{"draws":13,"losses":53,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"inclusionai/ling-3.0-flash":{"draws":31,"losses":3,"wins":60},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":25,"losses":9,"wins":110},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":60},"meta/muse-spark-1.2":{"draws":19,"losses":16,"wins":59},"meta/muse-spark-1.3":{"draws":22,"losses":24,"wins":44},"meta/muse-wonder":{"draws":15,"losses":27,"wins":42},"minimax/minimax-m3":{"draws":17,"losses":0,"wins":55},"mistralai/mistral-large-4-0":{"draws":12,"losses":7,"wins":35},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":34},"moonshotai/kimi-k3":{"draws":25,"losses":33,"wins":58},"nex-agi/nex-n2-pro":{"draws":2,"losses":8,"wins":52},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":1,"wins":75},"o3":{"draws":17,"losses":7,"wins":110},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":54},"poolside/laguna-s-2.1":{"draws":24,"losses":12,"wins":114},"qwen/qwen3.7-max":{"draws":13,"losses":13,"wins":66},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":61},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":41},"qwen/qwen3.8-flash":{"draws":15,"losses":9,"wins":34},"qwen/qwen3.8-max":{"draws":23,"losses":21,"wins":52},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":48},"stealth/ox-alpha":{"draws":75,"losses":76,"wins":161},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":46},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":27,"losses":4,"wins":57},"tencent/hy4-preview":{"draws":17,"losses":16,"wins":57},"thinkingmachines/inkling":{"draws":24,"losses":28,"wins":94},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":67},"unbiased/pareto-26.10-preview":{"draws":1,"losses":20,"wins":7},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":15},"x-ai/grok-4.5":{"draws":31,"losses":27,"wins":96},"x-ai/grok-4.6":{"draws":19,"losses":28,"wins":51},"x-ai/grok-4.7":{"draws":9,"losses":38,"wins":27},"x-ai/grok-build-0.1":{"draws":10,"losses":3,"wins":25},"xiaomi/mimo-v2.5":{"draws":36,"losses":15,"wins":139},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":2,"wins":64},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":16,"wins":27},"z-ai/glm-5.2":{"draws":64,"losses":18,"wins":158},"z-ai/glm-5.3":{"draws":16,"losses":32,"wins":34},"z-ai/glm-5.3-flash":{"draws":18,"losses":24,"wins":50},"z-ai/glm-5.3-flashx":{"draws":17,"losses":24,"wins":43}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":8,"losses":15,"wins":31},"claude-fable-5-1":{"draws":7,"losses":37,"wins":16},"claude-haiku-5-5":{"draws":12,"losses":7,"wins":33},"claude-opus-4-5":{"draws":16,"losses":15,"wins":57},"claude-opus-4-8":{"draws":9,"losses":14,"wins":27},"claude-opus-5":{"draws":16,"losses":50,"wins":28},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":11,"losses":10,"wins":33},"claude-sonnet-5-5":{"draws":7,"losses":16,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":66},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":4,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":36},"fireworks/ember-1":{"draws":8,"losses":11,"wins":35},"gemini-3.1-pro-preview":{"draws":7,"losses":5,"wins":42},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":49},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":22,"losses":9,"wins":71},"google/gemini-3.8-flash":{"draws":12,"losses":15,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":27},"gpt-4.1":{"draws":5,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":4,"wins":35},"gpt-5.4":{"draws":10,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":32},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":49},"gpt-5.5":{"draws":11,"losses":11,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":1,"wins":39},"gpt-5.6-sol":{"draws":10,"losses":12,"wins":32},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":42},"gpt-6-astra":{"draws":8,"losses":34,"wins":12},"gpt-6-luna":{"draws":13,"losses":1,"wins":40},"gpt-6-sol":{"draws":8,"losses":26,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":36,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":30},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":45},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":11,"losses":6,"wins":35},"meta/muse-spark-1.3":{"draws":7,"losses":11,"wins":36},"meta/muse-wonder":{"draws":6,"losses":20,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":2,"wins":21},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":38},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":45},"o3":{"draws":8,"losses":2,"wins":66},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":9,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":29},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":13,"wins":31},"qwen/qwen3.8-27b":{"draws":5,"losses":1,"wins":30},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":27},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":12,"losses":5,"wins":37},"stealth/ox-alpha":{"draws":40,"losses":25,"wins":109},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":34},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":24},"tencent/hy4-preview":{"draws":11,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":15,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":11,"wins":30},"x-ai/grok-4.6":{"draws":13,"losses":13,"wins":28},"x-ai/grok-4.7":{"draws":8,"losses":22,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":2,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":17,"losses":10,"wins":81},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":29},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":41},"z-ai/glm-5.3-flashx":{"draws":10,"losses":6,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":28,"wins":29},"claude-fable-5":{"draws":24,"losses":53,"wins":9},"claude-fable-5-1":{"draws":6,"losses":82,"wins":4},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":49,"losses":62,"wins":27},"claude-opus-4-8":{"draws":15,"losses":23,"wins":8},"claude-opus-5":{"draws":12,"losses":63,"wins":13},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":24,"losses":44,"wins":20},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":37,"losses":32,"wins":51},"deepseek/deepseek-v4-pro":{"draws":30,"losses":31,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":31,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"fireworks/ember-1":{"draws":19,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":15,"losses":20,"wins":13},"google/gemini-3.1-flash-lite":{"draws":11,"losses":5,"wins":20},"google/gemini-3.5-flash":{"draws":33,"losses":46,"wins":23},"google/gemini-3.5-flash-lite":{"draws":74,"losses":62,"wins":106},"google/gemini-3.6-flash":{"draws":58,"losses":109,"wins":65},"google/gemini-3.8-flash":{"draws":22,"losses":49,"wins":17},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":5,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":18,"wins":11},"gpt-5.4":{"draws":43,"losses":64,"wins":17},"gpt-5.4-mini":{"draws":15,"losses":15,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":21},"gpt-5.5":{"draws":19,"losses":21,"wins":6},"gpt-5.6-luna":{"draws":52,"losses":37,"wins":53},"gpt-5.6-sol":{"draws":24,"losses":107,"wins":13},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":17},"gpt-6-astra":{"draws":4,"losses":76,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":0,"losses":45,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":28,"losses":6,"wins":34},"inclusionai/ling-3.0-flash":{"draws":20,"losses":7,"wins":37},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":18,"wins":45},"meta/muse-glimmer-30b":{"draws":31,"losses":16,"wins":35},"meta/muse-spark-1.2":{"draws":32,"losses":49,"wins":21},"meta/muse-spark-1.3":{"draws":28,"losses":38,"wins":10},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":14},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":23,"losses":4,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":38,"losses":47,"wins":25},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":12,"wins":16},"o3":{"draws":17,"losses":66,"wins":55},"openai/gpt-oss-120b":{"draws":30,"losses":12,"wins":40},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":44},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":37,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":20,"wins":14},"qwen/qwen3.8-flash":{"draws":16,"losses":21,"wins":19},"qwen/qwen3.8-max":{"draws":34,"losses":38,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"stealth/ox-alpha":{"draws":66,"losses":141,"wins":71},"stealth/space-bunny-alpha":{"draws":12,"losses":15,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":12,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":10,"wins":11},"tencent/hy4-preview":{"draws":28,"losses":42,"wins":16},"thinkingmachines/inkling":{"draws":31,"losses":13,"wins":58},"thinkingmachines/inkling-small":{"draws":26,"losses":20,"wins":44},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":36,"losses":57,"wins":17},"x-ai/grok-4.6":{"draws":28,"losses":44,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":34,"losses":15,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":19,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":20,"wins":9},"z-ai/glm-5.2":{"draws":44,"losses":48,"wins":54},"z-ai/glm-5.3":{"draws":19,"losses":43,"wins":8},"z-ai/glm-5.3-flash":{"draws":20,"losses":38,"wins":26},"z-ai/glm-5.3-flashx":{"draws":14,"losses":27,"wins":7}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":18,"wins":18},"claude-fable-5":{"draws":8,"losses":32,"wins":8},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":22,"wins":15},"claude-opus-4-5":{"draws":18,"losses":34,"wins":26},"claude-opus-4-8":{"draws":12,"losses":24,"wins":8},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":12,"losses":21,"wins":15},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":22,"losses":21,"wins":29},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":25,"wins":10},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":26,"wins":21},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":42},"google/gemini-3.6-flash":{"draws":21,"losses":52,"wins":19},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":11},"google/gemma-4-31b-it":{"draws":7,"losses":10,"wins":11},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":14,"wins":18},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":10,"losses":15,"wins":23},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":16,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":27,"wins":10},"gpt-6-sol":{"draws":4,"losses":42,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":48,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":8},"meta/muse-wonder":{"draws":5,"losses":32,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":19},"o3":{"draws":8,"losses":29,"wins":29},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":21},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":14,"wins":14},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":25,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":28,"wins":9},"stealth/ox-alpha":{"draws":42,"losses":90,"wins":26},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":19,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":28,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":24},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.6":{"draws":9,"losses":30,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":16,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":27,"wins":13},"z-ai/glm-5.3-flashx":{"draws":11,"losses":27,"wins":10}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":2},"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":13,"wins":2},"claude-opus-4-5":{"draws":3,"losses":27,"wins":0},"claude-opus-4-8":{"draws":2,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":32,"wins":0},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":15,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":9,"losses":14,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":12,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":12,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":1},"fireworks/ember-1":{"draws":3,"losses":13,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":15,"wins":3},"google/gemini-3.5-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.6-flash":{"draws":6,"losses":28,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":7,"wins":1},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":6,"losses":12,"wins":0},"gpt-5.4":{"draws":4,"losses":14,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":7,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":2},"gpt-5.5":{"draws":4,"losses":14,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":18,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":12,"wins":0},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":4,"losses":12,"wins":2},"gpt-6-sol":{"draws":0,"losses":18,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":14,"wins":4},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":18,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":16,"wins":0},"meta/muse-wonder":{"draws":0,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":2},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":14,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":2},"o3":{"draws":8,"losses":25,"wins":1},"openai/gpt-oss-120b":{"draws":6,"losses":8,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.7-max":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":16,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":9,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":14,"wins":0},"qwen/qwen3.8-max-0902":{"draws":4,"losses":14,"wins":0},"stealth/ox-alpha":{"draws":5,"losses":46,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":13,"wins":8},"thinkingmachines/inkling-small":{"draws":6,"losses":9,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":18,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":15,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":13,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":25,"wins":1},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":4,"losses":13,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":22,"wins":30},"claude-fable-5":{"draws":14,"losses":50,"wins":0},"claude-fable-5-1":{"draws":3,"losses":55,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":4},"claude-opus-4-5":{"draws":29,"losses":50,"wins":17},"claude-opus-4-8":{"draws":8,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":61,"wins":2},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":21,"losses":41,"wins":16},"claude-sonnet-5-5":{"draws":7,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":31,"wins":26},"deepseek/deepseek-v4-pro":{"draws":17,"losses":31,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":28,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"fireworks/ember-1":{"draws":14,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":23,"losses":38,"wins":21},"google/gemini-3.5-flash-lite":{"draws":44,"losses":49,"wins":49},"google/gemini-3.6-flash":{"draws":26,"losses":90,"wins":16},"google/gemini-3.8-flash":{"draws":13,"losses":50,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":2,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":25,"wins":9},"gpt-5.4":{"draws":19,"losses":40,"wins":7},"gpt-5.4-mini":{"draws":11,"losses":9,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":10,"losses":22,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":34,"wins":24},"gpt-5.6-sol":{"draws":10,"losses":39,"wins":13},"gpt-5.6-terra":{"draws":22,"losses":36,"wins":12},"gpt-6-astra":{"draws":6,"losses":48,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":9},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":11,"wins":14},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":15,"losses":22,"wins":27},"meta/muse-glimmer-30b":{"draws":33,"losses":23,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":29,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":46,"wins":8},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":6},"mistralai/mistral-large-4-0":{"draws":6,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":12,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":29,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":12,"wins":15},"o3":{"draws":13,"losses":48,"wins":33},"openai/gpt-oss-120b":{"draws":28,"losses":24,"wins":20},"poolside/laguna-s-2.1":{"draws":26,"losses":23,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":36,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":18,"losses":24,"wins":8},"qwen/qwen3.8-max":{"draws":22,"losses":35,"wins":15},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"stealth/ox-alpha":{"draws":57,"losses":121,"wins":58},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":38,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":25,"wins":28},"thinkingmachines/inkling-small":{"draws":34,"losses":16,"wins":34},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":14,"losses":32,"wins":14},"x-ai/grok-4.6":{"draws":16,"losses":41,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":22,"losses":20,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":42,"losses":54,"wins":30},"z-ai/glm-5.3":{"draws":16,"losses":36,"wins":4},"z-ai/glm-5.3-flash":{"draws":27,"losses":31,"wins":10},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":22,"wins":18},"claude-fable-5":{"draws":13,"losses":30,"wins":7},"claude-fable-5-1":{"draws":3,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":7},"claude-opus-4-5":{"draws":21,"losses":42,"wins":11},"claude-opus-4-8":{"draws":8,"losses":18,"wins":6},"claude-opus-5":{"draws":8,"losses":53,"wins":9},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":23,"losses":20,"wins":19},"claude-sonnet-5-5":{"draws":7,"losses":22,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":33,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":21,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"fireworks/ember-1":{"draws":12,"losses":18,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":22},"google/gemini-3.5-flash-lite":{"draws":50,"losses":33,"wins":43},"google/gemini-3.6-flash":{"draws":45,"losses":46,"wins":19},"google/gemini-3.8-flash":{"draws":20,"losses":27,"wins":11},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":15,"losses":11,"wins":10},"gpt-5.4":{"draws":17,"losses":23,"wins":18},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":13,"losses":17,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":28,"wins":18},"gpt-5.6-sol":{"draws":7,"losses":38,"wins":5},"gpt-5.6-terra":{"draws":29,"losses":15,"wins":14},"gpt-6-astra":{"draws":3,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"wins":8},"gpt-6-sol":{"draws":3,"losses":29,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":27},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":20},"meta/muse-spark-1.2":{"draws":4,"losses":28,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":33,"wins":10},"meta/muse-wonder":{"draws":2,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":11},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":10,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":18,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":8},"o3":{"draws":16,"losses":29,"wins":27},"openai/gpt-oss-120b":{"draws":25,"losses":15,"wins":22},"poolside/laguna-s-2.1":{"draws":27,"losses":19,"wins":10},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":24,"wins":14},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":17,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":20,"losses":31,"wins":9},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"stealth/ox-alpha":{"draws":60,"losses":86,"wins":54},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":25,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":25,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":34,"losses":18,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":19,"losses":21,"wins":12},"x-ai/grok-4.6":{"draws":24,"losses":32,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":3},"xiaomi/mimo-v2.5":{"draws":25,"losses":11,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":48,"losses":34,"wins":30},"z-ai/glm-5.3":{"draws":12,"losses":33,"wins":7},"z-ai/glm-5.3-flash":{"draws":17,"losses":32,"wins":7},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":4}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":22,"wins":12},"claude-fable-5":{"draws":14,"losses":34,"wins":6},"claude-fable-5-1":{"draws":3,"losses":55,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":3},"claude-opus-4-5":{"draws":27,"losses":40,"wins":11},"claude-opus-4-8":{"draws":5,"losses":28,"wins":5},"claude-opus-5":{"draws":6,"losses":47,"wins":7},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":21,"losses":26,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":36,"losses":21,"wins":27},"deepseek/deepseek-v4-pro":{"draws":34,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":14,"losses":13,"wins":9},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":22,"losses":44,"wins":10},"google/gemini-3.5-flash-lite":{"draws":51,"losses":42,"wins":23},"google/gemini-3.6-flash":{"draws":39,"losses":53,"wins":22},"google/gemini-3.8-flash":{"draws":18,"losses":39,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":5,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":15,"wins":5},"gpt-5.4":{"draws":22,"losses":31,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":12},"gpt-5.5":{"draws":14,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":24,"losses":20,"wins":22},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":9},"gpt-5.6-terra":{"draws":26,"losses":28,"wins":10},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":9},"gpt-6-sol":{"draws":3,"losses":30,"wins":3},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":4,"wins":14},"inclusionai/ling-3.0-flash":{"draws":18,"losses":11,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":9,"wins":16},"meta/muse-glimmer-30b":{"draws":28,"losses":14,"wins":20},"meta/muse-spark-1.2":{"draws":14,"losses":23,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":35,"wins":7},"meta/muse-wonder":{"draws":7,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":8,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":13,"wins":19},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":16},"o3":{"draws":17,"losses":23,"wins":34},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":10},"poolside/laguna-s-2.1":{"draws":28,"losses":14,"wins":4},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":9,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":32,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":20,"losses":8,"wins":10},"qwen/qwen3.8-max":{"draws":17,"losses":29,"wins":12},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":70,"losses":94,"wins":44},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":25,"losses":27,"wins":10},"thinkingmachines/inkling":{"draws":30,"losses":18,"wins":12},"thinkingmachines/inkling-small":{"draws":30,"losses":14,"wins":20},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":15,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":30,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":20,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":30,"losses":12,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":48,"losses":30,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":36,"wins":6},"z-ai/glm-5.3-flash":{"draws":21,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":11,"losses":32,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":34,"wins":15},"claude-opus-4-8":{"draws":14,"losses":25,"wins":5},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":19,"losses":26,"wins":3},"claude-sonnet-5-5":{"draws":14,"losses":32,"wins":2},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":18,"wins":23},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":14,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":6},"fireworks/ember-1":{"draws":18,"losses":26,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":27,"wins":5},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":18,"losses":29,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":34,"wins":15},"google/gemini-3.6-flash":{"draws":30,"losses":52,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":33,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":14,"losses":15,"wins":13},"gpt-5.4":{"draws":17,"losses":27,"wins":2},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":20,"wins":15},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":20,"losses":17,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":18,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":17,"losses":23,"wins":8},"gpt-6-sol":{"draws":9,"losses":32,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":18,"wins":19},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-wonder":{"draws":9,"losses":35,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":10,"wins":12},"o3":{"draws":19,"losses":33,"wins":14},"openai/gpt-oss-120b":{"draws":20,"losses":15,"wins":7},"poolside/laguna-s-2.1":{"draws":23,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":43,"losses":82,"wins":32},"stealth/space-bunny-alpha":{"draws":16,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":18,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":18,"losses":15,"wins":15},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":31,"wins":6},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":4},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":17,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":12,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":40,"losses":36,"wins":20},"z-ai/glm-5.3":{"draws":11,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":30,"wins":4},"z-ai/glm-5.3-flashx":{"draws":14,"losses":30,"wins":4}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":15,"wins":12},"claude-fable-5":{"draws":12,"losses":35,"wins":1},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":34,"losses":28,"wins":16},"claude-opus-4-8":{"draws":17,"losses":24,"wins":3},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":19,"losses":17,"wins":12},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":21,"wins":22},"deepseek/deepseek-v4-pro":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":20,"wins":7},"fireworks/ember-1":{"draws":11,"losses":21,"wins":0},"gemini-3.1-pro-preview":{"draws":20,"losses":17,"wins":11},"google/gemini-3.1-flash-lite":{"draws":11,"losses":3,"wins":18},"google/gemini-3.5-flash":{"draws":23,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":40,"losses":24,"wins":20},"google/gemini-3.6-flash":{"draws":33,"losses":42,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":15,"wins":8},"gpt-5.4":{"draws":18,"losses":26,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":21},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":22,"losses":18,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":35,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":18,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":21,"wins":12},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":23,"losses":4,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":8,"wins":20},"meta/muse-glimmer-30b":{"draws":22,"losses":5,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":29,"wins":9},"meta/muse-wonder":{"draws":17,"losses":28,"wins":3},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":17,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":10,"wins":10},"o3":{"draws":20,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":26,"losses":10,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":21,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":12,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":12},"qwen/qwen3.8-max-0902":{"draws":17,"losses":24,"wins":7},"stealth/ox-alpha":{"draws":53,"losses":84,"wins":21},"stealth/space-bunny-alpha":{"draws":16,"losses":10,"wins":12},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":15},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":20,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":20,"wins":20},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":25,"wins":7},"x-ai/grok-4.7":{"draws":6,"losses":33,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":16,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":41,"losses":32,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":28,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":25,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":18,"wins":12},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":26,"wins":7},"claude-opus-4-5":{"draws":25,"losses":44,"wins":9},"claude-opus-4-8":{"draws":12,"losses":29,"wins":3},"claude-opus-5":{"draws":9,"losses":68,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":28,"losses":26,"wins":18},"deepseek/deepseek-v4-pro":{"draws":16,"losses":24,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":20,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":23,"wins":8},"fireworks/ember-1":{"draws":19,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":17,"losses":34,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":30,"wins":21},"google/gemini-3.6-flash":{"draws":31,"losses":54,"wins":7},"google/gemini-3.8-flash":{"draws":10,"losses":37,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":19,"losses":18,"wins":5},"gpt-5.4":{"draws":14,"losses":29,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":13,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":17,"wins":16},"gpt-5.5":{"draws":18,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":19,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":39,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":13,"losses":23,"wins":12},"gpt-6-sol":{"draws":8,"losses":36,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":23,"wins":13},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":27,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":35,"wins":4},"meta/muse-wonder":{"draws":8,"losses":38,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":13,"wins":12},"o3":{"draws":14,"losses":46,"wins":6},"openai/gpt-oss-120b":{"draws":18,"losses":17,"wins":7},"poolside/laguna-s-2.1":{"draws":21,"losses":18,"wins":7},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":27,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":15,"wins":3},"qwen/qwen3.8-max":{"draws":18,"losses":23,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":30,"wins":2},"stealth/ox-alpha":{"draws":39,"losses":106,"wins":13},"stealth/space-bunny-alpha":{"draws":15,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":11,"losses":19,"wins":4},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":15,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":25,"losses":24,"wins":15},"thinkingmachines/inkling-small":{"draws":19,"losses":16,"wins":13},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":32,"wins":1},"x-ai/grok-4.6":{"draws":16,"losses":31,"wins":1},"x-ai/grok-4.7":{"draws":4,"losses":36,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":38,"losses":40,"wins":18},"z-ai/glm-5.3":{"draws":10,"losses":35,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":29,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":34,"wins":4}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":18,"wins":5},"claude-fable-5":{"draws":4,"losses":26,"wins":0},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":25,"wins":0},"claude-opus-4-5":{"draws":19,"losses":44,"wins":3},"claude-opus-4-8":{"draws":5,"losses":34,"wins":1},"claude-opus-5":{"draws":7,"losses":46,"wins":1},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":6,"losses":23,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":11,"wins":3},"deepseek/deepseek-v4-flash":{"draws":20,"losses":42,"wins":16},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":16,"wins":3},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":18,"wins":14},"google/gemini-3.5-flash":{"draws":6,"losses":34,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":41,"wins":5},"google/gemini-3.6-flash":{"draws":12,"losses":46,"wins":2},"google/gemini-3.8-flash":{"draws":5,"losses":25,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":4},"gpt-4.1":{"draws":7,"losses":15,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":29,"wins":0},"gpt-5.4":{"draws":4,"losses":26,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":21,"wins":2},"gpt-5.4-nano":{"draws":9,"losses":31,"wins":16},"gpt-5.5":{"draws":12,"losses":26,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":20,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":22,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":6,"losses":20,"wins":4},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":27,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":11,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":15,"wins":10},"meituan/longcat-2.0":{"draws":7,"losses":38,"wins":7},"meta/muse-glimmer-30b":{"draws":12,"losses":14,"wins":4},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":0},"meta/muse-wonder":{"draws":3,"losses":26,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":19,"wins":13},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":12,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":18,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":38,"wins":6},"o3":{"draws":2,"losses":50,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":4},"poolside/laguna-s-2.1":{"draws":9,"losses":24,"wins":7},"qwen/qwen3.7-max":{"draws":13,"losses":18,"wins":3},"qwen/qwen3.7-plus":{"draws":12,"losses":27,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":1},"qwen/qwen3.8-max":{"draws":8,"losses":22,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"stealth/ox-alpha":{"draws":12,"losses":68,"wins":8},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":29,"wins":1},"tencent/hy3-preview":{"draws":8,"losses":19,"wins":3},"tencent/hy4-preview":{"draws":2,"losses":28,"wins":0},"thinkingmachines/inkling":{"draws":22,"losses":25,"wins":13},"thinkingmachines/inkling-small":{"draws":10,"losses":19,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":6,"losses":28,"wins":2},"x-ai/grok-4.6":{"draws":3,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":25,"losses":57,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":27,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":19,"losses":58,"wins":7},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":40,"wins":39},"claude-fable-5":{"draws":25,"losses":76,"wins":9},"claude-fable-5-1":{"draws":4,"losses":100,"wins":0},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":51,"losses":88,"wins":39},"claude-opus-4-8":{"draws":31,"losses":56,"wins":9},"claude-opus-5":{"draws":18,"losses":128,"wins":10},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":44,"losses":51,"wins":31},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":13,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":57,"losses":59,"wins":64},"deepseek/deepseek-v4-pro":{"draws":39,"losses":52,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":46,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":43,"wins":12},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":24,"losses":38,"wins":22},"google/gemini-3.1-flash-lite":{"draws":21,"losses":15,"wins":42},"google/gemini-3.5-flash":{"draws":25,"losses":63,"wins":16},"google/gemini-3.5-flash-lite":{"draws":78,"losses":93,"wins":61},"google/gemini-3.6-flash":{"draws":68,"losses":112,"wins":46},"google/gemini-3.8-flash":{"draws":30,"losses":74,"wins":8},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":12,"losses":15,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":29,"losses":39,"wins":24},"gpt-5.4":{"draws":21,"losses":65,"wins":22},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":21},"gpt-5.4-nano":{"draws":25,"losses":41,"wins":54},"gpt-5.5":{"draws":31,"losses":43,"wins":12},"gpt-5.6-luna":{"draws":41,"losses":46,"wins":37},"gpt-5.6-sol":{"draws":10,"losses":83,"wins":11},"gpt-5.6-terra":{"draws":40,"losses":48,"wins":18},"gpt-6-astra":{"draws":4,"losses":92,"wins":2},"gpt-6-luna":{"draws":29,"losses":34,"wins":21},"gpt-6-sol":{"draws":14,"losses":64,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":79,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":16,"wins":34},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":35},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":27,"wins":62},"meta/muse-glimmer-30b":{"draws":48,"losses":29,"wins":39},"meta/muse-spark-1.2":{"draws":26,"losses":60,"wins":20},"meta/muse-spark-1.3":{"draws":25,"losses":70,"wins":15},"meta/muse-wonder":{"draws":10,"losses":69,"wins":5},"minimax/minimax-m3":{"draws":15,"losses":23,"wins":18},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":27,"losses":15,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":43,"losses":38,"wins":23},"nex-agi/nex-n2-pro":{"draws":16,"losses":12,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":24,"wins":29},"o3":{"draws":31,"losses":73,"wins":64},"openai/gpt-oss-120b":{"draws":43,"losses":36,"wins":33},"poolside/laguna-s-2.1":{"draws":45,"losses":29,"wins":32},"qwen/qwen3.7-max":{"draws":20,"losses":28,"wins":12},"qwen/qwen3.7-plus":{"draws":16,"losses":14,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":67,"wins":12},"qwen/qwen3.8-27b":{"draws":10,"losses":37,"wins":17},"qwen/qwen3.8-flash":{"draws":34,"losses":29,"wins":19},"qwen/qwen3.8-max":{"draws":41,"losses":40,"wins":33},"qwen/qwen3.8-max-0902":{"draws":25,"losses":46,"wins":13},"stealth/ox-alpha":{"draws":75,"losses":216,"wins":61},"stealth/space-bunny-alpha":{"draws":23,"losses":27,"wins":18},"stepfun/step-3.7-flash":{"draws":17,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":20,"wins":13},"tencent/hy4-preview":{"draws":37,"losses":63,"wins":16},"thinkingmachines/inkling":{"draws":32,"losses":47,"wins":57},"thinkingmachines/inkling-small":{"draws":49,"losses":30,"wins":49},"unbiased/pareto-26.10-preview":{"draws":0,"losses":27,"wins":1},"upstage/solar-mini4":{"draws":5,"losses":10,"wins":9},"x-ai/grok-4.5":{"draws":27,"losses":70,"wins":17},"x-ai/grok-4.6":{"draws":34,"losses":74,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":56,"losses":43,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":25,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":35,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":82,"losses":86,"wins":52},"z-ai/glm-5.3":{"draws":20,"losses":71,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":63,"wins":15},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":43,"wins":56},"claude-fable-5":{"draws":32,"losses":95,"wins":25},"claude-fable-5-1":{"draws":11,"losses":149,"wins":2},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":100,"losses":107,"wins":91},"claude-opus-4-8":{"draws":28,"losses":55,"wins":19},"claude-opus-5":{"draws":28,"losses":170,"wins":18},"claude-opus-5-5":{"draws":3,"losses":93,"wins":2},"claude-sonnet-5":{"draws":79,"losses":119,"wins":62},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":13,"losses":7,"wins":14},"deepseek/deepseek-v4-flash":{"draws":75,"losses":59,"wins":80},"deepseek/deepseek-v4-pro":{"draws":52,"losses":67,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":61,"losses":59,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":41,"wins":18},"fireworks/ember-1":{"draws":32,"losses":36,"wins":22},"gemini-3.1-pro-preview":{"draws":32,"losses":33,"wins":25},"google/gemini-3.1-flash-lite":{"draws":20,"losses":9,"wins":39},"google/gemini-3.5-flash":{"draws":58,"losses":76,"wins":54},"google/gemini-3.5-flash-lite":{"draws":172,"losses":137,"wins":155},"google/gemini-3.6-flash":{"draws":179,"losses":227,"wins":126},"google/gemini-3.8-flash":{"draws":38,"losses":105,"wins":11},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":17,"losses":9,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":33,"losses":30,"wins":25},"gpt-5.4":{"draws":73,"losses":132,"wins":31},"gpt-5.4-mini":{"draws":27,"losses":23,"wins":26},"gpt-5.4-nano":{"draws":38,"losses":40,"wins":54},"gpt-5.5":{"draws":46,"losses":40,"wins":16},"gpt-5.6-luna":{"draws":85,"losses":84,"wins":95},"gpt-5.6-sol":{"draws":25,"losses":184,"wins":33},"gpt-5.6-terra":{"draws":55,"losses":53,"wins":50},"gpt-6-astra":{"draws":5,"losses":141,"wins":0},"gpt-6-luna":{"draws":33,"losses":35,"wins":22},"gpt-6-sol":{"draws":14,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":83,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":66,"losses":10,"wins":52},"inclusionai/ling-3.0-flash":{"draws":78,"losses":8,"wins":88},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":68,"losses":60,"wins":128},"meta/muse-glimmer-30b":{"draws":72,"losses":27,"wins":51},"meta/muse-spark-1.2":{"draws":58,"losses":84,"wins":48},"meta/muse-spark-1.3":{"draws":36,"losses":69,"wins":31},"meta/muse-wonder":{"draws":18,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":18,"losses":18,"wins":20},"mistralai/mistral-large-4-0":{"draws":20,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":40,"losses":16,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":12,"wins":10},"moonshotai/kimi-k3":{"draws":83,"losses":103,"wins":50},"nex-agi/nex-n2-pro":{"draws":23,"losses":14,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":16,"wins":30},"o3":{"draws":53,"losses":126,"wins":111},"openai/gpt-oss-120b":{"draws":52,"losses":35,"wins":55},"poolside/laguna-s-2.1":{"draws":100,"losses":66,"wins":74},"qwen/qwen3.7-max":{"draws":20,"losses":20,"wins":24},"qwen/qwen3.7-plus":{"draws":17,"losses":20,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":55,"losses":67,"wins":34},"qwen/qwen3.8-27b":{"draws":15,"losses":43,"wins":24},"qwen/qwen3.8-flash":{"draws":39,"losses":40,"wins":29},"qwen/qwen3.8-max":{"draws":52,"losses":61,"wins":47},"qwen/qwen3.8-max-0902":{"draws":31,"losses":44,"wins":15},"stealth/ox-alpha":{"draws":124,"losses":239,"wins":121},"stealth/space-bunny-alpha":{"draws":25,"losses":19,"wins":28},"stepfun/step-3.7-flash":{"draws":23,"losses":11,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":23,"wins":10},"tencent/hy4-preview":{"draws":52,"losses":70,"wins":32},"thinkingmachines/inkling":{"draws":88,"losses":67,"wins":97},"thinkingmachines/inkling-small":{"draws":66,"losses":38,"wins":70},"unbiased/pareto-26.10-preview":{"draws":2,"losses":28,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":12},"x-ai/grok-4.5":{"draws":64,"losses":133,"wins":67},"x-ai/grok-4.6":{"draws":38,"losses":86,"wins":28},"x-ai/grok-4.7":{"draws":9,"losses":59,"wins":12},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":11},"xiaomi/mimo-v2.5":{"draws":55,"losses":35,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":23,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":35,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":105,"losses":83,"wins":76},"z-ai/glm-5.3":{"draws":23,"losses":97,"wins":14},"z-ai/glm-5.3-flash":{"draws":46,"losses":90,"wins":30},"z-ai/glm-5.3-flashx":{"draws":28,"losses":41,"wins":21}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":48,"wins":61},"claude-fable-5":{"draws":39,"losses":85,"wins":20},"claude-fable-5-1":{"draws":13,"losses":144,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":47,"wins":17},"claude-opus-4-5":{"draws":107,"losses":127,"wins":78},"claude-opus-4-8":{"draws":32,"losses":43,"wins":29},"claude-opus-5":{"draws":25,"losses":170,"wins":23},"claude-opus-5-5":{"draws":4,"losses":99,"wins":1},"claude-sonnet-5":{"draws":91,"losses":118,"wins":65},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":15,"losses":4,"wins":19},"deepseek/deepseek-v4-flash":{"draws":86,"losses":57,"wins":81},"deepseek/deepseek-v4-pro":{"draws":54,"losses":66,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":67,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":40,"wins":22},"fireworks/ember-1":{"draws":35,"losses":45,"wins":16},"gemini-3.1-pro-preview":{"draws":32,"losses":38,"wins":26},"google/gemini-3.1-flash-lite":{"draws":25,"losses":9,"wins":30},"google/gemini-3.5-flash":{"draws":60,"losses":88,"wins":40},"google/gemini-3.5-flash-lite":{"draws":241,"losses":171,"wins":182},"google/gemini-3.6-flash":{"draws":124,"losses":233,"wins":81},"google/gemini-3.8-flash":{"draws":43,"losses":93,"wins":21},"google/gemma-4-31b-it":{"draws":23,"losses":11,"wins":22},"gpt-4.1":{"draws":18,"losses":16,"wins":14},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":29,"losses":41,"wins":20},"gpt-5.4":{"draws":79,"losses":118,"wins":49},"gpt-5.4-mini":{"draws":31,"losses":20,"wins":31},"gpt-5.4-nano":{"draws":41,"losses":43,"wins":42},"gpt-5.5":{"draws":49,"losses":41,"wins":22},"gpt-5.6-luna":{"draws":114,"losses":72,"wins":90},"gpt-5.6-sol":{"draws":41,"losses":182,"wins":25},"gpt-5.6-terra":{"draws":61,"losses":60,"wins":35},"gpt-6-astra":{"draws":13,"losses":125,"wins":0},"gpt-6-luna":{"draws":34,"losses":31,"wins":31},"gpt-6-sol":{"draws":13,"losses":76,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":90,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":64,"losses":10,"wins":58},"inclusionai/ling-3.0-flash":{"draws":99,"losses":40,"wins":65},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":81,"losses":63,"wins":114},"meta/muse-glimmer-30b":{"draws":80,"losses":32,"wins":54},"meta/muse-spark-1.2":{"draws":47,"losses":116,"wins":39},"meta/muse-spark-1.3":{"draws":39,"losses":72,"wins":31},"meta/muse-wonder":{"draws":16,"losses":68,"wins":12},"minimax/minimax-m3":{"draws":20,"losses":15,"wins":35},"mistralai/mistral-large-4-0":{"draws":18,"losses":25,"wins":17},"mistralai/mistral-medium-3-5":{"draws":58,"losses":16,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":14,"wins":6},"moonshotai/kimi-k3":{"draws":100,"losses":118,"wins":38},"nex-agi/nex-n2-pro":{"draws":28,"losses":8,"wins":38},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":17,"wins":28},"o3":{"draws":55,"losses":181,"wins":80},"openai/gpt-oss-120b":{"draws":76,"losses":34,"wins":52},"poolside/laguna-s-2.1":{"draws":135,"losses":62,"wins":77},"qwen/qwen3.7-max":{"draws":26,"losses":22,"wins":26},"qwen/qwen3.7-plus":{"draws":27,"losses":16,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":60,"losses":70,"wins":38},"qwen/qwen3.8-27b":{"draws":20,"losses":42,"wins":22},"qwen/qwen3.8-flash":{"draws":57,"losses":32,"wins":29},"qwen/qwen3.8-max":{"draws":58,"losses":81,"wins":45},"qwen/qwen3.8-max-0902":{"draws":33,"losses":40,"wins":23},"stealth/ox-alpha":{"draws":144,"losses":262,"wins":138},"stealth/space-bunny-alpha":{"draws":25,"losses":26,"wins":25},"stepfun/step-3.7-flash":{"draws":21,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":29,"losses":14,"wins":23},"tencent/hy4-preview":{"draws":47,"losses":92,"wins":31},"thinkingmachines/inkling":{"draws":97,"losses":44,"wins":127},"thinkingmachines/inkling-small":{"draws":79,"losses":57,"wins":51},"unbiased/pareto-26.10-preview":{"draws":0,"losses":31,"wins":1},"upstage/solar-mini4":{"draws":7,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":67,"losses":138,"wins":73},"x-ai/grok-4.6":{"draws":51,"losses":83,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":71,"wins":11},"x-ai/grok-build-0.1":{"draws":13,"losses":4,"wins":15},"xiaomi/mimo-v2.5":{"draws":68,"losses":37,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":22,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":35,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":100,"losses":105,"wins":63},"z-ai/glm-5.3":{"draws":32,"losses":96,"wins":10},"z-ai/glm-5.3-flash":{"draws":51,"losses":86,"wins":31},"z-ai/glm-5.3-flashx":{"draws":27,"losses":48,"wins":21}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":19,"wins":30},"claude-fable-5":{"draws":15,"losses":55,"wins":18},"claude-fable-5-1":{"draws":7,"losses":87,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":39,"losses":23,"wins":50},"claude-opus-4-8":{"draws":10,"losses":23,"wins":15},"claude-opus-5":{"draws":18,"losses":64,"wins":14},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":27,"losses":20,"wins":39},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":16},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":26,"losses":18,"wins":62},"deepseek/deepseek-v4-pro":{"draws":18,"losses":19,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":24,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":16,"wins":18},"fireworks/ember-1":{"draws":13,"losses":18,"wins":17},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":20,"losses":42,"wins":36},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":88},"google/gemini-3.6-flash":{"draws":39,"losses":55,"wins":60},"google/gemini-3.8-flash":{"draws":20,"losses":24,"wins":16},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":11,"wins":22},"gpt-5.4":{"draws":21,"losses":32,"wins":31},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":6,"wins":34},"gpt-5.5":{"draws":15,"losses":13,"wins":16},"gpt-5.6-luna":{"draws":22,"losses":19,"wins":39},"gpt-5.6-sol":{"draws":13,"losses":48,"wins":27},"gpt-5.6-terra":{"draws":32,"losses":21,"wins":31},"gpt-6-astra":{"draws":10,"losses":73,"wins":5},"gpt-6-luna":{"draws":16,"losses":14,"wins":18},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":39,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":2,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":43},"meta/muse-glimmer-30b":{"draws":22,"losses":10,"wins":38},"meta/muse-spark-1.2":{"draws":17,"losses":24,"wins":27},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":35},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":18},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":21,"losses":19,"wins":34},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":26},"o3":{"draws":12,"losses":27,"wins":61},"openai/gpt-oss-120b":{"draws":14,"losses":6,"wins":40},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":42},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":26,"wins":31},"qwen/qwen3.8-27b":{"draws":11,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":14,"losses":14,"wins":24},"qwen/qwen3.8-max":{"draws":26,"losses":24,"wins":34},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"stealth/ox-alpha":{"draws":73,"losses":114,"wins":95},"stealth/space-bunny-alpha":{"draws":14,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":22,"losses":33,"wins":23},"thinkingmachines/inkling":{"draws":22,"losses":9,"wins":43},"thinkingmachines/inkling-small":{"draws":29,"losses":11,"wins":44},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":23},"x-ai/grok-4.6":{"draws":30,"losses":34,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":2,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":15,"wins":8},"z-ai/glm-5.2":{"draws":43,"losses":37,"wins":54},"z-ai/glm-5.3":{"draws":16,"losses":36,"wins":14},"z-ai/glm-5.3-flash":{"draws":14,"losses":36,"wins":30},"z-ai/glm-5.3-flashx":{"draws":8,"losses":22,"wins":18}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":7},"claude-fable-5":{"draws":7,"losses":28,"wins":1},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":3},"claude-opus-4-5":{"draws":18,"losses":40,"wins":2},"claude-opus-4-8":{"draws":11,"losses":23,"wins":2},"claude-opus-5":{"draws":8,"losses":47,"wins":3},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":2},"claude-sonnet-5-5":{"draws":5,"losses":23,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":24,"losses":22,"wins":8},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":3},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":10,"wins":11},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":5},"google/gemini-3.5-flash-lite":{"draws":26,"losses":27,"wins":11},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":5},"google/gemini-3.8-flash":{"draws":13,"losses":21,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":1},"gpt-4.1":{"draws":6,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":15,"wins":1},"gpt-5.4":{"draws":11,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":11,"wins":4},"gpt-5.4-nano":{"draws":9,"losses":23,"wins":6},"gpt-5.5":{"draws":11,"losses":20,"wins":1},"gpt-5.6-luna":{"draws":14,"losses":16,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":0},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":13,"losses":20,"wins":3},"gpt-6-sol":{"draws":4,"losses":32,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":20,"wins":10},"meta/muse-glimmer-30b":{"draws":16,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":2},"meta/muse-spark-1.3":{"draws":11,"losses":23,"wins":2},"meta/muse-wonder":{"draws":7,"losses":27,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"o3":{"draws":11,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":2},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":22,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":1},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"stealth/ox-alpha":{"draws":28,"losses":69,"wins":5},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":2},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":19,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":8},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":26,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":25,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":2},"xiaomi/mimo-v2.5":{"draws":27,"losses":22,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":3},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":11,"wins":17},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":58,"losses":37,"wins":27},"claude-opus-4-8":{"draws":29,"losses":42,"wins":9},"claude-opus-5":{"draws":20,"losses":126,"wins":11},"claude-opus-5-5":{"draws":5,"losses":46,"wins":1},"claude-sonnet-5":{"draws":17,"losses":18,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":11,"losses":5,"wins":16},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":43},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":20,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":25,"losses":10,"wins":33},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":20},"google/gemini-3.5-flash-lite":{"draws":38,"losses":39,"wins":35},"google/gemini-3.6-flash":{"draws":36,"losses":56,"wins":26},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":7},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":24,"losses":21,"wins":25},"gpt-5.4":{"draws":15,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":29,"losses":27,"wins":12},"gpt-5.4-nano":{"draws":21,"losses":37,"wins":34},"gpt-5.5":{"draws":27,"losses":38,"wins":19},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":6},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":15},"gpt-6-astra":{"draws":5,"losses":45,"wins":0},"gpt-6-luna":{"draws":11,"losses":18,"wins":19},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":14,"wins":13},"inclusionai/ling-3.0-flash":{"draws":29,"losses":1,"wins":36},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":26,"losses":16,"wins":42},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":16},"meta/muse-spark-1.2":{"draws":19,"losses":23,"wins":10},"meta/muse-spark-1.3":{"draws":18,"losses":30,"wins":4},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":18,"losses":14,"wins":28},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":15,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":8},"moonshotai/kimi-k3":{"draws":14,"losses":25,"wins":13},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":15,"wins":33},"o3":{"draws":19,"losses":35,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":24,"losses":20,"wins":30},"qwen/qwen3.7-max":{"draws":26,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":19,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":79,"wins":36},"stealth/space-bunny-alpha":{"draws":15,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":25},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":30,"losses":12,"wins":20},"tencent/hy4-preview":{"draws":13,"losses":28,"wins":11},"thinkingmachines/inkling":{"draws":24,"losses":35,"wins":33},"thinkingmachines/inkling-small":{"draws":17,"losses":13,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":36,"wins":12},"x-ai/grok-4.6":{"draws":20,"losses":24,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":14,"losses":8,"wins":12},"xiaomi/mimo-v2.5":{"draws":60,"losses":30,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":14,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":17,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":49,"losses":54,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":30,"wins":7}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":6,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":0},"claude-opus-4-5":{"draws":17,"losses":11,"wins":0},"claude-opus-4-8":{"draws":7,"losses":7,"wins":0},"claude-opus-5":{"draws":8,"losses":18,"wins":0},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":9,"losses":9,"wins":0},"claude-sonnet-5-5":{"draws":8,"losses":9,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":3},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":1},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":1},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":1},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":3},"google/gemini-3.6-flash":{"draws":14,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":6,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":1},"gpt-4.1":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":4,"wins":0},"gpt-5.4":{"draws":10,"losses":6,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":1},"gpt-5.5":{"draws":9,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":8,"wins":0},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":9,"losses":7,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":17,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":3,"wins":5},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":1},"meta/muse-spark-1.2":{"draws":9,"losses":5,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":0},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":6,"losses":10,"wins":2},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":0},"poolside/laguna-s-2.1":{"draws":13,"losses":2,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":1},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":33,"losses":34,"wins":5},"stealth/space-bunny-alpha":{"draws":7,"losses":5,"wins":0},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":1},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":0},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":9,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":13,"wins":11},"claude-fable-5":{"draws":8,"losses":27,"wins":3},"claude-fable-5-1":{"draws":0,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":18,"wins":10},"claude-opus-4-5":{"draws":18,"losses":27,"wins":19},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":13,"losses":69,"wins":6},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":10,"losses":22,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":25,"losses":20,"wins":23},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":10},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":10},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":15,"losses":23,"wins":14},"google/gemini-3.5-flash-lite":{"draws":23,"losses":15,"wins":28},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":17,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":7,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":12,"wins":11},"gpt-5.4":{"draws":9,"losses":22,"wins":5},"gpt-5.4-mini":{"draws":17,"losses":14,"wins":7},"gpt-5.4-nano":{"draws":9,"losses":12,"wins":19},"gpt-5.5":{"draws":20,"losses":28,"wins":2},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":23,"wins":7},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":10,"losses":14,"wins":12},"gpt-6-sol":{"draws":4,"losses":28,"wins":4},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":3},"inception/mercury-2.5-preview":{"draws":9,"losses":4,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":15,"wins":17},"meta/muse-glimmer-30b":{"draws":12,"losses":10,"wins":18},"meta/muse-spark-1.2":{"draws":7,"losses":25,"wins":6},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":5},"meta/muse-wonder":{"draws":7,"losses":23,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":8,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":10,"losses":8,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":19,"wins":10},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":16},"o3":{"draws":14,"losses":18,"wins":24},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":15},"poolside/laguna-s-2.1":{"draws":18,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":1,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-max":{"draws":10,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":9},"stealth/ox-alpha":{"draws":28,"losses":73,"wins":31},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":12},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":11,"losses":17,"wins":26},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":18,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":25,"losses":10,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":27,"losses":35,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":9,"losses":19,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":23},"claude-fable-5":{"draws":17,"losses":51,"wins":20},"claude-fable-5-1":{"draws":6,"losses":84,"wins":4},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":13},"claude-opus-4-5":{"draws":44,"losses":45,"wins":45},"claude-opus-4-8":{"draws":13,"losses":21,"wins":14},"claude-opus-5":{"draws":15,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":44,"losses":32,"wins":56},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":48,"losses":19,"wins":43},"deepseek/deepseek-v4-pro":{"draws":25,"losses":31,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":25,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"fireworks/ember-1":{"draws":19,"losses":15,"wins":14},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":21,"losses":41,"wins":32},"google/gemini-3.5-flash-lite":{"draws":83,"losses":45,"wins":100},"google/gemini-3.6-flash":{"draws":57,"losses":93,"wins":74},"google/gemini-3.8-flash":{"draws":27,"losses":40,"wins":19},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":16},"gpt-5.4":{"draws":25,"losses":78,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":16,"wins":19},"gpt-5.5":{"draws":19,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":69,"losses":31,"wins":48},"gpt-5.6-sol":{"draws":27,"losses":69,"wins":30},"gpt-5.6-terra":{"draws":37,"losses":25,"wins":18},"gpt-6-astra":{"draws":1,"losses":74,"wins":7},"gpt-6-luna":{"draws":20,"losses":15,"wins":13},"gpt-6-sol":{"draws":8,"losses":35,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":18,"losses":10,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":35,"losses":20,"wins":37},"meta/muse-glimmer-30b":{"draws":28,"losses":24,"wins":22},"meta/muse-spark-1.2":{"draws":21,"losses":52,"wins":25},"meta/muse-spark-1.3":{"draws":15,"losses":39,"wins":18},"meta/muse-wonder":{"draws":9,"losses":29,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":13},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":32,"losses":29,"wins":47},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":3,"wins":23},"o3":{"draws":25,"losses":49,"wins":56},"openai/gpt-oss-120b":{"draws":32,"losses":14,"wins":28},"poolside/laguna-s-2.1":{"draws":50,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":37,"wins":24},"qwen/qwen3.8-27b":{"draws":10,"losses":19,"wins":15},"qwen/qwen3.8-flash":{"draws":20,"losses":26,"wins":8},"qwen/qwen3.8-max":{"draws":28,"losses":33,"wins":21},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"stealth/ox-alpha":{"draws":82,"losses":125,"wins":69},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":39,"wins":19},"thinkingmachines/inkling":{"draws":28,"losses":17,"wins":49},"thinkingmachines/inkling-small":{"draws":41,"losses":11,"wins":24},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":25,"losses":50,"wins":37},"x-ai/grok-4.6":{"draws":29,"losses":44,"wins":17},"x-ai/grok-4.7":{"draws":4,"losses":33,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":50,"losses":37,"wins":47},"z-ai/glm-5.3":{"draws":18,"losses":36,"wins":16},"z-ai/glm-5.3-flash":{"draws":20,"losses":38,"wins":28},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":20,"wins":5},"claude-fable-5":{"draws":11,"losses":36,"wins":1},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":30,"wins":2},"claude-opus-4-5":{"draws":56,"losses":55,"wins":17},"claude-opus-4-8":{"draws":26,"losses":45,"wins":7},"claude-opus-5":{"draws":32,"losses":76,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":23,"losses":19,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":5},"deepseek/deepseek-v4-flash":{"draws":49,"losses":38,"wins":19},"deepseek/deepseek-v4-pro":{"draws":18,"losses":21,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":21,"wins":5},"fireworks/ember-1":{"draws":23,"losses":22,"wins":3},"gemini-3.1-pro-preview":{"draws":23,"losses":19,"wins":6},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":34},"google/gemini-3.5-flash":{"draws":29,"losses":37,"wins":4},"google/gemini-3.5-flash-lite":{"draws":44,"losses":41,"wins":19},"google/gemini-3.6-flash":{"draws":48,"losses":64,"wins":10},"google/gemini-3.8-flash":{"draws":18,"losses":30,"wins":2},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":15,"losses":5,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":34,"losses":27,"wins":5},"gpt-5.4":{"draws":20,"losses":26,"wins":0},"gpt-5.4-mini":{"draws":14,"losses":14,"wins":4},"gpt-5.4-nano":{"draws":32,"losses":50,"wins":14},"gpt-5.5":{"draws":36,"losses":30,"wins":10},"gpt-5.6-luna":{"draws":20,"losses":22,"wins":8},"gpt-5.6-sol":{"draws":14,"losses":35,"wins":1},"gpt-5.6-terra":{"draws":22,"losses":22,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":22,"losses":23,"wins":3},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":44,"losses":16,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":42,"losses":30,"wins":14},"meta/muse-glimmer-30b":{"draws":24,"losses":11,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":28,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":1},"meta/muse-wonder":{"draws":14,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":13,"losses":32,"wins":9},"mistralai/mistral-large-4-0":{"draws":16,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":12,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":22,"losses":18,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":23,"wins":9},"o3":{"draws":23,"losses":41,"wins":8},"openai/gpt-oss-120b":{"draws":25,"losses":16,"wins":7},"poolside/laguna-s-2.1":{"draws":41,"losses":22,"wins":7},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":24,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":28,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":24,"losses":23,"wins":1},"stealth/ox-alpha":{"draws":59,"losses":90,"wins":13},"stealth/space-bunny-alpha":{"draws":16,"losses":22,"wins":0},"stepfun/step-3.7-flash":{"draws":18,"losses":18,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":20,"wins":6},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":0},"thinkingmachines/inkling":{"draws":40,"losses":31,"wins":19},"thinkingmachines/inkling-small":{"draws":26,"losses":19,"wins":7},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":28,"losses":33,"wins":3},"x-ai/grok-4.6":{"draws":21,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":73,"losses":51,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":16,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":21,"wins":1},"z-ai/glm-5.2":{"draws":81,"losses":53,"wins":8},"z-ai/glm-5.3":{"draws":17,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":26,"wins":5},"z-ai/glm-5.3-flashx":{"draws":16,"losses":31,"wins":1}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":30,"wins":21},"claude-fable-5":{"draws":11,"losses":58,"wins":3},"claude-fable-5-1":{"draws":1,"losses":75,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":38,"wins":15},"claude-opus-4-5":{"draws":51,"losses":97,"wins":40},"claude-opus-4-8":{"draws":29,"losses":75,"wins":26},"claude-opus-5":{"draws":26,"losses":165,"wins":5},"claude-opus-5-5":{"draws":4,"losses":76,"wins":0},"claude-sonnet-5":{"draws":26,"losses":36,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":53,"wins":7},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":21},"deepseek/deepseek-v4-flash":{"draws":39,"losses":65,"wins":52},"deepseek/deepseek-v4-pro":{"draws":17,"losses":29,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":14},"fireworks/ember-1":{"draws":18,"losses":44,"wins":10},"gemini-3.1-pro-preview":{"draws":22,"losses":34,"wins":16},"google/gemini-3.1-flash-lite":{"draws":18,"losses":30,"wins":50},"google/gemini-3.5-flash":{"draws":26,"losses":67,"wins":19},"google/gemini-3.5-flash-lite":{"draws":60,"losses":56,"wins":50},"google/gemini-3.6-flash":{"draws":50,"losses":90,"wins":32},"google/gemini-3.8-flash":{"draws":18,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":15,"losses":10,"wins":17},"gpt-4.1":{"draws":16,"losses":17,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":20,"losses":47,"wins":19},"gpt-5.4":{"draws":13,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":38,"losses":24,"wins":34},"gpt-5.4-nano":{"draws":35,"losses":52,"wins":43},"gpt-5.5":{"draws":40,"losses":56,"wins":30},"gpt-5.6-luna":{"draws":26,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":59,"wins":4},"gpt-5.6-terra":{"draws":17,"losses":39,"wins":14},"gpt-6-astra":{"draws":3,"losses":71,"wins":0},"gpt-6-luna":{"draws":16,"losses":42,"wins":14},"gpt-6-sol":{"draws":7,"losses":57,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":65,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":11,"wins":25},"inclusionai/ling-3.0-flash":{"draws":40,"losses":12,"wins":44},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":33,"losses":41,"wins":54},"meta/muse-glimmer-30b":{"draws":18,"losses":20,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":39,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":52,"wins":8},"meta/muse-wonder":{"draws":5,"losses":55,"wins":12},"minimax/minimax-m3":{"draws":26,"losses":28,"wins":34},"mistralai/mistral-large-4-0":{"draws":8,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":9,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":7,"wins":10},"moonshotai/kimi-k3":{"draws":24,"losses":53,"wins":15},"nex-agi/nex-n2-pro":{"draws":21,"losses":31,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":29,"wins":44},"o3":{"draws":16,"losses":66,"wins":44},"openai/gpt-oss-120b":{"draws":26,"losses":22,"wins":16},"poolside/laguna-s-2.1":{"draws":52,"losses":41,"wins":31},"qwen/qwen3.7-max":{"draws":34,"losses":36,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":28,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":45,"wins":15},"qwen/qwen3.8-27b":{"draws":15,"losses":24,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":24,"wins":12},"qwen/qwen3.8-max":{"draws":17,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":22,"losses":35,"wins":15},"stealth/ox-alpha":{"draws":51,"losses":135,"wins":52},"stealth/space-bunny-alpha":{"draws":13,"losses":27,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":25,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":27,"losses":38,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":48,"wins":10},"thinkingmachines/inkling":{"draws":33,"losses":49,"wins":34},"thinkingmachines/inkling-small":{"draws":28,"losses":23,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":23,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":8,"wins":9},"x-ai/grok-4.5":{"draws":19,"losses":62,"wins":13},"x-ai/grok-4.6":{"draws":15,"losses":45,"wins":12},"x-ai/grok-4.7":{"draws":10,"losses":54,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":22},"xiaomi/mimo-v2.5":{"draws":58,"losses":86,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":43,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":25,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":68,"losses":84,"wins":46},"z-ai/glm-5.3":{"draws":13,"losses":48,"wins":11},"z-ai/glm-5.3-flash":{"draws":15,"losses":43,"wins":14},"z-ai/glm-5.3-flashx":{"draws":17,"losses":41,"wins":14}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":10,"wins":13},"claude-fable-5":{"draws":13,"losses":23,"wins":8},"claude-fable-5-1":{"draws":2,"losses":45,"wins":3},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":64,"losses":39,"wins":19},"claude-opus-4-8":{"draws":31,"losses":29,"wins":8},"claude-opus-5":{"draws":30,"losses":105,"wins":1},"claude-opus-5-5":{"draws":8,"losses":38,"wins":0},"claude-sonnet-5":{"draws":22,"losses":10,"wins":12},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":10,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":44,"losses":8,"wins":22},"deepseek/deepseek-v4-pro":{"draws":21,"losses":13,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":8},"fireworks/ember-1":{"draws":17,"losses":17,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":15,"wins":11},"google/gemini-3.1-flash-lite":{"draws":17,"losses":0,"wins":19},"google/gemini-3.5-flash":{"draws":24,"losses":18,"wins":10},"google/gemini-3.5-flash-lite":{"draws":56,"losses":18,"wins":24},"google/gemini-3.6-flash":{"draws":43,"losses":50,"wins":19},"google/gemini-3.8-flash":{"draws":19,"losses":16,"wins":7},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":8},"gpt-4.1":{"draws":14,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":30,"losses":18,"wins":8},"gpt-5.4":{"draws":14,"losses":17,"wins":9},"gpt-5.4-mini":{"draws":31,"losses":11,"wins":10},"gpt-5.4-nano":{"draws":32,"losses":12,"wins":28},"gpt-5.5":{"draws":30,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":25,"wins":7},"gpt-5.6-terra":{"draws":23,"losses":13,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":16,"losses":15,"wins":11},"gpt-6-sol":{"draws":10,"losses":30,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":39,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":47,"losses":2,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":15,"wins":18},"meta/muse-glimmer-30b":{"draws":24,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":6},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":14,"losses":14,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":16,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":24,"losses":23,"wins":11},"nex-agi/nex-n2-pro":{"draws":18,"losses":4,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":6,"wins":15},"o3":{"draws":26,"losses":17,"wins":23},"openai/gpt-oss-120b":{"draws":22,"losses":6,"wins":12},"poolside/laguna-s-2.1":{"draws":39,"losses":19,"wins":12},"qwen/qwen3.7-max":{"draws":27,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":19,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":17,"wins":8},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":17,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":17,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":19,"losses":18,"wins":5},"stealth/ox-alpha":{"draws":51,"losses":70,"wins":27},"stealth/space-bunny-alpha":{"draws":18,"losses":7,"wins":9},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":13,"wins":7},"tencent/hy4-preview":{"draws":20,"losses":20,"wins":4},"thinkingmachines/inkling":{"draws":39,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":22,"losses":30,"wins":2},"x-ai/grok-4.6":{"draws":19,"losses":24,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":19,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":78,"losses":14,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":11,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":5},"z-ai/glm-5.2":{"draws":57,"losses":38,"wins":35},"z-ai/glm-5.3":{"draws":9,"losses":25,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":8},"z-ai/glm-5.3-flashx":{"draws":18,"losses":18,"wins":6}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":45,"wins":16},"claude-fable-5":{"draws":16,"losses":39,"wins":5},"claude-fable-5-1":{"draws":2,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":42,"losses":79,"wins":13},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":9,"losses":72,"wins":5},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":41,"losses":83,"wins":14},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":47,"losses":49,"wins":16},"deepseek/deepseek-v4-pro":{"draws":27,"losses":43,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":35,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":28,"wins":6},"fireworks/ember-1":{"draws":15,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":26,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":16,"wins":9},"google/gemini-3.5-flash":{"draws":20,"losses":56,"wins":10},"google/gemini-3.5-flash-lite":{"draws":61,"losses":127,"wins":58},"google/gemini-3.6-flash":{"draws":68,"losses":137,"wins":15},"google/gemini-3.8-flash":{"draws":10,"losses":55,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":15,"wins":3},"gpt-4.1":{"draws":4,"losses":11,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":11,"losses":27,"wins":4},"gpt-5.4":{"draws":40,"losses":74,"wins":10},"gpt-5.4-mini":{"draws":11,"losses":17,"wins":4},"gpt-5.4-nano":{"draws":15,"losses":27,"wins":10},"gpt-5.5":{"draws":13,"losses":28,"wins":3},"gpt-5.6-luna":{"draws":41,"losses":41,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":92,"wins":10},"gpt-5.6-terra":{"draws":26,"losses":38,"wins":16},"gpt-6-astra":{"draws":5,"losses":47,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":26,"wins":10},"inclusionai/ling-3.0-flash":{"draws":27,"losses":25,"wins":6},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":51,"wins":18},"meta/muse-glimmer-30b":{"draws":34,"losses":44,"wins":6},"meta/muse-spark-1.2":{"draws":31,"losses":53,"wins":16},"meta/muse-spark-1.3":{"draws":17,"losses":44,"wins":5},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":19,"wins":3},"mistralai/mistral-medium-3-5":{"draws":20,"losses":20,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":34,"losses":59,"wins":11},"nex-agi/nex-n2-pro":{"draws":9,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":24,"wins":6},"o3":{"draws":14,"losses":108,"wins":14},"openai/gpt-oss-120b":{"draws":36,"losses":28,"wins":16},"poolside/laguna-s-2.1":{"draws":32,"losses":48,"wins":12},"qwen/qwen3.7-max":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":0},"qwen/qwen3.8-27b":{"draws":13,"losses":23,"wins":4},"qwen/qwen3.8-flash":{"draws":22,"losses":20,"wins":10},"qwen/qwen3.8-max":{"draws":24,"losses":46,"wins":12},"qwen/qwen3.8-max-0902":{"draws":14,"losses":31,"wins":3},"stealth/ox-alpha":{"draws":84,"losses":148,"wins":14},"stealth/space-bunny-alpha":{"draws":15,"losses":19,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":16,"wins":7},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":18,"wins":0},"tencent/hy4-preview":{"draws":20,"losses":46,"wins":8},"thinkingmachines/inkling":{"draws":36,"losses":38,"wins":26},"thinkingmachines/inkling-small":{"draws":35,"losses":47,"wins":14},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":33,"losses":62,"wins":5},"x-ai/grok-4.6":{"draws":16,"losses":51,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":38,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":7,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":35,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":17,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":25,"wins":1},"z-ai/glm-5.2":{"draws":49,"losses":72,"wins":9},"z-ai/glm-5.3":{"draws":14,"losses":44,"wins":2},"z-ai/glm-5.3-flash":{"draws":23,"losses":37,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":34,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":6,"wins":49},"claude-fable-5":{"draws":15,"losses":58,"wins":23},"claude-fable-5-1":{"draws":5,"losses":95,"wins":8},"claude-haiku-5-5":{"draws":4,"losses":22,"wins":20},"claude-opus-4-5":{"draws":36,"losses":27,"wins":81},"claude-opus-4-8":{"draws":16,"losses":26,"wins":16},"claude-opus-5":{"draws":9,"losses":73,"wins":8},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":47,"losses":27,"wins":80},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":65},"deepseek/deepseek-v4-pro":{"draws":20,"losses":29,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":31,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":21,"wins":13},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":10,"losses":13,"wins":25},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":19,"losses":34,"wins":51},"google/gemini-3.5-flash-lite":{"draws":62,"losses":28,"wins":146},"google/gemini-3.6-flash":{"draws":50,"losses":86,"wins":104},"google/gemini-3.8-flash":{"draws":19,"losses":41,"wins":34},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":6,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":14,"wins":22},"gpt-5.4":{"draws":43,"losses":64,"wins":37},"gpt-5.4-mini":{"draws":16,"losses":9,"wins":13},"gpt-5.4-nano":{"draws":13,"losses":7,"wins":30},"gpt-5.5":{"draws":14,"losses":22,"wins":10},"gpt-5.6-luna":{"draws":41,"losses":27,"wins":64},"gpt-5.6-sol":{"draws":14,"losses":59,"wins":29},"gpt-5.6-terra":{"draws":34,"losses":23,"wins":33},"gpt-6-astra":{"draws":5,"losses":83,"wins":8},"gpt-6-luna":{"draws":12,"losses":11,"wins":25},"gpt-6-sol":{"draws":3,"losses":36,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":42,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":0,"wins":37},"inclusionai/ling-3.0-flash":{"draws":16,"losses":3,"wins":39},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":22,"losses":8,"wins":74},"meta/muse-glimmer-30b":{"draws":24,"losses":8,"wins":40},"meta/muse-spark-1.2":{"draws":23,"losses":36,"wins":43},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":29},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":13},"mistralai/mistral-medium-3-5":{"draws":16,"losses":3,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":25,"losses":31,"wins":48},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":28},"o3":{"draws":8,"losses":29,"wins":103},"openai/gpt-oss-120b":{"draws":22,"losses":2,"wins":58},"poolside/laguna-s-2.1":{"draws":30,"losses":5,"wins":61},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":38,"wins":33},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":25},"qwen/qwen3.8-flash":{"draws":23,"losses":16,"wins":21},"qwen/qwen3.8-max":{"draws":23,"losses":31,"wins":39},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":19},"stealth/ox-alpha":{"draws":62,"losses":117,"wins":119},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":6,"wins":18},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":36},"thinkingmachines/inkling":{"draws":26,"losses":9,"wins":63},"thinkingmachines/inkling-small":{"draws":24,"losses":8,"wins":55},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":18,"losses":56,"wins":40},"x-ai/grok-4.6":{"draws":25,"losses":42,"wins":29},"x-ai/grok-4.7":{"draws":6,"losses":23,"wins":13},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":25,"losses":5,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":14,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":38,"wins":71},"z-ai/glm-5.3":{"draws":12,"losses":41,"wins":23},"z-ai/glm-5.3-flash":{"draws":18,"losses":38,"wins":38},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":15,"wins":34},"claude-fable-5":{"draws":23,"losses":51,"wins":2},"claude-fable-5-1":{"draws":7,"losses":73,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":39,"losses":41,"wins":10},"claude-opus-4-8":{"draws":16,"losses":19,"wins":3},"claude-opus-5":{"draws":14,"losses":50,"wins":8},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":39,"losses":26,"wins":13},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":41,"losses":20,"wins":43},"deepseek/deepseek-v4-pro":{"draws":28,"losses":28,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":25,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":16,"wins":9},"fireworks/ember-1":{"draws":16,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":18,"losses":17,"wins":7},"google/gemini-3.1-flash-lite":{"draws":13,"losses":3,"wins":14},"google/gemini-3.5-flash":{"draws":41,"losses":34,"wins":7},"google/gemini-3.5-flash-lite":{"draws":55,"losses":43,"wins":34},"google/gemini-3.6-flash":{"draws":49,"losses":50,"wins":23},"google/gemini-3.8-flash":{"draws":32,"losses":36,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":9,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":15,"wins":7},"gpt-5.4":{"draws":27,"losses":34,"wins":13},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":16},"gpt-5.5":{"draws":21,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":28,"losses":30,"wins":20},"gpt-5.6-sol":{"draws":27,"losses":44,"wins":7},"gpt-5.6-terra":{"draws":24,"losses":11,"wins":15},"gpt-6-astra":{"draws":8,"losses":61,"wins":3},"gpt-6-luna":{"draws":17,"losses":18,"wins":7},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":24},"inclusionai/ling-3.0-flash":{"draws":20,"losses":9,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":14,"wins":19},"meta/muse-glimmer-30b":{"draws":36,"losses":8,"wins":28},"meta/muse-spark-1.2":{"draws":30,"losses":20,"wins":16},"meta/muse-spark-1.3":{"draws":20,"losses":28,"wins":16},"meta/muse-wonder":{"draws":10,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":5,"wins":7},"mistralai/mistral-large-4-0":{"draws":16,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":18,"losses":2,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":29,"wins":10},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":6,"wins":13},"o3":{"draws":28,"losses":38,"wins":18},"openai/gpt-oss-120b":{"draws":39,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":37,"losses":6,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":27,"wins":12},"qwen/qwen3.8-27b":{"draws":19,"losses":18,"wins":3},"qwen/qwen3.8-flash":{"draws":21,"losses":11,"wins":12},"qwen/qwen3.8-max":{"draws":38,"losses":20,"wins":20},"qwen/qwen3.8-max-0902":{"draws":19,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":101,"losses":106,"wins":41},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":3},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":27,"losses":30,"wins":11},"thinkingmachines/inkling":{"draws":25,"losses":18,"wins":23},"thinkingmachines/inkling-small":{"draws":30,"losses":16,"wins":30},"unbiased/pareto-26.10-preview":{"draws":2,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":21,"losses":39,"wins":6},"x-ai/grok-4.6":{"draws":29,"losses":42,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":34,"losses":7,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":4},"z-ai/glm-5.2":{"draws":66,"losses":25,"wins":31},"z-ai/glm-5.3":{"draws":22,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":31,"losses":34,"wins":11},"z-ai/glm-5.3-flashx":{"draws":13,"losses":24,"wins":5}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":46},"claude-fable-5":{"draws":9,"losses":21,"wins":62},"claude-fable-5-1":{"draws":10,"losses":49,"wins":49},"claude-haiku-5-5":{"draws":5,"losses":3,"wins":38},"claude-opus-4-5":{"draws":12,"losses":10,"wins":88},"claude-opus-4-8":{"draws":8,"losses":7,"wins":35},"claude-opus-5":{"draws":15,"losses":28,"wins":47},"claude-opus-5-5":{"draws":7,"losses":27,"wins":18},"claude-sonnet-5":{"draws":10,"losses":12,"wins":64},"claude-sonnet-5-5":{"draws":5,"losses":11,"wins":32},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":82},"deepseek/deepseek-v4-pro":{"draws":9,"losses":9,"wins":52},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":0,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":2,"wins":35},"fireworks/ember-1":{"draws":9,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":1,"wins":42},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":18,"losses":1,"wins":77},"google/gemini-3.5-flash-lite":{"draws":12,"losses":2,"wins":112},"google/gemini-3.6-flash":{"draws":23,"losses":11,"wins":106},"google/gemini-3.8-flash":{"draws":13,"losses":11,"wins":66},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":4,"losses":0,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":0,"wins":37},"gpt-5.4":{"draws":11,"losses":13,"wins":58},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":47},"gpt-5.5":{"draws":3,"losses":3,"wins":38},"gpt-5.6-luna":{"draws":13,"losses":1,"wins":52},"gpt-5.6-sol":{"draws":13,"losses":6,"wins":75},"gpt-5.6-terra":{"draws":16,"losses":5,"wins":61},"gpt-6-astra":{"draws":9,"losses":31,"wins":24},"gpt-6-luna":{"draws":8,"losses":4,"wins":36},"gpt-6-sol":{"draws":3,"losses":15,"wins":30},"gpt-6.1-sol":{"draws":6,"losses":23,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":36},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":34},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":52},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":49},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":55},"meta/muse-spark-1.3":{"draws":11,"losses":11,"wins":44},"meta/muse-wonder":{"draws":8,"losses":7,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":27},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":56},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":36},"o3":{"draws":4,"losses":0,"wins":86},"openai/gpt-oss-120b":{"draws":7,"losses":0,"wins":47},"poolside/laguna-s-2.1":{"draws":13,"losses":0,"wins":45},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":24},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":7,"wins":69},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":41},"qwen/qwen3.8-flash":{"draws":15,"losses":1,"wins":36},"qwen/qwen3.8-max":{"draws":14,"losses":4,"wins":62},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":37},"stealth/ox-alpha":{"draws":43,"losses":20,"wins":219},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":33},"stepfun/step-3.7-flash":{"draws":3,"losses":0,"wins":31},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":14,"losses":4,"wins":64},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":62},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":62},"unbiased/pareto-26.10-preview":{"draws":0,"losses":7,"wins":9},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":51},"x-ai/grok-4.6":{"draws":13,"losses":14,"wins":65},"x-ai/grok-4.7":{"draws":6,"losses":9,"wins":27},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":17,"losses":9,"wins":90},"z-ai/glm-5.3":{"draws":17,"losses":5,"wins":52},"z-ai/glm-5.3-flash":{"draws":13,"losses":9,"wins":64},"z-ai/glm-5.3-flashx":{"draws":10,"losses":3,"wins":35}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":16},"claude-fable-5":{"draws":12,"losses":31,"wins":5},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":20,"wins":9},"claude-opus-4-5":{"draws":30,"losses":25,"wins":23},"claude-opus-4-8":{"draws":17,"losses":22,"wins":5},"claude-opus-5":{"draws":17,"losses":60,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":12,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":24,"losses":19,"wins":29},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":21,"wins":8},"fireworks/ember-1":{"draws":16,"losses":22,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":21,"wins":9},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":22,"losses":23,"wins":15},"google/gemini-3.5-flash-lite":{"draws":40,"losses":15,"wins":29},"google/gemini-3.6-flash":{"draws":37,"losses":40,"wins":15},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":9},"gpt-4.1":{"draws":3,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":13,"wins":12},"gpt-5.4":{"draws":17,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":21,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":10,"losses":10,"wins":12},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":12,"wins":20},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":5},"meta/muse-wonder":{"draws":15,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":5,"wins":14},"o3":{"draws":17,"losses":24,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":9,"wins":13},"poolside/laguna-s-2.1":{"draws":23,"losses":9,"wins":14},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":12,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":44,"losses":75,"wins":39},"stealth/space-bunny-alpha":{"draws":19,"losses":5,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":21,"losses":12,"wins":15},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":35,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":35,"losses":6,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":38,"losses":23,"wins":35},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":8,"losses":20,"wins":20},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":9,"losses":14,"wins":23},"claude-opus-4-5":{"draws":15,"losses":11,"wins":52},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":5,"losses":21,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":53},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":7,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":21},"fireworks/ember-1":{"draws":11,"losses":12,"wins":25},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":15,"wins":35},"google/gemini-3.5-flash-lite":{"draws":12,"losses":8,"wins":64},"google/gemini-3.6-flash":{"draws":17,"losses":26,"wins":49},"google/gemini-3.8-flash":{"draws":9,"losses":20,"wins":19},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":23},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":12,"losses":5,"wins":31},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":29},"gpt-6-astra":{"draws":3,"losses":41,"wins":4},"gpt-6-luna":{"draws":9,"losses":6,"wins":33},"gpt-6-sol":{"draws":5,"losses":21,"wins":6},"gpt-6.1-sol":{"draws":5,"losses":37,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.0-flash":{"draws":5,"losses":2,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":11,"losses":9,"wins":28},"meta/muse-wonder":{"draws":12,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":5,"wins":18},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":36},"o3":{"draws":4,"losses":4,"wins":58},"openai/gpt-oss-120b":{"draws":10,"losses":2,"wins":30},"poolside/laguna-s-2.1":{"draws":10,"losses":3,"wins":33},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":23},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":12,"wins":24},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":26},"stealth/ox-alpha":{"draws":25,"losses":33,"wins":100},"stealth/space-bunny-alpha":{"draws":9,"losses":4,"wins":25},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":27},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":1,"wins":17},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":12,"wins":22},"x-ai/grok-4.6":{"draws":12,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":4,"losses":25,"wins":13},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":23,"losses":12,"wins":61},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":21,"wins":20}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":32},"claude-fable-5":{"draws":4,"losses":18,"wins":26},"claude-fable-5-1":{"draws":4,"losses":35,"wins":15},"claude-haiku-5-5":{"draws":8,"losses":4,"wins":34},"claude-opus-4-5":{"draws":18,"losses":9,"wins":51},"claude-opus-4-8":{"draws":4,"losses":9,"wins":31},"claude-opus-5":{"draws":14,"losses":36,"wins":32},"claude-opus-5-5":{"draws":10,"losses":25,"wins":17},"claude-sonnet-5":{"draws":5,"losses":7,"wins":36},"claude-sonnet-5-5":{"draws":2,"losses":17,"wins":29},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":61},"deepseek/deepseek-v4-pro":{"draws":7,"losses":4,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":3,"wins":35},"fireworks/ember-1":{"draws":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":5,"wins":39},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":9,"wins":45},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":14,"wins":69},"google/gemini-3.8-flash":{"draws":14,"losses":8,"wins":26},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":25},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":4,"wins":33},"gpt-5.4":{"draws":4,"losses":10,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":38},"gpt-5.6-sol":{"draws":8,"losses":9,"wins":31},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":5,"losses":35,"wins":8},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":2,"losses":22,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":3,"wins":44},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":31},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":32},"meta/muse-wonder":{"draws":8,"losses":14,"wins":26},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":34},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"o3":{"draws":2,"losses":7,"wins":57},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":1,"wins":37},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":10,"wins":31},"qwen/qwen3.8-27b":{"draws":7,"losses":1,"wins":26},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":23},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":38},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"stealth/ox-alpha":{"draws":27,"losses":18,"wins":113},"stealth/space-bunny-alpha":{"draws":8,"losses":4,"wins":26},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":5,"losses":8,"wins":33},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":50},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":30},"x-ai/grok-4.6":{"draws":11,"losses":5,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":15,"losses":6,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":5,"wins":73},"z-ai/glm-5.3":{"draws":8,"losses":14,"wins":24},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":34},"z-ai/glm-5.3-flashx":{"draws":13,"losses":8,"wins":27}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":17,"wins":19},"claude-fable-5":{"draws":15,"losses":22,"wins":7},"claude-fable-5-1":{"draws":5,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":27,"losses":28,"wins":9},"claude-opus-4-8":{"draws":11,"losses":7,"wins":8},"claude-opus-5":{"draws":13,"losses":35,"wins":2},"claude-opus-5-5":{"draws":4,"losses":26,"wins":0},"claude-sonnet-5":{"draws":23,"losses":19,"wins":12},"claude-sonnet-5-5":{"draws":8,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":27,"losses":24,"wins":17},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":25,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":12,"wins":3},"fireworks/ember-1":{"draws":13,"losses":12,"wins":5},"gemini-3.1-pro-preview":{"draws":9,"losses":8,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":20,"losses":23,"wins":13},"google/gemini-3.5-flash-lite":{"draws":37,"losses":27,"wins":40},"google/gemini-3.6-flash":{"draws":28,"losses":45,"wins":15},"google/gemini-3.8-flash":{"draws":21,"losses":25,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":7},"gpt-5.4":{"draws":26,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":9},"gpt-5.5":{"draws":13,"losses":9,"wins":4},"gpt-5.6-luna":{"draws":28,"losses":19,"wins":11},"gpt-5.6-sol":{"draws":14,"losses":35,"wins":1},"gpt-5.6-terra":{"draws":24,"losses":18,"wins":10},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":4},"gpt-6-sol":{"draws":7,"losses":22,"wins":1},"gpt-6.1-sol":{"draws":5,"losses":25,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":8},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":18,"losses":14,"wins":16},"meta/muse-glimmer-30b":{"draws":23,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":18,"losses":17,"wins":9},"meta/muse-spark-1.3":{"draws":12,"losses":25,"wins":7},"meta/muse-wonder":{"draws":10,"losses":17,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":6,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":24,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":8},"o3":{"draws":9,"losses":27,"wins":14},"openai/gpt-oss-120b":{"draws":21,"losses":11,"wins":18},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":29,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":16,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":22,"losses":24,"wins":8},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":2},"stealth/ox-alpha":{"draws":63,"losses":89,"wins":38},"stealth/space-bunny-alpha":{"draws":8,"losses":11,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":25,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":23,"losses":7,"wins":22},"thinkingmachines/inkling-small":{"draws":29,"losses":11,"wins":20},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":19,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":19,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":14,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":1},"z-ai/glm-5.2":{"draws":41,"losses":32,"wins":15},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":5},"z-ai/glm-5.3-flash":{"draws":17,"losses":23,"wins":8},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":28,"wins":10},"claude-fable-5":{"draws":14,"losses":49,"wins":3},"claude-fable-5-1":{"draws":5,"losses":67,"wins":0},"claude-haiku-5-5":{"draws":21,"losses":37,"wins":4},"claude-opus-4-5":{"draws":58,"losses":76,"wins":12},"claude-opus-4-8":{"draws":41,"losses":57,"wins":0},"claude-opus-5":{"draws":31,"losses":121,"wins":8},"claude-opus-5-5":{"draws":4,"losses":74,"wins":0},"claude-sonnet-5":{"draws":27,"losses":42,"wins":7},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":22,"losses":9,"wins":9},"deepseek/deepseek-v4-flash":{"draws":73,"losses":48,"wins":27},"deepseek/deepseek-v4-pro":{"draws":29,"losses":25,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":26,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":28,"wins":6},"fireworks/ember-1":{"draws":32,"losses":34,"wins":0},"gemini-3.1-pro-preview":{"draws":29,"losses":32,"wins":5},"google/gemini-3.1-flash-lite":{"draws":32,"losses":30,"wins":16},"google/gemini-3.5-flash":{"draws":36,"losses":51,"wins":5},"google/gemini-3.5-flash-lite":{"draws":93,"losses":65,"wins":18},"google/gemini-3.6-flash":{"draws":99,"losses":89,"wins":16},"google/gemini-3.8-flash":{"draws":23,"losses":43,"wins":0},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":5},"gpt-4.1":{"draws":23,"losses":29,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":35,"losses":23,"wins":34},"gpt-5.4":{"draws":24,"losses":34,"wins":6},"gpt-5.4-mini":{"draws":49,"losses":30,"wins":13},"gpt-5.4-nano":{"draws":52,"losses":55,"wins":21},"gpt-5.5":{"draws":69,"losses":41,"wins":6},"gpt-5.6-luna":{"draws":39,"losses":24,"wins":7},"gpt-5.6-sol":{"draws":9,"losses":60,"wins":1},"gpt-5.6-terra":{"draws":28,"losses":41,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":26,"losses":33,"wins":7},"gpt-6-sol":{"draws":10,"losses":50,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":63,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":27,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":40,"losses":24,"wins":24},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":82,"losses":52,"wins":24},"meta/muse-glimmer-30b":{"draws":39,"losses":17,"wins":8},"meta/muse-spark-1.2":{"draws":16,"losses":43,"wins":5},"meta/muse-spark-1.3":{"draws":15,"losses":48,"wins":5},"meta/muse-wonder":{"draws":9,"losses":52,"wins":5},"minimax/minimax-m3":{"draws":36,"losses":37,"wins":9},"mistralai/mistral-large-4-0":{"draws":21,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":19,"losses":22,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":10,"wins":4},"moonshotai/kimi-k3":{"draws":41,"losses":37,"wins":6},"nex-agi/nex-n2-pro":{"draws":44,"losses":24,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":60,"losses":29,"wins":17},"o3":{"draws":37,"losses":53,"wins":6},"openai/gpt-oss-120b":{"draws":33,"losses":23,"wins":2},"poolside/laguna-s-2.1":{"draws":85,"losses":43,"wins":20},"qwen/qwen3.7-max":{"draws":45,"losses":18,"wins":11},"qwen/qwen3.7-plus":{"draws":33,"losses":19,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":41,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":29,"wins":9},"qwen/qwen3.8-flash":{"draws":26,"losses":26,"wins":2},"qwen/qwen3.8-max":{"draws":28,"losses":35,"wins":7},"qwen/qwen3.8-max-0902":{"draws":29,"losses":34,"wins":3},"stealth/ox-alpha":{"draws":76,"losses":147,"wins":11},"stealth/space-bunny-alpha":{"draws":24,"losses":16,"wins":6},"stepfun/step-3.7-flash":{"draws":27,"losses":20,"wins":11},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":33,"wins":8},"tencent/hy4-preview":{"draws":30,"losses":36,"wins":2},"thinkingmachines/inkling":{"draws":58,"losses":61,"wins":35},"thinkingmachines/inkling-small":{"draws":37,"losses":20,"wins":11},"unbiased/pareto-26.10-preview":{"draws":2,"losses":20,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":2},"x-ai/grok-4.5":{"draws":29,"losses":78,"wins":9},"x-ai/grok-4.6":{"draws":26,"losses":39,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":49,"wins":3},"x-ai/grok-build-0.1":{"draws":21,"losses":23,"wins":0},"xiaomi/mimo-v2.5":{"draws":92,"losses":65,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":29,"losses":28,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":115,"losses":51,"wins":16},"z-ai/glm-5.3":{"draws":19,"losses":42,"wins":3},"z-ai/glm-5.3-flash":{"draws":30,"losses":32,"wins":6},"z-ai/glm-5.3-flashx":{"draws":25,"losses":35,"wins":6}},"inclusionai/ling-3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":8,"losses":1,"wins":1},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":0,"wins":1},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":6,"losses":0,"wins":0},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":3,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":2,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":9,"wins":1},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":0},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":1,"losses":4,"wins":1},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":2,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":33,"wins":22},"claude-fable-5":{"draws":12,"losses":64,"wins":10},"claude-fable-5-1":{"draws":0,"losses":91,"wins":3},"claude-haiku-5-5":{"draws":18,"losses":52,"wins":10},"claude-opus-4-5":{"draws":65,"losses":110,"wins":33},"claude-opus-4-8":{"draws":22,"losses":68,"wins":18},"claude-opus-5":{"draws":23,"losses":175,"wins":18},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":30,"losses":41,"wins":17},"claude-sonnet-5-5":{"draws":12,"losses":58,"wins":14},"cohere/north-mini-code":{"draws":17,"losses":7,"wins":24},"deepseek/deepseek-v4-flash":{"draws":54,"losses":66,"wins":60},"deepseek/deepseek-v4-pro":{"draws":21,"losses":47,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":44,"wins":20},"fireworks/ember-1":{"draws":32,"losses":47,"wins":5},"gemini-3.1-pro-preview":{"draws":24,"losses":39,"wins":21},"google/gemini-3.1-flash-lite":{"draws":25,"losses":33,"wins":58},"google/gemini-3.5-flash":{"draws":28,"losses":68,"wins":20},"google/gemini-3.5-flash-lite":{"draws":73,"losses":93,"wins":40},"google/gemini-3.6-flash":{"draws":70,"losses":126,"wins":44},"google/gemini-3.8-flash":{"draws":15,"losses":67,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":11,"wins":17},"gpt-4.1":{"draws":16,"losses":32,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":42,"losses":58,"wins":36},"gpt-5.4":{"draws":26,"losses":52,"wins":8},"gpt-5.4-mini":{"draws":50,"losses":35,"wins":25},"gpt-5.4-nano":{"draws":38,"losses":86,"wins":56},"gpt-5.5":{"draws":65,"losses":42,"wins":27},"gpt-5.6-luna":{"draws":27,"losses":36,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":75,"wins":5},"gpt-5.6-terra":{"draws":31,"losses":44,"wins":17},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":24,"losses":44,"wins":16},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":76,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":16,"wins":19},"inclusionai/ling-3.0-flash":{"draws":72,"losses":36,"wins":50},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":38,"losses":37,"wins":33},"meta/muse-glimmer-30b":{"draws":35,"losses":24,"wins":17},"meta/muse-spark-1.2":{"draws":18,"losses":55,"wins":11},"meta/muse-spark-1.3":{"draws":18,"losses":62,"wins":12},"meta/muse-wonder":{"draws":20,"losses":54,"wins":10},"minimax/minimax-m3":{"draws":22,"losses":30,"wins":32},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":22,"losses":18,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":23,"wins":4},"moonshotai/kimi-k3":{"draws":42,"losses":41,"wins":21},"nex-agi/nex-n2-pro":{"draws":23,"losses":23,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":66,"losses":40,"wins":28},"o3":{"draws":33,"losses":77,"wins":34},"openai/gpt-oss-120b":{"draws":26,"losses":23,"wins":25},"poolside/laguna-s-2.1":{"draws":75,"losses":63,"wins":34},"qwen/qwen3.7-max":{"draws":39,"losses":34,"wins":17},"qwen/qwen3.7-plus":{"draws":20,"losses":26,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":51,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":27,"losses":25,"wins":12},"qwen/qwen3.8-max":{"draws":29,"losses":40,"wins":21},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":14},"stealth/ox-alpha":{"draws":67,"losses":189,"wins":44},"stealth/space-bunny-alpha":{"draws":22,"losses":33,"wins":11},"stepfun/step-3.7-flash":{"draws":20,"losses":28,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":33,"wins":26},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":12},"thinkingmachines/inkling":{"draws":45,"losses":69,"wins":60},"thinkingmachines/inkling-small":{"draws":34,"losses":26,"wins":26},"unbiased/pareto-26.10-preview":{"draws":1,"losses":26,"wins":1},"upstage/solar-mini4":{"draws":4,"losses":8,"wins":10},"x-ai/grok-4.5":{"draws":30,"losses":91,"wins":25},"x-ai/grok-4.6":{"draws":32,"losses":51,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":17,"losses":15,"wins":18},"xiaomi/mimo-v2.5":{"draws":81,"losses":77,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":49,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":30,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":37,"wins":5},"z-ai/glm-5.2":{"draws":85,"losses":107,"wins":54},"z-ai/glm-5.3":{"draws":12,"losses":63,"wins":5},"z-ai/glm-5.3-flash":{"draws":25,"losses":49,"wins":18},"z-ai/glm-5.3-flashx":{"draws":16,"losses":56,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":26,"wins":11},"claude-fable-5":{"draws":14,"losses":36,"wins":6},"claude-fable-5-1":{"draws":4,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":3},"claude-opus-4-5":{"draws":21,"losses":46,"wins":7},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":18,"losses":37,"wins":7},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":3},"deepseek/deepseek-v4-flash":{"draws":33,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":24,"losses":25,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":15,"wins":2},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":22,"losses":39,"wins":11},"google/gemini-3.5-flash-lite":{"draws":47,"losses":46,"wins":29},"google/gemini-3.6-flash":{"draws":40,"losses":66,"wins":10},"google/gemini-3.8-flash":{"draws":19,"losses":32,"wins":9},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":5,"losses":6,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":12,"losses":16,"wins":8},"gpt-5.4":{"draws":21,"losses":31,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":19,"wins":11},"gpt-5.5":{"draws":17,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":27,"losses":22,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":40,"wins":2},"gpt-5.6-terra":{"draws":24,"losses":32,"wins":8},"gpt-6-astra":{"draws":1,"losses":45,"wins":0},"gpt-6-luna":{"draws":12,"losses":19,"wins":5},"gpt-6-sol":{"draws":5,"losses":29,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":20,"wins":16},"meta/muse-glimmer-30b":{"draws":21,"losses":20,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":37,"wins":5},"meta/muse-spark-1.3":{"draws":14,"losses":34,"wins":6},"meta/muse-wonder":{"draws":6,"losses":26,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":11,"wins":5},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":16,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":28,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":9},"o3":{"draws":16,"losses":43,"wins":15},"openai/gpt-oss-120b":{"draws":22,"losses":22,"wins":16},"poolside/laguna-s-2.1":{"draws":23,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":28,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":24,"losses":8,"wins":10},"qwen/qwen3.8-max":{"draws":21,"losses":27,"wins":10},"qwen/qwen3.8-max-0902":{"draws":13,"losses":20,"wins":3},"stealth/ox-alpha":{"draws":54,"losses":123,"wins":29},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":12,"wins":1},"tencent/hy4-preview":{"draws":28,"losses":29,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":24,"wins":20},"thinkingmachines/inkling-small":{"draws":31,"losses":15,"wins":22},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":13,"losses":32,"wins":7},"x-ai/grok-4.6":{"draws":25,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":27,"losses":15,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":11,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":51,"losses":36,"wins":17},"z-ai/glm-5.3":{"draws":6,"losses":36,"wins":6},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":2},"z-ai/glm-5.3-flashx":{"draws":9,"losses":22,"wins":5}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":25,"wins":26},"claude-fable-5":{"draws":13,"losses":53,"wins":10},"claude-fable-5-1":{"draws":7,"losses":81,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":30,"wins":6},"claude-opus-4-5":{"draws":40,"losses":60,"wins":42},"claude-opus-4-8":{"draws":13,"losses":31,"wins":6},"claude-opus-5":{"draws":7,"losses":71,"wins":12},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":43,"losses":53,"wins":40},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":13},"deepseek/deepseek-v4-flash":{"draws":29,"losses":34,"wins":43},"deepseek/deepseek-v4-pro":{"draws":15,"losses":37,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":36,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":26,"wins":11},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":22,"wins":13},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":23,"losses":47,"wins":22},"google/gemini-3.5-flash-lite":{"draws":67,"losses":66,"wins":97},"google/gemini-3.6-flash":{"draws":54,"losses":119,"wins":59},"google/gemini-3.8-flash":{"draws":22,"losses":43,"wins":19},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":13,"losses":19,"wins":14},"gpt-5.4":{"draws":26,"losses":60,"wins":38},"gpt-5.4-mini":{"draws":10,"losses":13,"wins":15},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":12,"losses":28,"wins":12},"gpt-5.6-luna":{"draws":32,"losses":50,"wins":50},"gpt-5.6-sol":{"draws":17,"losses":96,"wins":17},"gpt-5.6-terra":{"draws":23,"losses":33,"wins":26},"gpt-6-astra":{"draws":2,"losses":72,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":6,"losses":38,"wins":4},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":6,"wins":38},"inclusionai/ling-3.0-flash":{"draws":23,"losses":10,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":24,"losses":39,"wins":39},"meta/muse-glimmer-30b":{"draws":22,"losses":24,"wins":28},"meta/muse-spark-1.2":{"draws":14,"losses":34,"wins":10},"meta/muse-spark-1.3":{"draws":17,"losses":37,"wins":16},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":10,"losses":8,"wins":18},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":18,"losses":6,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":25,"losses":50,"wins":31},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":23},"o3":{"draws":12,"losses":87,"wins":41},"openai/gpt-oss-120b":{"draws":22,"losses":12,"wins":42},"poolside/laguna-s-2.1":{"draws":25,"losses":16,"wins":51},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":18},"qwen/qwen3.7-plus":{"draws":8,"losses":5,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":44,"wins":14},"qwen/qwen3.8-27b":{"draws":11,"losses":23,"wins":10},"qwen/qwen3.8-flash":{"draws":17,"losses":25,"wins":16},"qwen/qwen3.8-max":{"draws":25,"losses":42,"wins":21},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"stealth/ox-alpha":{"draws":66,"losses":153,"wins":67},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":15,"wins":13},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":16},"tencent/hy4-preview":{"draws":15,"losses":46,"wins":23},"thinkingmachines/inkling":{"draws":40,"losses":21,"wins":43},"thinkingmachines/inkling-small":{"draws":25,"losses":28,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":26,"losses":64,"wins":16},"x-ai/grok-4.6":{"draws":18,"losses":55,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":30,"losses":19,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":13,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":42,"losses":47,"wins":49},"z-ai/glm-5.3":{"draws":12,"losses":40,"wins":14},"z-ai/glm-5.3-flash":{"draws":15,"losses":46,"wins":21},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":18,"wins":31},"claude-fable-5":{"draws":17,"losses":46,"wins":5},"claude-fable-5-1":{"draws":2,"losses":70,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":36,"losses":42,"wins":26},"claude-opus-4-8":{"draws":13,"losses":29,"wins":6},"claude-opus-5":{"draws":12,"losses":65,"wins":7},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":36,"losses":29,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":31,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":36,"losses":30,"wins":46},"deepseek/deepseek-v4-pro":{"draws":21,"losses":37,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"fireworks/ember-1":{"draws":20,"losses":21,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":31,"losses":40,"wins":23},"google/gemini-3.5-flash-lite":{"draws":57,"losses":42,"wins":63},"google/gemini-3.6-flash":{"draws":37,"losses":73,"wins":44},"google/gemini-3.8-flash":{"draws":21,"losses":46,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":19,"wins":11},"gpt-5.4":{"draws":25,"losses":41,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":18,"losses":12,"wins":18},"gpt-5.5":{"draws":16,"losses":20,"wins":8},"gpt-5.6-luna":{"draws":36,"losses":27,"wins":25},"gpt-5.6-sol":{"draws":10,"losses":58,"wins":2},"gpt-5.6-terra":{"draws":20,"losses":35,"wins":19},"gpt-6-astra":{"draws":6,"losses":54,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":8,"losses":39,"wins":1},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":5,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":8,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":12,"wins":34},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":21},"meta/muse-spark-1.2":{"draws":19,"losses":33,"wins":12},"meta/muse-spark-1.3":{"draws":7,"losses":32,"wins":3},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":33,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":5,"wins":21},"o3":{"draws":18,"losses":51,"wins":29},"openai/gpt-oss-120b":{"draws":33,"losses":13,"wins":36},"poolside/laguna-s-2.1":{"draws":28,"losses":24,"wins":18},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":34,"wins":19},"qwen/qwen3.8-27b":{"draws":8,"losses":24,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":22,"wins":18},"qwen/qwen3.8-max":{"draws":38,"losses":22,"wins":24},"qwen/qwen3.8-max-0902":{"draws":19,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":75,"losses":139,"wins":60},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":28,"losses":44,"wins":10},"thinkingmachines/inkling":{"draws":27,"losses":10,"wins":45},"thinkingmachines/inkling-small":{"draws":44,"losses":17,"wins":33},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":14,"losses":46,"wins":18},"x-ai/grok-4.6":{"draws":23,"losses":38,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":33,"losses":16,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":13,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":6},"z-ai/glm-5.2":{"draws":44,"losses":45,"wins":43},"z-ai/glm-5.3":{"draws":17,"losses":45,"wins":6},"z-ai/glm-5.3-flash":{"draws":24,"losses":45,"wins":13},"z-ai/glm-5.3-flashx":{"draws":13,"losses":27,"wins":8}},"meta/muse-wonder":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":4,"losses":39,"wins":11},"claude-haiku-5-5":{"draws":16,"losses":12,"wins":18},"claude-opus-4-5":{"draws":27,"losses":17,"wins":34},"claude-opus-4-8":{"draws":12,"losses":19,"wins":13},"claude-opus-5":{"draws":11,"losses":54,"wins":17},"claude-opus-5-5":{"draws":0,"losses":43,"wins":9},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":11,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":16,"losses":18,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":15,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":16,"wins":16},"fireworks/ember-1":{"draws":18,"losses":10,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":26},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":34},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":27,"losses":30,"wins":35},"google/gemini-3.8-flash":{"draws":17,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":14},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":15,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":18,"losses":12,"wins":14},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":18,"losses":9,"wins":19},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":18,"losses":14,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":37,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":2,"wins":21},"inclusionai/ling-3.0-flash":{"draws":7,"losses":3,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":32},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":8,"wins":25},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":1,"wins":20},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":0,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":4,"wins":17},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":17,"losses":12,"wins":19},"stealth/ox-alpha":{"draws":43,"losses":60,"wins":55},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":25,"losses":7,"wins":32},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":2},"upstage/solar-mini4":{"draws":1,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":24,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":11,"losses":21,"wins":16},"z-ai/glm-5.3-flashx":{"draws":14,"losses":18,"wins":16}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":26,"wins":8},"claude-fable-5":{"draws":10,"losses":23,"wins":5},"claude-fable-5-1":{"draws":1,"losses":38,"wins":1},"claude-haiku-5-5":{"draws":2,"losses":22,"wins":10},"claude-opus-4-5":{"draws":26,"losses":58,"wins":16},"claude-opus-4-8":{"draws":8,"losses":42,"wins":14},"claude-opus-5":{"draws":16,"losses":93,"wins":9},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":8,"losses":18,"wins":12},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":10,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":22,"wins":33},"deepseek/deepseek-v4-pro":{"draws":5,"losses":21,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":10},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":15},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":21,"wins":35},"google/gemini-3.6-flash":{"draws":15,"losses":58,"wins":19},"google/gemini-3.8-flash":{"draws":4,"losses":32,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":4,"losses":16,"wins":12},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":10,"losses":24,"wins":18},"gpt-5.4":{"draws":5,"losses":18,"wins":15},"gpt-5.4-mini":{"draws":16,"losses":10,"wins":24},"gpt-5.4-nano":{"draws":19,"losses":20,"wins":35},"gpt-5.5":{"draws":15,"losses":36,"wins":15},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":12},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":20,"wins":12},"gpt-6-astra":{"draws":0,"losses":36,"wins":2},"gpt-6-luna":{"draws":9,"losses":18,"wins":9},"gpt-6-sol":{"draws":2,"losses":29,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":32,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":16,"losses":8,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":15,"wins":27},"meta/muse-glimmer-30b":{"draws":12,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":6,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":33,"wins":5},"meta/muse-wonder":{"draws":5,"losses":23,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":8},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":5,"losses":7,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":32,"wins":6},"nex-agi/nex-n2-pro":{"draws":11,"losses":8,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":12,"wins":36},"o3":{"draws":7,"losses":35,"wins":18},"openai/gpt-oss-120b":{"draws":9,"losses":14,"wins":15},"poolside/laguna-s-2.1":{"draws":14,"losses":18,"wins":28},"qwen/qwen3.7-max":{"draws":20,"losses":21,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":11,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":24,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":10,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":25,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":68,"wins":32},"stealth/space-bunny-alpha":{"draws":7,"losses":12,"wins":9},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":20},"tencent/hy4-preview":{"draws":6,"losses":25,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":20,"wins":36},"thinkingmachines/inkling-small":{"draws":8,"losses":9,"wins":21},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":34,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":13},"xiaomi/mimo-v2.5":{"draws":30,"losses":25,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":25,"losses":28,"wins":37},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":10},"claude-fable-5":{"draws":10,"losses":24,"wins":8},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":7},"claude-opus-4-5":{"draws":24,"losses":31,"wins":13},"claude-opus-4-8":{"draws":11,"losses":17,"wins":10},"claude-opus-5":{"draws":11,"losses":62,"wins":7},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":14,"losses":20,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":17,"wins":7},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":9},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":19,"losses":20,"wins":13},"google/gemini-3.5-flash-lite":{"draws":35,"losses":15,"wins":22},"google/gemini-3.6-flash":{"draws":27,"losses":42,"wins":11},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":7},"gpt-4.1":{"draws":6,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":10,"wins":9},"gpt-5.4":{"draws":15,"losses":22,"wins":3},"gpt-5.4-mini":{"draws":17,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":17},"gpt-5.5":{"draws":19,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":15},"gpt-5.6-sol":{"draws":10,"losses":27,"wins":5},"gpt-5.6-terra":{"draws":21,"losses":10,"wins":9},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":13,"losses":17,"wins":12},"gpt-6-sol":{"draws":6,"losses":31,"wins":5},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":5,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":13},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":5},"meta/muse-wonder":{"draws":7,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":6},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":11},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":11},"o3":{"draws":18,"losses":21,"wins":15},"openai/gpt-oss-120b":{"draws":17,"losses":11,"wins":10},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":13},"qwen/qwen3.7-max":{"draws":13,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":9,"losses":1,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":22,"wins":6},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":5},"stealth/ox-alpha":{"draws":48,"losses":67,"wins":27},"stealth/space-bunny-alpha":{"draws":15,"losses":8,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":7},"thinkingmachines/inkling":{"draws":24,"losses":15,"wins":19},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":14},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":3},"x-ai/grok-4.5":{"draws":11,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":31,"losses":11,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":10,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":7},"z-ai/glm-5.2":{"draws":42,"losses":19,"wins":23},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":18,"wins":9}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":28,"wins":15},"claude-fable-5":{"draws":12,"losses":38,"wins":4},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":27,"wins":2},"claude-opus-4-5":{"draws":26,"losses":57,"wins":3},"claude-opus-4-8":{"draws":14,"losses":21,"wins":3},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":26,"losses":46,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":32,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":44,"losses":37,"wins":11},"deepseek/deepseek-v4-pro":{"draws":23,"losses":41,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":36,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":23,"wins":3},"fireworks/ember-1":{"draws":13,"losses":28,"wins":1},"gemini-3.1-pro-preview":{"draws":14,"losses":26,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":12},"google/gemini-3.5-flash":{"draws":21,"losses":43,"wins":10},"google/gemini-3.5-flash-lite":{"draws":46,"losses":69,"wins":27},"google/gemini-3.6-flash":{"draws":52,"losses":64,"wins":10},"google/gemini-3.8-flash":{"draws":15,"losses":40,"wins":1},"google/gemma-4-31b-it":{"draws":11,"losses":11,"wins":2},"gpt-4.1":{"draws":8,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":13,"losses":17,"wins":8},"gpt-5.4":{"draws":22,"losses":26,"wins":12},"gpt-5.4-mini":{"draws":14,"losses":11,"wins":3},"gpt-5.4-nano":{"draws":10,"losses":27,"wins":5},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":30,"losses":34,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":45,"wins":4},"gpt-5.6-terra":{"draws":22,"losses":42,"wins":6},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":15,"losses":25,"wins":2},"gpt-6-sol":{"draws":3,"losses":38,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":29,"losses":21,"wins":10},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":28,"wins":14},"meta/muse-glimmer-30b":{"draws":34,"losses":28,"wins":10},"meta/muse-spark-1.2":{"draws":14,"losses":41,"wins":5},"meta/muse-spark-1.3":{"draws":12,"losses":45,"wins":1},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":5},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":44,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":15,"wins":4},"o3":{"draws":19,"losses":54,"wins":5},"openai/gpt-oss-120b":{"draws":33,"losses":31,"wins":6},"poolside/laguna-s-2.1":{"draws":31,"losses":26,"wins":9},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":51,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":23,"wins":1},"qwen/qwen3.8-flash":{"draws":18,"losses":29,"wins":5},"qwen/qwen3.8-max":{"draws":21,"losses":45,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":25,"wins":2},"stealth/ox-alpha":{"draws":63,"losses":133,"wins":22},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":19,"losses":45,"wins":4},"thinkingmachines/inkling":{"draws":26,"losses":37,"wins":9},"thinkingmachines/inkling-small":{"draws":41,"losses":25,"wins":18},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":14,"losses":40,"wins":6},"x-ai/grok-4.6":{"draws":22,"losses":34,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":29,"losses":26,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":2},"z-ai/glm-5.2":{"draws":54,"losses":55,"wins":9},"z-ai/glm-5.3":{"draws":12,"losses":42,"wins":2},"z-ai/glm-5.3-flash":{"draws":26,"losses":31,"wins":9},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":16,"wins":41},"claude-fable-5":{"draws":9,"losses":59,"wins":22},"claude-fable-5-1":{"draws":4,"losses":92,"wins":4},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":58,"losses":37,"wins":71},"claude-opus-4-8":{"draws":18,"losses":19,"wins":23},"claude-opus-5":{"draws":18,"losses":78,"wins":28},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":42,"losses":29,"wins":67},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":14},"deepseek/deepseek-v4-flash":{"draws":28,"losses":26,"wins":54},"deepseek/deepseek-v4-pro":{"draws":16,"losses":27,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":32,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":23},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":31,"losses":40,"wins":29},"google/gemini-3.5-flash-lite":{"draws":89,"losses":55,"wins":132},"google/gemini-3.6-flash":{"draws":84,"losses":110,"wins":102},"google/gemini-3.8-flash":{"draws":16,"losses":47,"wins":21},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":5,"losses":3,"wins":14},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":12,"wins":18},"gpt-5.4":{"draws":15,"losses":76,"wins":45},"gpt-5.4-mini":{"draws":21,"losses":13,"wins":20},"gpt-5.4-nano":{"draws":18,"losses":10,"wins":46},"gpt-5.5":{"draws":15,"losses":18,"wins":27},"gpt-5.6-luna":{"draws":36,"losses":27,"wins":69},"gpt-5.6-sol":{"draws":25,"losses":81,"wins":30},"gpt-5.6-terra":{"draws":23,"losses":29,"wins":36},"gpt-6-astra":{"draws":9,"losses":71,"wins":10},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":38,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":23,"losses":7,"wins":32},"inclusionai/ling-3.0-flash":{"draws":38,"losses":7,"wins":35},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":42,"losses":27,"wins":63},"meta/muse-glimmer-30b":{"draws":19,"losses":9,"wins":42},"meta/muse-spark-1.2":{"draws":23,"losses":35,"wins":40},"meta/muse-spark-1.3":{"draws":14,"losses":39,"wins":25},"meta/muse-wonder":{"draws":8,"losses":29,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":29},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":5,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":31,"losses":23,"wins":22},"nex-agi/nex-n2-pro":{"draws":8,"losses":9,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":23},"o3":{"draws":21,"losses":71,"wins":64},"openai/gpt-oss-120b":{"draws":19,"losses":14,"wins":39},"poolside/laguna-s-2.1":{"draws":47,"losses":14,"wins":61},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":23},"qwen/qwen3.7-plus":{"draws":16,"losses":8,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":30,"wins":40},"qwen/qwen3.8-27b":{"draws":12,"losses":13,"wins":19},"qwen/qwen3.8-flash":{"draws":17,"losses":28,"wins":15},"qwen/qwen3.8-max":{"draws":18,"losses":36,"wins":39},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":12},"stealth/ox-alpha":{"draws":75,"losses":117,"wins":94},"stealth/space-bunny-alpha":{"draws":13,"losses":7,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":23,"losses":33,"wins":30},"thinkingmachines/inkling":{"draws":42,"losses":26,"wins":58},"thinkingmachines/inkling-small":{"draws":27,"losses":20,"wins":46},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":2,"wins":9},"x-ai/grok-4.5":{"draws":47,"losses":51,"wins":54},"x-ai/grok-4.6":{"draws":12,"losses":49,"wins":27},"x-ai/grok-4.7":{"draws":2,"losses":31,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":37,"losses":16,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":17,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":55,"losses":27,"wins":54},"z-ai/glm-5.3":{"draws":19,"losses":32,"wins":19},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":25,"wins":10}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":8},"claude-fable-5":{"draws":12,"losses":29,"wins":1},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":7},"claude-opus-4-5":{"draws":33,"losses":47,"wins":22},"claude-opus-4-8":{"draws":33,"losses":37,"wins":10},"claude-opus-5":{"draws":3,"losses":88,"wins":9},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":20,"losses":17,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":17},"deepseek/deepseek-v4-flash":{"draws":34,"losses":37,"wins":19},"deepseek/deepseek-v4-pro":{"draws":19,"losses":15,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":20,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":4},"fireworks/ember-1":{"draws":17,"losses":18,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":6},"google/gemini-3.1-flash-lite":{"draws":18,"losses":9,"wins":21},"google/gemini-3.5-flash":{"draws":23,"losses":20,"wins":13},"google/gemini-3.5-flash-lite":{"draws":47,"losses":21,"wins":26},"google/gemini-3.6-flash":{"draws":40,"losses":51,"wins":19},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":7},"gpt-4.1":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":27,"losses":13,"wins":10},"gpt-5.4":{"draws":16,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":32,"losses":15,"wins":11},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":24},"gpt-5.5":{"draws":31,"losses":27,"wins":8},"gpt-5.6-luna":{"draws":16,"losses":21,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":20,"losses":17,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":23,"wins":6},"gpt-6-sol":{"draws":7,"losses":32,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":43,"losses":11,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":16,"wins":19},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":11},"meta/muse-spark-1.2":{"draws":12,"losses":25,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":27,"wins":6},"meta/muse-wonder":{"draws":12,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":23,"losses":16,"wins":11},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":16,"losses":12,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":27,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":20,"wins":15},"o3":{"draws":14,"losses":35,"wins":19},"openai/gpt-oss-120b":{"draws":17,"losses":9,"wins":12},"poolside/laguna-s-2.1":{"draws":29,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":21,"losses":22,"wins":7},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":20,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":19,"losses":23,"wins":2},"qwen/qwen3.8-max-0902":{"draws":17,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":83,"wins":20},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":33,"losses":7,"wins":14},"tencent/hy4-preview":{"draws":17,"losses":22,"wins":3},"thinkingmachines/inkling":{"draws":31,"losses":23,"wins":20},"thinkingmachines/inkling-small":{"draws":20,"losses":12,"wins":10},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":19,"losses":34,"wins":5},"x-ai/grok-4.6":{"draws":17,"losses":27,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":57,"losses":33,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":62,"losses":36,"wins":18},"z-ai/glm-5.3":{"draws":12,"losses":30,"wins":2},"z-ai/glm-5.3-flash":{"draws":16,"losses":23,"wins":3},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":4}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":14},"claude-fable-5":{"draws":8,"losses":28,"wins":8},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":12},"claude-opus-4-5":{"draws":25,"losses":54,"wins":15},"claude-opus-4-8":{"draws":8,"losses":35,"wins":19},"claude-opus-5":{"draws":23,"losses":90,"wins":5},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":13,"losses":20,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":9,"losses":14,"wins":7},"deepseek/deepseek-v4-flash":{"draws":23,"losses":45,"wins":20},"deepseek/deepseek-v4-pro":{"draws":17,"losses":15,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":6},"fireworks/ember-1":{"draws":12,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"google/gemini-3.1-flash-lite":{"draws":14,"losses":23,"wins":19},"google/gemini-3.5-flash":{"draws":15,"losses":30,"wins":13},"google/gemini-3.5-flash-lite":{"draws":32,"losses":23,"wins":25},"google/gemini-3.6-flash":{"draws":21,"losses":52,"wins":17},"google/gemini-3.8-flash":{"draws":11,"losses":31,"wins":6},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":8},"gpt-4.1":{"draws":8,"losses":16,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":21,"losses":22,"wins":15},"gpt-5.4":{"draws":17,"losses":24,"wins":3},"gpt-5.4-mini":{"draws":22,"losses":14,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":31,"wins":21},"gpt-5.5":{"draws":36,"losses":29,"wins":5},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":23,"wins":7},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":4,"losses":34,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":39,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":14,"wins":9},"inclusionai/ling-3.0-flash":{"draws":25,"losses":12,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":29,"wins":13},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":33,"wins":4},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":10,"losses":23,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":6,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":25,"wins":9},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":5,"wins":15},"o3":{"draws":23,"losses":31,"wins":22},"openai/gpt-oss-120b":{"draws":14,"losses":16,"wins":12},"poolside/laguna-s-2.1":{"draws":22,"losses":16,"wins":20},"qwen/qwen3.7-max":{"draws":18,"losses":21,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":16,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":25,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":88,"wins":28},"stealth/space-bunny-alpha":{"draws":12,"losses":13,"wins":9},"stepfun/step-3.7-flash":{"draws":16,"losses":18,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":14},"tencent/hy4-preview":{"draws":12,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":25,"losses":27,"wins":24},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":13},"unbiased/pareto-26.10-preview":{"draws":1,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":6,"wins":3},"x-ai/grok-4.5":{"draws":9,"losses":36,"wins":3},"x-ai/grok-4.6":{"draws":15,"losses":25,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":33,"wins":2},"x-ai/grok-build-0.1":{"draws":16,"losses":12,"wins":4},"xiaomi/mimo-v2.5":{"draws":38,"losses":40,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":21,"wins":3},"z-ai/glm-5.2":{"draws":38,"losses":37,"wins":35},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":29,"wins":7}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":11,"wins":14},"claude-fable-5":{"draws":10,"losses":31,"wins":7},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":17,"losses":19,"wins":10},"claude-opus-4-5":{"draws":18,"losses":38,"wins":22},"claude-opus-4-8":{"draws":14,"losses":22,"wins":8},"claude-opus-5":{"draws":13,"losses":65,"wins":4},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":14,"losses":20,"wins":14},"claude-sonnet-5-5":{"draws":8,"losses":31,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":25,"losses":14,"wins":33},"deepseek/deepseek-v4-pro":{"draws":14,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":16},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":25,"wins":16},"google/gemini-3.5-flash-lite":{"draws":28,"losses":20,"wins":36},"google/gemini-3.6-flash":{"draws":25,"losses":44,"wins":23},"google/gemini-3.8-flash":{"draws":16,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":11,"wins":13},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":20,"wins":16},"gpt-5.5":{"draws":13,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":18,"losses":13,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"gpt-6-sol":{"draws":2,"losses":44,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":27,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":29,"wins":7},"meta/muse-wonder":{"draws":7,"losses":36,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":13},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":9,"wins":16},"o3":{"draws":10,"losses":22,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":26,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":23,"wins":10},"qwen/qwen3.8-max-0902":{"draws":11,"losses":26,"wins":11},"stealth/ox-alpha":{"draws":44,"losses":82,"wins":32},"stealth/space-bunny-alpha":{"draws":13,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":20,"losses":14,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":25,"losses":20,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":27,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":27,"wins":33},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":14,"losses":25,"wins":9},"z-ai/glm-5.3-flashx":{"draws":11,"losses":28,"wins":9}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":26,"wins":16},"claude-fable-5":{"draws":10,"losses":37,"wins":5},"claude-fable-5-1":{"draws":0,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":5},"claude-opus-4-5":{"draws":26,"losses":49,"wins":7},"claude-opus-4-8":{"draws":9,"losses":22,"wins":1},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":24,"losses":36,"wins":8},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":3},"deepseek/deepseek-v4-flash":{"draws":35,"losses":24,"wins":29},"deepseek/deepseek-v4-pro":{"draws":18,"losses":30,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":4},"fireworks/ember-1":{"draws":14,"losses":20,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":21,"losses":38,"wins":13},"google/gemini-3.5-flash-lite":{"draws":42,"losses":41,"wins":35},"google/gemini-3.6-flash":{"draws":40,"losses":57,"wins":13},"google/gemini-3.8-flash":{"draws":18,"losses":34,"wins":4},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":2,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":16,"wins":7},"gpt-5.4":{"draws":18,"losses":29,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":15},"gpt-5.5":{"draws":13,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":30,"losses":26,"wins":14},"gpt-5.6-sol":{"draws":4,"losses":46,"wins":0},"gpt-5.6-terra":{"draws":19,"losses":39,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"gpt-6-sol":{"draws":6,"losses":28,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":14,"wins":14},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":17,"wins":11},"meta/muse-glimmer-30b":{"draws":30,"losses":16,"wins":22},"meta/muse-spark-1.2":{"draws":13,"losses":40,"wins":1},"meta/muse-spark-1.3":{"draws":16,"losses":28,"wins":8},"meta/muse-wonder":{"draws":4,"losses":28,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":16,"losses":8,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":28,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":9},"o3":{"draws":13,"losses":49,"wins":12},"openai/gpt-oss-120b":{"draws":17,"losses":15,"wins":12},"poolside/laguna-s-2.1":{"draws":26,"losses":24,"wins":12},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":28,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":20,"wins":5},"qwen/qwen3.8-flash":{"draws":16,"losses":16,"wins":8},"qwen/qwen3.8-max":{"draws":23,"losses":27,"wins":6},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":4},"stealth/ox-alpha":{"draws":60,"losses":124,"wins":18},"stealth/space-bunny-alpha":{"draws":6,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":20,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":15,"losses":31,"wins":18},"thinkingmachines/inkling-small":{"draws":28,"losses":12,"wins":32},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":15,"losses":26,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":33,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":18,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":47,"losses":37,"wins":20},"z-ai/glm-5.3":{"draws":16,"losses":30,"wins":0},"z-ai/glm-5.3-flash":{"draws":22,"losses":27,"wins":5},"z-ai/glm-5.3-flashx":{"draws":13,"losses":21,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":22,"wins":27},"claude-fable-5":{"draws":12,"losses":49,"wins":17},"claude-fable-5-1":{"draws":2,"losses":85,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":30,"wins":23},"claude-opus-4-5":{"draws":60,"losses":82,"wins":36},"claude-opus-4-8":{"draws":27,"losses":66,"wins":19},"claude-opus-5":{"draws":16,"losses":193,"wins":17},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":24,"losses":42,"wins":20},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":15},"cohere/north-mini-code":{"draws":17,"losses":14,"wins":15},"deepseek/deepseek-v4-flash":{"draws":55,"losses":41,"wins":62},"deepseek/deepseek-v4-pro":{"draws":18,"losses":32,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":34,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":14},"fireworks/ember-1":{"draws":23,"losses":36,"wins":13},"gemini-3.1-pro-preview":{"draws":20,"losses":31,"wins":21},"google/gemini-3.1-flash-lite":{"draws":18,"losses":22,"wins":40},"google/gemini-3.5-flash":{"draws":24,"losses":54,"wins":26},"google/gemini-3.5-flash-lite":{"draws":49,"losses":55,"wins":88},"google/gemini-3.6-flash":{"draws":60,"losses":100,"wins":64},"google/gemini-3.8-flash":{"draws":15,"losses":54,"wins":15},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":17},"gpt-4.1":{"draws":11,"losses":24,"wins":13},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":33,"losses":32,"wins":47},"gpt-5.4":{"draws":29,"losses":46,"wins":11},"gpt-5.4-mini":{"draws":37,"losses":25,"wins":24},"gpt-5.4-nano":{"draws":42,"losses":45,"wins":57},"gpt-5.5":{"draws":49,"losses":47,"wins":28},"gpt-5.6-luna":{"draws":29,"losses":27,"wins":32},"gpt-5.6-sol":{"draws":13,"losses":67,"wins":8},"gpt-5.6-terra":{"draws":28,"losses":36,"wins":14},"gpt-6-astra":{"draws":5,"losses":73,"wins":0},"gpt-6-luna":{"draws":20,"losses":25,"wins":27},"gpt-6-sol":{"draws":10,"losses":54,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":67,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":14,"wins":20},"inclusionai/ling-3.0-flash":{"draws":52,"losses":18,"wins":46},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":56,"losses":34,"wins":52},"meta/muse-glimmer-30b":{"draws":27,"losses":23,"wins":26},"meta/muse-spark-1.2":{"draws":15,"losses":47,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":47,"wins":22},"meta/muse-wonder":{"draws":10,"losses":57,"wins":5},"minimax/minimax-m3":{"draws":24,"losses":26,"wins":32},"mistralai/mistral-large-4-0":{"draws":13,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":13,"losses":12,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":23},"moonshotai/kimi-k3":{"draws":31,"losses":38,"wins":29},"nex-agi/nex-n2-pro":{"draws":26,"losses":9,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":24,"wins":39},"o3":{"draws":22,"losses":63,"wins":37},"openai/gpt-oss-120b":{"draws":23,"losses":13,"wins":38},"poolside/laguna-s-2.1":{"draws":47,"losses":32,"wins":41},"qwen/qwen3.7-max":{"draws":25,"losses":28,"wins":21},"qwen/qwen3.7-plus":{"draws":21,"losses":9,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":47,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":25,"wins":16},"qwen/qwen3.8-flash":{"draws":20,"losses":21,"wins":17},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":25},"qwen/qwen3.8-max-0902":{"draws":19,"losses":35,"wins":18},"stealth/ox-alpha":{"draws":67,"losses":154,"wins":73},"stealth/space-bunny-alpha":{"draws":13,"losses":22,"wins":21},"stepfun/step-3.7-flash":{"draws":17,"losses":20,"wins":25},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":26,"wins":24},"tencent/hy4-preview":{"draws":25,"losses":43,"wins":18},"thinkingmachines/inkling":{"draws":38,"losses":45,"wins":71},"thinkingmachines/inkling-small":{"draws":30,"losses":10,"wins":40},"unbiased/pareto-26.10-preview":{"draws":0,"losses":23,"wins":1},"upstage/solar-mini4":{"draws":3,"losses":9,"wins":4},"x-ai/grok-4.5":{"draws":27,"losses":88,"wins":29},"x-ai/grok-4.6":{"draws":23,"losses":44,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":12,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":54,"losses":53,"wins":81},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":32,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":25,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":33,"wins":13},"z-ai/glm-5.2":{"draws":87,"losses":73,"wins":66},"z-ai/glm-5.3":{"draws":9,"losses":53,"wins":10},"z-ai/glm-5.3-flash":{"draws":21,"losses":42,"wins":15},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":20,"wins":11},"claude-fable-5":{"draws":8,"losses":30,"wins":6},"claude-fable-5-1":{"draws":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":19,"wins":8},"claude-opus-4-5":{"draws":33,"losses":57,"wins":20},"claude-opus-4-8":{"draws":21,"losses":33,"wins":16},"claude-opus-5":{"draws":18,"losses":102,"wins":4},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":16,"losses":23,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":9,"losses":9,"wins":8},"deepseek/deepseek-v4-flash":{"draws":36,"losses":21,"wins":35},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":7},"fireworks/ember-1":{"draws":13,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":13},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":32},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":18,"losses":26,"wins":34},"google/gemini-3.6-flash":{"draws":28,"losses":57,"wins":19},"google/gemini-3.8-flash":{"draws":16,"losses":19,"wins":13},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":8,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":24,"losses":22,"wins":12},"gpt-5.4":{"draws":11,"losses":20,"wins":11},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":25},"gpt-5.4-nano":{"draws":26,"losses":27,"wins":31},"gpt-5.5":{"draws":27,"losses":23,"wins":14},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":24,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":11,"losses":16,"wins":15},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":4,"losses":37,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":11,"wins":13},"inclusionai/ling-3.0-flash":{"draws":30,"losses":7,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":15,"wins":27},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":29,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":9},"meta/muse-wonder":{"draws":5,"losses":28,"wins":9},"minimax/minimax-m3":{"draws":22,"losses":5,"wins":23},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":31,"wins":12},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":14,"wins":25},"o3":{"draws":13,"losses":41,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":15},"poolside/laguna-s-2.1":{"draws":24,"losses":24,"wins":22},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":7},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.8-max":{"draws":22,"losses":17,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":9},"stealth/ox-alpha":{"draws":33,"losses":89,"wins":30},"stealth/space-bunny-alpha":{"draws":10,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":13,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":28,"losses":10,"wins":18},"tencent/hy4-preview":{"draws":10,"losses":25,"wins":7},"thinkingmachines/inkling":{"draws":25,"losses":15,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":15,"losses":28,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":12,"wins":5},"xiaomi/mimo-v2.5":{"draws":47,"losses":28,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":11,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":15,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":42,"losses":39,"wins":33},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":7},"z-ai/glm-5.3-flashx":{"draws":9,"losses":25,"wins":8}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":15,"wins":7},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":5,"losses":35,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":52,"losses":39,"wins":11},"claude-opus-4-8":{"draws":16,"losses":39,"wins":9},"claude-opus-5":{"draws":8,"losses":58,"wins":14},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":11,"losses":25,"wins":6},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":4,"losses":11,"wins":7},"deepseek/deepseek-v4-flash":{"draws":24,"losses":34,"wins":24},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":2},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":19,"wins":29},"google/gemini-3.5-flash":{"draws":13,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":24,"losses":37,"wins":13},"google/gemini-3.6-flash":{"draws":35,"losses":53,"wins":6},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":6},"gpt-4.1":{"draws":8,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":20,"wins":2},"gpt-5.4":{"draws":6,"losses":27,"wins":1},"gpt-5.4-mini":{"draws":16,"losses":20,"wins":12},"gpt-5.4-nano":{"draws":18,"losses":40,"wins":18},"gpt-5.5":{"draws":22,"losses":34,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":17,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":28,"wins":3},"gpt-5.6-terra":{"draws":11,"losses":23,"wins":2},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":14,"losses":20,"wins":2},"gpt-6-sol":{"draws":7,"losses":28,"wins":1},"gpt-6.1-sol":{"draws":0,"losses":36,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":21,"losses":23,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":29,"wins":7},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":32,"wins":5},"meta/muse-wonder":{"draws":4,"losses":30,"wins":2},"minimax/minimax-m3":{"draws":13,"losses":21,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":9,"losses":9,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":7},"nex-agi/nex-n2-pro":{"draws":12,"losses":17,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":24,"wins":15},"o3":{"draws":8,"losses":43,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":19,"wins":4},"poolside/laguna-s-2.1":{"draws":14,"losses":29,"wins":5},"qwen/qwen3.7-max":{"draws":16,"losses":22,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":12,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":21,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":2},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":2},"stealth/ox-alpha":{"draws":25,"losses":76,"wins":7},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"wins":3},"stepfun/step-3.7-flash":{"draws":5,"losses":17,"wins":10},"tencent/hy3-preview":{"draws":16,"losses":23,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":38,"wins":18},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":7,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":28,"wins":0},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":4},"xiaomi/mimo-v2.5":{"draws":46,"losses":60,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":30,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":2},"z-ai/glm-5.2":{"draws":36,"losses":58,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":27,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":23,"wins":31},"claude-fable-5":{"draws":21,"losses":48,"wins":15},"claude-fable-5-1":{"draws":4,"losses":88,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":34,"losses":34,"wins":36},"claude-opus-4-8":{"draws":17,"losses":21,"wins":14},"claude-opus-5":{"draws":7,"losses":67,"wins":14},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":30,"losses":18,"wins":40},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":35,"losses":18,"wins":57},"deepseek/deepseek-v4-pro":{"draws":24,"losses":23,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":28,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"wins":16},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"google/gemini-3.1-flash-lite":{"draws":10,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":28,"losses":34,"wins":36},"google/gemini-3.5-flash-lite":{"draws":54,"losses":32,"wins":64},"google/gemini-3.6-flash":{"draws":36,"losses":75,"wins":47},"google/gemini-3.8-flash":{"draws":17,"losses":45,"wins":24},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":21},"gpt-5.4":{"draws":18,"losses":28,"wins":32},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":27},"gpt-5.5":{"draws":12,"losses":20,"wins":14},"gpt-5.6-luna":{"draws":34,"losses":19,"wins":31},"gpt-5.6-sol":{"draws":16,"losses":54,"wins":12},"gpt-5.6-terra":{"draws":24,"losses":19,"wins":39},"gpt-6-astra":{"draws":7,"losses":70,"wins":1},"gpt-6-luna":{"draws":10,"losses":22,"wins":16},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":24,"losses":6,"wins":28},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":18,"losses":11,"wins":43},"meta/muse-glimmer-30b":{"draws":27,"losses":19,"wins":26},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":37},"meta/muse-spark-1.3":{"draws":20,"losses":27,"wins":27},"meta/muse-wonder":{"draws":10,"losses":24,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":17,"losses":27,"wins":32},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":24},"o3":{"draws":16,"losses":27,"wins":51},"openai/gpt-oss-120b":{"draws":27,"losses":8,"wins":35},"poolside/laguna-s-2.1":{"draws":25,"losses":11,"wins":32},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":22,"wins":13},"qwen/qwen3.8-27b":{"draws":14,"losses":14,"wins":14},"qwen/qwen3.8-flash":{"draws":12,"losses":22,"wins":26},"qwen/qwen3.8-max":{"draws":22,"losses":42,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"stealth/ox-alpha":{"draws":64,"losses":116,"wins":94},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":25,"losses":37,"wins":18},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":42},"thinkingmachines/inkling-small":{"draws":25,"losses":11,"wins":56},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":18,"losses":31,"wins":25},"x-ai/grok-4.6":{"draws":20,"losses":37,"wins":25},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":43,"losses":38,"wins":55},"z-ai/glm-5.3":{"draws":14,"losses":43,"wins":9},"z-ai/glm-5.3-flash":{"draws":22,"losses":31,"wins":27},"z-ai/glm-5.3-flashx":{"draws":12,"losses":25,"wins":11}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":8},"claude-fable-5":{"draws":5,"losses":17,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":15,"wins":2},"claude-opus-4-5":{"draws":17,"losses":19,"wins":2},"claude-opus-4-8":{"draws":5,"losses":12,"wins":3},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":6,"losses":13,"wins":5},"claude-sonnet-5-5":{"draws":8,"losses":14,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":2},"fireworks/ember-1":{"draws":12,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":20,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":18,"wins":12},"google/gemini-3.6-flash":{"draws":14,"losses":26,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":17,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":3,"wins":3},"gpt-4.1":{"draws":3,"losses":4,"wins":1},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":8,"wins":5},"gpt-5.4":{"draws":7,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":4},"gpt-5.5":{"draws":8,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":9,"losses":11,"wins":4},"gpt-6-sol":{"draws":7,"losses":16,"wins":1},"gpt-6.1-sol":{"draws":3,"losses":21,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":1,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":8},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":15,"wins":1},"meta/muse-wonder":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":3,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":3},"o3":{"draws":4,"losses":19,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":6,"wins":7},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":18,"losses":54,"wins":16},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":15,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":4},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":5},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":8,"losses":15,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":2},"xiaomi/mimo-v2.5":{"draws":15,"losses":14,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":20,"losses":22,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":2}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":28,"wins":25},"claude-fable-5":{"draws":17,"losses":53,"wins":2},"claude-fable-5-1":{"draws":7,"losses":67,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":31,"wins":2},"claude-opus-4-5":{"draws":40,"losses":53,"wins":11},"claude-opus-4-8":{"draws":13,"losses":30,"wins":3},"claude-opus-5":{"draws":14,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":34,"losses":42,"wins":12},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":37,"losses":38,"wins":35},"deepseek/deepseek-v4-pro":{"draws":28,"losses":37,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":34,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":4},"fireworks/ember-1":{"draws":17,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":17,"losses":19,"wins":12},"google/gemini-3.1-flash-lite":{"draws":14,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":28,"losses":56,"wins":12},"google/gemini-3.5-flash-lite":{"draws":60,"losses":41,"wins":55},"google/gemini-3.6-flash":{"draws":67,"losses":75,"wins":12},"google/gemini-3.8-flash":{"draws":17,"losses":60,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":24,"wins":9},"gpt-5.4":{"draws":22,"losses":35,"wins":15},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":14,"losses":21,"wins":19},"gpt-5.5":{"draws":21,"losses":22,"wins":5},"gpt-5.6-luna":{"draws":32,"losses":39,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":53,"wins":11},"gpt-5.6-terra":{"draws":19,"losses":37,"wins":16},"gpt-6-astra":{"draws":9,"losses":59,"wins":0},"gpt-6-luna":{"draws":14,"losses":25,"wins":9},"gpt-6-sol":{"draws":2,"losses":41,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":32,"losses":12,"wins":24},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":20,"wins":25},"meta/muse-glimmer-30b":{"draws":42,"losses":23,"wins":17},"meta/muse-spark-1.2":{"draws":21,"losses":35,"wins":12},"meta/muse-spark-1.3":{"draws":17,"losses":47,"wins":10},"meta/muse-wonder":{"draws":11,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":16,"wins":4},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":1},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":29,"losses":40,"wins":7},"nex-agi/nex-n2-pro":{"draws":18,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":14},"o3":{"draws":25,"losses":49,"wins":20},"openai/gpt-oss-120b":{"draws":28,"losses":28,"wins":24},"poolside/laguna-s-2.1":{"draws":29,"losses":24,"wins":17},"qwen/qwen3.7-max":{"draws":16,"losses":22,"wins":4},"qwen/qwen3.7-plus":{"draws":9,"losses":16,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":47,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":21,"wins":13},"qwen/qwen3.8-flash":{"draws":16,"losses":10,"wins":0},"qwen/qwen3.8-max":{"draws":34,"losses":32,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":24,"wins":8},"stealth/ox-alpha":{"draws":75,"losses":141,"wins":48},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":11,"wins":6},"tencent/hy4-preview":{"draws":19,"losses":49,"wins":10},"thinkingmachines/inkling":{"draws":29,"losses":22,"wins":31},"thinkingmachines/inkling-small":{"draws":42,"losses":23,"wins":29},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":13},"x-ai/grok-4.6":{"draws":30,"losses":40,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":12,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":31,"losses":26,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":22,"wins":4},"z-ai/glm-5.2":{"draws":53,"losses":56,"wins":23},"z-ai/glm-5.3":{"draws":19,"losses":42,"wins":5},"z-ai/glm-5.3-flash":{"draws":34,"losses":34,"wins":8},"z-ai/glm-5.3-flashx":{"draws":19,"losses":26,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":27,"wins":21},"claude-fable-5":{"draws":17,"losses":27,"wins":30},"claude-fable-5-1":{"draws":2,"losses":66,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":35,"losses":38,"wins":31},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":15,"losses":61,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":36,"losses":32,"wins":23},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":53,"losses":17,"wins":38},"deepseek/deepseek-v4-pro":{"draws":25,"losses":23,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":24,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":15,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":20},"google/gemini-3.5-flash":{"draws":35,"losses":21,"wins":30},"google/gemini-3.5-flash-lite":{"draws":62,"losses":42,"wins":45},"google/gemini-3.6-flash":{"draws":48,"losses":54,"wins":50},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":33},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":10},"gpt-4.1":{"draws":6,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":7,"wins":21},"gpt-5.4":{"draws":28,"losses":24,"wins":30},"gpt-5.4-mini":{"draws":18,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":38,"losses":20,"wins":33},"gpt-5.6-sol":{"draws":16,"losses":44,"wins":19},"gpt-5.6-terra":{"draws":34,"losses":20,"wins":30},"gpt-6-astra":{"draws":2,"losses":62,"wins":2},"gpt-6-luna":{"draws":13,"losses":19,"wins":16},"gpt-6-sol":{"draws":5,"losses":29,"wins":14},"gpt-6.1-sol":{"draws":2,"losses":44,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":10,"wins":20},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":25},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":37,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":26,"losses":16,"wins":34},"meta/muse-spark-1.2":{"draws":19,"losses":24,"wins":27},"meta/muse-spark-1.3":{"draws":17,"losses":27,"wins":20},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":17,"losses":10,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":18,"losses":27,"wins":25},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":17},"o3":{"draws":23,"losses":33,"wins":40},"openai/gpt-oss-120b":{"draws":34,"losses":7,"wins":31},"poolside/laguna-s-2.1":{"draws":29,"losses":19,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":32,"wins":22},"qwen/qwen3.8-27b":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-flash":{"draws":18,"losses":15,"wins":17},"qwen/qwen3.8-max":{"draws":28,"losses":40,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"stealth/ox-alpha":{"draws":83,"losses":104,"wins":77},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":12,"losses":7,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":12,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":35,"wins":22},"thinkingmachines/inkling":{"draws":28,"losses":16,"wins":32},"thinkingmachines/inkling-small":{"draws":53,"losses":36,"wins":41},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":3,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":26,"losses":31,"wins":25},"x-ai/grok-4.6":{"draws":24,"losses":39,"wins":19},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":26,"losses":19,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":12,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":51,"losses":30,"wins":51},"z-ai/glm-5.3":{"draws":17,"losses":34,"wins":17},"z-ai/glm-5.3-flash":{"draws":19,"losses":32,"wins":25},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":5,"wins":19},"claude-fable-5":{"draws":12,"losses":29,"wins":7},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":29,"losses":26,"wins":23},"claude-opus-4-8":{"draws":17,"losses":13,"wins":14},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":2,"losses":48,"wins":2},"claude-sonnet-5":{"draws":17,"losses":14,"wins":17},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":26,"losses":10,"wins":36},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":18,"losses":13,"wins":17},"gemini-3.1-pro-preview":{"draws":15,"losses":14,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":23,"losses":13,"wins":24},"google/gemini-3.5-flash-lite":{"draws":34,"losses":10,"wins":40},"google/gemini-3.6-flash":{"draws":37,"losses":30,"wins":25},"google/gemini-3.8-flash":{"draws":16,"losses":22,"wins":10},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":8,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":11,"wins":16},"gpt-5.4":{"draws":13,"losses":21,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":22,"losses":12,"wins":10},"gpt-5.6-luna":{"draws":22,"losses":12,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":17,"losses":17,"wins":12},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":19,"losses":15,"wins":14},"gpt-6-sol":{"draws":6,"losses":36,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":42,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":11},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":8,"wins":29},"meta/muse-glimmer-30b":{"draws":18,"losses":3,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":20,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":12},"meta/muse-wonder":{"draws":13,"losses":29,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":2,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":9,"wins":21},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":2,"wins":16},"o3":{"draws":16,"losses":22,"wins":28},"openai/gpt-oss-120b":{"draws":18,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-27b":{"draws":12,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":10},"stealth/ox-alpha":{"draws":44,"losses":61,"wins":53},"stealth/space-bunny-alpha":{"draws":13,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":10,"losses":6,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":21,"losses":2,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":31,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":33,"losses":9,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":17,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":44,"losses":16,"wins":36},"z-ai/glm-5.3":{"draws":16,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":101,"losses":62,"wins":119},"claude-fable-5":{"draws":69,"losses":171,"wins":42},"claude-fable-5-1":{"draws":15,"losses":292,"wins":3},"claude-haiku-5-5":{"draws":48,"losses":71,"wins":33},"claude-opus-4-5":{"draws":142,"losses":124,"wins":98},"claude-opus-4-8":{"draws":42,"losses":74,"wins":36},"claude-opus-5":{"draws":43,"losses":243,"wins":26},"claude-opus-5-5":{"draws":17,"losses":158,"wins":1},"claude-sonnet-5":{"draws":104,"losses":100,"wins":98},"claude-sonnet-5-5":{"draws":37,"losses":90,"wins":41},"cohere/north-mini-code":{"draws":21,"losses":10,"wins":33},"deepseek/deepseek-v4-flash":{"draws":167,"losses":91,"wins":120},"deepseek/deepseek-v4-pro":{"draws":121,"losses":92,"wins":77},"deepseek/deepseek-v4-pro-0813":{"draws":106,"losses":113,"wins":65},"deepseek/deepseek-v4.1-flash":{"draws":52,"losses":77,"wins":39},"fireworks/ember-1":{"draws":62,"losses":75,"wins":31},"gemini-3.1-pro-preview":{"draws":55,"losses":59,"wins":54},"google/gemini-3.1-flash-lite":{"draws":28,"losses":9,"wins":61},"google/gemini-3.5-flash":{"draws":99,"losses":152,"wins":79},"google/gemini-3.5-flash-lite":{"draws":196,"losses":149,"wins":195},"google/gemini-3.6-flash":{"draws":151,"losses":248,"wins":145},"google/gemini-3.8-flash":{"draws":90,"losses":152,"wins":48},"google/gemma-4-31b-it":{"draws":35,"losses":15,"wins":40},"gpt-4.1":{"draws":27,"losses":18,"wins":15},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":61,"losses":53,"wins":44},"gpt-5.4":{"draws":124,"losses":124,"wins":42},"gpt-5.4-mini":{"draws":49,"losses":34,"wins":33},"gpt-5.4-nano":{"draws":48,"losses":47,"wins":65},"gpt-5.5":{"draws":65,"losses":61,"wins":36},"gpt-5.6-luna":{"draws":141,"losses":89,"wins":88},"gpt-5.6-sol":{"draws":56,"losses":178,"wins":42},"gpt-5.6-terra":{"draws":126,"losses":86,"wins":68},"gpt-6-astra":{"draws":23,"losses":240,"wins":1},"gpt-6-luna":{"draws":54,"losses":69,"wins":45},"gpt-6-sol":{"draws":20,"losses":133,"wins":15},"gpt-6.1-sol":{"draws":11,"losses":151,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":91,"losses":20,"wins":89},"inclusionai/ling-3.0-flash":{"draws":73,"losses":20,"wins":57},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":94,"losses":38,"wins":114},"meta/muse-glimmer-30b":{"draws":124,"losses":52,"wins":108},"meta/muse-spark-1.2":{"draws":82,"losses":86,"wins":74},"meta/muse-spark-1.3":{"draws":67,"losses":133,"wins":50},"meta/muse-wonder":{"draws":44,"losses":101,"wins":23},"minimax/minimax-m3":{"draws":33,"losses":18,"wins":43},"mistralai/mistral-large-4-0":{"draws":50,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":81,"losses":27,"wins":82},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":13,"wins":12},"moonshotai/kimi-k3":{"draws":84,"losses":87,"wins":75},"nex-agi/nex-n2-pro":{"draws":35,"losses":12,"wins":45},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":53,"losses":24,"wins":55},"o3":{"draws":75,"losses":141,"wins":92},"openai/gpt-oss-120b":{"draws":126,"losses":48,"wins":102},"poolside/laguna-s-2.1":{"draws":114,"losses":55,"wins":83},"qwen/qwen3.7-max":{"draws":40,"losses":27,"wins":33},"qwen/qwen3.7-plus":{"draws":26,"losses":13,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":102,"losses":109,"wins":73},"qwen/qwen3.8-27b":{"draws":47,"losses":60,"wins":41},"qwen/qwen3.8-flash":{"draws":87,"losses":67,"wins":36},"qwen/qwen3.8-max":{"draws":100,"losses":128,"wins":68},"qwen/qwen3.8-max-0902":{"draws":57,"losses":71,"wins":40},"stealth/ox-alpha":{"draws":291,"losses":542,"wins":313},"stealth/space-bunny-alpha":{"draws":55,"losses":37,"wins":38},"stepfun/step-3.7-flash":{"draws":41,"losses":23,"wins":60},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":36,"losses":23,"wins":29},"tencent/hy4-preview":{"draws":101,"losses":130,"wins":55},"thinkingmachines/inkling":{"draws":117,"losses":61,"wins":122},"thinkingmachines/inkling-small":{"draws":147,"losses":50,"wins":123},"unbiased/pareto-26.10-preview":{"draws":0,"losses":56,"wins":0},"upstage/solar-mini4":{"draws":7,"losses":6,"wins":23},"x-ai/grok-4.5":{"draws":83,"losses":106,"wins":69},"x-ai/grok-4.6":{"draws":123,"losses":117,"wins":54},"x-ai/grok-4.7":{"draws":19,"losses":106,"wins":15},"x-ai/grok-build-0.1":{"draws":24,"losses":13,"wins":25},"xiaomi/mimo-v2.5":{"draws":93,"losses":50,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":36,"losses":30,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":52,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":64,"wins":22},"z-ai/glm-5.2":{"draws":207,"losses":126,"wins":159},"z-ai/glm-5.3":{"draws":60,"losses":146,"wins":32},"z-ai/glm-5.3-flash":{"draws":87,"losses":140,"wins":67},"z-ai/glm-5.3-flashx":{"draws":43,"losses":94,"wins":31}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":13,"losses":19,"wins":4},"claude-fable-5-1":{"draws":2,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":4},"claude-opus-4-5":{"draws":19,"losses":29,"wins":10},"claude-opus-4-8":{"draws":11,"losses":15,"wins":6},"claude-opus-5":{"draws":10,"losses":55,"wins":3},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":17,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":20,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":12,"wins":14},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":7},"fireworks/ember-1":{"draws":14,"losses":18,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":8},"google/gemini-3.5-flash-lite":{"draws":26,"losses":16,"wins":20},"google/gemini-3.6-flash":{"draws":21,"losses":41,"wins":6},"google/gemini-3.8-flash":{"draws":11,"losses":19,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":5,"losses":3,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":12,"wins":7},"gpt-5.4":{"draws":17,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":9},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":12},"gpt-5.5":{"draws":20,"losses":13,"wins":1},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":12,"wins":9},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":14,"losses":16,"wins":6},"gpt-6-sol":{"draws":6,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":3,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":2},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":15},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":2},"meta/muse-wonder":{"draws":9,"losses":23,"wins":4},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":6},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":12,"losses":1,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":1,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":0,"wins":12},"o3":{"draws":14,"losses":23,"wins":7},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":11},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":2},"stealth/ox-alpha":{"draws":46,"losses":67,"wins":13},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":6},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":18,"losses":10,"wins":8},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":14,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":22,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":19,"wins":3},"z-ai/glm-5.3-flashx":{"draws":14,"losses":16,"wins":6}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":11},"claude-fable-5":{"draws":11,"losses":24,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":4},"claude-opus-4-5":{"draws":18,"losses":25,"wins":15},"claude-opus-4-8":{"draws":11,"losses":18,"wins":3},"claude-opus-5":{"draws":11,"losses":43,"wins":4},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":14,"losses":9,"wins":13},"claude-sonnet-5-5":{"draws":8,"losses":18,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":12,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"fireworks/ember-1":{"draws":14,"losses":15,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":12,"losses":25,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":23,"losses":37,"wins":10},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":8},"gpt-4.1":{"draws":6,"losses":5,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":11,"wins":9},"gpt-5.4":{"draws":12,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":5,"wins":7},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":9},"gpt-5.5":{"draws":14,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":13,"wins":9},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":8},"gpt-6-astra":{"draws":6,"losses":30,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":7},"gpt-6-sol":{"draws":9,"losses":24,"wins":3},"gpt-6.1-sol":{"draws":3,"losses":33,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":14,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":18},"meta/muse-glimmer-30b":{"draws":13,"losses":11,"wins":6},"meta/muse-spark-1.2":{"draws":14,"losses":10,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":4},"meta/muse-wonder":{"draws":10,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"mistralai/mistral-large-4-0":{"draws":10,"losses":8,"wins":4},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":15,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":13},"o3":{"draws":11,"losses":20,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":2,"wins":11},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":9},"stealth/ox-alpha":{"draws":32,"losses":68,"wins":24},"stealth/space-bunny-alpha":{"draws":13,"losses":9,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":4,"wins":7},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":19,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":21,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":12,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":3},"z-ai/glm-5.2":{"draws":27,"losses":26,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":23,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":18,"wins":10},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":3}},"stepfun/step-5-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":1},"claude-opus-4-5":{"draws":3,"losses":7,"wins":0},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":0},"claude-sonnet-5-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":2},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":2},"fireworks/ember-1":{"draws":3,"losses":3,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":10,"losses":0,"wins":0},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.8-flash":{"draws":3,"losses":3,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":5,"losses":1,"wins":0},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":4,"wins":1},"gpt-5.5":{"draws":6,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":0},"meta/muse-wonder":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"o3":{"draws":8,"losses":2,"wins":0},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":3,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":3,"losses":3,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":2,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":0,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":9},"claude-fable-5":{"draws":9,"losses":23,"wins":6},"claude-fable-5-1":{"draws":5,"losses":32,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":13,"wins":7},"claude-opus-4-5":{"draws":32,"losses":33,"wins":15},"claude-opus-4-8":{"draws":26,"losses":27,"wins":11},"claude-opus-5":{"draws":28,"losses":71,"wins":15},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":20,"losses":13,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":12,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":15,"wins":4},"fireworks/ember-1":{"draws":15,"losses":15,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":7},"google/gemini-3.1-flash-lite":{"draws":16,"losses":7,"wins":11},"google/gemini-3.5-flash":{"draws":16,"losses":20,"wins":12},"google/gemini-3.5-flash-lite":{"draws":42,"losses":9,"wins":27},"google/gemini-3.6-flash":{"draws":36,"losses":33,"wins":21},"google/gemini-3.8-flash":{"draws":22,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":4},"gpt-4.1":{"draws":14,"losses":6,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":22,"losses":12,"wins":12},"gpt-5.4":{"draws":19,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":23,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":24,"losses":11,"wins":29},"gpt-5.5":{"draws":30,"losses":22,"wins":10},"gpt-5.6-luna":{"draws":16,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":13,"wins":4},"gpt-6-astra":{"draws":7,"losses":29,"wins":0},"gpt-6-luna":{"draws":13,"losses":15,"wins":8},"gpt-6-sol":{"draws":10,"losses":24,"wins":2},"gpt-6.1-sol":{"draws":3,"losses":32,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":7,"wins":6},"inclusionai/ling-3.0-flash":{"draws":25,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":31,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":18,"losses":6,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":23,"wins":4},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":6},"meta/muse-wonder":{"draws":9,"losses":21,"wins":6},"minimax/minimax-m3":{"draws":22,"losses":12,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":21,"wins":9},"nex-agi/nex-n2-pro":{"draws":21,"losses":10,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":10,"wins":10},"o3":{"draws":17,"losses":22,"wins":13},"openai/gpt-oss-120b":{"draws":18,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":22,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":23,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":20,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":15,"wins":6},"qwen/qwen3.8-flash":{"draws":15,"losses":11,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":14,"losses":17,"wins":5},"stealth/ox-alpha":{"draws":43,"losses":65,"wins":26},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":13,"losses":4,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":15,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":23,"losses":26,"wins":21},"thinkingmachines/inkling-small":{"draws":19,"losses":5,"wins":12},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":18,"losses":24,"wins":8},"x-ai/grok-4.6":{"draws":22,"losses":21,"wins":3},"x-ai/grok-4.7":{"draws":9,"losses":23,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":52,"losses":24,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":6,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":9,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":51,"losses":32,"wins":23},"z-ai/glm-5.3":{"draws":7,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":19,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":15,"wins":40},"claude-fable-5":{"draws":15,"losses":54,"wins":3},"claude-fable-5-1":{"draws":5,"losses":72,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":39,"losses":45,"wins":22},"claude-opus-4-8":{"draws":12,"losses":21,"wins":17},"claude-opus-5":{"draws":13,"losses":64,"wins":9},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":31,"losses":33,"wins":28},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":37,"losses":30,"wins":41},"deepseek/deepseek-v4-pro":{"draws":31,"losses":29,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":27,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":15},"fireworks/ember-1":{"draws":20,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":25},"google/gemini-3.5-flash":{"draws":28,"losses":39,"wins":31},"google/gemini-3.5-flash-lite":{"draws":58,"losses":39,"wins":59},"google/gemini-3.6-flash":{"draws":51,"losses":61,"wins":42},"google/gemini-3.8-flash":{"draws":21,"losses":39,"wins":18},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":16,"losses":15,"wins":15},"gpt-5.4":{"draws":29,"losses":37,"wins":12},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":23},"gpt-5.5":{"draws":22,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":35,"losses":18,"wins":35},"gpt-5.6-sol":{"draws":13,"losses":60,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":32,"wins":23},"gpt-6-astra":{"draws":4,"losses":70,"wins":0},"gpt-6-luna":{"draws":18,"losses":17,"wins":13},"gpt-6-sol":{"draws":9,"losses":36,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":45,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":30},"inclusionai/ling-3.0-flash":{"draws":15,"losses":7,"wins":28},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":27,"losses":9,"wins":36},"meta/muse-glimmer-30b":{"draws":38,"losses":12,"wins":30},"meta/muse-spark-1.2":{"draws":18,"losses":34,"wins":20},"meta/muse-spark-1.3":{"draws":20,"losses":34,"wins":18},"meta/muse-wonder":{"draws":12,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":4,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":26,"losses":6,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":32,"losses":26,"wins":18},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":7,"wins":16},"o3":{"draws":19,"losses":50,"wins":31},"openai/gpt-oss-120b":{"draws":30,"losses":17,"wins":29},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":30},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":30,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":16,"wins":13},"qwen/qwen3.8-flash":{"draws":20,"losses":18,"wins":20},"qwen/qwen3.8-max":{"draws":29,"losses":25,"wins":30},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"stealth/ox-alpha":{"draws":67,"losses":126,"wins":79},"stealth/space-bunny-alpha":{"draws":14,"losses":14,"wins":10},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":16},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":25,"wins":9},"thinkingmachines/inkling":{"draws":28,"losses":20,"wins":38},"thinkingmachines/inkling-small":{"draws":39,"losses":15,"wins":38},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":24,"losses":37,"wins":11},"x-ai/grok-4.6":{"draws":26,"losses":34,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":10,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":43,"losses":35,"wins":48},"z-ai/glm-5.3":{"draws":17,"losses":43,"wins":10},"z-ai/glm-5.3-flash":{"draws":25,"losses":35,"wins":20},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":25,"wins":20},"claude-fable-5":{"draws":17,"losses":49,"wins":6},"claude-fable-5-1":{"draws":5,"losses":77,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":43,"wins":12},"claude-opus-4-5":{"draws":74,"losses":84,"wins":38},"claude-opus-4-8":{"draws":28,"losses":61,"wins":19},"claude-opus-5":{"draws":27,"losses":155,"wins":26},"claude-opus-5-5":{"draws":6,"losses":70,"wins":0},"claude-sonnet-5":{"draws":24,"losses":38,"wins":14},"claude-sonnet-5-5":{"draws":15,"losses":42,"wins":15},"cohere/north-mini-code":{"draws":9,"losses":15,"wins":12},"deepseek/deepseek-v4-flash":{"draws":50,"losses":44,"wins":50},"deepseek/deepseek-v4-pro":{"draws":19,"losses":38,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":27,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":31,"wins":15},"fireworks/ember-1":{"draws":24,"losses":35,"wins":13},"gemini-3.1-pro-preview":{"draws":21,"losses":30,"wins":21},"google/gemini-3.1-flash-lite":{"draws":29,"losses":28,"wins":37},"google/gemini-3.5-flash":{"draws":22,"losses":56,"wins":20},"google/gemini-3.5-flash-lite":{"draws":50,"losses":76,"wins":54},"google/gemini-3.6-flash":{"draws":70,"losses":103,"wins":33},"google/gemini-3.8-flash":{"draws":12,"losses":50,"wins":10},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":10},"gpt-4.1":{"draws":12,"losses":16,"wins":22},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":34,"losses":47,"wins":19},"gpt-5.4":{"draws":23,"losses":40,"wins":13},"gpt-5.4-mini":{"draws":40,"losses":27,"wins":25},"gpt-5.4-nano":{"draws":18,"losses":48,"wins":40},"gpt-5.5":{"draws":32,"losses":62,"wins":26},"gpt-5.6-luna":{"draws":25,"losses":32,"wins":17},"gpt-5.6-sol":{"draws":13,"losses":54,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":32,"wins":16},"gpt-6-astra":{"draws":3,"losses":70,"wins":1},"gpt-6-luna":{"draws":23,"losses":31,"wins":18},"gpt-6-sol":{"draws":13,"losses":56,"wins":3},"gpt-6.1-sol":{"draws":4,"losses":65,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":19,"losses":14,"wins":15},"inclusionai/ling-3.0-flash":{"draws":40,"losses":33,"wins":49},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":36,"losses":42,"wins":52},"meta/muse-glimmer-30b":{"draws":27,"losses":20,"wins":23},"meta/muse-spark-1.2":{"draws":22,"losses":32,"wins":22},"meta/muse-spark-1.3":{"draws":15,"losses":51,"wins":10},"meta/muse-wonder":{"draws":12,"losses":47,"wins":13},"minimax/minimax-m3":{"draws":19,"losses":29,"wins":28},"mistralai/mistral-large-4-0":{"draws":16,"losses":20,"wins":10},"mistralai/mistral-medium-3-5":{"draws":16,"losses":11,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":16,"wins":14},"moonshotai/kimi-k3":{"draws":27,"losses":43,"wins":20},"nex-agi/nex-n2-pro":{"draws":19,"losses":12,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":37,"wins":40},"o3":{"draws":16,"losses":74,"wins":28},"openai/gpt-oss-120b":{"draws":16,"losses":23,"wins":23},"poolside/laguna-s-2.1":{"draws":38,"losses":53,"wins":43},"qwen/qwen3.7-max":{"draws":34,"losses":36,"wins":12},"qwen/qwen3.7-plus":{"draws":21,"losses":26,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":36,"wins":18},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":14},"qwen/qwen3.8-flash":{"draws":14,"losses":26,"wins":10},"qwen/qwen3.8-max":{"draws":29,"losses":31,"wins":16},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"stealth/ox-alpha":{"draws":60,"losses":152,"wins":54},"stealth/space-bunny-alpha":{"draws":19,"losses":23,"wins":16},"stepfun/step-3.7-flash":{"draws":13,"losses":39,"wins":12},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":26,"losses":23,"wins":23},"tencent/hy4-preview":{"draws":28,"losses":38,"wins":10},"thinkingmachines/inkling":{"draws":44,"losses":29,"wins":35},"thinkingmachines/inkling-small":{"draws":26,"losses":21,"wins":25},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":0},"upstage/solar-mini4":{"draws":6,"losses":7,"wins":5},"x-ai/grok-4.5":{"draws":37,"losses":64,"wins":23},"x-ai/grok-4.6":{"draws":27,"losses":34,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":50,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":17,"wins":12},"xiaomi/mimo-v2.5":{"draws":74,"losses":91,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":38,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":29,"wins":5},"z-ai/glm-5.2":{"draws":70,"losses":82,"wins":50},"z-ai/glm-5.3":{"draws":15,"losses":46,"wins":11},"z-ai/glm-5.3-flash":{"draws":20,"losses":41,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":44,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":36,"wins":13},"claude-fable-5":{"draws":15,"losses":44,"wins":9},"claude-fable-5-1":{"draws":4,"losses":65,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":5},"claude-opus-4-5":{"draws":34,"losses":60,"wins":8},"claude-opus-4-8":{"draws":13,"losses":29,"wins":2},"claude-opus-5":{"draws":12,"losses":66,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":31,"losses":47,"wins":14},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":57,"losses":42,"wins":13},"deepseek/deepseek-v4-pro":{"draws":39,"losses":34,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":26,"wins":8},"fireworks/ember-1":{"draws":16,"losses":28,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":26,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.5-flash":{"draws":32,"losses":45,"wins":9},"google/gemini-3.5-flash-lite":{"draws":58,"losses":62,"wins":42},"google/gemini-3.6-flash":{"draws":47,"losses":71,"wins":27},"google/gemini-3.8-flash":{"draws":27,"losses":38,"wins":7},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":21,"losses":17,"wins":4},"gpt-5.4":{"draws":37,"losses":25,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":18,"losses":18,"wins":12},"gpt-5.5":{"draws":16,"losses":25,"wins":3},"gpt-5.6-luna":{"draws":44,"losses":35,"wins":15},"gpt-5.6-sol":{"draws":15,"losses":54,"wins":3},"gpt-5.6-terra":{"draws":32,"losses":46,"wins":4},"gpt-6-astra":{"draws":2,"losses":56,"wins":0},"gpt-6-luna":{"draws":13,"losses":25,"wins":10},"gpt-6-sol":{"draws":4,"losses":44,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":45,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":33,"losses":16,"wins":17},"inclusionai/ling-3.0-flash":{"draws":22,"losses":12,"wins":12},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":33,"wins":16},"meta/muse-glimmer-30b":{"draws":42,"losses":28,"wins":12},"meta/muse-spark-1.2":{"draws":22,"losses":34,"wins":10},"meta/muse-spark-1.3":{"draws":25,"losses":40,"wins":5},"meta/muse-wonder":{"draws":12,"losses":34,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":12,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":32,"losses":12,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":27,"losses":36,"wins":9},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":14,"wins":8},"o3":{"draws":25,"losses":53,"wins":19},"openai/gpt-oss-120b":{"draws":37,"losses":29,"wins":16},"poolside/laguna-s-2.1":{"draws":39,"losses":26,"wins":5},"qwen/qwen3.7-max":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":48,"wins":6},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.8-flash":{"draws":26,"losses":24,"wins":6},"qwen/qwen3.8-max":{"draws":47,"losses":46,"wins":34},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"stealth/ox-alpha":{"draws":87,"losses":135,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":13,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":13,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":26,"losses":43,"wins":9},"thinkingmachines/inkling":{"draws":37,"losses":35,"wins":10},"thinkingmachines/inkling-small":{"draws":41,"losses":36,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":7,"wins":3},"x-ai/grok-4.5":{"draws":24,"losses":40,"wins":5},"x-ai/grok-4.6":{"draws":24,"losses":42,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":32,"losses":26,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":19,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":54,"losses":59,"wins":21},"z-ai/glm-5.3":{"draws":15,"losses":45,"wins":2},"z-ai/glm-5.3-flash":{"draws":25,"losses":43,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":29,"wins":6}},"unbiased/pareto-26.10-preview":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":5,"losses":10,"wins":33},"claude-fable-5-1":{"draws":3,"losses":22,"wins":29},"claude-haiku-5-5":{"draws":2,"losses":9,"wins":35},"claude-opus-4-5":{"draws":1,"losses":1,"wins":76},"claude-opus-4-8":{"draws":2,"losses":1,"wins":41},"claude-opus-5":{"draws":3,"losses":29,"wins":50},"claude-opus-5-5":{"draws":1,"losses":26,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":71},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":0,"losses":5,"wins":55},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":78},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":42},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":0,"losses":0,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":2,"losses":6,"wins":38},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":47},"gpt-5.5":{"draws":1,"losses":4,"wins":39},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":42},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":43},"gpt-5.6-terra":{"draws":3,"losses":4,"wins":39},"gpt-6-astra":{"draws":6,"losses":22,"wins":20},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":5,"losses":9,"wins":34},"gpt-6.1-sol":{"draws":2,"losses":18,"wins":28},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":2,"wins":49},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":42},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":42},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"mistralai/mistral-large-4-0":{"draws":3,"losses":3,"wins":24},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"o3":{"draws":0,"losses":3,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"poolside/laguna-s-2.1":{"draws":0,"losses":1,"wins":45},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":42},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":34},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":7,"wins":141},"stealth/space-bunny-alpha":{"draws":1,"losses":0,"wins":37},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":33},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":24},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":63},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":41},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":31},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":25},"z-ai/glm-5.2":{"draws":4,"losses":4,"wins":88},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"upstage/solar-mini4":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":1,"wins":0},"claude-fable-5":{"draws":4,"losses":2,"wins":0},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":1,"wins":0},"claude-opus-4-5":{"draws":8,"losses":1,"wins":1},"claude-opus-4-8":{"draws":6,"losses":0,"wins":0},"claude-opus-5":{"draws":7,"losses":5,"wins":0},"claude-opus-5-5":{"draws":2,"losses":4,"wins":0},"claude-sonnet-5":{"draws":5,"losses":1,"wins":0},"claude-sonnet-5-5":{"draws":4,"losses":2,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":1,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":0},"fireworks/ember-1":{"draws":5,"losses":1,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":11,"losses":1,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":1,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":1},"gpt-5.5":{"draws":5,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":0},"gpt-6-astra":{"draws":2,"losses":4,"wins":0},"gpt-6-luna":{"draws":1,"losses":5,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"gpt-6.1-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":3},"meta/muse-wonder":{"draws":3,"losses":3,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-large-4-0":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":1},"o3":{"draws":3,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":10,"losses":8,"wins":0},"stealth/space-bunny-alpha":{"draws":5,"losses":0,"wins":1},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":0,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":0},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":0}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":22,"wins":35},"claude-fable-5":{"draws":17,"losses":54,"wins":15},"claude-fable-5-1":{"draws":1,"losses":85,"wins":6},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":59,"losses":56,"wins":59},"claude-opus-4-8":{"draws":26,"losses":18,"wins":18},"claude-opus-5":{"draws":20,"losses":81,"wins":21},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":64,"losses":23,"wins":51},"claude-sonnet-5-5":{"draws":15,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":29,"losses":27,"wins":48},"deepseek/deepseek-v4-pro":{"draws":22,"losses":38,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":30,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":17},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":30,"losses":34,"wins":34},"google/gemini-3.5-flash-lite":{"draws":110,"losses":45,"wins":133},"google/gemini-3.6-flash":{"draws":74,"losses":131,"wins":77},"google/gemini-3.8-flash":{"draws":21,"losses":32,"wins":25},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":16},"gpt-4.1":{"draws":8,"losses":6,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":18,"wins":16},"gpt-5.4":{"draws":25,"losses":75,"wins":28},"gpt-5.4-mini":{"draws":21,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":36},"gpt-5.5":{"draws":16,"losses":21,"wins":19},"gpt-5.6-luna":{"draws":43,"losses":45,"wins":44},"gpt-5.6-sol":{"draws":15,"losses":88,"wins":33},"gpt-5.6-terra":{"draws":24,"losses":32,"wins":28},"gpt-6-astra":{"draws":5,"losses":71,"wins":6},"gpt-6-luna":{"draws":18,"losses":15,"wins":15},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":40,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":4,"wins":28},"inclusionai/ling-3.0-flash":{"draws":32,"losses":9,"wins":41},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":36,"losses":32,"wins":58},"meta/muse-glimmer-30b":{"draws":29,"losses":10,"wins":33},"meta/muse-spark-1.2":{"draws":31,"losses":33,"wins":38},"meta/muse-spark-1.3":{"draws":10,"losses":40,"wins":22},"meta/muse-wonder":{"draws":9,"losses":28,"wins":11},"minimax/minimax-m3":{"draws":11,"losses":6,"wins":19},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":12,"losses":12,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":45,"losses":52,"wins":29},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":21},"o3":{"draws":7,"losses":72,"wins":77},"openai/gpt-oss-120b":{"draws":32,"losses":10,"wins":30},"poolside/laguna-s-2.1":{"draws":44,"losses":24,"wins":52},"qwen/qwen3.7-max":{"draws":12,"losses":11,"wins":19},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":30,"wins":24},"qwen/qwen3.8-27b":{"draws":11,"losses":16,"wins":15},"qwen/qwen3.8-flash":{"draws":15,"losses":14,"wins":21},"qwen/qwen3.8-max":{"draws":35,"losses":33,"wins":27},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"stealth/ox-alpha":{"draws":67,"losses":115,"wins":84},"stealth/space-bunny-alpha":{"draws":15,"losses":7,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":14},"tencent/hy4-preview":{"draws":20,"losses":44,"wins":20},"thinkingmachines/inkling":{"draws":38,"losses":18,"wins":68},"thinkingmachines/inkling-small":{"draws":34,"losses":11,"wins":48},"unbiased/pareto-26.10-preview":{"draws":1,"losses":14,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":27,"losses":41,"wins":12},"x-ai/grok-4.6":{"draws":32,"losses":37,"wins":17},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":7},"xiaomi/mimo-v2.5":{"draws":35,"losses":8,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":22,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":41,"losses":36,"wins":51},"z-ai/glm-5.3":{"draws":16,"losses":41,"wins":11},"z-ai/glm-5.3-flash":{"draws":14,"losses":40,"wins":24},"z-ai/glm-5.3-flashx":{"draws":12,"losses":24,"wins":12}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":14,"wins":31},"claude-fable-5":{"draws":26,"losses":50,"wins":10},"claude-fable-5-1":{"draws":3,"losses":86,"wins":3},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":13},"claude-opus-4-5":{"draws":37,"losses":32,"wins":37},"claude-opus-4-8":{"draws":16,"losses":20,"wins":12},"claude-opus-5":{"draws":17,"losses":68,"wins":7},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":37,"losses":33,"wins":22},"claude-sonnet-5-5":{"draws":13,"losses":27,"wins":8},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":45,"losses":22,"wins":47},"deepseek/deepseek-v4-pro":{"draws":32,"losses":21,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":28,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":19,"wins":9},"fireworks/ember-1":{"draws":20,"losses":23,"wins":5},"gemini-3.1-pro-preview":{"draws":20,"losses":14,"wins":14},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":18},"google/gemini-3.5-flash":{"draws":37,"losses":29,"wins":30},"google/gemini-3.5-flash-lite":{"draws":67,"losses":31,"wins":56},"google/gemini-3.6-flash":{"draws":56,"losses":58,"wins":38},"google/gemini-3.8-flash":{"draws":30,"losses":39,"wins":13},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":8,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":17,"losses":13,"wins":18},"gpt-5.4":{"draws":32,"losses":44,"wins":10},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":22,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":38,"losses":21,"wins":33},"gpt-5.6-sol":{"draws":19,"losses":53,"wins":16},"gpt-5.6-terra":{"draws":43,"losses":21,"wins":22},"gpt-6-astra":{"draws":9,"losses":73,"wins":0},"gpt-6-luna":{"draws":21,"losses":11,"wins":16},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":7,"losses":41,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":28,"losses":10,"wins":24},"inclusionai/ling-3.0-flash":{"draws":21,"losses":6,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":21,"wins":22},"meta/muse-glimmer-30b":{"draws":42,"losses":6,"wins":28},"meta/muse-spark-1.2":{"draws":25,"losses":19,"wins":28},"meta/muse-spark-1.3":{"draws":22,"losses":29,"wins":21},"meta/muse-wonder":{"draws":20,"losses":26,"wins":2},"minimax/minimax-m3":{"draws":12,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":7,"wins":10},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":27,"losses":18,"wins":29},"nex-agi/nex-n2-pro":{"draws":12,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":9,"wins":14},"o3":{"draws":21,"losses":42,"wins":41},"openai/gpt-oss-120b":{"draws":40,"losses":12,"wins":26},"poolside/laguna-s-2.1":{"draws":38,"losses":15,"wins":21},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":36,"wins":20},"qwen/qwen3.8-27b":{"draws":15,"losses":22,"wins":9},"qwen/qwen3.8-flash":{"draws":24,"losses":16,"wins":14},"qwen/qwen3.8-max":{"draws":42,"losses":34,"wins":18},"qwen/qwen3.8-max-0902":{"draws":21,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":107,"losses":128,"wins":45},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":11,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":33,"losses":33,"wins":18},"thinkingmachines/inkling":{"draws":31,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":39,"losses":20,"wins":33},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":25,"losses":42,"wins":13},"x-ai/grok-4.6":{"draws":23,"losses":30,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":36,"losses":13,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":54,"losses":34,"wins":52},"z-ai/glm-5.3":{"draws":17,"losses":41,"wins":12},"z-ai/glm-5.3-flash":{"draws":23,"losses":40,"wins":21},"z-ai/glm-5.3-flashx":{"draws":14,"losses":29,"wins":5}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":15,"wins":18},"claude-fable-5":{"draws":5,"losses":26,"wins":11},"claude-fable-5-1":{"draws":3,"losses":37,"wins":6},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":18},"claude-opus-4-5":{"draws":13,"losses":26,"wins":31},"claude-opus-4-8":{"draws":11,"losses":17,"wins":14},"claude-opus-5":{"draws":10,"losses":43,"wins":17},"claude-opus-5-5":{"draws":5,"losses":36,"wins":5},"claude-sonnet-5":{"draws":9,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":19,"wins":17},"fireworks/ember-1":{"draws":6,"losses":14,"wins":22},"gemini-3.1-pro-preview":{"draws":7,"losses":14,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":29},"google/gemini-3.5-flash":{"draws":11,"losses":17,"wins":26},"google/gemini-3.5-flash-lite":{"draws":13,"losses":21,"wins":40},"google/gemini-3.6-flash":{"draws":9,"losses":36,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":17,"wins":15},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":16},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":15,"wins":15},"gpt-5.4":{"draws":9,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":9,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":8,"wins":27},"gpt-5.5":{"draws":8,"losses":19,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":28,"wins":9},"gpt-5.6-terra":{"draws":8,"losses":15,"wins":17},"gpt-6-astra":{"draws":3,"losses":34,"wins":5},"gpt-6-luna":{"draws":7,"losses":13,"wins":22},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":4,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":8,"losses":19,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":17},"meta/muse-wonder":{"draws":10,"losses":18,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":28},"o3":{"draws":7,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":19},"qwen/qwen3.7-max":{"draws":6,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":28,"losses":44,"wins":46},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":11,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":31},"unbiased/pareto-26.10-preview":{"draws":1,"losses":12,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":19,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":17,"losses":11,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":22,"losses":21,"wins":41},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":13},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":18,"wins":17}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":39,"wins":33},"claude-fable-5":{"draws":14,"losses":86,"wins":2},"claude-fable-5-1":{"draws":5,"losses":105,"wins":2},"claude-haiku-5-5":{"draws":16,"losses":64,"wins":20},"claude-opus-4-5":{"draws":84,"losses":133,"wins":59},"claude-opus-4-8":{"draws":42,"losses":118,"wins":22},"claude-opus-5":{"draws":35,"losses":193,"wins":10},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":28,"losses":61,"wins":19},"claude-sonnet-5-5":{"draws":15,"losses":74,"wins":13},"cohere/north-mini-code":{"draws":18,"losses":13,"wins":23},"deepseek/deepseek-v4-flash":{"draws":62,"losses":76,"wins":80},"deepseek/deepseek-v4-pro":{"draws":28,"losses":48,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":53,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":57,"wins":17},"fireworks/ember-1":{"draws":32,"losses":54,"wins":16},"gemini-3.1-pro-preview":{"draws":24,"losses":52,"wins":26},"google/gemini-3.1-flash-lite":{"draws":38,"losses":43,"wins":63},"google/gemini-3.5-flash":{"draws":31,"losses":80,"wins":31},"google/gemini-3.5-flash-lite":{"draws":49,"losses":93,"wins":64},"google/gemini-3.6-flash":{"draws":61,"losses":136,"wins":41},"google/gemini-3.8-flash":{"draws":26,"losses":66,"wins":12},"google/gemma-4-31b-it":{"draws":19,"losses":16,"wins":25},"gpt-4.1":{"draws":22,"losses":29,"wins":17},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":43,"losses":60,"wins":27},"gpt-5.4":{"draws":22,"losses":74,"wins":6},"gpt-5.4-mini":{"draws":46,"losses":37,"wins":47},"gpt-5.4-nano":{"draws":38,"losses":101,"wins":85},"gpt-5.5":{"draws":67,"losses":70,"wins":19},"gpt-5.6-luna":{"draws":34,"losses":42,"wins":26},"gpt-5.6-sol":{"draws":13,"losses":81,"wins":10},"gpt-5.6-terra":{"draws":29,"losses":65,"wins":8},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":25,"losses":62,"wins":15},"gpt-6-sol":{"draws":14,"losses":78,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":90,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":26,"losses":13,"wins":35},"inclusionai/ling-3.0-flash":{"draws":46,"losses":26,"wins":52},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":71,"wins":59},"meta/muse-glimmer-30b":{"draws":30,"losses":34,"wins":26},"meta/muse-spark-1.2":{"draws":24,"losses":62,"wins":16},"meta/muse-spark-1.3":{"draws":18,"losses":77,"wins":13},"meta/muse-wonder":{"draws":10,"losses":83,"wins":9},"minimax/minimax-m3":{"draws":28,"losses":39,"wins":45},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":12},"mistralai/mistral-medium-3-5":{"draws":18,"losses":17,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":22,"wins":15},"moonshotai/kimi-k3":{"draws":36,"losses":75,"wins":23},"nex-agi/nex-n2-pro":{"draws":27,"losses":26,"wins":43},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":57,"losses":55,"wins":64},"o3":{"draws":29,"losses":109,"wins":40},"openai/gpt-oss-120b":{"draws":26,"losses":34,"wins":28},"poolside/laguna-s-2.1":{"draws":37,"losses":65,"wins":42},"qwen/qwen3.7-max":{"draws":36,"losses":46,"wins":30},"qwen/qwen3.7-plus":{"draws":19,"losses":35,"wins":48},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":58,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":47,"wins":19},"qwen/qwen3.8-flash":{"draws":22,"losses":31,"wins":17},"qwen/qwen3.8-max":{"draws":27,"losses":55,"wins":26},"qwen/qwen3.8-max-0902":{"draws":34,"losses":57,"wins":11},"stealth/ox-alpha":{"draws":61,"losses":214,"wins":53},"stealth/space-bunny-alpha":{"draws":26,"losses":33,"wins":23},"stepfun/step-3.7-flash":{"draws":20,"losses":33,"wins":43},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":32,"losses":47,"wins":31},"tencent/hy4-preview":{"draws":28,"losses":77,"wins":9},"thinkingmachines/inkling":{"draws":35,"losses":59,"wins":88},"thinkingmachines/inkling-small":{"draws":34,"losses":28,"wins":42},"unbiased/pareto-26.10-preview":{"draws":2,"losses":32,"wins":0},"upstage/solar-mini4":{"draws":5,"losses":17,"wins":10},"x-ai/grok-4.5":{"draws":28,"losses":81,"wins":15},"x-ai/grok-4.6":{"draws":33,"losses":59,"wins":10},"x-ai/grok-4.7":{"draws":7,"losses":74,"wins":9},"x-ai/grok-build-0.1":{"draws":16,"losses":29,"wins":19},"xiaomi/mimo-v2.5":{"draws":93,"losses":81,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":57,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":44,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":95,"losses":124,"wins":71},"z-ai/glm-5.3":{"draws":13,"losses":82,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":61,"wins":20},"z-ai/glm-5.3-flashx":{"draws":22,"losses":70,"wins":10}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":15,"wins":8},"claude-fable-5":{"draws":6,"losses":34,"wins":2},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":8},"claude-opus-4-5":{"draws":26,"losses":47,"wins":27},"claude-opus-4-8":{"draws":19,"losses":29,"wins":14},"claude-opus-5":{"draws":8,"losses":99,"wins":3},"claude-opus-5-5":{"draws":1,"losses":44,"wins":1},"claude-sonnet-5":{"draws":10,"losses":28,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":35,"losses":35,"wins":28},"deepseek/deepseek-v4-pro":{"draws":11,"losses":23,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":5},"fireworks/ember-1":{"draws":15,"losses":21,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":21,"wins":9},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":34},"google/gemini-3.5-flash":{"draws":16,"losses":26,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":40,"wins":23},"google/gemini-3.6-flash":{"draws":24,"losses":57,"wins":13},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":10},"gpt-4.1":{"draws":8,"losses":16,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":19,"losses":21,"wins":14},"gpt-5.4":{"draws":10,"losses":25,"wins":5},"gpt-5.4-mini":{"draws":15,"losses":22,"wins":11},"gpt-5.4-nano":{"draws":26,"losses":26,"wins":32},"gpt-5.5":{"draws":26,"losses":25,"wins":13},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":28,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":12,"losses":24,"wins":6},"gpt-6-sol":{"draws":1,"losses":35,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":24,"losses":15,"wins":23},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":26,"wins":29},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":28,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":40,"wins":3},"meta/muse-wonder":{"draws":4,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":26,"wins":13},"nex-agi/nex-n2-pro":{"draws":16,"losses":11,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":14,"wins":22},"o3":{"draws":16,"losses":40,"wins":14},"openai/gpt-oss-120b":{"draws":16,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":22,"losses":26,"wins":22},"qwen/qwen3.7-max":{"draws":17,"losses":24,"wins":11},"qwen/qwen3.7-plus":{"draws":20,"losses":8,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":20,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":20,"wins":4},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":9},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":88,"wins":23},"stealth/space-bunny-alpha":{"draws":13,"losses":15,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":13,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":19,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":19,"wins":41},"thinkingmachines/inkling-small":{"draws":20,"losses":9,"wins":19},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":11,"losses":42,"wins":9},"x-ai/grok-4.6":{"draws":12,"losses":33,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":1},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":8},"xiaomi/mimo-v2.5":{"draws":46,"losses":38,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":8,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":48,"losses":48,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":27,"wins":4},"z-ai/glm-5.3-flashx":{"draws":12,"losses":27,"wins":3}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":17},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":1,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":10},"claude-opus-4-5":{"draws":22,"losses":27,"wins":19},"claude-opus-4-8":{"draws":10,"losses":16,"wins":12},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":10,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":11,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":11},"fireworks/ember-1":{"draws":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":21,"wins":19},"google/gemini-3.5-flash-lite":{"draws":14,"losses":15,"wins":43},"google/gemini-3.6-flash":{"draws":18,"losses":38,"wins":24},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":6,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":1},"gpt-5":{"draws":12,"losses":18,"wins":8},"gpt-5.4":{"draws":16,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":9},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":21},"gpt-5.5":{"draws":20,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":9},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":14,"losses":20,"wins":8},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":5,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":31,"wins":6},"meta/muse-wonder":{"draws":4,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":11},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":17},"o3":{"draws":9,"losses":21,"wins":32},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":22},"poolside/laguna-s-2.1":{"draws":16,"losses":9,"wins":19},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":11},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":17,"wins":14},"stealth/ox-alpha":{"draws":35,"losses":72,"wins":33},"stealth/space-bunny-alpha":{"draws":10,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":20},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":20,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":5,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":27},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":24,"wins":6},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":10}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":6,"losses":32,"wins":10},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":21,"wins":12},"claude-opus-4-5":{"draws":28,"losses":25,"wins":25},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":10,"losses":60,"wins":12},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":15,"losses":15,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":28,"losses":42,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":10,"losses":17,"wins":21},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":17,"losses":3,"wins":32},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":17},"meta/muse-spark-1.3":{"draws":10,"losses":24,"wins":14},"meta/muse-wonder":{"draws":8,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":24},"o3":{"draws":10,"losses":18,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":10,"losses":19,"wins":19},"stealth/ox-alpha":{"draws":43,"losses":68,"wins":47},"stealth/space-bunny-alpha":{"draws":15,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":28},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":30,"losses":4,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":40,"losses":22,"wins":34},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":11,"losses":23,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":73,"losses":58,"wins":47},"claude-fable-5":{"draws":37,"losses":107,"wins":22},"claude-fable-5-1":{"draws":8,"losses":164,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":116,"losses":165,"wins":91},"claude-opus-4-8":{"draws":58,"losses":108,"wins":40},"claude-opus-5":{"draws":57,"losses":262,"wins":35},"claude-opus-5-5":{"draws":9,"losses":142,"wins":5},"claude-sonnet-5":{"draws":65,"losses":83,"wins":44},"claude-sonnet-5-5":{"draws":28,"losses":90,"wins":26},"cohere/north-mini-code":{"draws":15,"losses":3,"wins":44},"deepseek/deepseek-v4-flash":{"draws":104,"losses":69,"wins":125},"deepseek/deepseek-v4-pro":{"draws":61,"losses":74,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":72,"losses":57,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":50,"losses":66,"wins":28},"fireworks/ember-1":{"draws":48,"losses":69,"wins":27},"gemini-3.1-pro-preview":{"draws":43,"losses":64,"wins":37},"google/gemini-3.1-flash-lite":{"draws":35,"losses":26,"wins":91},"google/gemini-3.5-flash":{"draws":55,"losses":101,"wins":64},"google/gemini-3.5-flash-lite":{"draws":113,"losses":131,"wins":118},"google/gemini-3.6-flash":{"draws":121,"losses":146,"wins":85},"google/gemini-3.8-flash":{"draws":51,"losses":96,"wins":29},"google/gemma-4-31b-it":{"draws":35,"losses":14,"wins":35},"gpt-4.1":{"draws":25,"losses":22,"wins":29},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":58,"losses":74,"wins":58},"gpt-5.4":{"draws":53,"losses":83,"wins":36},"gpt-5.4-mini":{"draws":69,"losses":29,"wins":52},"gpt-5.4-nano":{"draws":58,"losses":80,"wins":90},"gpt-5.5":{"draws":78,"losses":86,"wins":44},"gpt-5.6-luna":{"draws":67,"losses":50,"wins":73},"gpt-5.6-sol":{"draws":21,"losses":130,"wins":19},"gpt-5.6-terra":{"draws":73,"losses":69,"wins":44},"gpt-6-astra":{"draws":7,"losses":142,"wins":3},"gpt-6-luna":{"draws":54,"losses":57,"wins":33},"gpt-6-sol":{"draws":26,"losses":107,"wins":11},"gpt-6.1-sol":{"draws":12,"losses":127,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":60,"losses":13,"wins":65},"inclusionai/ling-3.0-flash":{"draws":71,"losses":26,"wins":45},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":72,"losses":54,"wins":112},"meta/muse-glimmer-30b":{"draws":85,"losses":27,"wins":56},"meta/muse-spark-1.2":{"draws":42,"losses":78,"wins":50},"meta/muse-spark-1.3":{"draws":37,"losses":97,"wins":34},"meta/muse-wonder":{"draws":30,"losses":95,"wins":19},"minimax/minimax-m3":{"draws":40,"losses":26,"wins":44},"mistralai/mistral-large-4-0":{"draws":29,"losses":43,"wins":18},"mistralai/mistral-medium-3-5":{"draws":56,"losses":12,"wins":44},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":26,"wins":19},"moonshotai/kimi-k3":{"draws":55,"losses":73,"wins":42},"nex-agi/nex-n2-pro":{"draws":44,"losses":17,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":81,"losses":42,"wins":55},"o3":{"draws":46,"losses":119,"wins":83},"openai/gpt-oss-120b":{"draws":61,"losses":46,"wins":63},"poolside/laguna-s-2.1":{"draws":86,"losses":70,"wins":56},"qwen/qwen3.7-max":{"draws":43,"losses":50,"wins":45},"qwen/qwen3.7-plus":{"draws":40,"losses":26,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":76,"losses":69,"wins":33},"qwen/qwen3.8-27b":{"draws":37,"losses":45,"wins":28},"qwen/qwen3.8-flash":{"draws":51,"losses":36,"wins":33},"qwen/qwen3.8-max":{"draws":66,"losses":70,"wins":46},"qwen/qwen3.8-max-0902":{"draws":50,"losses":65,"wins":29},"stealth/ox-alpha":{"draws":158,"losses":308,"wins":122},"stealth/space-bunny-alpha":{"draws":40,"losses":37,"wins":37},"stepfun/step-3.7-flash":{"draws":27,"losses":38,"wins":49},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":44,"losses":33,"wins":41},"tencent/hy4-preview":{"draws":48,"losses":93,"wins":31},"thinkingmachines/inkling":{"draws":81,"losses":65,"wins":106},"thinkingmachines/inkling-small":{"draws":77,"losses":50,"wins":69},"unbiased/pareto-26.10-preview":{"draws":2,"losses":45,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":50,"losses":111,"wins":31},"x-ai/grok-4.6":{"draws":50,"losses":107,"wins":23},"x-ai/grok-4.7":{"draws":15,"losses":95,"wins":16},"x-ai/grok-build-0.1":{"draws":23,"losses":16,"wins":27},"xiaomi/mimo-v2.5":{"draws":124,"losses":89,"wins":137},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":47,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":53,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":121,"losses":114,"wins":101},"z-ai/glm-5.3":{"draws":42,"losses":104,"wins":14},"z-ai/glm-5.3-flash":{"draws":49,"losses":98,"wins":33},"z-ai/glm-5.3-flashx":{"draws":35,"losses":77,"wins":32}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":19,"wins":34},"claude-fable-5":{"draws":17,"losses":51,"wins":22},"claude-fable-5-1":{"draws":6,"losses":84,"wins":4},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":39,"losses":31,"wins":36},"claude-opus-4-8":{"draws":11,"losses":17,"wins":20},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":31,"losses":17,"wins":38},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":45,"losses":12,"wins":49},"deepseek/deepseek-v4-pro":{"draws":32,"losses":24,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":31,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"fireworks/ember-1":{"draws":18,"losses":14,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":20},"google/gemini-3.1-flash-lite":{"draws":12,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":32,"losses":38,"wins":30},"google/gemini-3.5-flash-lite":{"draws":51,"losses":25,"wins":82},"google/gemini-3.6-flash":{"draws":40,"losses":56,"wins":54},"google/gemini-3.8-flash":{"draws":22,"losses":42,"wins":24},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":11},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":28,"losses":46,"wins":14},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":11,"losses":15,"wins":26},"gpt-5.5":{"draws":15,"losses":11,"wins":20},"gpt-5.6-luna":{"draws":33,"losses":25,"wins":32},"gpt-5.6-sol":{"draws":16,"losses":57,"wins":13},"gpt-5.6-terra":{"draws":30,"losses":24,"wins":30},"gpt-6-astra":{"draws":9,"losses":72,"wins":3},"gpt-6-luna":{"draws":11,"losses":19,"wins":18},"gpt-6-sol":{"draws":8,"losses":30,"wins":10},"gpt-6.1-sol":{"draws":2,"losses":40,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":24},"inclusionai/ling-3.0-flash":{"draws":21,"losses":2,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":11,"wins":37},"meta/muse-glimmer-30b":{"draws":21,"losses":16,"wins":35},"meta/muse-spark-1.2":{"draws":15,"losses":37,"wins":16},"meta/muse-spark-1.3":{"draws":16,"losses":29,"wins":25},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":33,"losses":20,"wins":17},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":13,"wins":17},"o3":{"draws":14,"losses":39,"wins":43},"openai/gpt-oss-120b":{"draws":34,"losses":6,"wins":36},"poolside/laguna-s-2.1":{"draws":25,"losses":15,"wins":30},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":20,"wins":28},"qwen/qwen3.8-27b":{"draws":15,"losses":6,"wins":25},"qwen/qwen3.8-flash":{"draws":27,"losses":17,"wins":12},"qwen/qwen3.8-max":{"draws":29,"losses":34,"wins":23},"qwen/qwen3.8-max-0902":{"draws":18,"losses":18,"wins":12},"stealth/ox-alpha":{"draws":87,"losses":111,"wins":78},"stealth/space-bunny-alpha":{"draws":16,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"losses":3,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":8,"wins":13},"tencent/hy4-preview":{"draws":28,"losses":21,"wins":39},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":41},"thinkingmachines/inkling-small":{"draws":29,"losses":20,"wins":39},"unbiased/pareto-26.10-preview":{"draws":2,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":24,"losses":22,"wins":30},"x-ai/grok-4.6":{"draws":26,"losses":42,"wins":22},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":30,"losses":3,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":12,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":53,"losses":33,"wins":54},"z-ai/glm-5.3":{"draws":8,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":27,"losses":33,"wins":26},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":13}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":10,"wins":38},"claude-fable-5":{"draws":18,"losses":49,"wins":13},"claude-fable-5-1":{"draws":5,"losses":79,"wins":6},"claude-haiku-5-5":{"draws":11,"losses":24,"wins":11},"claude-opus-4-5":{"draws":30,"losses":37,"wins":41},"claude-opus-4-8":{"draws":6,"losses":23,"wins":15},"claude-opus-5":{"draws":16,"losses":65,"wins":13},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":27,"losses":33,"wins":28},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":50,"losses":22,"wins":36},"deepseek/deepseek-v4-pro":{"draws":27,"losses":18,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":28,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":19,"wins":14},"fireworks/ember-1":{"draws":15,"losses":15,"wins":18},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":21},"google/gemini-3.5-flash":{"draws":26,"losses":40,"wins":32},"google/gemini-3.5-flash-lite":{"draws":53,"losses":47,"wins":52},"google/gemini-3.6-flash":{"draws":42,"losses":58,"wins":48},"google/gemini-3.8-flash":{"draws":21,"losses":42,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":2,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":13,"wins":18},"gpt-5.4":{"draws":18,"losses":39,"wins":25},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":15,"losses":15,"wins":18},"gpt-5.5":{"draws":16,"losses":16,"wins":14},"gpt-5.6-luna":{"draws":37,"losses":23,"wins":26},"gpt-5.6-sol":{"draws":22,"losses":49,"wins":15},"gpt-5.6-terra":{"draws":27,"losses":24,"wins":29},"gpt-6-astra":{"draws":11,"losses":63,"wins":4},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":7,"losses":29,"wins":12},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":22,"losses":6,"wins":30},"inclusionai/ling-3.0-flash":{"draws":17,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":22,"wins":35},"meta/muse-glimmer-30b":{"draws":32,"losses":14,"wins":30},"meta/muse-spark-1.2":{"draws":16,"losses":26,"wins":24},"meta/muse-spark-1.3":{"draws":16,"losses":33,"wins":21},"meta/muse-wonder":{"draws":16,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":9,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":18,"losses":10,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":28,"losses":21,"wins":21},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":16,"wins":13},"o3":{"draws":15,"losses":43,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":13,"wins":31},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":21},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":31,"wins":21},"qwen/qwen3.8-27b":{"draws":14,"losses":16,"wins":14},"qwen/qwen3.8-flash":{"draws":23,"losses":19,"wins":12},"qwen/qwen3.8-max":{"draws":29,"losses":30,"wins":19},"qwen/qwen3.8-max-0902":{"draws":14,"losses":23,"wins":11},"stealth/ox-alpha":{"draws":73,"losses":130,"wins":73},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":11,"losses":11,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":11,"wins":11},"tencent/hy4-preview":{"draws":26,"losses":34,"wins":16},"thinkingmachines/inkling":{"draws":29,"losses":22,"wins":31},"thinkingmachines/inkling-small":{"draws":32,"losses":22,"wins":36},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":7},"x-ai/grok-4.5":{"draws":14,"losses":29,"wins":23},"x-ai/grok-4.6":{"draws":31,"losses":28,"wins":21},"x-ai/grok-4.7":{"draws":6,"losses":30,"wins":6},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":32,"losses":17,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":11,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":56,"losses":31,"wins":49},"z-ai/glm-5.3":{"draws":19,"losses":37,"wins":10},"z-ai/glm-5.3-flash":{"draws":16,"losses":30,"wins":10},"z-ai/glm-5.3-flashx":{"draws":15,"losses":23,"wins":10}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":22,"wins":11},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":11,"losses":21,"wins":12},"claude-opus-5":{"draws":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":19,"losses":11,"wins":18},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":15,"wins":35},"deepseek/deepseek-v4-pro":{"draws":15,"losses":13,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":14,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":19,"losses":11,"wins":18},"google/gemini-3.1-flash-lite":{"draws":15,"losses":0,"wins":17},"google/gemini-3.5-flash":{"draws":20,"losses":16,"wins":24},"google/gemini-3.5-flash-lite":{"draws":32,"losses":13,"wins":39},"google/gemini-3.6-flash":{"draws":31,"losses":35,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":10,"wins":15},"gpt-5.4":{"draws":17,"losses":17,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":11,"wins":25},"gpt-5.5":{"draws":19,"losses":16,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":8},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":17},"gpt-6-astra":{"draws":6,"losses":41,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":14,"losses":2,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":8,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":11,"wins":16},"nex-agi/nex-n2-pro":{"draws":9,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"o3":{"draws":12,"losses":14,"wins":40},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":13,"wins":18},"qwen/qwen3.8-27b":{"draws":11,"losses":9,"wins":14},"qwen/qwen3.8-flash":{"draws":13,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":15},"stealth/ox-alpha":{"draws":36,"losses":70,"wins":52},"stealth/space-bunny-alpha":{"draws":14,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":3,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":31,"losses":0,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":24,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":12,"wins":10}}}}}