{"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":"2026-11-01T08:00:50Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:4163374b7b930edd","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":3.2723400000000002},"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":1.91349}},"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":3.27234},"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":15.613269999999998},"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":89.82766301643608,"highest":94.68896824965196,"medium":89.75649941769984,"none":85.03752138195645},"economics_best_value":{"per_model":{"all":true,"highest":true,"none":true},"per_setting":{"highest":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":89.10616108960575,"score":89.10616108960575},"GB2-02":{"attempts":3,"playable":83.12770581585005,"score":83.12770581585005},"GB2-03":{"attempts":3,"playable":89.2216277917978,"score":89.2216277917978},"GB2-04":{"attempts":3,"playable":89.1423917540795,"score":89.1423917540795},"GB2-05":{"attempts":3,"playable":95.42258472064724,"score":95.42258472064724},"GB2-06":{"attempts":3,"playable":87.05340955195406,"score":87.05340955195406},"GB2-07":{"attempts":3,"playable":96.35632499141633,"score":96.35632499141633},"GB2-08":{"attempts":3,"playable":89.19109841613793,"score":89.19109841613793}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":97.26345060375083,"score":97.26345060375083},"GB2-02":{"attempts":1,"playable":95.28622817901866,"score":95.28622817901866},"GB2-03":{"attempts":1,"playable":97.71674983801944,"score":97.71674983801944},"GB2-04":{"attempts":1,"playable":92.4293167178963,"score":92.4293167178963},"GB2-05":{"attempts":1,"playable":98.93313785231533,"score":98.93313785231533},"GB2-06":{"attempts":1,"playable":87.05560026670089,"score":87.05560026670089},"GB2-07":{"attempts":1,"playable":97.81813759659185,"score":97.81813759659185},"GB2-08":{"attempts":1,"playable":91.00912494292237,"score":91.00912494292237}},"medium":{"GB2-01":{"attempts":1,"playable":76.89442459289783,"score":76.89442459289783},"GB2-02":{"attempts":1,"playable":81.18050179343724,"score":81.18050179343724},"GB2-03":{"attempts":1,"playable":94.79906872075871,"score":94.79906872075871},"GB2-04":{"attempts":1,"playable":91.60246245740011,"score":91.60246245740011},"GB2-05":{"attempts":1,"playable":93.07420359693637,"score":93.07420359693637},"GB2-06":{"attempts":1,"playable":88.94879409264351,"score":88.94879409264351},"GB2-07":{"attempts":1,"playable":96.65945092904707,"score":96.65945092904707},"GB2-08":{"attempts":1,"playable":94.89308915847776,"score":94.89308915847776}},"none":{"GB2-01":{"attempts":1,"playable":93.1606080721686,"score":93.1606080721686},"GB2-02":{"attempts":1,"playable":72.91638747509423,"score":72.91638747509423},"GB2-03":{"attempts":1,"playable":75.14906481661524,"score":75.14906481661524},"GB2-04":{"attempts":1,"playable":83.39539608694211,"score":83.39539608694211},"GB2-05":{"attempts":1,"playable":94.26041271268998,"score":94.26041271268998},"GB2-06":{"attempts":1,"playable":85.15583429651774,"score":85.15583429651774},"GB2-07":{"attempts":1,"playable":94.59138644861007,"score":94.59138644861007},"GB2-08":{"attempts":1,"playable":81.67108114701365,"score":81.67108114701365}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-10-31T15:52:54Z","match_totals_all":{"draws":871,"losses":877,"wins":10522},"match_totals_tracks":{"highest":{"draws":99,"losses":174,"wins":3817},"medium":{"draws":260,"losses":308,"wins":3522},"none":{"draws":512,"losses":395,"wins":3183}},"model_slug":"gpt-6-astra","official_rank_by_reasoning":{"highest":2,"medium":2,"none":4},"overall":{"max":98.93313785231533,"mean":89.82766301643608,"min":72.91638747509423},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":97.26345060375083,"GB2-02":95.28622817901866,"GB2-03":97.71674983801944,"GB2-04":92.4293167178963,"GB2-05":98.93313785231533,"GB2-06":87.05560026670089,"GB2-07":97.81813759659185,"GB2-08":91.00912494292237},"per_game_all":{"GB2-01":89.10616108960575,"GB2-02":83.12770581585005,"GB2-03":89.2216277917978,"GB2-04":89.1423917540795,"GB2-05":95.42258472064724,"GB2-06":87.05340955195406,"GB2-07":96.35632499141633,"GB2-08":89.19109841613793},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":154,"wins":1333},"GB2-02":{"draws":402,"losses":54,"wins":984},"GB2-03":{"draws":175,"losses":89,"wins":1224},"GB2-04":{"draws":163,"losses":90,"wins":1241},"GB2-05":{"draws":0,"losses":70,"wins":1520},"GB2-06":{"draws":70,"losses":181,"wins":1255},"GB2-07":{"draws":0,"losses":47,"wins":1543},"GB2-08":{"draws":0,"losses":192,"wins":1422}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":15,"wins":501},"GB2-02":{"draws":25,"losses":10,"wins":445},"GB2-03":{"draws":9,"losses":6,"wins":481},"GB2-04":{"draws":37,"losses":21,"wins":440},"GB2-05":{"draws":0,"losses":3,"wins":527},"GB2-06":{"draws":28,"losses":58,"wins":416},"GB2-07":{"draws":0,"losses":8,"wins":522},"GB2-08":{"draws":0,"losses":53,"wins":485}},"medium":{"GB2-01":{"draws":37,"losses":111,"wins":368},"GB2-02":{"draws":157,"losses":17,"wins":306},"GB2-03":{"draws":5,"losses":25,"wins":466},"GB2-04":{"draws":42,"losses":23,"wins":433},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-06":{"draws":19,"losses":52,"wins":431},"GB2-07":{"draws":0,"losses":14,"wins":516},"GB2-08":{"draws":0,"losses":29,"wins":509}},"none":{"GB2-01":{"draws":24,"losses":28,"wins":464},"GB2-02":{"draws":220,"losses":27,"wins":233},"GB2-03":{"draws":161,"losses":58,"wins":277},"GB2-04":{"draws":84,"losses":46,"wins":368},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":23,"losses":71,"wins":408},"GB2-07":{"draws":0,"losses":25,"wins":505},"GB2-08":{"draws":0,"losses":110,"wins":428}}},"per_game_raw_elo_all":{"GB2-01":2036.7605852399745,"GB2-02":1848.1828049732837,"GB2-03":2104.334368698489,"GB2-04":1915.1291597066702,"GB2-05":2599.5485838836034,"GB2-06":2106.277794309394,"GB2-07":2541.209290349007,"GB2-08":2176.252964378575},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2278.8290780846587,"GB2-02":2103.7274931859183,"GB2-03":2416.4184010017616,"GB2-04":1983.3441866987844,"GB2-05":2940.8513912548024,"GB2-06":2105.1147196191514,"GB2-07":2659.4415606402044,"GB2-08":2209.8669486236818},"medium":{"GB2-01":1755.4513960015938,"GB2-02":1770.1722128141269,"GB2-03":2201.9128182019317,"GB2-04":1960.6494784752472,"GB2-05":2395.4678721554847,"GB2-06":2153.5419917768895,"GB2-07":2553.3147650225283,"GB2-08":2373.007380960298},"none":{"GB2-01":2076.001281633671,"GB2-02":1670.6487089198063,"GB2-03":1694.6718868917735,"GB2-04":1801.3938139459792,"GB2-05":2462.3264882405238,"GB2-06":2060.176671532141,"GB2-07":2410.8715453842888,"GB2-08":1945.8845635517453}},"per_game_tracks":{"highest":{"GB2-01":97.26345060375083,"GB2-02":95.28622817901866,"GB2-03":97.71674983801944,"GB2-04":92.4293167178963,"GB2-05":98.93313785231533,"GB2-06":87.05560026670089,"GB2-07":97.81813759659185,"GB2-08":91.00912494292237},"medium":{"GB2-01":76.89442459289783,"GB2-02":81.18050179343724,"GB2-03":94.79906872075871,"GB2-04":91.60246245740011,"GB2-05":93.07420359693637,"GB2-06":88.94879409264351,"GB2-07":96.65945092904707,"GB2-08":94.89308915847776},"none":{"GB2-01":93.1606080721686,"GB2-02":72.91638747509423,"GB2-03":75.14906481661524,"GB2-04":83.39539608694211,"GB2-05":94.26041271268998,"GB2-06":85.15583429651774,"GB2-07":94.59138644861007,"GB2-08":81.67108114701365}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T01:59:42Z","reasoning":{"highest":94.68896824965196,"medium":89.75649941769984,"none":85.03752138195645},"reasoning_agg":{"highest":{"max":98.93313785231533,"mean":94.68896824965196,"min":87.05560026670089},"medium":{"max":96.65945092904707,"mean":89.75649941769984,"min":76.89442459289783},"none":{"max":94.59138644861007,"mean":85.03752138195645,"min":72.91638747509423}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.651446867695512},"working_program_strength":{"all":89.82766301643608,"highest":94.68896824965196,"medium":89.75649941769984,"none":85.03752138195645}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:b52ae01f6a026bcf","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":17.677192},"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":3.0063079999999998},"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":21.736292000000002},"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":88.8101408780564,"highest":95.23106099570691,"medium":92.84649050857384,"none":78.35287112988843},"economics_best_value":{"per_model":{"highest":true,"medium":true},"per_setting":{"highest":true,"medium":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":89.73632494435606,"score":89.73632494435606},"GB2-02":{"attempts":3,"playable":90.3779979513897,"score":90.3779979513897},"GB2-03":{"attempts":3,"playable":80.80648479074027,"score":80.80648479074027},"GB2-04":{"attempts":3,"playable":84.7461851276913,"score":84.7461851276913},"GB2-05":{"attempts":3,"playable":93.29283184801331,"score":93.29283184801331},"GB2-06":{"attempts":3,"playable":89.99287002762956,"score":89.99287002762956},"GB2-07":{"attempts":3,"playable":94.39781540606124,"score":94.39781540606124},"GB2-08":{"attempts":5,"playable":87.13061692856968,"score":87.13061692856968}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":84.36605504027904,"score":84.36605504027904},"GB2-02":{"attempts":1,"playable":95.95274210401446,"score":95.95274210401446},"GB2-03":{"attempts":1,"playable":97.28771467152548,"score":97.28771467152548},"GB2-04":{"attempts":1,"playable":95.25970618902171,"score":95.25970618902171},"GB2-05":{"attempts":1,"playable":98.24590773399218,"score":98.24590773399218},"GB2-06":{"attempts":1,"playable":99.47876957025215,"score":99.47876957025215},"GB2-07":{"attempts":1,"playable":97.81813759659185,"score":97.81813759659185},"GB2-08":{"attempts":1,"playable":93.43945505997844,"score":93.43945505997844}},"medium":{"GB2-01":{"attempts":1,"playable":93.91942211321275,"score":93.91942211321275},"GB2-02":{"attempts":1,"playable":95.38149520158238,"score":95.38149520158238},"GB2-03":{"attempts":1,"playable":92.40167474514536,"score":92.40167474514536},"GB2-04":{"attempts":1,"playable":87.99267353388296,"score":87.99267353388296},"GB2-05":{"attempts":1,"playable":89.73288350194329,"score":89.73288350194329},"GB2-06":{"attempts":1,"playable":92.87267973900107,"score":92.87267973900107},"GB2-07":{"attempts":1,"playable":93.49402140792446,"score":93.49402140792446},"GB2-08":{"attempts":2,"playable":96.97707382589837,"score":96.97707382589837}},"none":{"GB2-01":{"attempts":1,"playable":90.9234976795764,"score":90.9234976795764},"GB2-02":{"attempts":1,"playable":79.79975654857226,"score":79.79975654857226},"GB2-03":{"attempts":1,"playable":52.73006495554995,"score":52.73006495554995},"GB2-04":{"attempts":1,"playable":70.98617566016924,"score":70.98617566016924},"GB2-05":{"attempts":1,"playable":91.89970430810443,"score":91.89970430810443},"GB2-06":{"attempts":1,"playable":77.62716077363545,"score":77.62716077363545},"GB2-07":{"attempts":1,"playable":91.8812872136674,"score":91.8812872136674},"GB2-08":{"attempts":2,"playable":70.97532189983224,"score":70.97532189983224}}},"id":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-10-31T16:11:08Z","match_totals_all":{"draws":930,"losses":1172,"wins":11244},"match_totals_tracks":{"highest":{"draws":77,"losses":160,"wins":3853},"medium":{"draws":128,"losses":258,"wins":4242},"none":{"draws":725,"losses":754,"wins":3149}},"model_slug":"claude-opus-5-5","official_rank_by_reasoning":{"highest":1,"medium":1,"none":7},"overall":{"max":99.47876957025215,"mean":88.8101408780564,"min":52.73006495554995},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":84.36605504027904,"GB2-02":95.95274210401446,"GB2-03":97.28771467152548,"GB2-04":95.25970618902171,"GB2-05":98.24590773399218,"GB2-06":99.47876957025215,"GB2-07":97.81813759659185,"GB2-08":93.43945505997844},"per_game_all":{"GB2-01":89.73632494435606,"GB2-02":90.3779979513897,"GB2-03":80.80648479074027,"GB2-04":84.7461851276913,"GB2-05":93.29283184801331,"GB2-06":89.99287002762956,"GB2-07":94.39781540606124,"GB2-08":87.13061692856968},"per_game_match_totals_all":{"GB2-01":{"draws":66,"losses":145,"wins":1337},"GB2-02":{"draws":151,"losses":68,"wins":1221},"GB2-03":{"draws":350,"losses":133,"wins":1005},"GB2-04":{"draws":306,"losses":87,"wins":1101},"GB2-05":{"draws":0,"losses":108,"wins":1482},"GB2-06":{"draws":45,"losses":141,"wins":1320},"GB2-07":{"draws":0,"losses":79,"wins":1511},"GB2-08":{"draws":12,"losses":411,"wins":2267}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":85,"wins":422},"GB2-02":{"draws":24,"losses":7,"wins":449},"GB2-03":{"draws":2,"losses":12,"wins":482},"GB2-04":{"draws":42,"losses":3,"wins":453},"GB2-05":{"draws":0,"losses":7,"wins":523},"GB2-06":{"draws":0,"losses":0,"wins":502},"GB2-07":{"draws":0,"losses":8,"wins":522},"GB2-08":{"draws":0,"losses":38,"wins":500}},"medium":{"GB2-01":{"draws":35,"losses":18,"wins":463},"GB2-02":{"draws":16,"losses":14,"wins":450},"GB2-03":{"draws":23,"losses":30,"wins":443},"GB2-04":{"draws":39,"losses":44,"wins":415},"GB2-05":{"draws":0,"losses":57,"wins":473},"GB2-06":{"draws":15,"losses":32,"wins":455},"GB2-07":{"draws":0,"losses":31,"wins":499},"GB2-08":{"draws":0,"losses":32,"wins":1044}},"none":{"GB2-01":{"draws":22,"losses":42,"wins":452},"GB2-02":{"draws":111,"losses":47,"wins":322},"GB2-03":{"draws":325,"losses":91,"wins":80},"GB2-04":{"draws":225,"losses":40,"wins":233},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":30,"losses":109,"wins":363},"GB2-07":{"draws":0,"losses":40,"wins":490},"GB2-08":{"draws":12,"losses":341,"wins":723}}},"per_game_raw_elo_all":{"GB2-01":1993.1212412335535,"GB2-02":1998.8687613402155,"GB2-03":1972.5514117880873,"GB2-04":1871.4575068821314,"GB2-05":2463.241745622988,"GB2-06":2357.228529751323,"GB2-07":2423.735865404599,"GB2-08":2185.6270678155447},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1867.8731933820497,"GB2-02":2136.994704267022,"GB2-03":2375.061362806668,"GB2-04":2081.9256142479426,"GB2-05":2816.441750671376,"GB2-06":2895.8935920964245,"GB2-07":2659.4415606402044,"GB2-08":2304.022847057209},"medium":{"GB2-01":2103.4143882260937,"GB2-02":2108.2222600368145,"GB2-03":2087.7109845725518,"GB2-04":1879.4846867002673,"GB2-05":2237.4602228910617,"GB2-06":2274.388628586834,"GB2-07":2347.454491308868,"GB2-08":2539.8076115127906},"none":{"GB2-01":2008.0761420925173,"GB2-02":1751.3893197168104,"GB2-03":1454.881887985042,"GB2-04":1652.9622196981845,"GB2-05":2335.823263306526,"GB2-06":1901.4033685707104,"GB2-07":2264.311544264724,"GB2-08":1713.0507448766339}},"per_game_tracks":{"highest":{"GB2-01":84.36605504027904,"GB2-02":95.95274210401446,"GB2-03":97.28771467152548,"GB2-04":95.25970618902171,"GB2-05":98.24590773399218,"GB2-06":99.47876957025215,"GB2-07":97.81813759659185,"GB2-08":93.43945505997844},"medium":{"GB2-01":93.91942211321275,"GB2-02":95.38149520158238,"GB2-03":92.40167474514536,"GB2-04":87.99267353388296,"GB2-05":89.73288350194329,"GB2-06":92.87267973900107,"GB2-07":93.49402140792446,"GB2-08":96.97707382589837},"none":{"GB2-01":90.9234976795764,"GB2-02":79.79975654857226,"GB2-03":52.73006495554995,"GB2-04":70.98617566016924,"GB2-05":91.89970430810443,"GB2-06":77.62716077363545,"GB2-07":91.8812872136674,"GB2-08":70.97532189983224}},"program_outcomes":{"all":{"counted_attempts":26,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":23,"working":26},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":9,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":8,"working":9},"none":{"counted_attempts":9,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":9,"working":9}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T01:54:23Z","reasoning":{"highest":95.23106099570691,"medium":92.84649050857384,"none":78.35287112988843},"reasoning_agg":{"highest":{"max":99.47876957025215,"mean":95.23106099570691,"min":84.36605504027904},"medium":{"max":96.97707382589837,"mean":92.84649050857384,"min":87.99267353388296},"none":{"max":91.89970430810443,"mean":78.35287112988843,"min":52.73006495554995}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.878189865818484},"working_program_strength":{"all":88.8101408780564,"highest":95.23106099570691,"medium":92.84649050857384,"none":78.35287112988843}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:0aa5e99bfd3b790d","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":48.7391179312137},"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":6.33905201032609}},"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":6.339052010326091},"historical-provider-setting-intensive-variant-1":{"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":11.79121,"mean":5.15427625,"median":3.933625,"min":2.88134,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":8,"token_priced_attempt_count":10,"total":41.234210000000004},"historical-provider-setting-intensive-variant-2":{"admitted_cell_count":3,"cell_count":3,"cost_basis_counts":{"local_list_price_estimate":3},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.970960728273602,"mean":2.501635977071231,"median":2.662375536110322,"min":1.8715716668297693,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3},"run_count":3,"token_priced_attempt_count":3,"total":7.504907931213694}},"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":88.60275507384898,"highest":94.39945886544025,"medium":84.92872647398966,"none":86.48007988211704},"economics_best_value":{"per_model":{"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":85.09629822101213,"score":85.09629822101213},"GB2-02":{"attempts":3,"playable":89.76978303026802,"score":89.76978303026802},"GB2-03":{"attempts":4,"playable":93.75778266316706,"score":93.75778266316706},"GB2-04":{"attempts":4,"playable":75.5882025751651,"score":75.5882025751651},"GB2-05":{"attempts":3,"playable":91.2362160358462,"score":91.2362160358462},"GB2-06":{"attempts":3,"playable":90.38182538652067,"score":90.38182538652067},"GB2-07":{"attempts":4,"playable":91.97710870267822,"score":91.97710870267822},"GB2-08":{"attempts":3,"playable":91.01482397613448,"score":91.01482397613448}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":93.1606080721686,"score":93.1606080721686},"GB2-02":{"attempts":1,"playable":95.19094589086761,"score":95.19094589086761},"GB2-03":{"attempts":2,"playable":95.69973958360646,"score":95.69973958360646},"GB2-04":{"attempts":2,"playable":88.26061591245605,"score":88.26061591245605},"GB2-05":{"attempts":1,"playable":93.41174923079485,"score":93.41174923079485},"GB2-06":{"attempts":1,"playable":98.30878230210418,"score":98.30878230210418},"GB2-07":{"attempts":2,"playable":93.8578824864666,"score":93.8578824864666},"GB2-08":{"attempts":1,"playable":97.30534744505772,"score":97.30534744505772}},"medium":{"GB2-01":{"attempts":1,"playable":73.85761426133848,"score":73.85761426133848},"GB2-02":{"attempts":1,"playable":91.46465470312141,"score":91.46465470312141},"GB2-03":{"attempts":1,"playable":92.31607743311734,"score":92.31607743311734},"GB2-04":{"attempts":1,"playable":64.88698910893464,"score":64.88698910893464},"GB2-05":{"attempts":1,"playable":88.56429019588857,"score":88.56429019588857},"GB2-06":{"attempts":1,"playable":88.8588487701753,"score":88.8588487701753},"GB2-07":{"attempts":1,"playable":93.85761234240468,"score":93.85761234240468},"GB2-08":{"attempts":1,"playable":85.62372497693673,"score":85.62372497693673}},"none":{"GB2-01":{"attempts":1,"playable":88.2706723295293,"score":88.2706723295293},"GB2-02":{"attempts":1,"playable":82.65374849681506,"score":82.65374849681506},"GB2-03":{"attempts":1,"playable":93.25753097277737,"score":93.25753097277737},"GB2-04":{"attempts":1,"playable":73.6170027041046,"score":73.6170027041046},"GB2-05":{"attempts":1,"playable":91.73260868085514,"score":91.73260868085514},"GB2-06":{"attempts":1,"playable":83.97784508728256,"score":83.97784508728256},"GB2-07":{"attempts":1,"playable":88.21583127916338,"score":88.21583127916338},"GB2-08":{"attempts":1,"playable":90.11539950640896,"score":90.11539950640896}}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-10-31T17:10:42Z","match_totals_all":{"draws":747,"losses":1212,"wins":11835},"match_totals_tracks":{"highest":{"draws":116,"losses":288,"wins":5210},"medium":{"draws":295,"losses":507,"wins":3288},"none":{"draws":336,"losses":417,"wins":3337}},"model_slug":"claude-fable-5-1","official_rank_by_reasoning":{"highest":3,"medium":4,"none":3},"overall":{"max":98.30878230210418,"mean":88.60275507384898,"min":64.88698910893464},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":93.1606080721686,"GB2-02":95.19094589086761,"GB2-03":95.69973958360646,"GB2-04":88.26061591245605,"GB2-05":93.41174923079485,"GB2-06":98.30878230210418,"GB2-07":93.8578824864666,"GB2-08":97.30534744505772},"per_game_all":{"GB2-01":85.09629822101213,"GB2-02":89.76978303026802,"GB2-03":93.75778266316706,"GB2-04":75.5882025751651,"GB2-05":91.2362160358462,"GB2-06":90.38182538652067,"GB2-07":91.97710870267822,"GB2-08":91.01482397613448},"per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":250,"wins":1291},"GB2-02":{"draws":175,"losses":66,"wins":1199},"GB2-03":{"draws":20,"losses":113,"wins":1851},"GB2-04":{"draws":505,"losses":194,"wins":1293},"GB2-05":{"draws":0,"losses":144,"wins":1446},"GB2-06":{"draws":39,"losses":139,"wins":1328},"GB2-07":{"draws":0,"losses":148,"wins":1972},"GB2-08":{"draws":1,"losses":158,"wins":1455}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":39,"wins":475},"GB2-02":{"draws":22,"losses":12,"wins":446},"GB2-03":{"draws":7,"losses":41,"wins":944},"GB2-04":{"draws":82,"losses":83,"wins":831},"GB2-05":{"draws":0,"losses":35,"wins":495},"GB2-06":{"draws":3,"losses":6,"wins":493},"GB2-07":{"draws":0,"losses":58,"wins":1002},"GB2-08":{"draws":0,"losses":14,"wins":524}},"medium":{"GB2-01":{"draws":1,"losses":145,"wins":370},"GB2-02":{"draws":35,"losses":25,"wins":420},"GB2-03":{"draws":10,"losses":37,"wins":449},"GB2-04":{"draws":239,"losses":64,"wins":195},"GB2-05":{"draws":0,"losses":64,"wins":466},"GB2-06":{"draws":10,"losses":57,"wins":435},"GB2-07":{"draws":0,"losses":29,"wins":501},"GB2-08":{"draws":0,"losses":86,"wins":452}},"none":{"GB2-01":{"draws":4,"losses":66,"wins":446},"GB2-02":{"draws":118,"losses":29,"wins":333},"GB2-03":{"draws":3,"losses":35,"wins":458},"GB2-04":{"draws":184,"losses":47,"wins":267},"GB2-05":{"draws":0,"losses":45,"wins":485},"GB2-06":{"draws":26,"losses":76,"wins":400},"GB2-07":{"draws":0,"losses":61,"wins":469},"GB2-08":{"draws":1,"losses":58,"wins":479}}},"per_game_raw_elo_all":{"GB2-01":1912.2113032357158,"GB2-02":1952.831806923629,"GB2-03":2155.373446265026,"GB2-04":1721.845330266485,"GB2-05":2310.2473213784374,"GB2-06":2268.4368876173503,"GB2-07":2282.655223097908,"GB2-08":2253.303803022986},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2076.001281633671,"GB2-02":2099.310083754458,"GB2-03":2257.2074787330002,"GB2-04":1889.604918883299,"GB2-05":2413.7064758150877,"GB2-06":2620.5165738300893,"GB2-07":2367.8838310202727,"GB2-08":2533.8149689586153},"medium":{"GB2-01":1716.839595789594,"GB2-02":1967.662444291513,"GB2-03":2084.2000340828154,"GB2-04":1596.0536463118256,"GB2-05":2189.2843935686305,"GB2-06":2151.1370340416015,"GB2-07":2367.7862038418175,"GB2-08":2046.6074059191742},"none":{"GB2-01":1943.793032283883,"GB2-02":1791.5228927249154,"GB2-03":2124.712825979262,"GB2-04":1679.877425604331,"GB2-05":2327.7510947515934,"GB2-06":2033.6570549803596,"GB2-07":2112.2956344316335,"GB2-08":2179.489034191168}},"per_game_tracks":{"highest":{"GB2-01":93.1606080721686,"GB2-02":95.19094589086761,"GB2-03":95.69973958360646,"GB2-04":88.26061591245605,"GB2-05":93.41174923079485,"GB2-06":98.30878230210418,"GB2-07":93.8578824864666,"GB2-08":97.30534744505772},"medium":{"GB2-01":73.85761426133848,"GB2-02":91.46465470312141,"GB2-03":92.31607743311734,"GB2-04":64.88698910893464,"GB2-05":88.56429019588857,"GB2-06":88.8588487701753,"GB2-07":93.85761234240468,"GB2-08":85.62372497693673},"none":{"GB2-01":88.2706723295293,"GB2-02":82.65374849681506,"GB2-03":93.25753097277737,"GB2-04":73.6170027041046,"GB2-05":91.73260868085514,"GB2-06":83.97784508728256,"GB2-07":88.21583127916338,"GB2-08":90.11539950640896}},"program_outcomes":{"all":{"counted_attempts":27,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":24,"working":27},"highest":{"counted_attempts":11,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":9,"working":11},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T02:06:27Z","reasoning":{"highest":94.39945886544025,"medium":84.92872647398966,"none":86.48007988211704},"reasoning_agg":{"highest":{"max":98.30878230210418,"mean":94.39945886544025,"min":88.26061591245605},"medium":{"max":93.85761234240468,"mean":84.92872647398966,"min":64.88698910893464},"none":{"max":93.25753097277737,"mean":86.48007988211704,"min":73.6170027041046}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.470732391450596},"working_program_strength":{"all":88.60275507384898,"highest":94.39945886544025,"medium":84.92872647398966,"none":86.48007988211704}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-1-sol:ffe1770d7a9b76a6","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":0.6746989999999999},"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":0.674699},"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":3.1954350000000007},"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":86.10385539537276,"highest":92.7067875100589,"medium":87.73719804492112,"none":77.86758063113828},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true},"per_setting":{"highest":true,"medium":true,"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":67.71497598569562,"score":67.71497598569562},"GB2-02":{"attempts":3,"playable":79.99932264509833,"score":79.99932264509833},"GB2-03":{"attempts":3,"playable":93.58398246426852,"score":93.58398246426852},"GB2-04":{"attempts":3,"playable":85.44241714712643,"score":85.44241714712643},"GB2-05":{"attempts":3,"playable":94.69004212241434,"score":94.69004212241434},"GB2-06":{"attempts":3,"playable":87.54207353872748,"score":87.54207353872748},"GB2-07":{"attempts":3,"playable":95.39998850446828,"score":95.39998850446828},"GB2-08":{"attempts":3,"playable":84.45804075518322,"score":84.45804075518322}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.04246980122839,"score":76.04246980122839},"GB2-02":{"attempts":1,"playable":94.80967289020985,"score":94.80967289020985},"GB2-03":{"attempts":1,"playable":98.23093263670124,"score":98.23093263670124},"GB2-04":{"attempts":1,"playable":94.89606507884886,"score":94.89606507884886},"GB2-05":{"attempts":1,"playable":97.89812890736457,"score":97.89812890736457},"GB2-06":{"attempts":1,"playable":90.115651828225,"score":90.115651828225},"GB2-07":{"attempts":1,"playable":95.89860433452299,"score":95.89860433452299},"GB2-08":{"attempts":1,"playable":93.76277460337033,"score":93.76277460337033}},"medium":{"GB2-01":{"attempts":1,"playable":75.47352594367854,"score":75.47352594367854},"GB2-02":{"attempts":1,"playable":80.19481697491676,"score":80.19481697491676},"GB2-03":{"attempts":1,"playable":96.6008943521444,"score":96.6008943521444},"GB2-04":{"attempts":1,"playable":87.61996375119062,"score":87.61996375119062},"GB2-05":{"attempts":1,"playable":94.77321423066255,"score":94.77321423066255},"GB2-06":{"attempts":1,"playable":92.34266337804645,"score":92.34266337804645},"GB2-07":{"attempts":1,"playable":95.70997473027177,"score":95.70997473027177},"GB2-08":{"attempts":1,"playable":79.1825309984579,"score":79.1825309984579}},"none":{"GB2-01":{"attempts":1,"playable":51.62893221217991,"score":51.62893221217991},"GB2-02":{"attempts":1,"playable":64.99347807016835,"score":64.99347807016835},"GB2-03":{"attempts":1,"playable":85.9201204039599,"score":85.9201204039599},"GB2-04":{"attempts":1,"playable":73.81122261133983,"score":73.81122261133983},"GB2-05":{"attempts":1,"playable":91.39878322921588,"score":91.39878322921588},"GB2-06":{"attempts":1,"playable":80.16790540991097,"score":80.16790540991097},"GB2-07":{"attempts":1,"playable":94.59138644861007,"score":94.59138644861007},"GB2-08":{"attempts":1,"playable":80.42881666372142,"score":80.42881666372142}}},"id":"gpt-6.1-sol","is_recent_addition":false,"last_measured_at":"2026-10-31T17:01:19Z","match_totals_all":{"draws":876,"losses":1359,"wins":10035},"match_totals_tracks":{"highest":{"draws":99,"losses":261,"wins":3730},"medium":{"draws":209,"losses":429,"wins":3452},"none":{"draws":568,"losses":669,"wins":2853}},"model_slug":"gpt-6-1-sol","official_rank_by_reasoning":{"highest":4,"medium":3,"none":8},"overall":{"max":98.23093263670124,"mean":86.10385539537276,"min":51.62893221217991},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.04246980122839,"GB2-02":94.80967289020985,"GB2-03":98.23093263670124,"GB2-04":94.89606507884886,"GB2-05":97.89812890736457,"GB2-06":90.115651828225,"GB2-07":95.89860433452299,"GB2-08":93.76277460337033},"per_game_all":{"GB2-01":67.71497598569562,"GB2-02":79.99932264509833,"GB2-03":93.58398246426852,"GB2-04":85.44241714712643,"GB2-05":94.69004212241434,"GB2-06":87.54207353872748,"GB2-07":95.39998850446828,"GB2-08":84.45804075518322},"per_game_match_totals_all":{"GB2-01":{"draws":77,"losses":493,"wins":978},"GB2-02":{"draws":443,"losses":80,"wins":917},"GB2-03":{"draws":35,"losses":86,"wins":1367},"GB2-04":{"draws":241,"losses":109,"wins":1144},"GB2-05":{"draws":0,"losses":83,"wins":1507},"GB2-06":{"draws":79,"losses":168,"wins":1259},"GB2-07":{"draws":0,"losses":62,"wins":1528},"GB2-08":{"draws":1,"losses":278,"wins":1335}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":134,"wins":382},"GB2-02":{"draws":30,"losses":10,"wins":440},"GB2-03":{"draws":1,"losses":7,"wins":488},"GB2-04":{"draws":38,"losses":7,"wins":453},"GB2-05":{"draws":0,"losses":9,"wins":521},"GB2-06":{"draws":30,"losses":40,"wins":432},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":36,"wins":502}},"medium":{"GB2-01":{"draws":12,"losses":131,"wins":373},"GB2-02":{"draws":133,"losses":34,"wins":313},"GB2-03":{"draws":4,"losses":15,"wins":477},"GB2-04":{"draws":39,"losses":46,"wins":413},"GB2-05":{"draws":0,"losses":27,"wins":503},"GB2-06":{"draws":21,"losses":32,"wins":449},"GB2-07":{"draws":0,"losses":19,"wins":511},"GB2-08":{"draws":0,"losses":125,"wins":413}},"none":{"GB2-01":{"draws":65,"losses":228,"wins":223},"GB2-02":{"draws":280,"losses":36,"wins":164},"GB2-03":{"draws":30,"losses":64,"wins":402},"GB2-04":{"draws":164,"losses":56,"wins":278},"GB2-05":{"draws":0,"losses":47,"wins":483},"GB2-06":{"draws":28,"losses":96,"wins":378},"GB2-07":{"draws":0,"losses":25,"wins":505},"GB2-08":{"draws":1,"losses":117,"wins":420}}},"per_game_raw_elo_all":{"GB2-01":1655.2857122775847,"GB2-02":1811.1338436642818,"GB2-03":2226.7007136961442,"GB2-04":1873.6684707411005,"GB2-05":2524.609353873751,"GB2-06":2131.4079028118363,"GB2-07":2463.390521683454,"GB2-08":2040.5568355571966},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.3133288927406,"GB2-02":2082.360360171336,"GB2-03":2474.912229485163,"GB2-04":2066.7507224236047,"GB2-05":2767.8786062114405,"GB2-06":2185.9071548965476,"GB2-07":2496.232053149095,"GB2-08":2318.302276466091},"medium":{"GB2-01":1737.0146300692527,"GB2-02":1756.6527290781703,"GB2-03":2318.21972515739,"GB2-04":1872.3189891292443,"GB2-05":2494.0558518389994,"GB2-06":2255.647274979163,"GB2-07":2483.0679665169787,"GB2-08":1887.173516842135},"none":{"GB2-01":1484.5291778707608,"GB2-02":1594.388441743339,"GB2-03":1886.97018644588,"GB2-04":1681.9357006704524,"GB2-05":2311.8936035708116,"GB2-06":1952.6692785597977,"GB2-07":2410.8715453842888,"GB2-08":1916.1947133633644}},"per_game_tracks":{"highest":{"GB2-01":76.04246980122839,"GB2-02":94.80967289020985,"GB2-03":98.23093263670124,"GB2-04":94.89606507884886,"GB2-05":97.89812890736457,"GB2-06":90.115651828225,"GB2-07":95.89860433452299,"GB2-08":93.76277460337033},"medium":{"GB2-01":75.47352594367854,"GB2-02":80.19481697491676,"GB2-03":96.6008943521444,"GB2-04":87.61996375119062,"GB2-05":94.77321423066255,"GB2-06":92.34266337804645,"GB2-07":95.70997473027177,"GB2-08":79.1825309984579},"none":{"GB2-01":51.62893221217991,"GB2-02":64.99347807016835,"GB2-03":85.9201204039599,"GB2-04":73.81122261133983,"GB2-05":91.39878322921588,"GB2-06":80.16790540991097,"GB2-07":94.59138644861007,"GB2-08":80.42881666372142}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T01:57:23Z","reasoning":{"highest":92.7067875100589,"medium":87.73719804492112,"none":77.86758063113828},"reasoning_agg":{"highest":{"max":98.23093263670124,"mean":92.7067875100589,"min":76.04246980122839},"medium":{"max":96.6008943521444,"mean":87.73719804492112,"min":75.47352594367854},"none":{"max":94.59138644861007,"mean":77.86758063113828,"min":51.62893221217991}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.83920687892062},"working_program_strength":{"all":86.10385539537276,"highest":92.7067875100589,"medium":87.73719804492112,"none":77.86758063113828}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-4-argon:5891bb750a1513bb","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":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.5240959999999997},"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":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.774334},"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":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.674042}},"codegen_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":0.22172,"mean":0.09679175,"median":0.079292,"min":0.064396,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"run_count":8,"token_priced_attempt_count":9,"total":0.774334},"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":0.124048,"mean":0.08425525,"median":0.081095,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"run_count":8,"token_priced_attempt_count":8,"total":0.6740420000000001},"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":0.582036,"mean":0.440512,"median":0.446556,"min":0.29813,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"run_count":8,"token_priced_attempt_count":11,"total":3.5240959999999997}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":28},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.582036,"mean":0.20718633333333333,"median":0.09228,"min":0.062404,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":28},"run_count":24,"token_priced_attempt_count":28,"total":4.972472000000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":633783,"mean_ms":198313.91666666666,"min_ms":46974,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":633783,"mean_ms":450301.75,"min_ms":322608,"run_count":8},"medium":{"attempt_count":9,"max_ms":152424,"mean_ms":70572.25,"min_ms":46974,"run_count":8},"none":{"attempt_count":8,"max_ms":113522,"mean_ms":74067.75,"min_ms":52299,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":54729,"output_mean":18449.125,"output_min":4647,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":54729,"output_mean":41092.75,"output_min":28061,"run_count":8},"medium":{"attempt_count":9,"output_max":17530,"output_mean":7576.5,"output_min":4801,"run_count":8},"none":{"attempt_count":8,"output_max":10605,"output_mean":6678.125,"output_min":4647,"run_count":8}},"display_name":"Gemini 4 Argon","economics":{"all":83.29016201280741,"highest":90.10348897689178,"medium":78.75049879081652,"none":81.01649827071394},"economics_best_value":{"per_model":{"none":true},"per_setting":{"none":true}},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":28,"effective_max_output_tokens":[943718],"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":[943718],"total_output_tokens":442779,"total_reasoning_output_tokens":206667,"total_visible_output_tokens":236112,"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"gemini-4-argon","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"google","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":92.96860024672651,"score":92.96860024672651},"GB2-02":{"attempts":3,"playable":79.10905574980336,"score":79.10905574980336},"GB2-03":{"attempts":3,"playable":85.99989569276623,"score":85.99989569276623},"GB2-04":{"attempts":3,"playable":72.14682504454923,"score":72.14682504454923},"GB2-05":{"attempts":3,"playable":91.70798480301232,"score":91.70798480301232},"GB2-06":{"attempts":3,"playable":93.55387957620114,"score":93.55387957620114},"GB2-07":{"attempts":3,"playable":73.86611081231185,"score":73.86611081231185},"GB2-08":{"attempts":3,"playable":76.9689441770886,"score":76.9689441770886}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.32886904830103,"score":95.32886904830103},"GB2-02":{"attempts":1,"playable":94.90501196277401,"score":94.90501196277401},"GB2-03":{"attempts":1,"playable":92.31607743311734,"score":92.31607743311734},"GB2-04":{"attempts":1,"playable":71.37694820860871,"score":71.37694820860871},"GB2-05":{"attempts":1,"playable":96.3280002832477,"score":96.3280002832477},"GB2-06":{"attempts":1,"playable":97.58119902114734,"score":97.58119902114734},"GB2-07":{"attempts":1,"playable":84.26059309281739,"score":84.26059309281739},"GB2-08":{"attempts":1,"playable":88.7312127651206,"score":88.7312127651206}},"medium":{"GB2-01":{"attempts":1,"playable":91.09779248806583,"score":91.09779248806583},"GB2-02":{"attempts":1,"playable":65.30067944004625,"score":65.30067944004625},"GB2-03":{"attempts":1,"playable":80.02695947030269,"score":80.02695947030269},"GB2-04":{"attempts":1,"playable":68.92901896792554,"score":68.92901896792554},"GB2-05":{"attempts":1,"playable":90.39909746459303,"score":90.39909746459303},"GB2-06":{"attempts":1,"playable":92.696238964601,"score":92.696238964601},"GB2-07":{"attempts":1,"playable":77.8945940905917,"score":77.8945940905917},"GB2-08":{"attempts":1,"playable":63.659609440406115,"score":63.659609440406115}},"none":{"GB2-01":{"attempts":1,"playable":92.47913920381265,"score":92.47913920381265},"GB2-02":{"attempts":1,"playable":77.12147584658983,"score":77.12147584658983},"GB2-03":{"attempts":1,"playable":85.65665017487866,"score":85.65665017487866},"GB2-04":{"attempts":1,"playable":76.13450795711343,"score":76.13450795711343},"GB2-05":{"attempts":1,"playable":88.39685666119624,"score":88.39685666119624},"GB2-06":{"attempts":1,"playable":90.38420074285504,"score":90.38420074285504},"GB2-07":{"attempts":1,"playable":59.443145253526474,"score":59.443145253526474},"GB2-08":{"attempts":1,"playable":78.5160103257391,"score":78.5160103257391}}},"id":"gemini-4-argon","is_recent_addition":false,"last_measured_at":"2026-10-27T23:45:47Z","match_totals_all":{"draws":960,"losses":1716,"wins":9594},"match_totals_tracks":{"highest":{"draws":168,"losses":341,"wins":3581},"medium":{"draws":464,"losses":699,"wins":2927},"none":{"draws":328,"losses":676,"wins":3086}},"model_slug":"gemini-4-argon","official_rank_by_reasoning":{"highest":6,"medium":5,"none":5},"overall":{"max":97.58119902114734,"mean":83.29016201280741,"min":59.443145253526474},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":5,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.32886904830103,"GB2-02":94.90501196277401,"GB2-03":92.31607743311734,"GB2-04":71.37694820860871,"GB2-05":96.3280002832477,"GB2-06":97.58119902114734,"GB2-07":84.26059309281739,"GB2-08":88.7312127651206},"per_game_all":{"GB2-01":92.96860024672651,"GB2-02":79.10905574980336,"GB2-03":85.99989569276623,"GB2-04":72.14682504454923,"GB2-05":91.70798480301232,"GB2-06":93.55387957620114,"GB2-07":73.86611081231185,"GB2-08":76.9689441770886},"per_game_match_totals_all":{"GB2-01":{"draws":0,"losses":123,"wins":1425},"GB2-02":{"draws":348,"losses":141,"wins":951},"GB2-03":{"draws":165,"losses":152,"wins":1171},"GB2-04":{"draws":399,"losses":240,"wins":855},"GB2-05":{"draws":0,"losses":136,"wins":1454},"GB2-06":{"draws":48,"losses":82,"wins":1376},"GB2-07":{"draws":0,"losses":431,"wins":1159},"GB2-08":{"draws":0,"losses":411,"wins":1203}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":27,"wins":489},"GB2-02":{"draws":45,"losses":2,"wins":433},"GB2-03":{"draws":44,"losses":20,"wins":432},"GB2-04":{"draws":71,"losses":115,"wins":312},"GB2-05":{"draws":0,"losses":18,"wins":512},"GB2-06":{"draws":8,"losses":8,"wins":486},"GB2-07":{"draws":0,"losses":84,"wins":446},"GB2-08":{"draws":0,"losses":67,"wins":471}},"medium":{"GB2-01":{"draws":0,"losses":52,"wins":464},"GB2-02":{"draws":159,"losses":95,"wins":226},"GB2-03":{"draws":100,"losses":62,"wins":334},"GB2-04":{"draws":180,"losses":73,"wins":245},"GB2-05":{"draws":0,"losses":53,"wins":477},"GB2-06":{"draws":25,"losses":28,"wins":449},"GB2-07":{"draws":0,"losses":121,"wins":409},"GB2-08":{"draws":0,"losses":215,"wins":323}},"none":{"GB2-01":{"draws":0,"losses":44,"wins":472},"GB2-02":{"draws":144,"losses":44,"wins":292},"GB2-03":{"draws":21,"losses":70,"wins":405},"GB2-04":{"draws":148,"losses":52,"wins":298},"GB2-05":{"draws":0,"losses":65,"wins":465},"GB2-06":{"draws":15,"losses":46,"wins":441},"GB2-07":{"draws":0,"losses":226,"wins":304},"GB2-08":{"draws":0,"losses":129,"wins":409}}},"per_game_raw_elo_all":{"GB2-01":2076.5555949390687,"GB2-02":1800.4569920275565,"GB2-03":1911.4696396059544,"GB2-04":1665.767627375765,"GB2-05":2351.865945924201,"GB2-06":2332.5943551148275,"GB2-07":1804.0364594203368,"GB2-08":1862.788219367136},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2163.318435283094,"GB2-02":2086.4948077481677,"GB2-03":2084.2000340828154,"GB2-04":1656.8537386005223,"GB2-05":2606.6155088091264,"GB2-06":2536.049134173492,"GB2-07":1992.1668530030215,"GB2-08":2135.5373033124847},"medium":{"GB2-01":2012.8249863242306,"GB2-02":1597.1286435252555,"GB2-03":1769.4242280939732,"GB2-04":1633.0152202559898,"GB2-05":2266.3540294150202,"GB2-06":2268.0347024336056,"GB2-07":1851.366085692725,"GB2-08":1580.881323447018},"none":{"GB2-01":2053.5233632098807,"GB2-02":1717.7475248092462,"GB2-03":1880.7846566410744,"GB2-04":1707.4339232707825,"GB2-05":2182.6282995484557,"GB2-06":2193.699228737385,"GB2-07":1568.576439565264,"GB2-08":1871.9460313419054}},"per_game_tracks":{"highest":{"GB2-01":95.32886904830103,"GB2-02":94.90501196277401,"GB2-03":92.31607743311734,"GB2-04":71.37694820860871,"GB2-05":96.3280002832477,"GB2-06":97.58119902114734,"GB2-07":84.26059309281739,"GB2-08":88.7312127651206},"medium":{"GB2-01":91.09779248806583,"GB2-02":65.30067944004625,"GB2-03":80.02695947030269,"GB2-04":68.92901896792554,"GB2-05":90.39909746459303,"GB2-06":92.696238964601,"GB2-07":77.8945940905917,"GB2-08":63.659609440406115},"none":{"GB2-01":92.47913920381265,"GB2-02":77.12147584658983,"GB2-03":85.65665017487866,"GB2-04":76.13450795711343,"GB2-05":88.39685666119624,"GB2-06":90.38420074285504,"GB2-07":59.443145253526474,"GB2-08":78.5160103257391}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","reasoning":{"highest":90.10348897689178,"medium":78.75049879081652,"none":81.01649827071394},"reasoning_agg":{"highest":{"max":97.58119902114734,"mean":90.10348897689178,"min":71.37694820860871},"medium":{"max":92.696238964601,"mean":78.75049879081652,"min":63.659609440406115},"none":{"max":92.47913920381265,"mean":81.01649827071394,"min":59.443145253526474}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.35299018607526},"working_program_strength":{"all":83.29016201280741,"highest":90.10348897689178,"medium":78.75049879081652,"none":81.01649827071394}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3-1-pro:2810148fb3ae3498","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":0.520818,"mean":0.45841275000000004,"median":0.456374,"min":0.383384,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":3.667302},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.228888,"mean":0.1761925,"median":0.1786566,"min":0.1389952,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.40954},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.31477,"mean":0.2003284,"median":0.218258,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.6026272}},"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":0.228888,"mean":0.1761925,"median":0.1786566,"min":0.1389952,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.4095400000000002},"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":0.31477,"mean":0.2003284,"median":0.218258,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":1.6026272000000001},"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":0.520818,"mean":0.45841275000000004,"median":0.456374,"min":0.383384,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":3.667302}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.520818,"mean":0.2783112166666667,"median":0.227979,"min":0.093456,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":24,"run_count":24,"total":6.6794692},"codegen_latency_ms":{"attempt_count":24,"max_ms":1025651,"mean_ms":549120.875,"min_ms":169165,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":1025651,"mean_ms":925239.125,"min_ms":802488,"run_count":8},"medium":{"attempt_count":8,"max_ms":423651,"mean_ms":338545.75,"min_ms":271597,"run_count":8},"none":{"attempt_count":8,"max_ms":617894,"mean_ms":383577.75,"min_ms":169165,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":50450,"output_mean":26378.708333333332,"output_min":7904,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50450,"output_mean":44271.875,"output_min":36897,"run_count":8},"medium":{"attempt_count":8,"output_max":20868,"output_mean":16395.25,"output_min":12584,"run_count":8},"none":{"attempt_count":8,"output_max":29982,"output_mean":18469.0,"output_min":7904,"run_count":8}},"display_name":"Kimi K3.1 Pro","economics":{"all":79.8561663425903,"highest":85.71411646538674,"medium":73.10473691505912,"none":80.74964564732502},"first_seen_at":"2026-10-27T23:46:32Z","generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[943718],"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,"requested_max_output_token_observations":24,"requested_max_output_tokens":[943718],"total_output_tokens":633089,"total_reasoning_output_tokens":510905,"total_visible_output_tokens":122184,"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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"moonshotai","provider_model":"moonshotai/kimi-k3.1-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":65.99863935204819,"score":65.99863935204819},"GB2-02":{"attempts":3,"playable":79.42709020069992,"score":79.42709020069992},"GB2-03":{"attempts":3,"playable":63.889258099082404,"score":63.889258099082404},"GB2-04":{"attempts":3,"playable":81.62017693889307,"score":81.62017693889307},"GB2-05":{"attempts":3,"playable":85.34464618484127,"score":85.34464618484127},"GB2-06":{"attempts":3,"playable":89.83025897541187,"score":89.83025897541187},"GB2-07":{"attempts":3,"playable":79.8959508678496,"score":79.8959508678496},"GB2-08":{"attempts":3,"playable":92.84331012189612,"score":92.84331012189612}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":93.24533729514309,"score":93.24533729514309},"GB2-02":{"attempts":1,"playable":79.70092142855077,"score":79.70092142855077},"GB2-03":{"attempts":1,"playable":87.31867262184126,"score":87.31867262184126},"GB2-04":{"attempts":1,"playable":83.7732384821655,"score":83.7732384821655},"GB2-05":{"attempts":1,"playable":90.39909746459303,"score":90.39909746459303},"GB2-06":{"attempts":1,"playable":85.33695749257953,"score":85.33695749257953},"GB2-07":{"attempts":1,"playable":74.60495305505678,"score":74.60495305505678},"GB2-08":{"attempts":1,"playable":91.33375388316408,"score":91.33375388316408}},"medium":{"GB2-01":{"attempts":1,"playable":61.26369818844768,"score":61.26369818844768},"GB2-02":{"attempts":1,"playable":76.02462009144637,"score":76.02462009144637},"GB2-03":{"attempts":1,"playable":15.555748198578847,"score":15.555748198578847},"GB2-04":{"attempts":1,"playable":82.16433588826159,"score":82.16433588826159},"GB2-05":{"attempts":1,"playable":80.97538597774685,"score":80.97538597774685},"GB2-06":{"attempts":1,"playable":92.07690971682801,"score":92.07690971682801},"GB2-07":{"attempts":1,"playable":85.11900196619425,"score":85.11900196619425},"GB2-08":{"attempts":1,"playable":91.65819529296941,"score":91.65819529296941}},"none":{"GB2-01":{"attempts":1,"playable":43.48688257255377,"score":43.48688257255377},"GB2-02":{"attempts":1,"playable":82.55572908210263,"score":82.55572908210263},"GB2-03":{"attempts":1,"playable":88.7933534768271,"score":88.7933534768271},"GB2-04":{"attempts":1,"playable":78.92295644625212,"score":78.92295644625212},"GB2-05":{"attempts":1,"playable":84.6594551121839,"score":84.6594551121839},"GB2-06":{"attempts":1,"playable":92.07690971682801,"score":92.07690971682801},"GB2-07":{"attempts":1,"playable":79.96389758229779,"score":79.96389758229779},"GB2-08":{"attempts":1,"playable":95.53798118955486,"score":95.53798118955486}}},"id":"moonshotai/kimi-k3.1-pro","is_recent_addition":true,"last_measured_at":"2026-10-27T23:46:32Z","match_totals_all":{"draws":1182,"losses":1999,"wins":9089},"match_totals_tracks":{"highest":{"draws":338,"losses":456,"wins":3296},"medium":{"draws":469,"losses":901,"wins":2720},"none":{"draws":375,"losses":642,"wins":3073}},"model_slug":"moonshotai-kimi-k3-1-pro","official_rank_by_reasoning":{"highest":8,"medium":10,"none":6},"overall":{"max":95.53798118955486,"mean":79.8561663425903,"min":15.555748198578847},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":93.24533729514309,"GB2-02":79.70092142855077,"GB2-03":87.31867262184126,"GB2-04":83.7732384821655,"GB2-05":90.39909746459303,"GB2-06":85.33695749257953,"GB2-07":74.60495305505678,"GB2-08":91.33375388316408},"per_game_all":{"GB2-01":65.99863935204819,"GB2-02":79.42709020069992,"GB2-03":63.889258099082404,"GB2-04":81.62017693889307,"GB2-05":85.34464618484127,"GB2-06":89.83025897541187,"GB2-07":79.8959508678496,"GB2-08":92.84331012189612},"per_game_match_totals_all":{"GB2-01":{"draws":347,"losses":379,"wins":822},"GB2-02":{"draws":374,"losses":126,"wins":940},"GB2-03":{"draws":68,"losses":528,"wins":892},"GB2-04":{"draws":342,"losses":121,"wins":1031},"GB2-05":{"draws":0,"losses":248,"wins":1342},"GB2-06":{"draws":51,"losses":144,"wins":1311},"GB2-07":{"draws":0,"losses":328,"wins":1262},"GB2-08":{"draws":0,"losses":125,"wins":1489}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":39,"wins":476},"GB2-02":{"draws":144,"losses":31,"wins":305},"GB2-03":{"draws":62,"losses":40,"wins":394},"GB2-04":{"draws":114,"losses":29,"wins":355},"GB2-05":{"draws":0,"losses":53,"wins":477},"GB2-06":{"draws":17,"losses":73,"wins":412},"GB2-07":{"draws":0,"losses":140,"wins":390},"GB2-08":{"draws":0,"losses":51,"wins":487}},"medium":{"GB2-01":{"draws":226,"losses":98,"wins":192},"GB2-02":{"draws":121,"losses":61,"wins":298},"GB2-03":{"draws":1,"losses":428,"wins":67},"GB2-04":{"draws":101,"losses":44,"wins":353},"GB2-05":{"draws":0,"losses":108,"wins":422},"GB2-06":{"draws":20,"losses":34,"wins":448},"GB2-07":{"draws":0,"losses":79,"wins":451},"GB2-08":{"draws":0,"losses":49,"wins":489}},"none":{"GB2-01":{"draws":120,"losses":242,"wins":154},"GB2-02":{"draws":109,"losses":34,"wins":337},"GB2-03":{"draws":5,"losses":60,"wins":431},"GB2-04":{"draws":127,"losses":48,"wins":323},"GB2-05":{"draws":0,"losses":87,"wins":443},"GB2-06":{"draws":14,"losses":37,"wins":451},"GB2-07":{"draws":0,"losses":109,"wins":421},"GB2-08":{"draws":0,"losses":25,"wins":513}}},"per_game_raw_elo_all":{"GB2-01":1688.1617073207753,"GB2-02":1748.3359312756922,"GB2-03":1657.803838376222,"GB2-04":1777.0410950730923,"GB2-05":2085.2892103639433,"GB2-06":2185.856892509551,"GB2-07":1899.9752135203698,"GB2-08":2287.686601982146},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2078.928634657678,"GB2-02":1750.0857122798297,"GB2-03":1921.7662468887538,"GB2-04":1807.1020288116847,"GB2-05":2266.3540294150202,"GB2-06":2064.3361881375213,"GB2-07":1792.1349759218995,"GB2-08":2221.3697500744597},"medium":{"GB2-01":1578.562531370826,"GB2-02":1704.8661510928036,"GB2-03":1089.041675322725,"GB2-04":1783.4818398247555,"GB2-05":1940.8356321914048,"GB2-06":2246.617244695566,"GB2-07":2015.3463544148285,"GB2-08":2233.147136256041},"none":{"GB2-01":1406.9939559338225,"GB2-02":1790.0559304544438,"GB2-03":1962.6035929171871,"GB2-04":1740.5394165828366,"GB2-05":2048.677969485405,"GB2-06":2246.617244695566,"GB2-07":1892.4443102243815,"GB2-08":2408.5429196159375}},"per_game_tracks":{"highest":{"GB2-01":93.24533729514309,"GB2-02":79.70092142855077,"GB2-03":87.31867262184126,"GB2-04":83.7732384821655,"GB2-05":90.39909746459303,"GB2-06":85.33695749257953,"GB2-07":74.60495305505678,"GB2-08":91.33375388316408},"medium":{"GB2-01":61.26369818844768,"GB2-02":76.02462009144637,"GB2-03":15.555748198578847,"GB2-04":82.16433588826159,"GB2-05":80.97538597774685,"GB2-06":92.07690971682801,"GB2-07":85.11900196619425,"GB2-08":91.65819529296941},"none":{"GB2-01":43.48688257255377,"GB2-02":82.55572908210263,"GB2-03":88.7933534768271,"GB2-04":78.92295644625212,"GB2-05":84.6594551121839,"GB2-06":92.07690971682801,"GB2-07":79.96389758229779,"GB2-08":95.53798118955486}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":85.71411646538674,"medium":73.10473691505912,"none":80.74964564732502},"reasoning_agg":{"highest":{"max":93.24533729514309,"mean":85.71411646538674,"min":74.60495305505678},"medium":{"max":92.07690971682801,"mean":73.10473691505912,"min":15.555748198578847},"none":{"max":95.53798118955486,"mean":80.74964564732502,"min":43.48688257255377}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":12.609379550327617},"working_program_strength":{"all":79.8561663425903,"highest":85.71411646538674,"medium":73.10473691505912,"none":80.74964564732502}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:fa5332f27167944a","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":7.1388750000000005},"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":4.570124999999999},"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":33.78345000000001},"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":78.18214887741195,"highest":85.96214392189566,"medium":76.7097551311159,"none":71.8745475792243},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"too_slow"},"medium":{"GB2-06":"too_slow"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":72.76754598161416,"score":72.76754598161416},"GB2-02":{"attempts":6,"playable":74.82757172693198,"score":74.82757172693198},"GB2-03":{"attempts":6,"playable":77.70273081525544,"score":77.70273081525544},"GB2-04":{"attempts":6,"playable":58.39542514261901,"score":58.39542514261901},"GB2-05":{"attempts":6,"playable":90.47910138521463,"score":90.47910138521463},"GB2-06":{"attempts":1,"playable":88.94879409264351,"score":88.94879409264351},"GB2-07":{"attempts":4,"playable":85.44973588984284,"score":85.44973588984284},"GB2-08":{"attempts":6,"playable":81.9615156959325,"score":81.9615156959325}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":70.03426873625008,"score":70.03426873625008},"GB2-02":{"attempts":2,"playable":83.21801392577188,"score":83.21801392577188},"GB2-03":{"attempts":2,"playable":94.58495055901135,"score":94.58495055901135},"GB2-04":{"attempts":2,"playable":79.9029083009307,"score":79.9029083009307},"GB2-05":{"attempts":2,"playable":93.32938948312548,"score":93.32938948312548},"GB2-07":{"attempts":1,"playable":95.89860433452299,"score":95.89860433452299},"GB2-08":{"attempts":2,"playable":84.76687211365716,"score":84.76687211365716}},"medium":{"GB2-01":{"attempts":2,"playable":71.56611510892026,"score":71.56611510892026},"GB2-02":{"attempts":2,"playable":69.88539175509473,"score":69.88539175509473},"GB2-03":{"attempts":2,"playable":86.66445720597295,"score":86.66445720597295},"GB2-04":{"attempts":2,"playable":46.083157131439236,"score":46.083157131439236},"GB2-05":{"attempts":2,"playable":88.95880590457227,"score":88.95880590457227},"GB2-07":{"attempts":2,"playable":84.2852069245497,"score":84.2852069245497},"GB2-08":{"attempts":2,"playable":89.52515188726213,"score":89.52515188726213}},"none":{"GB2-01":{"attempts":2,"playable":76.70225409967216,"score":76.70225409967216},"GB2-02":{"attempts":2,"playable":71.37930949992932,"score":71.37930949992932},"GB2-03":{"attempts":2,"playable":51.858784680781994,"score":51.858784680781994},"GB2-04":{"attempts":2,"playable":49.2002099954871,"score":49.2002099954871},"GB2-05":{"attempts":2,"playable":89.14910876794619,"score":89.14910876794619},"GB2-06":{"attempts":1,"playable":88.94879409264351,"score":88.94879409264351},"GB2-07":{"attempts":1,"playable":76.16539641045584,"score":76.16539641045584},"GB2-08":{"attempts":2,"playable":71.5925230868782,"score":71.5925230868782}}},"id":"claude-opus-5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:13:06Z","match_totals_all":{"draws":2686,"losses":3669,"wins":14615},"match_totals_tracks":{"highest":{"draws":374,"losses":850,"wins":5422},"medium":{"draws":993,"losses":1240,"wins":4943},"none":{"draws":1319,"losses":1579,"wins":4250}},"model_slug":"claude-opus-5","official_rank_by_reasoning":{"highest":7,"medium":6,"none":9},"overall":{"max":95.89860433452299,"mean":78.18214887741195,"min":46.083157131439236},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.03426873625008,"GB2-02":83.21801392577188,"GB2-03":94.58495055901135,"GB2-04":79.9029083009307,"GB2-05":93.32938948312548,"GB2-07":95.89860433452299,"GB2-08":84.76687211365716},"per_game_all":{"GB2-01":72.76754598161416,"GB2-02":74.82757172693198,"GB2-03":77.70273081525544,"GB2-04":58.39542514261901,"GB2-05":90.47910138521463,"GB2-07":85.44973588984284,"GB2-08":81.9615156959325},"per_game_match_totals_all":{"GB2-01":{"draws":469,"losses":663,"wins":1964},"GB2-02":{"draws":996,"losses":265,"wins":1619},"GB2-03":{"draws":157,"losses":644,"wins":2175},"GB2-04":{"draws":1016,"losses":781,"wins":1191},"GB2-05":{"draws":0,"losses":316,"wins":2864},"GB2-06":{"draws":23,"losses":50,"wins":429},"GB2-07":{"draws":0,"losses":317,"wins":1803},"GB2-08":{"draws":25,"losses":633,"wins":2570}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":17,"losses":317,"wins":698},"GB2-02":{"draws":184,"losses":78,"wins":698},"GB2-03":{"draws":9,"losses":53,"wins":930},"GB2-04":{"draws":164,"losses":130,"wins":702},"GB2-05":{"draws":0,"losses":72,"wins":988},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":182,"wins":894}},"medium":{"GB2-01":{"draws":98,"losses":265,"wins":669},"GB2-02":{"draws":422,"losses":93,"wins":445},"GB2-03":{"draws":17,"losses":141,"wins":834},"GB2-04":{"draws":454,"losses":327,"wins":215},"GB2-05":{"draws":0,"losses":123,"wins":937},"GB2-07":{"draws":0,"losses":168,"wins":892},"GB2-08":{"draws":2,"losses":123,"wins":951}},"none":{"GB2-01":{"draws":354,"losses":81,"wins":597},"GB2-02":{"draws":390,"losses":94,"wins":476},"GB2-03":{"draws":131,"losses":450,"wins":411},"GB2-04":{"draws":398,"losses":324,"wins":274},"GB2-05":{"draws":0,"losses":121,"wins":939},"GB2-06":{"draws":23,"losses":50,"wins":429},"GB2-07":{"draws":0,"losses":131,"wins":399},"GB2-08":{"draws":23,"losses":328,"wins":725}}},"per_game_raw_elo_all":{"GB2-01":1747.4025792588072,"GB2-02":1701.2952979387485,"GB2-03":1847.8030277883345,"GB2-04":1559.838841094227,"GB2-05":2332.9632298912625,"GB2-07":2121.6595211619665,"GB2-08":1983.0737301661347},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.3222660113884,"GB2-02":1806.57584032557,"GB2-03":2191.058342058089,"GB2-04":1765.9564118516087,"GB2-05":2565.5440031214066,"GB2-07":2496.232053149095,"GB2-08":2039.0784567022022},"medium":{"GB2-01":1702.6282037773929,"GB2-02":1639.9402453040739,"GB2-03":1905.0609460643925,"GB2-04":1444.3999004869436,"GB2-05":2220.2649253770705,"GB2-07":2049.3073584655604,"GB2-08":2182.7621858643206},"none":{"GB2-01":1795.2572679876398,"GB2-02":1657.3698081866019,"GB2-03":1447.2897952425221,"GB2-04":1469.1602109441292,"GB2-05":2213.08076117531,"GB2-06":2153.5419917768895,"GB2-07":1819.4391518712437,"GB2-08":1727.3805479318814}},"per_game_tracks":{"highest":{"GB2-01":70.03426873625008,"GB2-02":83.21801392577188,"GB2-03":94.58495055901135,"GB2-04":79.9029083009307,"GB2-05":93.32938948312548,"GB2-07":95.89860433452299,"GB2-08":84.76687211365716},"medium":{"GB2-01":71.56611510892026,"GB2-02":69.88539175509473,"GB2-03":86.66445720597295,"GB2-04":46.083157131439236,"GB2-05":88.95880590457227,"GB2-07":84.2852069245497,"GB2-08":89.52515188726213},"none":{"GB2-01":76.70225409967216,"GB2-02":71.37930949992932,"GB2-03":51.858784680781994,"GB2-04":49.2002099954871,"GB2-05":89.14910876794619,"GB2-06":88.94879409264351,"GB2-07":76.16539641045584,"GB2-08":71.5925230868782}},"program_outcomes":{"all":{"counted_attempts":41,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":7,"worked_after_repair":0,"worked_first_time":41,"working":41},"highest":{"counted_attempts":13,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":3,"worked_after_repair":0,"worked_first_time":13,"working":13},"medium":{"counted_attempts":14,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":2,"worked_after_repair":0,"worked_first_time":14,"working":14},"none":{"counted_attempts":14,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":2,"worked_after_repair":0,"worked_first_time":14,"working":14}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:53:21Z","reasoning":{"highest":85.96214392189566,"medium":76.7097551311159,"none":71.8745475792243},"reasoning_agg":{"highest":{"max":95.89860433452299,"mean":85.96214392189566,"min":70.03426873625008},"medium":{"max":89.52515188726213,"mean":76.7097551311159,"min":46.083157131439236},"none":{"max":89.14910876794619,"mean":71.8745475792243,"min":49.2002099954871}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.087596342671361},"working_program_strength":{"all":78.18214887741195,"highest":85.96214392189566,"medium":76.7097551311159,"none":71.8745475792243}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:b754b73699a66f23","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":1.6543580000000002},"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":0.6265164999999999},"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":0.3455680000000001}},"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":0.345568},"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":2.626442500000001},"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":74.70908056407242,"highest":80.56337622544314,"medium":76.46214400550568,"none":67.10172146126845},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.281761818475864,"score":37.281761818475864},"GB2-02":{"attempts":3,"playable":68.60116963314528,"score":68.60116963314528},"GB2-03":{"attempts":3,"playable":83.83838913176025,"score":83.83838913176025},"GB2-04":{"attempts":3,"playable":68.3194261344825,"score":68.3194261344825},"GB2-05":{"attempts":3,"playable":87.7448973912911,"score":87.7448973912911},"GB2-06":{"attempts":3,"playable":82.18206684860988,"score":82.18206684860988},"GB2-07":{"attempts":3,"playable":82.0909850703336,"score":82.0909850703336},"GB2-08":{"attempts":3,"playable":87.61394848448093,"score":87.61394848448093}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":10.355998781952678,"score":10.355998781952678},"GB2-02":{"attempts":1,"playable":83.33909920462729,"score":83.33909920462729},"GB2-03":{"attempts":1,"playable":94.54196801264237,"score":94.54196801264237},"GB2-04":{"attempts":1,"playable":88.2719030663921,"score":88.2719030663921},"GB2-05":{"attempts":1,"playable":93.75035376834877,"score":93.75035376834877},"GB2-06":{"attempts":1,"playable":90.29471801815929,"score":90.29471801815929},"GB2-07":{"attempts":1,"playable":94.4070848170927,"score":94.4070848170927},"GB2-08":{"attempts":1,"playable":89.5458841343299,"score":89.5458841343299}},"medium":{"GB2-01":{"attempts":1,"playable":39.83815229576664,"score":39.83815229576664},"GB2-02":{"attempts":1,"playable":69.58132118145313,"score":69.58132118145313},"GB2-03":{"attempts":1,"playable":74.86928852730651,"score":74.86928852730651},"GB2-04":{"attempts":1,"playable":73.1310501220888,"score":73.1310501220888},"GB2-05":{"attempts":1,"playable":91.56564021557342,"score":91.56564021557342},"GB2-06":{"attempts":1,"playable":81.98257826751053,"score":81.98257826751053},"GB2-07":{"attempts":1,"playable":94.04021088909377,"score":94.04021088909377},"GB2-08":{"attempts":1,"playable":86.6889105452526,"score":86.6889105452526}},"none":{"GB2-01":{"attempts":1,"playable":61.65113437770828,"score":61.65113437770828},"GB2-02":{"attempts":1,"playable":52.88308851335539,"score":52.88308851335539},"GB2-03":{"attempts":1,"playable":82.10391085533185,"score":82.10391085533185},"GB2-04":{"attempts":1,"playable":43.555325214966615,"score":43.555325214966615},"GB2-05":{"attempts":1,"playable":77.91869818995113,"score":77.91869818995113},"GB2-06":{"attempts":1,"playable":74.26890426015981,"score":74.26890426015981},"GB2-07":{"attempts":1,"playable":57.82565950481432,"score":57.82565950481432},"GB2-08":{"attempts":1,"playable":86.6070507738603,"score":86.6070507738603}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-10-31T17:15:04Z","match_totals_all":{"draws":1548,"losses":2469,"wins":8253},"match_totals_tracks":{"highest":{"draws":236,"losses":700,"wins":3154},"medium":{"draws":614,"losses":702,"wins":2774},"none":{"draws":698,"losses":1067,"wins":2325}},"model_slug":"gpt-6-sol","official_rank_by_reasoning":{"highest":10,"medium":7,"none":10},"overall":{"max":94.54196801264237,"mean":74.70908056407242,"min":10.355998781952678},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.355998781952678,"GB2-02":83.33909920462729,"GB2-03":94.54196801264237,"GB2-04":88.2719030663921,"GB2-05":93.75035376834877,"GB2-06":90.29471801815929,"GB2-07":94.4070848170927,"GB2-08":89.5458841343299},"per_game_all":{"GB2-01":37.281761818475864,"GB2-02":68.60116963314528,"GB2-03":83.83838913176025,"GB2-04":68.3194261344825,"GB2-05":87.7448973912911,"GB2-06":82.18206684860988,"GB2-07":82.0909850703336,"GB2-08":87.61394848448093},"per_game_match_totals_all":{"GB2-01":{"draws":208,"losses":893,"wins":447},"GB2-02":{"draws":645,"losses":150,"wins":645},"GB2-03":{"draws":77,"losses":231,"wins":1180},"GB2-04":{"draws":514,"losses":236,"wins":744},"GB2-05":{"draws":0,"losses":204,"wins":1386},"GB2-06":{"draws":91,"losses":251,"wins":1164},"GB2-07":{"draws":0,"losses":289,"wins":1301},"GB2-08":{"draws":13,"losses":215,"wins":1386}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":29,"losses":453,"wins":34},"GB2-02":{"draws":131,"losses":19,"wins":330},"GB2-03":{"draws":4,"losses":27,"wins":465},"GB2-04":{"draws":52,"losses":36,"wins":410},"GB2-05":{"draws":0,"losses":33,"wins":497},"GB2-06":{"draws":20,"losses":44,"wins":438},"GB2-07":{"draws":0,"losses":26,"wins":504},"GB2-08":{"draws":0,"losses":62,"wins":476}},"medium":{"GB2-01":{"draws":163,"losses":239,"wins":114},"GB2-02":{"draws":215,"losses":46,"wins":219},"GB2-03":{"draws":40,"losses":120,"wins":336},"GB2-04":{"draws":153,"losses":65,"wins":280},"GB2-05":{"draws":0,"losses":46,"wins":484},"GB2-06":{"draws":36,"losses":82,"wins":384},"GB2-07":{"draws":0,"losses":28,"wins":502},"GB2-08":{"draws":7,"losses":76,"wins":455}},"none":{"GB2-01":{"draws":16,"losses":201,"wins":299},"GB2-02":{"draws":299,"losses":85,"wins":96},"GB2-03":{"draws":33,"losses":84,"wins":379},"GB2-04":{"draws":309,"losses":135,"wins":54},"GB2-05":{"draws":0,"losses":125,"wins":405},"GB2-06":{"draws":35,"losses":125,"wins":342},"GB2-07":{"draws":0,"losses":235,"wins":295},"GB2-08":{"draws":6,"losses":77,"wins":455}}},"per_game_raw_elo_all":{"GB2-01":1314.8207559780997,"GB2-02":1644.439184203896,"GB2-03":1895.08834458006,"GB2-04":1661.5626157735558,"GB2-05":2206.094126570524,"GB2-06":2005.799737648247,"GB2-07":2108.4318925867606,"GB2-08":2103.478982521185},"per_game_raw_elo_tracks":{"highest":{"GB2-01":990.1948324549496,"GB2-02":1801.9808016940688,"GB2-03":2187.9140145384026,"GB2-04":1884.9744085053246,"GB2-05":2432.593944975167,"GB2-06":2191.0870672423407,"GB2-07":2399.7730044275077,"GB2-08":2160.995575390022},"medium":{"GB2-01":1371.7884789048876,"GB2-02":1636.9593583461642,"GB2-03":1690.7993236853592,"GB2-04":1674.772951296967,"GB2-05":2319.7759188307245,"GB2-06":1990.4844487598348,"GB2-07":2378.241039730883,"GB2-08":2075.8649347324636},"none":{"GB2-01":1582.4789565744618,"GB2-02":1494.3773925714554,"GB2-03":1806.5516955164185,"GB2-04":1424.9404875183757,"GB2-05":1865.9125159056807,"GB2-06":1835.8276969425651,"GB2-07":1547.2816336018911,"GB2-08":2073.5764374410696}},"per_game_tracks":{"highest":{"GB2-01":10.355998781952678,"GB2-02":83.33909920462729,"GB2-03":94.54196801264237,"GB2-04":88.2719030663921,"GB2-05":93.75035376834877,"GB2-06":90.29471801815929,"GB2-07":94.4070848170927,"GB2-08":89.5458841343299},"medium":{"GB2-01":39.83815229576664,"GB2-02":69.58132118145313,"GB2-03":74.86928852730651,"GB2-04":73.1310501220888,"GB2-05":91.56564021557342,"GB2-06":81.98257826751053,"GB2-07":94.04021088909377,"GB2-08":86.6889105452526},"none":{"GB2-01":61.65113437770828,"GB2-02":52.88308851335539,"GB2-03":82.10391085533185,"GB2-04":43.555325214966615,"GB2-05":77.91869818995113,"GB2-06":74.26890426015981,"GB2-07":57.82565950481432,"GB2-08":86.6070507738603}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:50:40Z","reasoning":{"highest":80.56337622544314,"medium":76.46214400550568,"none":67.10172146126845},"reasoning_agg":{"highest":{"max":94.54196801264237,"mean":80.56337622544314,"min":10.355998781952678},"medium":{"max":94.04021088909377,"mean":76.46214400550568,"min":39.83815229576664},"none":{"max":86.6070507738603,"mean":67.10172146126845,"min":43.555325214966615}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":13.461654764174682},"working_program_strength":{"all":74.70908056407242,"highest":80.56337622544314,"medium":76.46214400550568,"none":67.10172146126845}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:3d87e03198419df8","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":6.37255375},"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":1.832505},"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":9.22798375},"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":68.84414719534266,"highest":81.47710949059469,"medium":67.99699073921174,"none":57.05834135622154},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":74.44067530836007,"score":74.44067530836007},"GB2-02":{"attempts":3,"playable":62.99857345264335,"score":62.99857345264335},"GB2-03":{"attempts":3,"playable":65.1955832043755,"score":65.1955832043755},"GB2-04":{"attempts":3,"playable":67.94049919104665,"score":67.94049919104665},"GB2-05":{"attempts":3,"playable":68.88502042698067,"score":68.88502042698067},"GB2-06":{"attempts":3,"playable":63.07483232146391,"score":63.07483232146391},"GB2-07":{"attempts":3,"playable":69.21344581719681,"score":69.21344581719681},"GB2-08":{"attempts":3,"playable":79.00454784067426,"score":79.00454784067426}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":75.18877501327353,"score":75.18877501327353},"GB2-02":{"attempts":1,"playable":76.02462009144637,"score":76.02462009144637},"GB2-03":{"attempts":1,"playable":79.93609632407606,"score":79.93609632407606},"GB2-04":{"attempts":1,"playable":83.67881986360881,"score":83.67881986360881},"GB2-05":{"attempts":1,"playable":75.91363551983989,"score":75.91363551983989},"GB2-06":{"attempts":1,"playable":86.06108849202411,"score":86.06108849202411},"GB2-07":{"attempts":1,"playable":88.73435808286737,"score":88.73435808286737},"GB2-08":{"attempts":1,"playable":86.27948253762135,"score":86.27948253762135}},"medium":{"GB2-01":{"attempts":1,"playable":68.78861511489926,"score":68.78861511489926},"GB2-02":{"attempts":1,"playable":67.75148442671198,"score":67.75148442671198},"GB2-03":{"attempts":1,"playable":62.212200952993,"score":62.212200952993},"GB2-04":{"attempts":1,"playable":78.73133575214854,"score":78.73133575214854},"GB2-05":{"attempts":1,"playable":77.19174638354706,"score":77.19174638354706},"GB2-06":{"attempts":1,"playable":41.24475134078261,"score":41.24475134078261},"GB2-07":{"attempts":1,"playable":71.29634025454476,"score":71.29634025454476},"GB2-08":{"attempts":1,"playable":76.75945168806665,"score":76.75945168806665}},"none":{"GB2-01":{"attempts":1,"playable":79.34463579690743,"score":79.34463579690743},"GB2-02":{"attempts":1,"playable":45.2196158397717,"score":45.2196158397717},"GB2-03":{"attempts":1,"playable":53.438452336057416,"score":53.438452336057416},"GB2-04":{"attempts":1,"playable":41.41134195738264,"score":41.41134195738264},"GB2-05":{"attempts":1,"playable":53.54967937755506,"score":53.54967937755506},"GB2-06":{"attempts":1,"playable":61.918657131585,"score":61.918657131585},"GB2-07":{"attempts":1,"playable":47.60963911417833,"score":47.60963911417833},"GB2-08":{"attempts":1,"playable":73.97470929633478,"score":73.97470929633478}}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-10-31T16:44:29Z","match_totals_all":{"draws":1672,"losses":3224,"wins":7374},"match_totals_tracks":{"highest":{"draws":295,"losses":665,"wins":3130},"medium":{"draws":544,"losses":1126,"wins":2420},"none":{"draws":833,"losses":1433,"wins":1824}},"model_slug":"gpt-5-6-sol","official_rank_by_reasoning":{"highest":9,"medium":13,"none":12},"overall":{"max":88.73435808286737,"mean":68.84414719534266,"min":41.24475134078261},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":75.18877501327353,"GB2-02":76.02462009144637,"GB2-03":79.93609632407606,"GB2-04":83.67881986360881,"GB2-05":75.91363551983989,"GB2-06":86.06108849202411,"GB2-07":88.73435808286737,"GB2-08":86.27948253762135},"per_game_all":{"GB2-01":74.44067530836007,"GB2-02":62.99857345264335,"GB2-03":65.1955832043755,"GB2-04":67.94049919104665,"GB2-05":68.88502042698067,"GB2-06":63.07483232146391,"GB2-07":69.21344581719681,"GB2-08":79.00454784067426},"per_game_match_totals_all":{"GB2-01":{"draws":124,"losses":365,"wins":1059},"GB2-02":{"draws":752,"losses":179,"wins":509},"GB2-03":{"draws":197,"losses":470,"wins":821},"GB2-04":{"draws":536,"losses":231,"wins":727},"GB2-05":{"draws":0,"losses":520,"wins":1070},"GB2-06":{"draws":18,"losses":596,"wins":892},"GB2-07":{"draws":0,"losses":508,"wins":1082},"GB2-08":{"draws":45,"losses":355,"wins":1214}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":132,"wins":371},"GB2-02":{"draws":177,"losses":33,"wins":270},"GB2-03":{"draws":5,"losses":110,"wins":381},"GB2-04":{"draws":89,"losses":42,"wins":367},"GB2-05":{"draws":0,"losses":136,"wins":394},"GB2-06":{"draws":11,"losses":72,"wins":419},"GB2-07":{"draws":0,"losses":58,"wins":472},"GB2-08":{"draws":0,"losses":82,"wins":456}},"medium":{"GB2-01":{"draws":110,"losses":117,"wins":289},"GB2-02":{"draws":217,"losses":54,"wins":209},"GB2-03":{"draws":52,"losses":180,"wins":264},"GB2-04":{"draws":129,"losses":48,"wins":321},"GB2-05":{"draws":0,"losses":129,"wins":401},"GB2-06":{"draws":5,"losses":315,"wins":182},"GB2-07":{"draws":0,"losses":159,"wins":371},"GB2-08":{"draws":31,"losses":124,"wins":383}},"none":{"GB2-01":{"draws":1,"losses":116,"wins":399},"GB2-02":{"draws":358,"losses":92,"wins":30},"GB2-03":{"draws":140,"losses":180,"wins":176},"GB2-04":{"draws":318,"losses":141,"wins":39},"GB2-05":{"draws":0,"losses":255,"wins":275},"GB2-06":{"draws":2,"losses":209,"wins":291},"GB2-07":{"draws":0,"losses":291,"wins":239},"GB2-08":{"draws":14,"losses":149,"wins":375}}},"per_game_raw_elo_all":{"GB2-01":1726.7821277954736,"GB2-02":1586.486140767526,"GB2-03":1591.1007115364027,"GB2-04":1650.6947281579994,"GB2-05":1717.8727404408212,"GB2-06":1658.6207126958452,"GB2-07":1762.1839877709688,"GB2-08":1890.151124257792},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1733.4014474439384,"GB2-02":1704.8661510928036,"GB2-03":1767.8843689476173,"GB2-04":1805.6657828846576,"GB2-05":1822.3902490930673,"GB2-06":2081.2127822950847,"GB2-07":2131.0249106873816,"GB2-08":2064.487902514875},"medium":{"GB2-01":1657.8777927227104,"GB2-02":1619.5278550634034,"GB2-03":1544.1740448733935,"GB2-04":1738.163366243804,"GB2-05":1849.674753198548,"GB2-06":1283.2713381286126,"GB2-07":1737.9419895990486,"GB2-08":1832.740572551831},"none":{"GB2-01":1789.0671432197723,"GB2-02":1435.0644161463706,"GB2-03":1461.2437207881972,"GB2-04":1408.2550353455363,"GB2-05":1481.5532190308488,"GB2-06":1611.3780176638384,"GB2-07":1417.5850630264756,"GB2-08":1773.2248977066697}},"per_game_tracks":{"highest":{"GB2-01":75.18877501327353,"GB2-02":76.02462009144637,"GB2-03":79.93609632407606,"GB2-04":83.67881986360881,"GB2-05":75.91363551983989,"GB2-06":86.06108849202411,"GB2-07":88.73435808286737,"GB2-08":86.27948253762135},"medium":{"GB2-01":68.78861511489926,"GB2-02":67.75148442671198,"GB2-03":62.212200952993,"GB2-04":78.73133575214854,"GB2-05":77.19174638354706,"GB2-06":41.24475134078261,"GB2-07":71.29634025454476,"GB2-08":76.75945168806665},"none":{"GB2-01":79.34463579690743,"GB2-02":45.2196158397717,"GB2-03":53.438452336057416,"GB2-04":41.41134195738264,"GB2-05":53.54967937755506,"GB2-06":61.918657131585,"GB2-07":47.60963911417833,"GB2-08":73.97470929633478}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:03:22Z","reasoning":{"highest":81.47710949059469,"medium":67.99699073921174,"none":57.05834135622154},"reasoning_agg":{"highest":{"max":88.73435808286737,"mean":81.47710949059469,"min":75.18877501327353},"medium":{"max":78.73133575214854,"mean":67.99699073921174,"min":41.24475134078261},"none":{"max":79.34463579690743,"mean":57.05834135622154,"min":41.41134195738264}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.418768134373146},"working_program_strength":{"all":68.84414719534266,"highest":81.47710949059469,"medium":67.99699073921174,"none":57.05834135622154}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:f502312e3827252c","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":2.3088499999999996}},"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":18.260499999999997},"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":67.68382322344887,"highest":76.98462970687639,"medium":65.91579411409742,"none":60.15104584937278},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":78.09372643681886,"score":78.09372643681886},"GB2-02":{"attempts":3,"playable":60.71261058436659,"score":60.71261058436659},"GB2-03":{"attempts":3,"playable":47.78691911514147,"score":47.78691911514147},"GB2-04":{"attempts":3,"playable":58.98861867965413,"score":58.98861867965413},"GB2-05":{"attempts":3,"playable":64.91022142312562,"score":64.91022142312562},"GB2-06":{"attempts":3,"playable":82.03938657572753,"score":82.03938657572753},"GB2-07":{"attempts":3,"playable":67.23586591211709,"score":67.23586591211709},"GB2-08":{"attempts":3,"playable":81.70323706063965,"score":81.70323706063965}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":86.1949155590539,"score":86.1949155590539},"GB2-02":{"attempts":1,"playable":79.9973428126415,"score":79.9973428126415},"GB2-03":{"attempts":1,"playable":86.88279366989603,"score":86.88279366989603},"GB2-04":{"attempts":1,"playable":84.71587746882274,"score":84.71587746882274},"GB2-05":{"attempts":1,"playable":56.79198063744251,"score":56.79198063744251},"GB2-06":{"attempts":1,"playable":87.59734406733439,"score":87.59734406733439},"GB2-07":{"attempts":1,"playable":65.85094237132958,"score":65.85094237132958},"GB2-08":{"attempts":1,"playable":67.84584106849046,"score":67.84584106849046}},"medium":{"GB2-01":{"attempts":1,"playable":76.23194773158602,"score":76.23194773158602},"GB2-02":{"attempts":1,"playable":58.39838167516045,"score":58.39838167516045},"GB2-03":{"attempts":1,"playable":21.498401547852268,"score":21.498401547852268},"GB2-04":{"attempts":1,"playable":53.191874906884294,"score":53.191874906884294},"GB2-05":{"attempts":1,"playable":69.24965373957292,"score":69.24965373957292},"GB2-06":{"attempts":1,"playable":81.89185465704799,"score":81.89185465704799},"GB2-07":{"attempts":1,"playable":73.91007021254674,"score":73.91007021254674},"GB2-08":{"attempts":1,"playable":92.95416844212878,"score":92.95416844212878}},"none":{"GB2-01":{"attempts":1,"playable":71.85431601981665,"score":71.85431601981665},"GB2-02":{"attempts":1,"playable":43.742107265297825,"score":43.742107265297825},"GB2-03":{"attempts":1,"playable":34.979562127676125,"score":34.979562127676125},"GB2-04":{"attempts":1,"playable":39.05810366325533,"score":39.05810366325533},"GB2-05":{"attempts":1,"playable":68.68902989236143,"score":68.68902989236143},"GB2-06":{"attempts":1,"playable":76.62896100280021,"score":76.62896100280021},"GB2-07":{"attempts":1,"playable":61.94658515247495,"score":61.94658515247495},"GB2-08":{"attempts":1,"playable":84.30970167129969,"score":84.30970167129969}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-10-31T16:44:22Z","match_totals_all":{"draws":1954,"losses":3184,"wins":7132},"match_totals_tracks":{"highest":{"draws":310,"losses":869,"wins":2911},"medium":{"draws":734,"losses":1075,"wins":2281},"none":{"draws":910,"losses":1240,"wins":1940}},"model_slug":"claude-fable-5","official_rank_by_reasoning":{"highest":12,"medium":16,"none":11},"overall":{"max":92.95416844212878,"mean":67.68382322344887,"min":21.498401547852268},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.1949155590539,"GB2-02":79.9973428126415,"GB2-03":86.88279366989603,"GB2-04":84.71587746882274,"GB2-05":56.79198063744251,"GB2-06":87.59734406733439,"GB2-07":65.85094237132958,"GB2-08":67.84584106849046},"per_game_all":{"GB2-01":78.09372643681886,"GB2-02":60.71261058436659,"GB2-03":47.78691911514147,"GB2-04":58.98861867965413,"GB2-05":64.91022142312562,"GB2-06":82.03938657572753,"GB2-07":67.23586591211709,"GB2-08":81.70323706063965},"per_game_match_totals_all":{"GB2-01":{"draws":103,"losses":317,"wins":1128},"GB2-02":{"draws":757,"losses":209,"wins":474},"GB2-03":{"draws":336,"losses":646,"wins":506},"GB2-04":{"draws":665,"losses":302,"wins":527},"GB2-05":{"draws":0,"losses":585,"wins":1005},"GB2-06":{"draws":58,"losses":270,"wins":1178},"GB2-07":{"draws":0,"losses":546,"wins":1044},"GB2-08":{"draws":35,"losses":309,"wins":1270}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":79,"wins":436},"GB2-02":{"draws":127,"losses":38,"wins":315},"GB2-03":{"draws":51,"losses":48,"wins":397},"GB2-04":{"draws":74,"losses":44,"wins":380},"GB2-05":{"draws":0,"losses":238,"wins":292},"GB2-06":{"draws":22,"losses":58,"wins":422},"GB2-07":{"draws":0,"losses":190,"wins":340},"GB2-08":{"draws":35,"losses":174,"wins":329}},"medium":{"GB2-01":{"draws":38,"losses":114,"wins":364},"GB2-02":{"draws":282,"losses":67,"wins":131},"GB2-03":{"draws":97,"losses":353,"wins":46},"GB2-04":{"draws":288,"losses":98,"wins":112},"GB2-05":{"draws":0,"losses":172,"wins":358},"GB2-06":{"draws":29,"losses":86,"wins":387},"GB2-07":{"draws":0,"losses":144,"wins":386},"GB2-08":{"draws":0,"losses":41,"wins":497}},"none":{"GB2-01":{"draws":64,"losses":124,"wins":328},"GB2-02":{"draws":348,"losses":104,"wins":28},"GB2-03":{"draws":188,"losses":245,"wins":63},"GB2-04":{"draws":303,"losses":160,"wins":35},"GB2-05":{"draws":0,"losses":175,"wins":355},"GB2-06":{"draws":7,"losses":126,"wins":369},"GB2-07":{"draws":0,"losses":212,"wins":318},"GB2-08":{"draws":0,"losses":94,"wins":444}}},"per_game_raw_elo_all":{"GB2-01":1780.3059567822354,"GB2-02":1572.0123701459063,"GB2-03":1458.1358650057675,"GB2-04":1570.3953655842722,"GB2-05":1638.1441175376694,"GB2-06":1996.2628163338832,"GB2-07":1679.689287689401,"GB2-08":1982.9923391585617},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1901.3154791082225,"GB2-02":1754.0111293283594,"GB2-03":1910.5472053972526,"GB2-04":1821.8196893133274,"GB2-05":1522.8046382739633,"GB2-06":2118.540764743192,"GB2-07":1656.5235921041647,"GB2-08":1653.5676730574642},"medium":{"GB2-01":1746.7683142089038,"GB2-02":1538.3720351006152,"GB2-03":1164.7543184605752,"GB2-04":1499.6214408722062,"GB2-05":1700.353551660383,"GB2-06":1988.5647485551476,"GB2-07":1780.3701498652777,"GB2-08":2283.5093948901745},"none":{"GB2-01":1692.8340770295795,"GB2-02":1423.6539460087445,"GB2-03":1299.106071159475,"GB2-04":1389.7449665672827,"GB2-05":1691.2741626786617,"GB2-06":1881.6829357033098,"GB2-07":1602.1741210987616,"GB2-08":2011.8999495280464}},"per_game_tracks":{"highest":{"GB2-01":86.1949155590539,"GB2-02":79.9973428126415,"GB2-03":86.88279366989603,"GB2-04":84.71587746882274,"GB2-05":56.79198063744251,"GB2-06":87.59734406733439,"GB2-07":65.85094237132958,"GB2-08":67.84584106849046},"medium":{"GB2-01":76.23194773158602,"GB2-02":58.39838167516045,"GB2-03":21.498401547852268,"GB2-04":53.191874906884294,"GB2-05":69.24965373957292,"GB2-06":81.89185465704799,"GB2-07":73.91007021254674,"GB2-08":92.95416844212878},"none":{"GB2-01":71.85431601981665,"GB2-02":43.742107265297825,"GB2-03":34.979562127676125,"GB2-04":39.05810366325533,"GB2-05":68.68902989236143,"GB2-06":76.62896100280021,"GB2-07":61.94658515247495,"GB2-08":84.30970167129969}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:48:13Z","reasoning":{"highest":76.98462970687639,"medium":65.91579411409742,"none":60.15104584937278},"reasoning_agg":{"highest":{"max":87.59734406733439,"mean":76.98462970687639,"min":56.79198063744251},"medium":{"max":92.95416844212878,"mean":65.91579411409742,"min":21.498401547852268},"none":{"max":84.30970167129969,"mean":60.15104584937278,"min":34.979562127676125}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.833583857503612},"working_program_strength":{"all":67.68382322344887,"highest":76.98462970687639,"medium":65.91579411409742,"none":60.15104584937278}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-wonder:9b8b47ef6c870217","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":0.9656475999999999},"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":3.9007552}},"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":6.868588399999998},"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":66.34025398955627,"highest":78.79083939867014,"medium":63.38099491260955,"none":56.8489276573891},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":68.99318337961354,"score":68.99318337961354},"GB2-02":{"attempts":3,"playable":55.31750494356309,"score":55.31750494356309},"GB2-03":{"attempts":3,"playable":45.671449743806,"score":45.671449743806},"GB2-04":{"attempts":3,"playable":58.320459775594394,"score":58.320459775594394},"GB2-05":{"attempts":3,"playable":87.86612610409583,"score":87.86612610409583},"GB2-06":{"attempts":3,"playable":76.83513450544008,"score":76.83513450544008},"GB2-07":{"attempts":3,"playable":71.87854268394055,"score":71.87854268394055},"GB2-08":{"attempts":3,"playable":65.83963078039663,"score":65.83963078039663}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":85.09999163803012,"score":85.09999163803012},"GB2-02":{"attempts":1,"playable":66.83387359572146,"score":66.83387359572146},"GB2-03":{"attempts":1,"playable":82.90984076156815,"score":82.90984076156815},"GB2-04":{"attempts":1,"playable":81.5945853783887,"score":81.5945853783887},"GB2-05":{"attempts":1,"playable":93.07420359693637,"score":93.07420359693637},"GB2-06":{"attempts":1,"playable":84.61228190209295,"score":84.61228190209295},"GB2-07":{"attempts":1,"playable":74.08387133123723,"score":74.08387133123723},"GB2-08":{"attempts":1,"playable":62.11806698538614,"score":62.11806698538614}},"medium":{"GB2-01":{"attempts":1,"playable":52.89892153996082,"score":52.89892153996082},"GB2-02":{"attempts":1,"playable":56.010458517238284,"score":56.010458517238284},"GB2-03":{"attempts":1,"playable":36.78117525961954,"score":36.78117525961954},"GB2-04":{"attempts":1,"playable":39.570112478073014,"score":39.570112478073014},"GB2-05":{"attempts":1,"playable":85.34794643816096,"score":85.34794643816096},"GB2-06":{"attempts":1,"playable":76.90120533388199,"score":76.90120533388199},"GB2-07":{"attempts":1,"playable":87.52594134195262,"score":87.52594134195262},"GB2-08":{"attempts":1,"playable":72.0121983919892,"score":72.0121983919892}},"none":{"GB2-01":{"attempts":1,"playable":68.9806369608497,"score":68.9806369608497},"GB2-02":{"attempts":1,"playable":43.108182717729534,"score":43.108182717729534},"GB2-03":{"attempts":1,"playable":17.323333210230302,"score":17.323333210230302},"GB2-04":{"attempts":1,"playable":53.79668147032146,"score":53.79668147032146},"GB2-05":{"attempts":1,"playable":85.17622827719016,"score":85.17622827719016},"GB2-06":{"attempts":1,"playable":68.9919162803453,"score":68.9919162803453},"GB2-07":{"attempts":1,"playable":54.025815378631805,"score":54.025815378631805},"GB2-08":{"attempts":1,"playable":63.38862696381457,"score":63.38862696381457}}},"id":"meta/muse-wonder","is_recent_addition":false,"last_measured_at":"2026-10-31T17:11:15Z","match_totals_all":{"draws":2242,"losses":3210,"wins":6818},"match_totals_tracks":{"highest":{"draws":530,"losses":670,"wins":2890},"medium":{"draws":667,"losses":1223,"wins":2200},"none":{"draws":1045,"losses":1317,"wins":1728}},"model_slug":"meta-muse-wonder","official_rank_by_reasoning":{"highest":11,"medium":19,"none":13},"overall":{"max":93.07420359693637,"mean":66.34025398955627,"min":17.323333210230302},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":85.09999163803012,"GB2-02":66.83387359572146,"GB2-03":82.90984076156815,"GB2-04":81.5945853783887,"GB2-05":93.07420359693637,"GB2-06":84.61228190209295,"GB2-07":74.08387133123723,"GB2-08":62.11806698538614},"per_game_all":{"GB2-01":68.99318337961354,"GB2-02":55.31750494356309,"GB2-03":45.671449743806,"GB2-04":58.320459775594394,"GB2-05":87.86612610409583,"GB2-06":76.83513450544008,"GB2-07":71.87854268394055,"GB2-08":65.83963078039663},"per_game_match_totals_all":{"GB2-01":{"draws":173,"losses":424,"wins":951},"GB2-02":{"draws":933,"losses":201,"wins":306},"GB2-03":{"draws":276,"losses":709,"wins":503},"GB2-04":{"draws":585,"losses":353,"wins":556},"GB2-05":{"draws":0,"losses":204,"wins":1386},"GB2-06":{"draws":96,"losses":337,"wins":1073},"GB2-07":{"draws":0,"losses":464,"wins":1126},"GB2-08":{"draws":179,"losses":518,"wins":917}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":83,"wins":428},"GB2-02":{"draws":268,"losses":33,"wins":179},"GB2-03":{"draws":84,"losses":54,"wins":358},"GB2-04":{"draws":63,"losses":66,"wins":369},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-06":{"draws":31,"losses":70,"wins":401},"GB2-07":{"draws":0,"losses":143,"wins":387},"GB2-08":{"draws":79,"losses":184,"wins":275}},"medium":{"GB2-01":{"draws":4,"losses":252,"wins":260},"GB2-02":{"draws":293,"losses":73,"wins":114},"GB2-03":{"draws":103,"losses":279,"wins":114},"GB2-04":{"draws":214,"losses":202,"wins":82},"GB2-05":{"draws":0,"losses":83,"wins":447},"GB2-06":{"draws":28,"losses":114,"wins":360},"GB2-07":{"draws":0,"losses":65,"wins":465},"GB2-08":{"draws":25,"losses":155,"wins":358}},"none":{"GB2-01":{"draws":164,"losses":89,"wins":263},"GB2-02":{"draws":372,"losses":95,"wins":13},"GB2-03":{"draws":89,"losses":376,"wins":31},"GB2-04":{"draws":308,"losses":85,"wins":105},"GB2-05":{"draws":0,"losses":84,"wins":446},"GB2-06":{"draws":37,"losses":153,"wins":312},"GB2-07":{"draws":0,"losses":256,"wins":274},"GB2-08":{"draws":75,"losses":179,"wins":284}}},"per_game_raw_elo_all":{"GB2-01":1679.1978291826747,"GB2-02":1516.2889226856707,"GB2-03":1416.906905737061,"GB2-04":1557.895628201811,"GB2-05":2177.4794892666637,"GB2-06":1890.5338108035314,"GB2-07":1790.0518832077769,"GB2-08":1621.8391230847203},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1880.9111955094513,"GB2-02":1611.0235642074047,"GB2-03":1822.070069308933,"GB2-04":1775.5192343657586,"GB2-05":2395.4678721554847,"GB2-06":2047.8299113873663,"GB2-07":1783.2916722497234,"GB2-08":1555.895107301954},"medium":{"GB2-01":1496.66992175345,"GB2-02":1519.096715369912,"GB2-03":1315.2347717902044,"GB2-04":1393.7943397880306,"GB2-05":2071.3532474544463,"GB2-06":1887.0407081667763,"GB2-07":2088.601904605313,"GB2-08":1733.200300605045},"none":{"GB2-01":1660.012370285123,"GB2-02":1418.7464884796957,"GB2-03":1113.4158761120452,"GB2-04":1504.3733104516439,"GB2-05":2065.6173481900605,"GB2-06":1736.730812856452,"GB2-07":1498.2620727682945,"GB2-08":1576.421961347162}},"per_game_tracks":{"highest":{"GB2-01":85.09999163803012,"GB2-02":66.83387359572146,"GB2-03":82.90984076156815,"GB2-04":81.5945853783887,"GB2-05":93.07420359693637,"GB2-06":84.61228190209295,"GB2-07":74.08387133123723,"GB2-08":62.11806698538614},"medium":{"GB2-01":52.89892153996082,"GB2-02":56.010458517238284,"GB2-03":36.78117525961954,"GB2-04":39.570112478073014,"GB2-05":85.34794643816096,"GB2-06":76.90120533388199,"GB2-07":87.52594134195262,"GB2-08":72.0121983919892},"none":{"GB2-01":68.9806369608497,"GB2-02":43.108182717729534,"GB2-03":17.323333210230302,"GB2-04":53.79668147032146,"GB2-05":85.17622827719016,"GB2-06":68.9919162803453,"GB2-07":54.025815378631805,"GB2-08":63.38862696381457}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T16:50:59Z","reasoning":{"highest":78.79083939867014,"medium":63.38099491260955,"none":56.8489276573891},"reasoning_agg":{"highest":{"max":93.07420359693637,"mean":78.79083939867014,"min":62.11806698538614},"medium":{"max":87.52594134195262,"mean":63.38099491260955,"min":36.78117525961954},"none":{"max":85.17622827719016,"mean":56.8489276573891,"min":17.323333210230302}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":21.941911741281046},"working_program_strength":{"all":66.34025398955627,"highest":78.79083939867014,"medium":63.38099491260955,"none":56.8489276573891}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:0d963419cc256497","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":4.397416199999999},"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":0.43181687999999996}},"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":1.25555516},"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":0.43181688},"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":4.397416199999999}},"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":6.08478824},"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":65.93616410270165,"highest":73.47595743609465,"medium":71.97755045577898,"none":52.354984416231325},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.96779901510972,"score":39.97853267673981},"GB2-02":{"attempts":3,"playable":57.27378496453699,"score":57.27378496453699},"GB2-03":{"attempts":3,"playable":68.43669798275691,"score":68.43669798275691},"GB2-04":{"attempts":3,"playable":69.67882773032214,"score":69.67882773032214},"GB2-05":{"attempts":3,"playable":72.3554665191429,"score":72.3554665191429},"GB2-06":{"attempts":3,"playable":77.68755963015803,"score":77.68755963015803},"GB2-07":{"attempts":3,"playable":75.69659415117621,"score":75.69659415117621},"GB2-08":{"attempts":3,"playable":66.38184916678016,"score":66.38184916678016}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":73.51990364268744,"score":73.51990364268744},"GB2-03":{"attempts":1,"playable":84.33314862660123,"score":84.33314862660123},"GB2-04":{"attempts":1,"playable":76.90584266447512,"score":76.90584266447512},"GB2-05":{"attempts":1,"playable":90.23257928644439,"score":90.23257928644439},"GB2-06":{"attempts":1,"playable":91.27700342461371,"score":91.27700342461371},"GB2-07":{"attempts":1,"playable":78.58501340180649,"score":78.58501340180649},"GB2-08":{"attempts":1,"playable":92.95416844212878,"score":92.95416844212878}},"medium":{"GB2-01":{"attempts":1,"playable":51.53118177573665,"score":51.53118177573665},"GB2-02":{"attempts":1,"playable":54.03139479603072,"score":54.03139479603072},"GB2-03":{"attempts":1,"playable":78.10919628314772,"score":78.10919628314772},"GB2-04":{"attempts":1,"playable":83.48989863347825,"score":83.48989863347825},"GB2-05":{"attempts":1,"playable":67.19089355992637,"score":67.19089355992637},"GB2-06":{"attempts":1,"playable":92.34266337804645,"score":92.34266337804645},"GB2-07":{"attempts":1,"playable":76.68464797727704,"score":76.68464797727704},"GB2-08":{"attempts":1,"playable":72.44052724258854,"score":72.44052724258854}},"none":{"GB2-01":{"attempts":1,"playable":68.40441625448278,"score":68.40441625448278},"GB2-02":{"attempts":1,"playable":44.27005645489282,"score":44.27005645489282},"GB2-03":{"attempts":1,"playable":42.86774903852179,"score":42.86774903852179},"GB2-04":{"attempts":1,"playable":48.64074189301308,"score":48.64074189301308},"GB2-05":{"attempts":1,"playable":59.64292671105791,"score":59.64292671105791},"GB2-06":{"attempts":1,"playable":49.443012087813955,"score":49.443012087813955},"GB2-07":{"attempts":1,"playable":71.82012107444513,"score":71.82012107444513},"GB2-08":{"attempts":1,"playable":33.75085181562314,"score":33.75085181562314}}},"id":"z-ai/glm-5.3","is_recent_addition":false,"last_measured_at":"2026-10-31T17:09:35Z","match_totals_all":{"draws":2003,"losses":2863,"wins":6888},"match_totals_tracks":{"highest":{"draws":381,"losses":414,"wins":2779},"medium":{"draws":591,"losses":923,"wins":2576},"none":{"draws":1031,"losses":1526,"wins":1533}},"model_slug":"z-ai-glm-5-3","official_rank_by_reasoning":{"highest":13,"medium":11,"none":16},"overall":{"max":92.95416844212878,"mean":65.93616410270165,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-02":73.51990364268744,"GB2-03":84.33314862660123,"GB2-04":76.90584266447512,"GB2-05":90.23257928644439,"GB2-06":91.27700342461371,"GB2-07":78.58501340180649,"GB2-08":92.95416844212878},"per_game_all":{"GB2-02":57.27378496453699,"GB2-03":68.43669798275691,"GB2-04":69.67882773032214,"GB2-05":72.3554665191429,"GB2-06":77.68755963015803,"GB2-07":75.69659415117621,"GB2-08":66.38184916678016},"per_game_match_totals_all":{"GB2-01":{"draws":170,"losses":350,"wins":512},"GB2-02":{"draws":919,"losses":179,"wins":342},"GB2-03":{"draws":160,"losses":432,"wins":896},"GB2-04":{"draws":566,"losses":191,"wins":737},"GB2-05":{"draws":0,"losses":460,"wins":1130},"GB2-06":{"draws":56,"losses":339,"wins":1111},"GB2-07":{"draws":0,"losses":401,"wins":1189},"GB2-08":{"draws":132,"losses":511,"wins":971}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":214,"losses":27,"wins":239},"GB2-03":{"draws":4,"losses":86,"wins":406},"GB2-04":{"draws":138,"losses":53,"wins":307},"GB2-05":{"draws":0,"losses":54,"wins":476},"GB2-06":{"draws":25,"losses":36,"wins":441},"GB2-07":{"draws":0,"losses":117,"wins":413},"GB2-08":{"draws":0,"losses":41,"wins":497}},"medium":{"GB2-01":{"draws":88,"losses":217,"wins":211},"GB2-02":{"draws":326,"losses":66,"wins":88},"GB2-03":{"draws":27,"losses":109,"wins":360},"GB2-04":{"draws":97,"losses":39,"wins":362},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":23,"losses":31,"wins":448},"GB2-07":{"draws":0,"losses":128,"wins":402},"GB2-08":{"draws":30,"losses":150,"wins":358}},"none":{"GB2-01":{"draws":82,"losses":133,"wins":301},"GB2-02":{"draws":379,"losses":86,"wins":15},"GB2-03":{"draws":129,"losses":237,"wins":130},"GB2-04":{"draws":331,"losses":99,"wins":68},"GB2-05":{"draws":0,"losses":223,"wins":307},"GB2-06":{"draws":8,"losses":272,"wins":222},"GB2-07":{"draws":0,"losses":156,"wins":374},"GB2-08":{"draws":102,"losses":320,"wins":116}}},"per_game_raw_elo_all":{"GB2-02":1536.0623849133935,"GB2-03":1652.6797064707605,"GB2-04":1661.1136088478827,"GB2-05":1828.9574270693995,"GB2-06":1961.7920387899576,"GB2-07":1813.2499519660687,"GB2-08":1741.9454808665987},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1677.0554864257103,"GB2-03":1851.265687312049,"GB2-04":1716.2928917512877,"GB2-05":2259.028979350873,"GB2-06":2220.710781553527,"GB2-07":1864.688054517766,"GB2-08":2283.5093948901745},"medium":{"GB2-01":1483.5964086275437,"GB2-02":1503.3967199490573,"GB2-03":1738.2273578099362,"GB2-04":1802.811742496341,"GB2-05":1667.6926763956014,"GB2-06":2255.647274979163,"GB2-07":1828.8265728989181,"GB2-08":1741.7998785274744},"none":{"GB2-01":1653.6268861196454,"GB2-02":1427.7349483654125,"GB2-03":1368.5460742902962,"GB2-04":1464.2361922960195,"GB2-05":1560.1506254617245,"GB2-06":1409.0180598371824,"GB2-07":1746.2352284815217,"GB2-08":1200.5271691821474}},"per_game_tracks":{"highest":{"GB2-02":73.51990364268744,"GB2-03":84.33314862660123,"GB2-04":76.90584266447512,"GB2-05":90.23257928644439,"GB2-06":91.27700342461371,"GB2-07":78.58501340180649,"GB2-08":92.95416844212878},"medium":{"GB2-01":51.53118177573665,"GB2-02":54.03139479603072,"GB2-03":78.10919628314772,"GB2-04":83.48989863347825,"GB2-05":67.19089355992637,"GB2-06":92.34266337804645,"GB2-07":76.68464797727704,"GB2-08":72.44052724258854},"none":{"GB2-01":68.40441625448278,"GB2-02":44.27005645489282,"GB2-03":42.86774903852179,"GB2-04":48.64074189301308,"GB2-05":59.64292671105791,"GB2-06":49.443012087813955,"GB2-07":71.82012107444513,"GB2-08":33.75085181562314}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:05:10Z","reasoning":{"highest":73.47595743609465,"medium":71.97755045577898,"none":52.354984416231325},"reasoning_agg":{"highest":{"max":92.95416844212878,"mean":73.47595743609465,"min":0.0},"medium":{"max":92.34266337804645,"mean":71.97755045577898,"min":51.53118177573665},"none":{"max":71.82012107444513,"mean":52.354984416231325,"min":33.75085181562314}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":21.12097301986332},"working_program_strength":{"all":69.43501921870616,"highest":83.97252278410816,"medium":71.97755045577898,"none":52.354984416231325}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:04004322efc61b5f","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":3.189754},"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":0.6637360000000001}},"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":10.089050000000002},"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":64.88490343671403,"highest":72.97673557711678,"medium":73.40962586257214,"none":48.26834887045318},"first_seen_at":null,"game_gaps":{"highest":{"GB2-04":"failed"},"medium":{"GB2-06":"failed"},"none":{"GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":55.5817417201313,"score":55.5817417201313},"GB2-02":{"attempts":3,"playable":74.30399768656538,"score":74.30399768656538},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":80.0874548128541,"score":53.391636541902734},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":67.6352437611688,"score":45.09016250744586},"GB2-05":{"attempts":3,"playable":76.3654319448687,"score":76.3654319448687},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":86.68103154526531,"score":57.78735436351021},"GB2-07":{"attempts":3,"playable":70.07622985310644,"score":70.07622985310644},"GB2-08":{"attempts":3,"playable":86.48267287618164,"score":86.48267287618164}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":59.22719662255418,"score":59.22719662255418},"GB2-02":{"attempts":1,"playable":89.06347621855328,"score":89.06347621855328},"GB2-03":{"attempts":1,"playable":87.84039375664256,"score":87.84039375664256},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":93.41174923079485,"score":93.41174923079485},"GB2-06":{"attempts":1,"playable":90.56306185486608,"score":90.56306185486608},"GB2-07":{"attempts":1,"playable":78.41247250475357,"score":78.41247250475357},"GB2-08":{"attempts":1,"playable":85.29553442876971,"score":85.29553442876971}},"medium":{"GB2-01":{"attempts":1,"playable":80.0011797514601,"score":80.0011797514601},"GB2-02":{"attempts":1,"playable":81.27891545038818,"score":81.27891545038818},"GB2-03":{"attempts":1,"playable":72.33451586906564,"score":72.33451586906564},"GB2-04":{"attempts":1,"playable":92.4293167178963,"score":92.4293167178963},"GB2-05":{"attempts":1,"playable":93.07420359693637,"score":93.07420359693637},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":76.3385285884776,"score":76.3385285884776},"GB2-08":{"attempts":1,"playable":91.8203469263529,"score":91.8203469263529}},"none":{"GB2-01":{"attempts":1,"playable":27.516848786379583,"score":27.516848786379583},"GB2-02":{"attempts":1,"playable":52.56960139075472,"score":52.56960139075472},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":42.841170804441276,"score":42.841170804441276},"GB2-05":{"attempts":1,"playable":42.61034300687487,"score":42.61034300687487},"GB2-06":{"attempts":1,"playable":82.79900123566456,"score":82.79900123566456},"GB2-07":{"attempts":1,"playable":55.477688466088146,"score":55.477688466088146},"GB2-08":{"attempts":1,"playable":82.3321372734223,"score":82.3321372734223}}},"id":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-10-31T11:42:27Z","match_totals_all":{"draws":1024,"losses":2415,"wins":7335},"match_totals_tracks":{"highest":{"draws":156,"losses":560,"wins":2876},"medium":{"draws":208,"losses":512,"wins":2868},"none":{"draws":660,"losses":1343,"wins":1591}},"model_slug":"x-ai-grok-4-7","official_rank_by_reasoning":{"highest":14,"medium":8,"none":25},"overall":{"max":93.41174923079485,"mean":64.88490343671403,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.22719662255418,"GB2-02":89.06347621855328,"GB2-03":87.84039375664256,"GB2-05":93.41174923079485,"GB2-06":90.56306185486608,"GB2-07":78.41247250475357,"GB2-08":85.29553442876971},"per_game_all":{"GB2-01":55.5817417201313,"GB2-02":74.30399768656538,"GB2-05":76.3654319448687,"GB2-07":70.07622985310644,"GB2-08":86.48267287618164},"per_game_match_totals_all":{"GB2-01":{"draws":202,"losses":616,"wins":730},"GB2-02":{"draws":492,"losses":140,"wins":808},"GB2-03":{"draws":109,"losses":167,"wins":716},"GB2-04":{"draws":175,"losses":245,"wins":576},"GB2-05":{"draws":0,"losses":384,"wins":1206},"GB2-06":{"draws":46,"losses":125,"wins":833},"GB2-07":{"draws":0,"losses":496,"wins":1094},"GB2-08":{"draws":0,"losses":242,"wins":1372}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":215,"wins":288},"GB2-02":{"draws":50,"losses":30,"wins":400},"GB2-03":{"draws":84,"losses":26,"wins":386},"GB2-05":{"draws":0,"losses":35,"wins":495},"GB2-06":{"draws":9,"losses":48,"wins":445},"GB2-07":{"draws":0,"losses":118,"wins":412},"GB2-08":{"draws":0,"losses":88,"wins":450}},"medium":{"GB2-01":{"draws":34,"losses":96,"wins":386},"GB2-02":{"draws":108,"losses":41,"wins":331},"GB2-03":{"draws":25,"losses":141,"wins":330},"GB2-04":{"draws":41,"losses":19,"wins":438},"GB2-05":{"draws":0,"losses":37,"wins":493},"GB2-07":{"draws":0,"losses":130,"wins":400},"GB2-08":{"draws":0,"losses":48,"wins":490}},"none":{"GB2-01":{"draws":155,"losses":305,"wins":56},"GB2-02":{"draws":334,"losses":69,"wins":77},"GB2-04":{"draws":134,"losses":226,"wins":138},"GB2-05":{"draws":0,"losses":312,"wins":218},"GB2-06":{"draws":37,"losses":77,"wins":388},"GB2-07":{"draws":0,"losses":248,"wins":282},"GB2-08":{"draws":0,"losses":106,"wins":432}}},"per_game_raw_elo_all":{"GB2-01":1533.6767990790756,"GB2-02":1723.7711414094122,"GB2-05":2051.346403042953,"GB2-07":1733.5740022506682,"GB2-08":2079.6576841405945},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1558.1975883021616,"GB2-02":1907.8345918955342,"GB2-03":1935.6820072845712,"GB2-05":2413.706475815088,"GB2-06":2198.969463672578,"GB2-07":1861.3251361718135,"GB2-08":2037.8054415027132},"medium":{"GB2-01":1798.529682325637,"GB2-02":1771.5540276299116,"GB2-03":1657.3239146927308,"GB2-04":1983.3441866987844,"GB2-05":2395.4678721554847,"GB2-07":1822.5512784886669,"GB2-08":2239.145901922122},"none":{"GB2-01":1244.303126609428,"GB2-02":1491.9248047027907,"GB2-04":1419.3969830741412,"GB2-05":1344.8648611582864,"GB2-06":2007.9183595918194,"GB2-07":1516.8455920915248,"GB2-08":1962.0217089969492}},"per_game_tracks":{"highest":{"GB2-01":59.22719662255418,"GB2-02":89.06347621855328,"GB2-03":87.84039375664256,"GB2-05":93.41174923079485,"GB2-06":90.56306185486608,"GB2-07":78.41247250475357,"GB2-08":85.29553442876971},"medium":{"GB2-01":80.0011797514601,"GB2-02":81.27891545038818,"GB2-03":72.33451586906564,"GB2-04":92.4293167178963,"GB2-05":93.07420359693637,"GB2-07":76.3385285884776,"GB2-08":91.8203469263529},"none":{"GB2-01":27.516848786379583,"GB2-02":52.56960139075472,"GB2-04":42.841170804441276,"GB2-05":42.61034300687487,"GB2-06":82.79900123566456,"GB2-07":55.477688466088146,"GB2-08":82.3321372734223}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":19,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:55:26Z","reasoning":{"highest":72.97673557711678,"medium":73.40962586257214,"none":48.26834887045318},"reasoning_agg":{"highest":{"max":93.41174923079485,"mean":72.97673557711678,"min":0.0},"medium":{"max":93.07420359693637,"mean":73.40962586257214,"min":0.0},"none":{"max":82.79900123566456,"mean":48.26834887045318,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.14127699211896},"working_program_strength":{"all":74.15417535624461,"highest":83.4019835167049,"medium":83.89671527151101,"none":55.16382728051792}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash-1017:eb3e551d4b592621","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":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.336132894},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.046843572}},"codegen_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":0.065551536,"mean":0.04201661175,"median":0.0380097,"min":0.02021175,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.336132894},"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":0.00749985,"mean":0.0058554465,"median":0.006206184,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.046843572},"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":0.11170938600000001,"mean":0.07554854925,"median":0.075366243,"min":0.03476295,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.604388394}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.11170938600000001,"mean":0.0411402025,"median":0.037120068,"min":0.00308565,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":27},"recorded_attempt_count":27,"run_count":24,"total":0.9873648600000001},"codegen_latency_ms":{"attempt_count":27,"max_ms":473334,"mean_ms":151724.33333333334,"min_ms":8145,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":473334,"mean_ms":299503.0,"min_ms":228847,"run_count":8},"medium":{"attempt_count":8,"max_ms":206258,"mean_ms":144560.375,"min_ms":109598,"run_count":8},"none":{"attempt_count":9,"max_ms":15039,"mean_ms":11109.625,"min_ms":8145,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":101363,"output_mean":34770.375,"output_min":2168,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":101363,"output_mean":66009.25,"output_min":55824,"run_count":8},"medium":{"attempt_count":8,"output_max":52800,"output_mean":35105.0,"output_min":27852,"run_count":8},"none":{"attempt_count":9,"output_max":4467,"output_mean":3196.875,"output_min":2168,"run_count":8}},"display_name":"DeepSeek V4.1 Flash 1017","economics":{"all":63.4471288936787,"highest":71.88109141754686,"medium":66.72423793111,"none":51.73605733237926},"economics_best_value":{"per_model":{"all":true,"medium":true,"none":true}},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[393216],"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":[393216],"total_output_tokens":834489,"total_reasoning_output_tokens":719894,"total_visible_output_tokens":114595,"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":393216,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-flash-1017","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":75.48158134000828,"score":75.48158134000828},"GB2-02":{"attempts":3,"playable":56.26154427051597,"score":56.26154427051597},"GB2-03":{"attempts":3,"playable":46.05333145971721,"score":46.05333145971721},"GB2-04":{"attempts":3,"playable":60.68934627799143,"score":60.68934627799143},"GB2-05":{"attempts":3,"playable":62.737636350298594,"score":62.737636350298594},"GB2-06":{"attempts":3,"playable":69.27397304605378,"score":69.27397304605378},"GB2-07":{"attempts":3,"playable":59.91201860503859,"score":59.91201860503859},"GB2-08":{"attempts":3,"playable":77.16759979980579,"score":77.16759979980579}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.88463256139818,"score":68.88463256139818},"GB2-02":{"attempts":1,"playable":80.98358996158233,"score":80.98358996158233},"GB2-03":{"attempts":1,"playable":46.90689629916197,"score":46.90689629916197},"GB2-04":{"attempts":1,"playable":70.20359549773876,"score":70.20359549773876},"GB2-05":{"attempts":1,"playable":73.89184386154099,"score":73.89184386154099},"GB2-06":{"attempts":1,"playable":77.99012869413073,"score":77.99012869413073},"GB2-07":{"attempts":1,"playable":72.8661114453143,"score":72.8661114453143},"GB2-08":{"attempts":1,"playable":83.3219330195076,"score":83.3219330195076}},"medium":{"GB2-01":{"attempts":1,"playable":84.27410249639517,"score":84.27410249639517},"GB2-02":{"attempts":1,"playable":43.84772061297107,"score":43.84772061297107},"GB2-03":{"attempts":1,"playable":51.20707199663714,"score":51.20707199663714},"GB2-04":{"attempts":1,"playable":69.12533642288999,"score":69.12533642288999},"GB2-05":{"attempts":1,"playable":61.72707415605962,"score":61.72707415605962},"GB2-06":{"attempts":1,"playable":83.70586454387666,"score":83.70586454387666},"GB2-07":{"attempts":1,"playable":73.56230487927209,"score":73.56230487927209},"GB2-08":{"attempts":1,"playable":66.34442834077817,"score":66.34442834077817}},"none":{"GB2-01":{"attempts":1,"playable":73.28600896223145,"score":73.28600896223145},"GB2-02":{"attempts":1,"playable":43.95332223699452,"score":43.95332223699452},"GB2-03":{"attempts":1,"playable":40.0460260833525,"score":40.0460260833525},"GB2-04":{"attempts":1,"playable":42.73910691334554,"score":42.73910691334554},"GB2-05":{"attempts":1,"playable":52.593991033295175,"score":52.593991033295175},"GB2-06":{"attempts":1,"playable":46.12592590015396,"score":46.12592590015396},"GB2-07":{"attempts":1,"playable":33.307639490529354,"score":33.307639490529354},"GB2-08":{"attempts":1,"playable":81.83643803913164,"score":81.83643803913164}}},"id":"deepseek/deepseek-v4.1-flash-1017","is_recent_addition":false,"last_measured_at":"2026-10-27T23:45:40Z","match_totals_all":{"draws":2175,"losses":3640,"wins":6455},"match_totals_tracks":{"highest":{"draws":567,"losses":942,"wins":2581},"medium":{"draws":640,"losses":1119,"wins":2331},"none":{"draws":968,"losses":1579,"wins":1543}},"model_slug":"deepseek-deepseek-v4-1-flash-1017","official_rank_by_reasoning":{"highest":15,"medium":15,"none":17},"overall":{"max":84.27410249639517,"mean":63.4471288936787,"min":33.307639490529354},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.88463256139818,"GB2-02":80.98358996158233,"GB2-03":46.90689629916197,"GB2-04":70.20359549773876,"GB2-05":73.89184386154099,"GB2-06":77.99012869413073,"GB2-07":72.8661114453143,"GB2-08":83.3219330195076},"per_game_all":{"GB2-01":75.48158134000828,"GB2-02":56.26154427051597,"GB2-03":46.05333145971721,"GB2-04":60.68934627799143,"GB2-05":62.737636350298594,"GB2-06":69.27397304605378,"GB2-07":59.91201860503859,"GB2-08":77.16759979980579},"per_game_match_totals_all":{"GB2-01":{"draws":166,"losses":327,"wins":1055},"GB2-02":{"draws":836,"losses":233,"wins":371},"GB2-03":{"draws":358,"losses":679,"wins":451},"GB2-04":{"draws":766,"losses":229,"wins":499},"GB2-05":{"draws":0,"losses":619,"wins":971},"GB2-06":{"draws":49,"losses":481,"wins":976},"GB2-07":{"draws":0,"losses":663,"wins":927},"GB2-08":{"draws":0,"losses":409,"wins":1205}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":107,"losses":118,"wins":291},"GB2-02":{"draws":97,"losses":48,"wins":335},"GB2-03":{"draws":86,"losses":239,"wins":171},"GB2-04":{"draws":257,"losses":28,"wins":213},"GB2-05":{"draws":0,"losses":147,"wins":383},"GB2-06":{"draws":20,"losses":112,"wins":370},"GB2-07":{"draws":0,"losses":150,"wins":380},"GB2-08":{"draws":0,"losses":100,"wins":438}},"medium":{"GB2-01":{"draws":0,"losses":90,"wins":426},"GB2-02":{"draws":361,"losses":97,"wins":22},"GB2-03":{"draws":54,"losses":234,"wins":208},"GB2-04":{"draws":200,"losses":62,"wins":236},"GB2-05":{"draws":0,"losses":212,"wins":318},"GB2-06":{"draws":25,"losses":78,"wins":399},"GB2-07":{"draws":0,"losses":146,"wins":384},"GB2-08":{"draws":0,"losses":200,"wins":338}},"none":{"GB2-01":{"draws":59,"losses":119,"wins":338},"GB2-02":{"draws":378,"losses":88,"wins":14},"GB2-03":{"draws":218,"losses":206,"wins":72},"GB2-04":{"draws":309,"losses":139,"wins":50},"GB2-05":{"draws":0,"losses":260,"wins":270},"GB2-06":{"draws":4,"losses":291,"wins":207},"GB2-07":{"draws":0,"losses":367,"wins":163},"GB2-08":{"draws":0,"losses":109,"wins":429}}},"per_game_raw_elo_all":{"GB2-01":1745.0336261907094,"GB2-02":1539.06109314548,"GB2-03":1396.302118279462,"GB2-04":1566.252056364913,"GB2-05":1613.3546920676927,"GB2-06":1764.6836096780678,"GB2-07":1591.5300328365877,"GB2-08":1854.4097168322933},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1658.9443111753849,"GB2-02":1767.4253308755451,"GB2-03":1403.6027609440728,"GB2-04":1645.2705295543487,"GB2-05":1782.1426363118426,"GB2-06":1908.627907054507,"GB2-07":1763.0991362579668,"GB2-08":1986.6667315593877},"medium":{"GB2-01":1866.2728239397559,"GB2-02":1424.470731628572,"GB2-03":1441.3150650919422,"GB2-04":1634.8819561720015,"GB2-05":1588.3616621838805,"GB2-06":2027.653459492443,"GB2-07":1774.5649412001435,"GB2-08":1626.6642933333892},"none":{"GB2-01":1709.8837434569868,"GB2-02":1425.2872169323223,"GB2-03":1343.9885288023718,"GB2-04":1418.6036833683884,"GB2-05":1469.5597777073554,"GB2-06":1357.769462487253,"GB2-07":1236.926021051653,"GB2-08":1949.8981256041025}},"per_game_tracks":{"highest":{"GB2-01":68.88463256139818,"GB2-02":80.98358996158233,"GB2-03":46.90689629916197,"GB2-04":70.20359549773876,"GB2-05":73.89184386154099,"GB2-06":77.99012869413073,"GB2-07":72.8661114453143,"GB2-08":83.3219330195076},"medium":{"GB2-01":84.27410249639517,"GB2-02":43.84772061297107,"GB2-03":51.20707199663714,"GB2-04":69.12533642288999,"GB2-05":61.72707415605962,"GB2-06":83.70586454387666,"GB2-07":73.56230487927209,"GB2-08":66.34442834077817},"none":{"GB2-01":73.28600896223145,"GB2-02":43.95332223699452,"GB2-03":40.0460260833525,"GB2-04":42.73910691334554,"GB2-05":52.593991033295175,"GB2-06":46.12592590015396,"GB2-07":33.307639490529354,"GB2-08":81.83643803913164}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T17:50:09Z","reasoning":{"highest":71.88109141754686,"medium":66.72423793111,"none":51.73605733237926},"reasoning_agg":{"highest":{"max":83.3219330195076,"mean":71.88109141754686,"min":46.90689629916197},"medium":{"max":84.27410249639517,"mean":66.72423793111,"min":43.84772061297107},"none":{"max":81.83643803913164,"mean":51.73605733237926,"min":33.307639490529354}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":20.145034085167595},"working_program_strength":{"all":63.4471288936787,"highest":71.88109141754686,"medium":66.72423793111,"none":51.73605733237926}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5-5:4ef54dba72bc4f61","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":0.486378},"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":0.32749799999999996},"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":5.199238000000001},"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":61.79993897289637,"highest":91.99620240859609,"medium":51.87878344602902,"none":41.52483106406402},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.64553280065103,"score":59.64553280065103},"GB2-02":{"attempts":3,"playable":61.6686296588692,"score":61.6686296588692},"GB2-03":{"attempts":3,"playable":58.71689786891488,"score":58.71689786891488},"GB2-04":{"attempts":3,"playable":56.394380359392976,"score":56.394380359392976},"GB2-05":{"attempts":3,"playable":43.791806503043176,"score":43.791806503043176},"GB2-06":{"attempts":3,"playable":62.07831338556435,"score":62.07831338556435},"GB2-07":{"attempts":3,"playable":70.66126906936479,"score":70.66126906936479},"GB2-08":{"attempts":3,"playable":81.44268213737057,"score":81.44268213737057}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.2821071231467,"score":80.2821071231467},"GB2-02":{"attempts":1,"playable":96.04788342024116,"score":96.04788342024116},"GB2-03":{"attempts":1,"playable":95.39930045044393,"score":95.39930045044393},"GB2-04":{"attempts":1,"playable":83.30086563026019,"score":83.30086563026019},"GB2-05":{"attempts":1,"playable":97.37459571123685,"score":97.37459571123685},"GB2-06":{"attempts":1,"playable":90.92034578060459,"score":90.92034578060459},"GB2-07":{"attempts":1,"playable":93.67555408383942,"score":93.67555408383942},"GB2-08":{"attempts":1,"playable":98.96896706899584,"score":98.96896706899584}},"medium":{"GB2-01":{"attempts":1,"playable":47.02555906662648,"score":47.02555906662648},"GB2-02":{"attempts":1,"playable":42.47384387943976,"score":42.47384387943976},"GB2-03":{"attempts":1,"playable":31.995170094660647,"score":31.995170094660647},"GB2-04":{"attempts":1,"playable":40.90020870251904,"score":40.90020870251904},"GB2-05":{"attempts":1,"playable":19.49524724913211,"score":19.49524724913211},"GB2-06":{"attempts":1,"playable":77.08269762490603,"score":77.08269762490603},"GB2-07":{"attempts":1,"playable":71.99459713820777,"score":71.99459713820777},"GB2-08":{"attempts":1,"playable":84.06294381274026,"score":84.06294381274026}},"none":{"GB2-01":{"attempts":1,"playable":51.62893221217991,"score":51.62893221217991},"GB2-02":{"attempts":1,"playable":46.484161676926675,"score":46.484161676926675},"GB2-03":{"attempts":1,"playable":48.756223061640036,"score":48.756223061640036},"GB2-04":{"attempts":1,"playable":44.9820667453997,"score":44.9820667453997},"GB2-05":{"attempts":1,"playable":14.505576548760562,"score":14.505576548760562},"GB2-06":{"attempts":1,"playable":18.231896751182443,"score":18.231896751182443},"GB2-07":{"attempts":1,"playable":46.313655986047166,"score":46.313655986047166},"GB2-08":{"attempts":1,"playable":61.29613553037561,"score":61.29613553037561}}},"id":"claude-sonnet-5-5","is_recent_addition":false,"last_measured_at":"2026-10-31T16:54:52Z","match_totals_all":{"draws":2080,"losses":3821,"wins":6369},"match_totals_tracks":{"highest":{"draws":307,"losses":185,"wins":3598},"medium":{"draws":924,"losses":1571,"wins":1595},"none":{"draws":849,"losses":2065,"wins":1176}},"model_slug":"claude-sonnet-5-5","official_rank_by_reasoning":{"highest":5,"medium":35,"none":38},"overall":{"max":98.96896706899584,"mean":61.79993897289637,"min":14.505576548760562},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.2821071231467,"GB2-02":96.04788342024116,"GB2-03":95.39930045044393,"GB2-04":83.30086563026019,"GB2-05":97.37459571123685,"GB2-06":90.92034578060459,"GB2-07":93.67555408383942,"GB2-08":98.96896706899584},"per_game_all":{"GB2-01":59.64553280065103,"GB2-02":61.6686296588692,"GB2-03":58.71689786891488,"GB2-04":56.394380359392976,"GB2-05":43.791806503043176,"GB2-06":62.07831338556435,"GB2-07":70.66126906936479,"GB2-08":81.44268213737057},"per_game_match_totals_all":{"GB2-01":{"draws":218,"losses":547,"wins":783},"GB2-02":{"draws":767,"losses":184,"wins":489},"GB2-03":{"draws":328,"losses":486,"wins":674},"GB2-04":{"draws":691,"losses":328,"wins":475},"GB2-05":{"draws":0,"losses":902,"wins":688},"GB2-06":{"draws":36,"losses":584,"wins":886},"GB2-07":{"draws":0,"losses":483,"wins":1107},"GB2-08":{"draws":40,"losses":307,"wins":1267}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":157,"losses":33,"wins":326},"GB2-02":{"draws":23,"losses":7,"wins":450},"GB2-03":{"draws":0,"losses":24,"wins":472},"GB2-04":{"draws":91,"losses":43,"wins":364},"GB2-05":{"draws":0,"losses":12,"wins":518},"GB2-06":{"draws":31,"losses":35,"wins":436},"GB2-07":{"draws":0,"losses":30,"wins":500},"GB2-08":{"draws":5,"losses":1,"wins":532}},"medium":{"GB2-01":{"draws":14,"losses":277,"wins":225},"GB2-02":{"draws":376,"losses":96,"wins":8},"GB2-03":{"draws":214,"losses":246,"wins":36},"GB2-04":{"draws":315,"losses":145,"wins":38},"GB2-05":{"draws":0,"losses":432,"wins":98},"GB2-06":{"draws":2,"losses":126,"wins":374},"GB2-07":{"draws":0,"losses":155,"wins":375},"GB2-08":{"draws":3,"losses":94,"wins":441}},"none":{"GB2-01":{"draws":47,"losses":237,"wins":232},"GB2-02":{"draws":368,"losses":81,"wins":31},"GB2-03":{"draws":114,"losses":216,"wins":166},"GB2-04":{"draws":285,"losses":140,"wins":73},"GB2-05":{"draws":0,"losses":458,"wins":72},"GB2-06":{"draws":3,"losses":423,"wins":76},"GB2-07":{"draws":0,"losses":298,"wins":232},"GB2-08":{"draws":32,"losses":212,"wins":294}}},"per_game_raw_elo_all":{"GB2-01":1575.9688151272119,"GB2-02":1666.9213317141603,"GB2-03":1642.7576793561223,"GB2-04":1546.7405048239154,"GB2-05":1535.9815524619237,"GB2-06":1675.5641780394924,"GB2-07":1835.9996278497395,"GB2-08":2099.495884382187},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1802.644486915534,"GB2-02":2142.125140705838,"GB2-03":2236.7472143820482,"GB2-04":1799.9818588639034,"GB2-05":2705.7040527066,"GB2-06":2209.7025243107555,"GB2-07":2357.5266223096623,"GB2-08":2750.0118414554545},"medium":{"GB2-01":1440.7327805953407,"GB2-02":1413.8262385455776,"GB2-03":1271.7881639573811,"GB2-04":1404.255010390934,"GB2-05":1000.6482406667249,"GB2-06":1890.6209399392278,"GB2-07":1749.0195460167556,"GB2-08":2005.5322209108915},"none":{"GB2-01":1484.5291778707608,"GB2-02":1444.8126158910652,"GB2-03":1419.7376597289378,"GB2-04":1435.9846452169086,"GB2-05":901.5923640124466,"GB2-06":926.3690698684939,"GB2-07":1401.4527152228004,"GB2-08":1542.9435907802144}},"per_game_tracks":{"highest":{"GB2-01":80.2821071231467,"GB2-02":96.04788342024116,"GB2-03":95.39930045044393,"GB2-04":83.30086563026019,"GB2-05":97.37459571123685,"GB2-06":90.92034578060459,"GB2-07":93.67555408383942,"GB2-08":98.96896706899584},"medium":{"GB2-01":47.02555906662648,"GB2-02":42.47384387943976,"GB2-03":31.995170094660647,"GB2-04":40.90020870251904,"GB2-05":19.49524724913211,"GB2-06":77.08269762490603,"GB2-07":71.99459713820777,"GB2-08":84.06294381274026},"none":{"GB2-01":51.62893221217991,"GB2-02":46.484161676926675,"GB2-03":48.756223061640036,"GB2-04":44.9820667453997,"GB2-05":14.505576548760562,"GB2-06":18.231896751182443,"GB2-07":46.313655986047166,"GB2-08":61.29613553037561}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:09:58Z","reasoning":{"highest":91.99620240859609,"medium":51.87878344602902,"none":41.52483106406402},"reasoning_agg":{"highest":{"max":98.96896706899584,"mean":91.99620240859609,"min":80.2821071231467},"medium":{"max":84.06294381274026,"mean":51.87878344602902,"min":19.49524724913211},"none":{"max":61.29613553037561,"mean":41.52483106406402,"min":14.505576548760562}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":50.47137134453207},"working_program_strength":{"all":61.79993897289637,"highest":91.99620240859609,"medium":51.87878344602902,"none":41.52483106406402}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:0e946827094010a6","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":0.25482999999999995}},"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":3.1457180000000005},"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":61.08811953166215,"highest":66.84029416801354,"medium":71.00444927936125,"none":45.41961514761163},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.94828939640879,"score":59.94828939640879},"GB2-02":{"attempts":3,"playable":60.685445182655975,"score":60.685445182655975},"GB2-03":{"attempts":3,"playable":54.60997217907317,"score":54.60997217907317},"GB2-04":{"attempts":3,"playable":56.146811579324314,"score":56.146811579324314},"GB2-05":{"attempts":3,"playable":73.00088324449098,"score":73.00088324449098},"GB2-06":{"attempts":3,"playable":53.21813109570261,"score":53.21813109570261},"GB2-07":{"attempts":3,"playable":70.10751527220117,"score":70.10751527220117},"GB2-08":{"attempts":3,"playable":60.98790830344012,"score":60.98790830344012}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.55321475789722,"score":50.55321475789722},"GB2-02":{"attempts":1,"playable":83.33909920462729,"score":83.33909920462729},"GB2-03":{"attempts":1,"playable":51.81708693098591,"score":51.81708693098591},"GB2-04":{"attempts":1,"playable":60.115558926100675,"score":60.115558926100675},"GB2-05":{"attempts":1,"playable":85.00424106756313,"score":85.00424106756313},"GB2-06":{"attempts":1,"playable":66.79819657241505,"score":66.79819657241505},"GB2-07":{"attempts":1,"playable":76.16539641045584,"score":76.16539641045584},"GB2-08":{"attempts":1,"playable":60.92955947406313,"score":60.92955947406313}},"medium":{"GB2-01":{"attempts":1,"playable":62.52230096956972,"score":62.52230096956972},"GB2-02":{"attempts":1,"playable":54.55274615406843,"score":54.55274615406843},"GB2-03":{"attempts":1,"playable":67.27541993684892,"score":67.27541993684892},"GB2-04":{"attempts":1,"playable":65.38165151957736,"score":65.38165151957736},"GB2-05":{"attempts":1,"playable":82.74384298865276,"score":82.74384298865276},"GB2-06":{"attempts":1,"playable":79.53272342137946,"score":79.53272342137946},"GB2-07":{"attempts":1,"playable":76.51161229036667,"score":76.51161229036667},"GB2-08":{"attempts":1,"playable":79.51529695442676,"score":79.51529695442676}},"none":{"GB2-01":{"attempts":1,"playable":66.7693524617594,"score":66.7693524617594},"GB2-02":{"attempts":1,"playable":44.16449018927223,"score":44.16449018927223},"GB2-03":{"attempts":1,"playable":44.73740966938467,"score":44.73740966938467},"GB2-04":{"attempts":1,"playable":42.9432242922949,"score":42.9432242922949},"GB2-05":{"attempts":1,"playable":51.254565677257055,"score":51.254565677257055},"GB2-06":{"attempts":1,"playable":13.323473293313318,"score":13.323473293313318},"GB2-07":{"attempts":1,"playable":57.64553711578101,"score":57.64553711578101},"GB2-08":{"attempts":1,"playable":42.518868481830474,"score":42.518868481830474}}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-10-31T17:02:38Z","match_totals_all":{"draws":2874,"losses":3583,"wins":5813},"match_totals_tracks":{"highest":{"draws":777,"losses":1057,"wins":2256},"medium":{"draws":787,"losses":862,"wins":2441},"none":{"draws":1310,"losses":1664,"wins":1116}},"model_slug":"x-ai-grok-4-6","official_rank_by_reasoning":{"highest":22,"medium":12,"none":29},"overall":{"max":85.00424106756313,"mean":61.08811953166215,"min":13.323473293313318},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.55321475789722,"GB2-02":83.33909920462729,"GB2-03":51.81708693098591,"GB2-04":60.115558926100675,"GB2-05":85.00424106756313,"GB2-06":66.79819657241505,"GB2-07":76.16539641045584,"GB2-08":60.92955947406313},"per_game_all":{"GB2-01":59.94828939640879,"GB2-02":60.685445182655975,"GB2-03":54.60997217907317,"GB2-04":56.146811579324314,"GB2-05":73.00088324449098,"GB2-06":53.21813109570261,"GB2-07":70.10751527220117,"GB2-08":60.98790830344012},"per_game_match_totals_all":{"GB2-01":{"draws":444,"losses":431,"wins":673},"GB2-02":{"draws":746,"losses":214,"wins":480},"GB2-03":{"draws":591,"losses":435,"wins":462},"GB2-04":{"draws":834,"losses":264,"wins":396},"GB2-05":{"draws":0,"losses":450,"wins":1140},"GB2-06":{"draws":48,"losses":719,"wins":739},"GB2-07":{"draws":0,"losses":496,"wins":1094},"GB2-08":{"draws":211,"losses":574,"wins":829}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":252,"losses":140,"wins":124},"GB2-02":{"draws":65,"losses":52,"wins":363},"GB2-03":{"draws":102,"losses":207,"wins":187},"GB2-04":{"draws":271,"losses":72,"wins":155},"GB2-05":{"draws":0,"losses":85,"wins":445},"GB2-06":{"draws":29,"losses":169,"wins":304},"GB2-07":{"draws":0,"losses":131,"wins":399},"GB2-08":{"draws":58,"losses":201,"wins":279}},"medium":{"GB2-01":{"draws":131,"losses":139,"wins":246},"GB2-02":{"draws":301,"losses":76,"wins":103},"GB2-03":{"draws":94,"losses":133,"wins":269},"GB2-04":{"draws":248,"losses":57,"wins":193},"GB2-05":{"draws":0,"losses":98,"wins":432},"GB2-06":{"draws":13,"losses":107,"wins":382},"GB2-07":{"draws":0,"losses":129,"wins":401},"GB2-08":{"draws":0,"losses":123,"wins":415}},"none":{"GB2-01":{"draws":61,"losses":152,"wins":303},"GB2-02":{"draws":380,"losses":86,"wins":14},"GB2-03":{"draws":395,"losses":95,"wins":6},"GB2-04":{"draws":315,"losses":135,"wins":48},"GB2-05":{"draws":0,"losses":267,"wins":263},"GB2-06":{"draws":6,"losses":443,"wins":53},"GB2-07":{"draws":0,"losses":236,"wins":294},"GB2-08":{"draws":153,"losses":250,"wins":135}}},"per_game_raw_elo_all":{"GB2-01":1567.1436248154694,"GB2-02":1578.804051058043,"GB2-03":1476.3235681789647,"GB2-04":1525.3041130255524,"GB2-05":1834.2248054262388,"GB2-06":1490.7917957959364,"GB2-07":1730.015786628802,"GB2-08":1576.7384066386976},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1474.274957931267,"GB2-02":1801.9808016940688,"GB2-03":1446.7321938303162,"GB2-04":1555.2819935154967,"GB2-05":2059.926331511094,"GB2-06":1696.913351161495,"GB2-07":1819.4391518712437,"GB2-08":1537.2479955963086},"medium":{"GB2-01":1591.3396982986587,"GB2-02":1507.512033898504,"GB2-03":1597.4757823023008,"GB2-04":1600.440419573543,"GB2-05":1989.9160290986824,"GB2-06":1939.690337836714,"GB2-07":1825.6802983623043,"GB2-08":1894.8511143392225},"none":{"GB2-01":1635.8162182164824,"GB2-02":1426.9193175815556,"GB2-03":1384.7627284042778,"GB2-04":1420.1899259876172,"GB2-05":1452.83205566894,"GB2-06":835.7716983896004,"GB2-07":1544.9279096528583,"GB2-08":1298.1161099805615}},"per_game_tracks":{"highest":{"GB2-01":50.55321475789722,"GB2-02":83.33909920462729,"GB2-03":51.81708693098591,"GB2-04":60.115558926100675,"GB2-05":85.00424106756313,"GB2-06":66.79819657241505,"GB2-07":76.16539641045584,"GB2-08":60.92955947406313},"medium":{"GB2-01":62.52230096956972,"GB2-02":54.55274615406843,"GB2-03":67.27541993684892,"GB2-04":65.38165151957736,"GB2-05":82.74384298865276,"GB2-06":79.53272342137946,"GB2-07":76.51161229036667,"GB2-08":79.51529695442676},"none":{"GB2-01":66.7693524617594,"GB2-02":44.16449018927223,"GB2-03":44.73740966938467,"GB2-04":42.9432242922949,"GB2-05":51.254565677257055,"GB2-06":13.323473293313318,"GB2-07":57.64553711578101,"GB2-08":42.518868481830474}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:51:38Z","reasoning":{"highest":66.84029416801354,"medium":71.00444927936125,"none":45.41961514761163},"reasoning_agg":{"highest":{"max":85.00424106756313,"mean":66.84029416801354,"min":50.55321475789722},"medium":{"max":82.74384298865276,"mean":71.00444927936125,"min":54.55274615406843},"none":{"max":66.7693524617594,"mean":45.41961514761163,"min":13.323473293313318}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.584834131749624},"working_program_strength":{"all":61.08811953166215,"highest":66.84029416801354,"medium":71.00444927936125,"none":45.41961514761163}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:7fdf302c5dd6848a","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":1.1454976827810868},"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":0.5746151281850016},"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":0.2555334390339119},"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":1.97564625},"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":60.943294375422205,"highest":66.22474325492595,"medium":61.204227309049934,"none":55.40091256229073},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":61.041744260060774,"score":61.041744260060774},"GB2-02":{"attempts":3,"playable":50.09197632259832,"score":50.09197632259832},"GB2-03":{"attempts":3,"playable":69.13701936362344,"score":69.13701936362344},"GB2-04":{"attempts":3,"playable":51.342455829400585,"score":51.342455829400585},"GB2-05":{"attempts":3,"playable":59.305565003381616,"score":59.305565003381616},"GB2-06":{"attempts":3,"playable":80.34242812392931,"score":80.34242812392931},"GB2-07":{"attempts":3,"playable":56.59142327260299,"score":56.59142327260299},"GB2-08":{"attempts":3,"playable":59.69374282778063,"score":59.69374282778063}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.43460977470199,"score":55.43460977470199},"GB2-02":{"attempts":1,"playable":69.98694989715852,"score":69.98694989715852},"GB2-03":{"attempts":1,"playable":71.19850859912692,"score":71.19850859912692},"GB2-04":{"attempts":1,"playable":47.11811390250815,"score":47.11811390250815},"GB2-05":{"attempts":1,"playable":67.19089355992637,"score":67.19089355992637},"GB2-06":{"attempts":1,"playable":88.76887961013783,"score":88.76887961013783},"GB2-07":{"attempts":1,"playable":69.72174524050753,"score":69.72174524050753},"GB2-08":{"attempts":1,"playable":60.37824545534032,"score":60.37824545534032}},"medium":{"GB2-01":{"attempts":1,"playable":71.1849619569025,"score":71.1849619569025},"GB2-02":{"attempts":1,"playable":40.03849019131322,"score":40.03849019131322},"GB2-03":{"attempts":1,"playable":84.59868009318262,"score":84.59868009318262},"GB2-04":{"attempts":1,"playable":61.11286829372216,"score":61.11286829372216},"GB2-05":{"attempts":1,"playable":55.07686886095765,"score":55.07686886095765},"GB2-06":{"attempts":1,"playable":78.71605689835796,"score":78.71605689835796},"GB2-07":{"attempts":1,"playable":57.465333623522156,"score":57.465333623522156},"GB2-08":{"attempts":1,"playable":41.44055855444124,"score":41.44055855444124}},"none":{"GB2-01":{"attempts":1,"playable":56.50566104857786,"score":56.50566104857786},"GB2-02":{"attempts":1,"playable":40.25048887932319,"score":40.25048887932319},"GB2-03":{"attempts":1,"playable":51.613869398560766,"score":51.613869398560766},"GB2-04":{"attempts":1,"playable":45.796385291971426,"score":45.796385291971426},"GB2-05":{"attempts":1,"playable":55.64893258926082,"score":55.64893258926082},"GB2-06":{"attempts":1,"playable":73.54234786329214,"score":73.54234786329214},"GB2-07":{"attempts":1,"playable":42.58719095377929,"score":42.58719095377929},"GB2-08":{"attempts":1,"playable":77.26242447356034,"score":77.26242447356034}}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T16:50:35Z","match_totals_all":{"draws":2394,"losses":3864,"wins":6012},"match_totals_tracks":{"highest":{"draws":459,"losses":1241,"wins":2390},"medium":{"draws":964,"losses":1196,"wins":1930},"none":{"draws":971,"losses":1427,"wins":1692}},"model_slug":"google-gemini-3-8-flash","official_rank_by_reasoning":{"highest":24,"medium":22,"none":15},"overall":{"max":88.76887961013783,"mean":60.943294375422205,"min":40.03849019131322},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.43460977470199,"GB2-02":69.98694989715852,"GB2-03":71.19850859912692,"GB2-04":47.11811390250815,"GB2-05":67.19089355992637,"GB2-06":88.76887961013783,"GB2-07":69.72174524050753,"GB2-08":60.37824545534032},"per_game_all":{"GB2-01":61.041744260060774,"GB2-02":50.09197632259832,"GB2-03":69.13701936362344,"GB2-04":51.342455829400585,"GB2-05":59.305565003381616,"GB2-06":80.34242812392931,"GB2-07":56.59142327260299,"GB2-08":59.69374282778063},"per_game_match_totals_all":{"GB2-01":{"draws":316,"losses":478,"wins":754},"GB2-02":{"draws":931,"losses":276,"wins":233},"GB2-03":{"draws":192,"losses":409,"wins":887},"GB2-04":{"draws":698,"losses":404,"wins":392},"GB2-05":{"draws":0,"losses":674,"wins":916},"GB2-06":{"draws":34,"losses":310,"wins":1162},"GB2-07":{"draws":0,"losses":723,"wins":867},"GB2-08":{"draws":223,"losses":590,"wins":801}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":46,"losses":218,"wins":252},"GB2-02":{"draws":197,"losses":53,"wins":230},"GB2-03":{"draws":9,"losses":155,"wins":332},"GB2-04":{"draws":90,"losses":227,"wins":181},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":27,"losses":49,"wins":426},"GB2-07":{"draws":0,"losses":168,"wins":362},"GB2-08":{"draws":90,"losses":188,"wins":260}},"medium":{"GB2-01":{"draws":77,"losses":121,"wins":318},"GB2-02":{"draws":365,"losses":113,"wins":2},"GB2-03":{"draws":97,"losses":38,"wins":361},"GB2-04":{"draws":301,"losses":52,"wins":145},"GB2-05":{"draws":0,"losses":247,"wins":283},"GB2-06":{"draws":4,"losses":116,"wins":382},"GB2-07":{"draws":0,"losses":237,"wins":293},"GB2-08":{"draws":120,"losses":272,"wins":146}},"none":{"GB2-01":{"draws":193,"losses":139,"wins":184},"GB2-02":{"draws":369,"losses":110,"wins":1},"GB2-03":{"draws":86,"losses":216,"wins":194},"GB2-04":{"draws":307,"losses":125,"wins":66},"GB2-05":{"draws":0,"losses":244,"wins":286},"GB2-06":{"draws":3,"losses":145,"wins":354},"GB2-07":{"draws":0,"losses":318,"wins":212},"GB2-08":{"draws":13,"losses":130,"wins":395}}},"per_game_raw_elo_all":{"GB2-01":1579.192477178415,"GB2-02":1477.4035549125053,"GB2-03":1648.3590767451408,"GB2-04":1486.1178602172397,"GB2-05":1558.8974259464203,"GB2-06":1964.6074444422823,"GB2-07":1537.0707935613852,"GB2-08":1552.841053800287},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1521.074851924881,"GB2-02":1640.9163777519118,"GB2-03":1643.1602233450003,"GB2-04":1452.4785425595635,"GB2-05":1667.6926763956014,"GB2-06":2148.743091286882,"GB2-07":1713.5586734966937,"GB2-08":1528.7738326216377},"medium":{"GB2-01":1685.0320063396466,"GB2-02":1394.8150437400775,"GB2-03":1856.9918287341823,"GB2-04":1563.599298324822,"GB2-05":1500.8573163568524,"GB2-06":1923.1699005679639,"GB2-07":1542.576459186274,"GB2-08":1285.9167760828852},"none":{"GB2-01":1531.4705732707173,"GB2-02":1396.4792432455267,"GB2-03":1444.92517815624,"GB2-04":1442.275739767334,"GB2-05":1508.142285086807,"GB2-06":1821.909341472001,"GB2-07":1355.0772480011883,"GB2-08":1843.8325526963386}},"per_game_tracks":{"highest":{"GB2-01":55.43460977470199,"GB2-02":69.98694989715852,"GB2-03":71.19850859912692,"GB2-04":47.11811390250815,"GB2-05":67.19089355992637,"GB2-06":88.76887961013783,"GB2-07":69.72174524050753,"GB2-08":60.37824545534032},"medium":{"GB2-01":71.1849619569025,"GB2-02":40.03849019131322,"GB2-03":84.59868009318262,"GB2-04":61.11286829372216,"GB2-05":55.07686886095765,"GB2-06":78.71605689835796,"GB2-07":57.465333623522156,"GB2-08":41.44055855444124},"none":{"GB2-01":56.50566104857786,"GB2-02":40.25048887932319,"GB2-03":51.613869398560766,"GB2-04":45.796385291971426,"GB2-05":55.64893258926082,"GB2-06":73.54234786329214,"GB2-07":42.58719095377929,"GB2-08":77.26242447356034}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:47:54Z","reasoning":{"highest":66.22474325492595,"medium":61.204227309049934,"none":55.40091256229073},"reasoning_agg":{"highest":{"max":88.76887961013783,"mean":66.22474325492595,"min":47.11811390250815},"medium":{"max":84.59868009318262,"mean":61.204227309049934,"min":40.03849019131322},"none":{"max":77.26242447356034,"mean":55.40091256229073,"min":40.25048887932319}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.823830692635227},"working_program_strength":{"all":60.943294375422205,"highest":66.22474325492595,"medium":61.204227309049934,"none":55.40091256229073}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:a8f2ad3145988995","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":0.41740125000000006},"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":59.80545861470747,"highest":70.99953840787056,"medium":66.87854774702369,"none":41.53828968922815},"economics_best_value":{"per_model":{"medium":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.57012121146434,"score":59.57012121146434},"GB2-02":{"attempts":3,"playable":56.11869324112911,"score":56.11869324112911},"GB2-03":{"attempts":3,"playable":67.56354890443237,"score":67.56354890443237},"GB2-04":{"attempts":3,"playable":53.112330164593004,"score":53.112330164593004},"GB2-05":{"attempts":3,"playable":59.96214227662036,"score":59.96214227662036},"GB2-06":{"attempts":3,"playable":69.14509918085739,"score":69.14509918085739},"GB2-07":{"attempts":3,"playable":50.33825297823751,"score":50.33825297823751},"GB2-08":{"attempts":3,"playable":62.63348096032564,"score":62.63348096032564}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.79985271116222,"score":76.79985271116222},"GB2-02":{"attempts":1,"playable":62.735143417049954,"score":62.735143417049954},"GB2-03":{"attempts":1,"playable":83.26680056632817,"score":83.26680056632817},"GB2-04":{"attempts":1,"playable":51.87979175162969,"score":51.87979175162969},"GB2-05":{"attempts":1,"playable":79.36425071609834,"score":79.36425071609834},"GB2-06":{"attempts":1,"playable":84.61228190209295,"score":84.61228190209295},"GB2-07":{"attempts":1,"playable":58.18566177400884,"score":58.18566177400884},"GB2-08":{"attempts":1,"playable":71.15252442459426,"score":71.15252442459426}},"medium":{"GB2-01":{"attempts":1,"playable":75.09381773402575,"score":75.09381773402575},"GB2-02":{"attempts":1,"playable":58.29474306098563,"score":58.29474306098563},"GB2-03":{"attempts":1,"playable":64.17075216580167,"score":64.17075216580167},"GB2-04":{"attempts":1,"playable":63.6979243600585,"score":63.6979243600585},"GB2-05":{"attempts":1,"playable":59.45317473178169,"score":59.45317473178169},"GB2-06":{"attempts":1,"playable":81.98257826751053,"score":81.98257826751053},"GB2-07":{"attempts":1,"playable":54.570897094209435,"score":54.570897094209435},"GB2-08":{"attempts":1,"playable":77.76449456181625,"score":77.76449456181625}},"none":{"GB2-01":{"attempts":1,"playable":26.816693189205036,"score":26.816693189205036},"GB2-02":{"attempts":1,"playable":47.326193245351725,"score":47.326193245351725},"GB2-03":{"attempts":1,"playable":55.253093981167225,"score":55.253093981167225},"GB2-04":{"attempts":1,"playable":43.759274382090815,"score":43.759274382090815},"GB2-05":{"attempts":1,"playable":41.06900138198107,"score":41.06900138198107},"GB2-06":{"attempts":1,"playable":40.8404373729687,"score":40.8404373729687},"GB2-07":{"attempts":1,"playable":38.25820006649426,"score":38.25820006649426},"GB2-08":{"attempts":1,"playable":38.983423894566414,"score":38.983423894566414}}},"id":"meta/muse-spark-1.3","is_recent_addition":false,"last_measured_at":"2026-10-31T17:01:44Z","match_totals_all":{"draws":2169,"losses":4128,"wins":5973},"match_totals_tracks":{"highest":{"draws":531,"losses":1002,"wins":2557},"medium":{"draws":621,"losses":1133,"wins":2336},"none":{"draws":1017,"losses":1993,"wins":1080}},"model_slug":"meta-muse-spark-1-3","official_rank_by_reasoning":{"highest":16,"medium":14,"none":37},"overall":{"max":84.61228190209295,"mean":59.80545861470747,"min":26.816693189205036},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.79985271116222,"GB2-02":62.735143417049954,"GB2-03":83.26680056632817,"GB2-04":51.87979175162969,"GB2-05":79.36425071609834,"GB2-06":84.61228190209295,"GB2-07":58.18566177400884,"GB2-08":71.15252442459426},"per_game_all":{"GB2-01":59.57012121146434,"GB2-02":56.11869324112911,"GB2-03":67.56354890443237,"GB2-04":53.112330164593004,"GB2-05":59.96214227662036,"GB2-06":69.14509918085739,"GB2-07":50.33825297823751,"GB2-08":62.63348096032564},"per_game_match_totals_all":{"GB2-01":{"draws":104,"losses":603,"wins":841},"GB2-02":{"draws":931,"losses":191,"wins":318},"GB2-03":{"draws":178,"losses":442,"wins":868},"GB2-04":{"draws":669,"losses":392,"wins":433},"GB2-05":{"draws":0,"losses":661,"wins":929},"GB2-06":{"draws":56,"losses":477,"wins":973},"GB2-07":{"draws":0,"losses":827,"wins":763},"GB2-08":{"draws":231,"losses":535,"wins":848}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":128,"wins":384},"GB2-02":{"draws":268,"losses":53,"wins":159},"GB2-03":{"draws":38,"losses":75,"wins":383},"GB2-04":{"draws":135,"losses":181,"wins":182},"GB2-05":{"draws":0,"losses":117,"wins":413},"GB2-06":{"draws":35,"losses":68,"wins":399},"GB2-07":{"draws":0,"losses":233,"wins":297},"GB2-08":{"draws":51,"losses":147,"wins":340}},"medium":{"GB2-01":{"draws":0,"losses":139,"wins":377},"GB2-02":{"draws":299,"losses":59,"wins":122},"GB2-03":{"draws":56,"losses":168,"wins":272},"GB2-04":{"draws":249,"losses":65,"wins":184},"GB2-05":{"draws":0,"losses":224,"wins":306},"GB2-06":{"draws":12,"losses":94,"wins":396},"GB2-07":{"draws":0,"losses":253,"wins":277},"GB2-08":{"draws":5,"losses":131,"wins":402}},"none":{"GB2-01":{"draws":100,"losses":336,"wins":80},"GB2-02":{"draws":364,"losses":79,"wins":37},"GB2-03":{"draws":84,"losses":199,"wins":213},"GB2-04":{"draws":285,"losses":146,"wins":67},"GB2-05":{"draws":0,"losses":320,"wins":210},"GB2-06":{"draws":9,"losses":315,"wins":178},"GB2-07":{"draws":0,"losses":341,"wins":189},"GB2-08":{"draws":175,"losses":257,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1574.2580172783175,"GB2-02":1521.1581654857375,"GB2-03":1623.6849223283734,"GB2-04":1500.5088974345565,"GB2-05":1594.2455520312233,"GB2-06":1771.8159785529235,"GB2-07":1452.6497550093998,"GB2-08":1609.8689580559258},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1754.2021308648743,"GB2-02":1574.6462110967022,"GB2-03":1829.167600834786,"GB2-04":1489.3613139592157,"GB2-05":1899.9206412299527,"GB2-06":2047.8299113873663,"GB2-07":1551.9961166790242,"GB2-08":1716.1713433471766},"medium":{"GB2-01":1732.2022670702024,"GB2-02":1537.5266456563595,"GB2-03":1564.1707044193852,"GB2-04":1585.643904935775,"GB2-05":1557.624352126391,"GB2-06":1990.4844487598348,"GB2-07":1505.220068100964,"GB2-08":1855.0111703419004},"none":{"GB2-01":1236.369653899876,"GB2-02":1451.3016397041515,"GB2-03":1477.7164617309488,"GB2-04":1426.521473408679,"GB2-05":1325.1916627373264,"GB2-06":1277.1335755115692,"GB2-07":1300.7330802482106,"GB2-08":1258.4243604787005}},"per_game_tracks":{"highest":{"GB2-01":76.79985271116222,"GB2-02":62.735143417049954,"GB2-03":83.26680056632817,"GB2-04":51.87979175162969,"GB2-05":79.36425071609834,"GB2-06":84.61228190209295,"GB2-07":58.18566177400884,"GB2-08":71.15252442459426},"medium":{"GB2-01":75.09381773402575,"GB2-02":58.29474306098563,"GB2-03":64.17075216580167,"GB2-04":63.6979243600585,"GB2-05":59.45317473178169,"GB2-06":81.98257826751053,"GB2-07":54.570897094209435,"GB2-08":77.76449456181625},"none":{"GB2-01":26.816693189205036,"GB2-02":47.326193245351725,"GB2-03":55.253093981167225,"GB2-04":43.759274382090815,"GB2-05":41.06900138198107,"GB2-06":40.8404373729687,"GB2-07":38.25820006649426,"GB2-08":38.983423894566414}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":22,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:54:38Z","reasoning":{"highest":70.99953840787056,"medium":66.87854774702369,"none":41.53828968922815},"reasoning_agg":{"highest":{"max":84.61228190209295,"mean":70.99953840787056,"min":51.87979175162969},"medium":{"max":81.98257826751053,"mean":66.87854774702369,"min":54.570897094209435},"none":{"max":55.253093981167225,"mean":41.53828968922815,"min":26.816693189205036}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":29.46124871864241},"working_program_strength":{"all":59.80545861470747,"highest":70.99953840787056,"medium":66.87854774702369,"none":41.53828968922815}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:55ca101cc0f270a3","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":0.5964052000000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.13495079999999998,"mean":0.07082726666666667,"median":0.0661398,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":34},"recorded_attempt_count":34,"run_count":24,"total":1.6998543999999998},"codegen_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":58.45403181223494,"highest":63.425512066857316,"medium":62.11193233515538,"none":49.824651034692124},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":73.34777879388166,"score":73.34777879388166},"GB2-02":{"attempts":3,"playable":51.91586175097134,"score":51.91586175097134},"GB2-03":{"attempts":3,"playable":39.467886974212604,"score":39.467886974212604},"GB2-04":{"attempts":3,"playable":43.45306934812584,"score":43.45306934812584},"GB2-05":{"attempts":3,"playable":61.2962219872533,"score":61.2962219872533},"GB2-06":{"attempts":3,"playable":47.542165687486495,"score":47.542165687486495},"GB2-07":{"attempts":3,"playable":61.55310350712796,"score":61.55310350712796},"GB2-08":{"attempts":3,"playable":89.0561664488203,"score":89.0561664488203}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":83.62918652990561,"score":83.62918652990561},"GB2-02":{"attempts":1,"playable":59.226870455125,"score":59.226870455125},"GB2-03":{"attempts":1,"playable":45.048116952234146,"score":45.048116952234146},"GB2-04":{"attempts":1,"playable":44.47275945978772,"score":44.47275945978772},"GB2-05":{"attempts":1,"playable":73.70732700376902,"score":73.70732700376902},"GB2-06":{"attempts":1,"playable":54.234921394801226,"score":54.234921394801226},"GB2-07":{"attempts":1,"playable":56.5630928487914,"score":56.5630928487914},"GB2-08":{"attempts":1,"playable":90.52182189044443,"score":90.52182189044443}},"medium":{"GB2-01":{"attempts":1,"playable":83.90584256004632,"score":83.90584256004632},"GB2-02":{"attempts":1,"playable":52.77860753249117,"score":52.77860753249117},"GB2-03":{"attempts":1,"playable":57.35738888287932,"score":57.35738888287932},"GB2-04":{"attempts":1,"playable":42.9432242922949,"score":42.9432242922949},"GB2-05":{"attempts":1,"playable":67.37840016521139,"score":67.37840016521139},"GB2-06":{"attempts":1,"playable":45.238808368219836,"score":45.238808368219836},"GB2-07":{"attempts":1,"playable":58.72506198745043,"score":58.72506198745043},"GB2-08":{"attempts":1,"playable":88.5681248926496,"score":88.5681248926496}},"none":{"GB2-01":{"attempts":1,"playable":52.50830729169304,"score":52.50830729169304},"GB2-02":{"attempts":1,"playable":43.742107265297825,"score":43.742107265297825},"GB2-03":{"attempts":1,"playable":15.998155087524344,"score":15.998155087524344},"GB2-04":{"attempts":1,"playable":42.9432242922949,"score":42.9432242922949},"GB2-05":{"attempts":1,"playable":42.802938792779486,"score":42.802938792779486},"GB2-06":{"attempts":1,"playable":43.15276729943843,"score":43.15276729943843},"GB2-07":{"attempts":1,"playable":69.37115568514204,"score":69.37115568514204},"GB2-08":{"attempts":1,"playable":88.07855256336687,"score":88.07855256336687}}},"id":"x-ai/grok-4.5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:04:13Z","match_totals_all":{"draws":2548,"losses":4037,"wins":5685},"match_totals_tracks":{"highest":{"draws":669,"losses":1236,"wins":2185},"medium":{"draws":839,"losses":1208,"wins":2043},"none":{"draws":1040,"losses":1593,"wins":1457}},"model_slug":"x-ai-grok-4-5","official_rank_by_reasoning":{"highest":31,"medium":21,"none":23},"overall":{"max":90.52182189044443,"mean":58.45403181223494,"min":15.998155087524344},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":83.62918652990561,"GB2-02":59.226870455125,"GB2-03":45.048116952234146,"GB2-04":44.47275945978772,"GB2-05":73.70732700376902,"GB2-06":54.234921394801226,"GB2-07":56.5630928487914,"GB2-08":90.52182189044443},"per_game_all":{"GB2-01":73.34777879388166,"GB2-02":51.91586175097134,"GB2-03":39.467886974212604,"GB2-04":43.45306934812584,"GB2-05":61.2962219872533,"GB2-06":47.542165687486495,"GB2-07":61.55310350712796,"GB2-08":89.0561664488203},"per_game_match_totals_all":{"GB2-01":{"draws":395,"losses":244,"wins":909},"GB2-02":{"draws":910,"losses":262,"wins":268},"GB2-03":{"draws":314,"losses":791,"wins":383},"GB2-04":{"draws":912,"losses":414,"wins":168},"GB2-05":{"draws":0,"losses":641,"wins":949},"GB2-06":{"draws":17,"losses":848,"wins":641},"GB2-07":{"draws":0,"losses":642,"wins":948},"GB2-08":{"draws":0,"losses":195,"wins":1419}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":105,"losses":41,"wins":370},"GB2-02":{"draws":236,"losses":86,"wins":158},"GB2-03":{"draws":112,"losses":235,"wins":149},"GB2-04":{"draws":212,"losses":179,"wins":107},"GB2-05":{"draws":0,"losses":148,"wins":382},"GB2-06":{"draws":4,"losses":249,"wins":249},"GB2-07":{"draws":0,"losses":242,"wins":288},"GB2-08":{"draws":0,"losses":56,"wins":482}},"medium":{"GB2-01":{"draws":44,"losses":70,"wins":402},"GB2-02":{"draws":310,"losses":80,"wins":90},"GB2-03":{"draws":131,"losses":165,"wins":200},"GB2-04":{"draws":345,"losses":120,"wins":33},"GB2-05":{"draws":0,"losses":182,"wins":348},"GB2-06":{"draws":9,"losses":293,"wins":200},"GB2-07":{"draws":0,"losses":230,"wins":300},"GB2-08":{"draws":0,"losses":68,"wins":470}},"none":{"GB2-01":{"draws":246,"losses":133,"wins":137},"GB2-02":{"draws":364,"losses":96,"wins":20},"GB2-03":{"draws":71,"losses":391,"wins":34},"GB2-04":{"draws":355,"losses":115,"wins":28},"GB2-05":{"draws":0,"losses":311,"wins":219},"GB2-06":{"draws":4,"losses":306,"wins":192},"GB2-07":{"draws":0,"losses":170,"wins":360},"GB2-08":{"draws":0,"losses":71,"wins":467}}},"per_game_raw_elo_all":{"GB2-01":1736.0358524530454,"GB2-02":1487.4585622189,"GB2-03":1326.6589660682102,"GB2-04":1424.1419628029246,"GB2-05":1598.8432011575603,"GB2-06":1380.3264814638485,"GB2-07":1599.3902292671755,"GB2-08":2146.510550379837},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1855.2428779573977,"GB2-02":1545.1621925603959,"GB2-03":1387.4578285693376,"GB2-04":1432.046036433539,"GB2-05":1778.6288957830384,"GB2-06":1484.521551262157,"GB2-07":1530.85146039846,"GB2-08":2193.0830495530367},"medium":{"GB2-01":1859.9336520309134,"GB2-02":1493.55954808756,"GB2-03":1497.1938142994109,"GB2-04":1420.1899259876172,"GB2-05":1670.5929793752987,"GB2-06":1344.1631239193207,"GB2-07":1559.0862455839742,"GB2-08":2130.567735495387},"none":{"GB2-01":1492.9310273708254,"GB2-02":1423.6539460087445,"GB2-03":1095.3252553358823,"GB2-04":1420.1899259876172,"GB2-05":1347.3077283143439,"GB2-06":1312.294769210068,"GB2-07":1708.2329818190922,"GB2-08":2115.880866091087}},"per_game_tracks":{"highest":{"GB2-01":83.62918652990561,"GB2-02":59.226870455125,"GB2-03":45.048116952234146,"GB2-04":44.47275945978772,"GB2-05":73.70732700376902,"GB2-06":54.234921394801226,"GB2-07":56.5630928487914,"GB2-08":90.52182189044443},"medium":{"GB2-01":83.90584256004632,"GB2-02":52.77860753249117,"GB2-03":57.35738888287932,"GB2-04":42.9432242922949,"GB2-05":67.37840016521139,"GB2-06":45.238808368219836,"GB2-07":58.72506198745043,"GB2-08":88.5681248926496},"none":{"GB2-01":52.50830729169304,"GB2-02":43.742107265297825,"GB2-03":15.998155087524344,"GB2-04":42.9432242922949,"GB2-05":42.802938792779486,"GB2-06":43.15276729943843,"GB2-07":69.37115568514204,"GB2-08":88.07855256336687}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:18:06Z","reasoning":{"highest":63.425512066857316,"medium":62.11193233515538,"none":49.824651034692124},"reasoning_agg":{"highest":{"max":90.52182189044443,"mean":63.425512066857316,"min":44.47275945978772},"medium":{"max":88.5681248926496,"mean":62.11193233515538,"min":42.9432242922949},"none":{"max":88.07855256336687,"mean":49.824651034692124,"min":15.998155087524344}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":13.600861032165191},"working_program_strength":{"all":58.45403181223494,"highest":63.425512066857316,"medium":62.11193233515538,"none":49.824651034692124}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-open:fa3d224e721a03ab","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333794999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985000000004},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.2214736}},"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":0.0828612,"mean":0.042346231250000005,"median":0.032108575,"min":0.0286407,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":0.33876985000000004},"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":0.053624950000000005,"mean":0.0276842,"median":0.025075325,"min":0.0206182,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.22147360000000002},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.10417243749999998,"median":0.11212245,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":8,"run_count":8,"total":0.8333794999999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.15589245,"mean":0.05806762291666667,"median":0.032108575,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":27,"run_count":24,"total":1.3936229500000001},"codegen_latency_ms":{"attempt_count":26,"max_ms":402561,"mean_ms":134621.65217391305,"min_ms":29772,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":7,"max_ms":402561,"mean_ms":285010.28571428574,"min_ms":177131,"run_count":7},"medium":{"attempt_count":10,"max_ms":176476,"mean_ms":81184.125,"min_ms":41325,"run_count":8},"none":{"attempt_count":9,"max_ms":171955,"mean_ms":56469.125,"min_ms":29772,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":34389,"output_mean":11455.5,"output_min":2743,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":34389,"output_mean":23554.125,"output_min":8453,"run_count":8},"medium":{"attempt_count":10,"output_max":13963,"output_mean":6880.875,"output_min":3882,"run_count":8},"none":{"attempt_count":9,"output_max":7898,"output_mean":3931.5,"output_min":2743,"run_count":8}},"display_name":"Muse Spark Open","economics":{"all":58.31828978315901,"highest":63.64371574156702,"medium":55.01011355818594,"none":56.301040049724065},"economics_best_value":{"per_model":{"none":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"infra_excluded"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":27,"effective_max_output_tokens":[943718],"finish_reason_observations":26,"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":[943718],"total_output_tokens":274932,"total_reasoning_output_tokens":170578,"total_visible_output_tokens":104354,"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":"unknown_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":943718,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"meta","provider_model":"meta/muse-spark-open","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"infra_failures_excluded":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_excluded_game_aliases":["GB2-02"],"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":69.59312894530592,"score":69.59312894530592},"GB2-02":{"attempts":2,"playable":45.00846947709871,"score":45.00846947709871},"GB2-03":{"attempts":3,"playable":52.908140006227946,"score":52.908140006227946},"GB2-04":{"attempts":3,"playable":44.500216034862945,"score":44.500216034862945},"GB2-05":{"attempts":3,"playable":52.18347364773496,"score":52.18347364773496},"GB2-06":{"attempts":3,"playable":63.035192508139026,"score":63.035192508139026},"GB2-07":{"attempts":3,"playable":54.818467966013806,"score":54.818467966013806},"GB2-08":{"attempts":3,"playable":78.28748092506602,"score":78.28748092506602}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":92.30778402816699,"score":92.30778402816699},"GB2-03":{"attempts":1,"playable":67.75720572819999,"score":67.75720572819999},"GB2-04":{"attempts":1,"playable":39.46772973737559,"score":39.46772973737559},"GB2-05":{"attempts":1,"playable":40.68352168575525,"score":40.68352168575525},"GB2-06":{"attempts":1,"playable":50.02313998054594,"score":50.02313998054594},"GB2-07":{"attempts":1,"playable":74.25761858859823,"score":74.25761858859823},"GB2-08":{"attempts":1,"playable":81.00901044232724,"score":81.00901044232724}},"medium":{"GB2-01":{"attempts":1,"playable":51.72667423366556,"score":51.72667423366556},"GB2-02":{"attempts":1,"playable":44.37561087159538,"score":44.37561087159538},"GB2-03":{"attempts":1,"playable":33.80963396776804,"score":33.80963396776804},"GB2-04":{"attempts":1,"playable":47.32128421481703,"score":47.32128421481703},"GB2-05":{"attempts":1,"playable":57.553187500582126,"score":57.553187500582126},"GB2-06":{"attempts":1,"playable":77.62716077363545,"score":77.62716077363545},"GB2-07":{"attempts":1,"playable":57.465333623522156,"score":57.465333623522156},"GB2-08":{"attempts":1,"playable":70.20202327990181,"score":70.20202327990181}},"none":{"GB2-01":{"attempts":1,"playable":64.74492857408521,"score":64.74492857408521},"GB2-02":{"attempts":1,"playable":45.64132808260204,"score":45.64132808260204},"GB2-03":{"attempts":1,"playable":57.157580322715795,"score":57.157580322715795},"GB2-04":{"attempts":1,"playable":46.711634152396215,"score":46.711634152396215},"GB2-05":{"attempts":1,"playable":58.31371175686749,"score":58.31371175686749},"GB2-06":{"attempts":1,"playable":61.45527677023569,"score":61.45527677023569},"GB2-07":{"attempts":1,"playable":32.73245168592104,"score":32.73245168592104},"GB2-08":{"attempts":1,"playable":83.65140905296903,"score":83.65140905296903}}},"id":"meta/muse-spark-open","is_recent_addition":false,"last_measured_at":"2026-10-27T23:46:14Z","match_totals_all":{"draws":2129,"losses":4120,"wins":5541},"match_totals_tracks":{"highest":{"draws":344,"losses":1211,"wins":2055},"medium":{"draws":971,"losses":1438,"wins":1681},"none":{"draws":814,"losses":1471,"wins":1805}},"model_slug":"meta-muse-spark-open","official_rank_by_reasoning":{"medium":29,"none":14},"overall":{"max":92.30778402816699,"mean":58.31828978315901,"min":32.73245168592104},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":20,"overall_ranking_status":"partial","per_game":{"GB2-01":92.30778402816699,"GB2-03":67.75720572819999,"GB2-04":39.46772973737559,"GB2-05":40.68352168575525,"GB2-06":50.02313998054594,"GB2-07":74.25761858859823,"GB2-08":81.00901044232724},"per_game_all":{"GB2-01":69.59312894530592,"GB2-03":52.908140006227946,"GB2-04":44.500216034862945,"GB2-05":52.18347364773496,"GB2-06":63.035192508139026,"GB2-07":54.818467966013806,"GB2-08":78.28748092506602},"per_game_match_totals_all":{"GB2-01":{"draws":200,"losses":398,"wins":950},"GB2-02":{"draws":708,"losses":190,"wins":62},"GB2-03":{"draws":297,"losses":605,"wins":586},"GB2-04":{"draws":879,"losses":415,"wins":200},"GB2-05":{"draws":0,"losses":786,"wins":804},"GB2-06":{"draws":45,"losses":587,"wins":874},"GB2-07":{"draws":0,"losses":749,"wins":841},"GB2-08":{"draws":0,"losses":390,"wins":1224}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":45,"wins":471},"GB2-03":{"draws":59,"losses":148,"wins":289},"GB2-04":{"draws":267,"losses":176,"wins":55},"GB2-05":{"draws":0,"losses":322,"wins":208},"GB2-06":{"draws":18,"losses":264,"wins":220},"GB2-07":{"draws":0,"losses":142,"wins":388},"GB2-08":{"draws":0,"losses":114,"wins":424}},"medium":{"GB2-01":{"draws":126,"losses":197,"wins":193},"GB2-02":{"draws":360,"losses":95,"wins":25},"GB2-03":{"draws":135,"losses":277,"wins":84},"GB2-04":{"draws":326,"losses":108,"wins":64},"GB2-05":{"draws":0,"losses":234,"wins":296},"GB2-06":{"draws":24,"losses":112,"wins":366},"GB2-07":{"draws":0,"losses":237,"wins":293},"GB2-08":{"draws":0,"losses":178,"wins":360}},"none":{"GB2-01":{"draws":74,"losses":156,"wins":286},"GB2-02":{"draws":348,"losses":95,"wins":37},"GB2-03":{"draws":103,"losses":180,"wins":213},"GB2-04":{"draws":286,"losses":131,"wins":81},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":3,"losses":211,"wins":288},"GB2-07":{"draws":0,"losses":370,"wins":160},"GB2-08":{"draws":0,"losses":98,"wins":440}}},"per_game_raw_elo_all":{"GB2-01":1715.9781962877867,"GB2-03":1462.223724323103,"GB2-04":1432.1245494180628,"GB2-05":1465.1585229519706,"GB2-06":1640.9760271893483,"GB2-07":1519.3785662981911,"GB2-08":1874.2248094191318},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2048.1459525156383,"GB2-03":1602.848711724572,"GB2-04":1392.9856978834107,"GB2-05":1320.233822221002,"GB2-06":1418.0537501655292,"GB2-07":1786.2261429739074,"GB2-08":1929.9620448532448},"medium":{"GB2-01":1485.4620848498218,"GB2-02":1428.5503097108551,"GB2-03":1288.4976564205856,"GB2-04":1454.046729936642,"GB2-05":1532.6581498200278,"GB2-06":1901.4033685707104,"GB2-07":1542.576459186274,"GB2-08":1697.7037110881636},"none":{"GB2-01":1614.3265514978998,"GB2-02":1438.316399435508,"GB2-03":1495.3248048241508,"GB2-04":1449.3412204341357,"GB2-05":1542.5835968148824,"GB2-06":1603.470962831805,"GB2-07":1229.3330967343927,"GB2-08":1995.0086723159873}},"per_game_tracks":{"highest":{"GB2-01":92.30778402816699,"GB2-03":67.75720572819999,"GB2-04":39.46772973737559,"GB2-05":40.68352168575525,"GB2-06":50.02313998054594,"GB2-07":74.25761858859823,"GB2-08":81.00901044232724},"medium":{"GB2-01":51.72667423366556,"GB2-02":44.37561087159538,"GB2-03":33.80963396776804,"GB2-04":47.32128421481703,"GB2-05":57.553187500582126,"GB2-06":77.62716077363545,"GB2-07":57.465333623522156,"GB2-08":70.20202327990181},"none":{"GB2-01":64.74492857408521,"GB2-02":45.64132808260204,"GB2-03":57.157580322715795,"GB2-04":46.711634152396215,"GB2-05":58.31371175686749,"GB2-06":61.45527677023569,"GB2-07":32.73245168592104,"GB2-08":83.65140905296903}},"program_outcomes":{"all":{"counted_attempts":23,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":20,"working":23},"highest":{"counted_attempts":7,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":63.64371574156702,"medium":55.01011355818594,"none":56.301040049724065},"reasoning_agg":{"highest":{"max":92.30778402816699,"mean":63.64371574156702,"min":39.46772973737559},"medium":{"max":77.62716077363545,"mean":55.01011355818594,"min":33.80963396776804},"none":{"max":83.65140905296903,"mean":56.301040049724065,"min":32.73245168592104}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.633602183381079},"working_program_strength":{"all":58.31828978315901,"highest":63.64371574156702,"medium":55.01011355818594,"none":56.301040049724065}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:c228ee386657944a","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":0.21156558000000003},"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":0.06816269999999999}},"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":0.06816269999999999},"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":0.48296143999999996}},"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":57.82658473778565,"highest":69.55473189939964,"medium":52.39304336551148,"none":51.53197894844583},"economics_best_value":{"per_model":{"all":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":61.75946826144144,"score":61.75946826144144},"GB2-02":{"attempts":3,"playable":54.668218586270456,"score":54.668218586270456},"GB2-03":{"attempts":3,"playable":63.31705849812033,"score":63.31705849812033},"GB2-04":{"attempts":3,"playable":61.94841336916996,"score":61.94841336916996},"GB2-05":{"attempts":3,"playable":56.285517196946586,"score":56.285517196946586},"GB2-06":{"attempts":3,"playable":67.3837399745144,"score":67.3837399745144},"GB2-07":{"attempts":3,"playable":66.11480796238432,"score":66.11480796238432},"GB2-08":{"attempts":3,"playable":31.135454053437694,"score":31.135454053437694}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":42.00912430254327,"score":42.00912430254327},"GB2-02":{"attempts":1,"playable":69.1753238331345,"score":69.1753238331345},"GB2-03":{"attempts":1,"playable":84.86379313403386,"score":84.86379313403386},"GB2-04":{"attempts":1,"playable":78.15585535733744,"score":78.15585535733744},"GB2-05":{"attempts":1,"playable":78.64293591969604,"score":78.64293591969604},"GB2-06":{"attempts":1,"playable":82.07330019702137,"score":82.07330019702137},"GB2-07":{"attempts":1,"playable":72.8661114453143,"score":72.8661114453143},"GB2-08":{"attempts":1,"playable":48.651411006116305,"score":48.651411006116305}},"medium":{"GB2-01":{"attempts":1,"playable":77.3669347936817,"score":77.3669347936817},"GB2-02":{"attempts":1,"playable":52.77860753249117,"score":52.77860753249117},"GB2-03":{"attempts":1,"playable":57.35738888287932,"score":57.35738888287932},"GB2-04":{"attempts":1,"playable":55.708583715665405,"score":55.708583715665405},"GB2-05":{"attempts":1,"playable":40.68352168575525,"score":40.68352168575525},"GB2-06":{"attempts":1,"playable":56.12703674841457,"score":56.12703674841457},"GB2-07":{"attempts":1,"playable":59.98087768457404,"score":59.98087768457404},"GB2-08":{"attempts":1,"playable":19.141395880630316,"score":19.141395880630316}},"none":{"GB2-01":{"attempts":1,"playable":65.90234568809935,"score":65.90234568809935},"GB2-02":{"attempts":1,"playable":42.050724393185696,"score":42.050724393185696},"GB2-03":{"attempts":1,"playable":47.72999347744781,"score":47.72999347744781},"GB2-04":{"attempts":1,"playable":51.98080103450703,"score":51.98080103450703},"GB2-05":{"attempts":1,"playable":49.53009398538846,"score":49.53009398538846},"GB2-06":{"attempts":1,"playable":63.95088297810726,"score":63.95088297810726},"GB2-07":{"attempts":1,"playable":65.49743475726461,"score":65.49743475726461},"GB2-08":{"attempts":1,"playable":25.61355527356647,"score":25.61355527356647}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-10-31T16:39:40Z","match_totals_all":{"draws":2359,"losses":4282,"wins":5629},"match_totals_tracks":{"highest":{"draws":524,"losses":1069,"wins":2497},"medium":{"draws":785,"losses":1660,"wins":1645},"none":{"draws":1050,"losses":1553,"wins":1487}},"model_slug":"z-ai-glm-5-3-flashx","official_rank_by_reasoning":{"highest":19,"medium":33,"none":18},"overall":{"max":84.86379313403386,"mean":57.82658473778565,"min":19.141395880630316},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.00912430254327,"GB2-02":69.1753238331345,"GB2-03":84.86379313403386,"GB2-04":78.15585535733744,"GB2-05":78.64293591969604,"GB2-06":82.07330019702137,"GB2-07":72.8661114453143,"GB2-08":48.651411006116305},"per_game_all":{"GB2-01":61.75946826144144,"GB2-02":54.668218586270456,"GB2-03":63.31705849812033,"GB2-04":61.94841336916996,"GB2-05":56.285517196946586,"GB2-06":67.3837399745144,"GB2-07":66.11480796238432,"GB2-08":31.135454053437694},"per_game_match_totals_all":{"GB2-01":{"draws":115,"losses":566,"wins":867},"GB2-02":{"draws":939,"losses":207,"wins":294},"GB2-03":{"draws":163,"losses":512,"wins":813},"GB2-04":{"draws":794,"losses":196,"wins":504},"GB2-05":{"draws":0,"losses":719,"wins":871},"GB2-06":{"draws":51,"losses":514,"wins":941},"GB2-07":{"draws":0,"losses":565,"wins":1025},"GB2-08":{"draws":297,"losses":1003,"wins":314}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":308,"wins":205},"GB2-02":{"draws":219,"losses":46,"wins":215},"GB2-03":{"draws":6,"losses":82,"wins":408},"GB2-04":{"draws":157,"losses":37,"wins":304},"GB2-05":{"draws":0,"losses":121,"wins":409},"GB2-06":{"draws":25,"losses":87,"wins":390},"GB2-07":{"draws":0,"losses":150,"wins":380},"GB2-08":{"draws":114,"losses":238,"wins":186}},"medium":{"GB2-01":{"draws":6,"losses":124,"wins":386},"GB2-02":{"draws":352,"losses":59,"wins":69},"GB2-03":{"draws":51,"losses":205,"wins":240},"GB2-04":{"draws":295,"losses":82,"wins":121},"GB2-05":{"draws":0,"losses":322,"wins":208},"GB2-06":{"draws":20,"losses":231,"wins":251},"GB2-07":{"draws":0,"losses":223,"wins":307},"GB2-08":{"draws":61,"losses":414,"wins":63}},"none":{"GB2-01":{"draws":106,"losses":134,"wins":276},"GB2-02":{"draws":368,"losses":102,"wins":10},"GB2-03":{"draws":106,"losses":225,"wins":165},"GB2-04":{"draws":342,"losses":77,"wins":79},"GB2-05":{"draws":0,"losses":276,"wins":254},"GB2-06":{"draws":6,"losses":196,"wins":300},"GB2-07":{"draws":0,"losses":192,"wins":338},"GB2-08":{"draws":122,"losses":351,"wins":65}}},"per_game_raw_elo_all":{"GB2-01":1593.6970388202417,"GB2-02":1512.377157212056,"GB2-03":1590.2566663234963,"GB2-04":1580.260161954254,"GB2-05":1544.7561245740578,"GB2-06":1717.963953570298,"GB2-07":1663.436609327299,"GB2-08":1168.194617348433},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1392.8058982853313,"GB2-02":1633.0338128418016,"GB2-03":1862.803884301587,"GB2-04":1731.1228776976432,"GB2-05":1882.6525604781746,"GB2-06":1992.4074987389506,"GB2-07":1763.0991362579668,"GB2-08":1369.9934364370527},"medium":{"GB2-01":1761.743347908226,"GB2-02":1493.55954808756,"GB2-03":1497.1938142994109,"GB2-04":1519.508555418225,"GB2-05":1320.233822221002,"GB2-06":1514.991991070141,"GB2-07":1575.7235999477089,"GB2-08":1026.467989309815},"none":{"GB2-01":1626.541870267168,"GB2-02":1410.538110706807,"GB2-03":1410.7723003694907,"GB2-04":1490.1490527468936,"GB2-05":1431.381991022997,"GB2-06":1646.492370901802,"GB2-07":1651.487091776221,"GB2-08":1108.1224262984317}},"per_game_tracks":{"highest":{"GB2-01":42.00912430254327,"GB2-02":69.1753238331345,"GB2-03":84.86379313403386,"GB2-04":78.15585535733744,"GB2-05":78.64293591969604,"GB2-06":82.07330019702137,"GB2-07":72.8661114453143,"GB2-08":48.651411006116305},"medium":{"GB2-01":77.3669347936817,"GB2-02":52.77860753249117,"GB2-03":57.35738888287932,"GB2-04":55.708583715665405,"GB2-05":40.68352168575525,"GB2-06":56.12703674841457,"GB2-07":59.98087768457404,"GB2-08":19.141395880630316},"none":{"GB2-01":65.90234568809935,"GB2-02":42.050724393185696,"GB2-03":47.72999347744781,"GB2-04":51.98080103450703,"GB2-05":49.53009398538846,"GB2-06":63.95088297810726,"GB2-07":65.49743475726461,"GB2-08":25.61355527356647}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":19,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:08:25Z","reasoning":{"highest":69.55473189939964,"medium":52.39304336551148,"none":51.53197894844583},"reasoning_agg":{"highest":{"max":84.86379313403386,"mean":69.55473189939964,"min":42.00912430254327},"medium":{"max":77.3669347936817,"mean":52.39304336551148,"min":19.141395880630316},"none":{"max":65.90234568809935,"mean":51.53197894844583,"min":25.61355527356647}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":18.02275295095381},"working_program_strength":{"all":57.82658473778565,"highest":69.55473189939964,"medium":52.39304336551148,"none":51.53197894844583}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-haiku-5-5:c169a5f28df68275","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":0.09558079999999998},"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":0.024963200000000005},"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":0.5031476},"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":57.28834724265332,"highest":74.83616201466768,"medium":57.65443636629913,"none":39.37444334699315},"economics_best_value":{"per_model":{"all":true,"highest":true},"per_setting":{"highest":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"infra_excluded"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":40.81746779835844,"score":40.81746779835844},"GB2-02":{"attempts":3,"playable":58.565000514955415,"score":58.565000514955415},"GB2-03":{"attempts":2,"playable":55.516727280862625,"score":55.516727280862625},"GB2-04":{"attempts":3,"playable":63.28555831100325,"score":63.28555831100325},"GB2-05":{"attempts":3,"playable":53.38617200282656,"score":53.38617200282656},"GB2-06":{"attempts":3,"playable":69.95833420845231,"score":69.95833420845231},"GB2-07":{"attempts":3,"playable":58.676980129252335,"score":58.676980129252335},"GB2-08":{"attempts":3,"playable":51.660726117580595,"score":51.660726117580595}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.516099100293424,"score":41.516099100293424},"GB2-02":{"attempts":1,"playable":70.5946935483142,"score":70.5946935483142},"GB2-04":{"attempts":1,"playable":79.78396063438417,"score":79.78396063438417},"GB2-05":{"attempts":1,"playable":86.37272348569375,"score":86.37272348569375},"GB2-06":{"attempts":1,"playable":91.81069752094925,"score":91.81069752094925},"GB2-07":{"attempts":1,"playable":67.08604926778634,"score":67.08604926778634},"GB2-08":{"attempts":1,"playable":86.6889105452526,"score":86.6889105452526}},"medium":{"GB2-01":{"attempts":1,"playable":45.55246165850003,"score":45.55246165850003},"GB2-02":{"attempts":1,"playable":62.83800132764947,"score":62.83800132764947},"GB2-03":{"attempts":1,"playable":67.8534530834536,"score":67.8534530834536},"GB2-04":{"attempts":1,"playable":67.94620767676626,"score":67.94620767676626},"GB2-05":{"attempts":1,"playable":57.553187500582126,"score":57.553187500582126},"GB2-06":{"attempts":1,"playable":68.7181265542529,"score":68.7181265542529},"GB2-07":{"attempts":1,"playable":56.92423457896623,"score":56.92423457896623},"GB2-08":{"attempts":1,"playable":33.84981855022246,"score":33.84981855022246}},"none":{"GB2-01":{"attempts":1,"playable":35.383842636281884,"score":35.383842636281884},"GB2-02":{"attempts":1,"playable":42.26230666890257,"score":42.26230666890257},"GB2-03":{"attempts":1,"playable":43.18000147827165,"score":43.18000147827165},"GB2-04":{"attempts":1,"playable":42.12650662185929,"score":42.12650662185929},"GB2-05":{"attempts":1,"playable":16.23260502220381,"score":16.23260502220381},"GB2-06":{"attempts":1,"playable":49.34617855015477,"score":49.34617855015477},"GB2-07":{"attempts":1,"playable":52.02065654100442,"score":52.02065654100442},"GB2-08":{"attempts":1,"playable":34.44344925726674,"score":34.44344925726674}}},"id":"claude-haiku-5-5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:02:28Z","match_totals_all":{"draws":2603,"losses":4076,"wins":5095},"match_totals_tracks":{"highest":{"draws":395,"losses":755,"wins":2444},"medium":{"draws":943,"losses":1369,"wins":1778},"none":{"draws":1265,"losses":1952,"wins":873}},"model_slug":"claude-haiku-5-5","official_rank_by_reasoning":{"medium":25,"none":45},"overall":{"max":91.81069752094925,"mean":57.28834724265332,"min":16.23260502220381},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":22,"overall_ranking_status":"partial","per_game":{"GB2-01":41.516099100293424,"GB2-02":70.5946935483142,"GB2-04":79.78396063438417,"GB2-05":86.37272348569375,"GB2-06":91.81069752094925,"GB2-07":67.08604926778634,"GB2-08":86.6889105452526},"per_game_all":{"GB2-01":40.81746779835844,"GB2-02":58.565000514955415,"GB2-04":63.28555831100325,"GB2-05":53.38617200282656,"GB2-06":69.95833420845231,"GB2-07":58.676980129252335,"GB2-08":51.660726117580595},"per_game_match_totals_all":{"GB2-01":{"draws":257,"losses":818,"wins":473},"GB2-02":{"draws":846,"losses":197,"wins":397},"GB2-03":{"draws":276,"losses":339,"wins":377},"GB2-04":{"draws":635,"losses":254,"wins":605},"GB2-05":{"draws":0,"losses":760,"wins":830},"GB2-06":{"draws":62,"losses":464,"wins":980},"GB2-07":{"draws":0,"losses":690,"wins":900},"GB2-08":{"draws":527,"losses":554,"wins":533}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":34,"losses":295,"wins":187},"GB2-02":{"draws":215,"losses":41,"wins":224},"GB2-04":{"draws":106,"losses":54,"wins":338},"GB2-05":{"draws":0,"losses":77,"wins":453},"GB2-06":{"draws":39,"losses":26,"wins":437},"GB2-07":{"draws":0,"losses":183,"wins":347},"GB2-08":{"draws":1,"losses":79,"wins":458}},"medium":{"GB2-01":{"draws":133,"losses":225,"wins":158},"GB2-02":{"draws":251,"losses":61,"wins":168},"GB2-03":{"draws":94,"losses":130,"wins":272},"GB2-04":{"draws":208,"losses":64,"wins":226},"GB2-05":{"draws":0,"losses":234,"wins":296},"GB2-06":{"draws":6,"losses":170,"wins":326},"GB2-07":{"draws":0,"losses":240,"wins":290},"GB2-08":{"draws":251,"losses":245,"wins":42}},"none":{"GB2-01":{"draws":90,"losses":298,"wins":128},"GB2-02":{"draws":380,"losses":95,"wins":5},"GB2-03":{"draws":182,"losses":209,"wins":105},"GB2-04":{"draws":321,"losses":136,"wins":41},"GB2-05":{"draws":0,"losses":449,"wins":81},"GB2-06":{"draws":17,"losses":268,"wins":217},"GB2-07":{"draws":0,"losses":267,"wins":263},"GB2-08":{"draws":275,"losses":230,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1380.8225110503354,"GB2-02":1544.8757611736817,"GB2-04":1596.3451876140577,"GB2-05":1525.6858078372827,"GB2-06":1792.3405782362631,"GB2-07":1560.9004384020363,"GB2-08":1495.2254880746798},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1388.053057676658,"GB2-02":1646.9132332046936,"GB2-04":1751.4219141666179,"GB2-05":2106.7257086123764,"GB2-06":2237.793473852942,"GB2-07":1674.3291880445922,"GB2-08":2075.8649347324636},"medium":{"GB2-01":1426.7158799442684,"GB2-02":1575.5310363214958,"GB2-03":1603.9293314025122,"GB2-04":1623.777657728853,"GB2-05":1532.6581498200278,"GB2-06":1731.716043996489,"GB2-07":1535.5352186762796,"GB2-08":1201.622636075387},"none":{"GB2-01":1327.6985955300802,"GB2-02":1412.183013994855,"GB2-03":1371.2554782985903,"GB2-04":1413.8359909467022,"GB2-05":937.6735650794445,"GB2-06":1407.512216859358,"GB2-07":1472.8369084852372,"GB2-08":1208.1888934161886}},"per_game_tracks":{"highest":{"GB2-01":41.516099100293424,"GB2-02":70.5946935483142,"GB2-04":79.78396063438417,"GB2-05":86.37272348569375,"GB2-06":91.81069752094925,"GB2-07":67.08604926778634,"GB2-08":86.6889105452526},"medium":{"GB2-01":45.55246165850003,"GB2-02":62.83800132764947,"GB2-03":67.8534530834536,"GB2-04":67.94620767676626,"GB2-05":57.553187500582126,"GB2-06":68.7181265542529,"GB2-07":56.92423457896623,"GB2-08":33.84981855022246},"none":{"GB2-01":35.383842636281884,"GB2-02":42.26230666890257,"GB2-03":43.18000147827165,"GB2-04":42.12650662185929,"GB2-05":16.23260502220381,"GB2-06":49.34617855015477,"GB2-07":52.02065654100442,"GB2-08":34.44344925726674}},"program_outcomes":{"all":{"counted_attempts":23,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":22,"working":23},"highest":{"counted_attempts":7,"failed":0,"infra_excluded":1,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":74.83616201466768,"medium":57.65443636629913,"none":39.37444334699315},"reasoning_agg":{"highest":{"max":91.81069752094925,"mean":74.83616201466768,"min":41.516099100293424},"medium":{"max":68.7181265542529,"mean":57.65443636629913,"min":33.84981855022246},"none":{"max":52.02065654100442,"mean":39.37444334699315,"min":16.23260502220381}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":35.46171866767453},"working_program_strength":{"all":57.28834724265332,"highest":74.83616201466768,"medium":57.65443636629913,"none":39.37444334699315}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:3a66a45fd2484e0f","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":0.04628865},"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":0.19534587500000003},"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":56.93507582226283,"highest":59.12651113912252,"medium":63.474375917973155,"none":48.20434040969281},"economics_best_value":{"per_model":{"all":true,"highest":true,"medium":true,"none":true},"per_setting":{"medium":true,"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":58.11827923896609,"score":58.11827923896609},"GB2-02":{"attempts":3,"playable":52.638384221640244,"score":52.638384221640244},"GB2-03":{"attempts":3,"playable":72.02258872408538,"score":72.02258872408538},"GB2-04":{"attempts":3,"playable":72.43937313795567,"score":72.43937313795567},"GB2-05":{"attempts":3,"playable":53.47655978876557,"score":53.47655978876557},"GB2-06":{"attempts":3,"playable":47.6440781225839,"score":47.6440781225839},"GB2-07":{"attempts":3,"playable":72.33724101239176,"score":72.33724101239176},"GB2-08":{"attempts":3,"playable":26.80410233171401,"score":26.80410233171401}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":65.99872530832613,"score":65.99872530832613},"GB2-02":{"attempts":1,"playable":66.52761490637418,"score":66.52761490637418},"GB2-03":{"attempts":1,"playable":78.56762844837525,"score":78.56762844837525},"GB2-04":{"attempts":1,"playable":78.92295644625212,"score":78.92295644625212},"GB2-05":{"attempts":1,"playable":74.26053822340887,"score":74.26053822340887},"GB2-06":{"attempts":1,"playable":16.982100171333386,"score":16.982100171333386},"GB2-07":{"attempts":1,"playable":69.72174524050753,"score":69.72174524050753},"GB2-08":{"attempts":1,"playable":22.03078036840265,"score":22.03078036840265}},"medium":{"GB2-01":{"attempts":1,"playable":71.08927913510176,"score":71.08927913510176},"GB2-02":{"attempts":1,"playable":46.37885098681369,"score":46.37885098681369},"GB2-03":{"attempts":1,"playable":80.84263448466797,"score":80.84263448466797},"GB2-04":{"attempts":1,"playable":74.10237850204857,"score":74.10237850204857},"GB2-05":{"attempts":1,"playable":48.57098662831747,"score":48.57098662831747},"GB2-06":{"attempts":1,"playable":81.80112947102765,"score":81.80112947102765},"GB2-07":{"attempts":1,"playable":75.81898482243845,"score":75.81898482243845},"GB2-08":{"attempts":1,"playable":29.190763313369704,"score":29.190763313369704}},"none":{"GB2-01":{"attempts":1,"playable":37.266833273470354,"score":37.266833273470354},"GB2-02":{"attempts":1,"playable":45.008686771732854,"score":45.008686771732854},"GB2-03":{"attempts":1,"playable":56.65750323921293,"score":56.65750323921293},"GB2-04":{"attempts":1,"playable":64.29278446556636,"score":64.29278446556636},"GB2-05":{"attempts":1,"playable":37.59815451457036,"score":37.59815451457036},"GB2-06":{"attempts":1,"playable":44.14900472539066,"score":44.14900472539066},"GB2-07":{"attempts":1,"playable":71.47099297422929,"score":71.47099297422929},"GB2-08":{"attempts":1,"playable":29.190763313369683,"score":29.190763313369683}}},"id":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T16:55:05Z","match_totals_all":{"draws":2158,"losses":4478,"wins":5634},"match_totals_tracks":{"highest":{"draws":453,"losses":1533,"wins":2104},"medium":{"draws":705,"losses":1226,"wins":2159},"none":{"draws":1000,"losses":1719,"wins":1371}},"model_slug":"z-ai-glm-5-3-flash","official_rank_by_reasoning":{"highest":34,"medium":18,"none":26},"overall":{"max":81.80112947102765,"mean":56.93507582226283,"min":16.982100171333386},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":23,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.99872530832613,"GB2-02":66.52761490637418,"GB2-03":78.56762844837525,"GB2-04":78.92295644625212,"GB2-05":74.26053822340887,"GB2-06":16.982100171333386,"GB2-07":69.72174524050753,"GB2-08":22.03078036840265},"per_game_all":{"GB2-01":58.11827923896609,"GB2-02":52.638384221640244,"GB2-03":72.02258872408538,"GB2-04":72.43937313795567,"GB2-05":53.47655978876557,"GB2-06":47.6440781225839,"GB2-07":72.33724101239176,"GB2-08":26.80410233171401},"per_game_match_totals_all":{"GB2-01":{"draws":242,"losses":559,"wins":747},"GB2-02":{"draws":956,"losses":228,"wins":256},"GB2-03":{"draws":147,"losses":388,"wins":953},"GB2-04":{"draws":499,"losses":185,"wins":810},"GB2-05":{"draws":0,"losses":764,"wins":826},"GB2-06":{"draws":56,"losses":806,"wins":644},"GB2-07":{"draws":0,"losses":459,"wins":1131},"GB2-08":{"draws":258,"losses":1089,"wins":267}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":5,"losses":184,"wins":327},"GB2-02":{"draws":245,"losses":46,"wins":189},"GB2-03":{"draws":8,"losses":116,"wins":372},"GB2-04":{"draws":137,"losses":43,"wins":318},"GB2-05":{"draws":0,"losses":145,"wins":385},"GB2-06":{"draws":14,"losses":423,"wins":65},"GB2-07":{"draws":0,"losses":168,"wins":362},"GB2-08":{"draws":44,"losses":408,"wins":86}},"medium":{"GB2-01":{"draws":20,"losses":150,"wins":346},"GB2-02":{"draws":349,"losses":91,"wins":40},"GB2-03":{"draws":25,"losses":95,"wins":376},"GB2-04":{"draws":159,"losses":57,"wins":282},"GB2-05":{"draws":0,"losses":281,"wins":249},"GB2-06":{"draws":32,"losses":85,"wins":385},"GB2-07":{"draws":0,"losses":133,"wins":397},"GB2-08":{"draws":120,"losses":334,"wins":84}},"none":{"GB2-01":{"draws":217,"losses":225,"wins":74},"GB2-02":{"draws":362,"losses":91,"wins":27},"GB2-03":{"draws":114,"losses":177,"wins":205},"GB2-04":{"draws":203,"losses":85,"wins":210},"GB2-05":{"draws":0,"losses":338,"wins":192},"GB2-06":{"draws":10,"losses":298,"wins":194},"GB2-07":{"draws":0,"losses":158,"wins":372},"GB2-08":{"draws":94,"losses":347,"wins":97}}},"per_game_raw_elo_all":{"GB2-01":1552.6736387079509,"GB2-02":1495.2186416961695,"GB2-03":1673.2210334453123,"GB2-04":1672.1363835484578,"GB2-05":1496.1987040488548,"GB2-06":1406.23573989597,"GB2-07":1755.8398293313687,"GB2-08":1121.1386467895409},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1627.5674066011793,"GB2-02":1608.2176186568772,"GB2-03":1745.447333380417,"GB2-04":1740.5394165828366,"GB2-05":1789.2394520608145,"GB2-06":904.5649260997758,"GB2-07":1713.5586734966937,"GB2-08":1064.3593101127774},"medium":{"GB2-01":1683.9249758149515,"GB2-02":1444.001059081438,"GB2-03":1783.5498570824875,"GB2-04":1685.0412485856693,"GB2-05":1419.468782960289,"GB2-06":1986.6483514541806,"GB2-07":1813.2641791423544,"GB2-08":1149.5283151279227},"none":{"GB2-01":1346.5285337077225,"GB2-02":1433.4372473501935,"GB2-03":1490.6659098730324,"GB2-04":1590.828485476867,"GB2-05":1279.887877125461,"GB2-06":1327.4939421339539,"GB2-07":1740.696635355058,"GB2-08":1149.5283151279225}},"per_game_tracks":{"highest":{"GB2-01":65.99872530832613,"GB2-02":66.52761490637418,"GB2-03":78.56762844837525,"GB2-04":78.92295644625212,"GB2-05":74.26053822340887,"GB2-06":16.982100171333386,"GB2-07":69.72174524050753,"GB2-08":22.03078036840265},"medium":{"GB2-01":71.08927913510176,"GB2-02":46.37885098681369,"GB2-03":80.84263448466797,"GB2-04":74.10237850204857,"GB2-05":48.57098662831747,"GB2-06":81.80112947102765,"GB2-07":75.81898482243845,"GB2-08":29.190763313369704},"none":{"GB2-01":37.266833273470354,"GB2-02":45.008686771732854,"GB2-03":56.65750323921293,"GB2-04":64.29278446556636,"GB2-05":37.59815451457036,"GB2-06":44.14900472539066,"GB2-07":71.47099297422929,"GB2-08":29.190763313369683}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:37:36Z","reasoning":{"highest":59.12651113912252,"medium":63.474375917973155,"none":48.20434040969281},"reasoning_agg":{"highest":{"max":78.92295644625212,"mean":59.12651113912252,"min":16.982100171333386},"medium":{"max":81.80112947102765,"mean":63.474375917973155,"min":29.190763313369704},"none":{"max":71.47099297422929,"mean":48.20434040969281,"min":29.190763313369683}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":15.270035508280344},"working_program_strength":{"all":56.93507582226283,"highest":59.12651113912252,"medium":63.474375917973155,"none":48.20434040969281}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:27f0ad746deb6345","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":3.1890240000000007},"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":0.873722},"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":0.9697739999999999}},"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":0.8737219999999999},"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":5.032520000000001},"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":55.41313294349275,"highest":70.24120267368225,"medium":44.97378840578687,"none":51.02440775100915},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":48.37772478958933,"score":48.37772478958933},"GB2-02":{"attempts":3,"playable":46.82839921327162,"score":46.82839921327162},"GB2-03":{"attempts":3,"playable":61.49638485707376,"score":61.49638485707376},"GB2-04":{"attempts":3,"playable":56.01456604240597,"score":56.01456604240597},"GB2-05":{"attempts":3,"playable":65.33339663041112,"score":65.33339663041112},"GB2-06":{"attempts":3,"playable":68.63658136281362,"score":68.63658136281362},"GB2-07":{"attempts":3,"playable":50.76066630956285,"score":50.76066630956285},"GB2-08":{"attempts":3,"playable":45.85734434281386,"score":45.85734434281386}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":76.6106405694137,"score":76.6106405694137},"GB2-02":{"attempts":1,"playable":49.6375012766101,"score":49.6375012766101},"GB2-03":{"attempts":1,"playable":71.57780906043338,"score":71.57780906043338},"GB2-04":{"attempts":1,"playable":84.6217405965923,"score":84.6217405965923},"GB2-05":{"attempts":1,"playable":92.40190828557452,"score":92.40190828557452},"GB2-06":{"attempts":1,"playable":64.31928435320305,"score":64.31928435320305},"GB2-07":{"attempts":1,"playable":76.3385285884776,"score":76.3385285884776},"GB2-08":{"attempts":1,"playable":46.422208659153405,"score":46.422208659153405}},"medium":{"GB2-01":{"attempts":1,"playable":26.316261127613792,"score":26.316261127613792},"GB2-02":{"attempts":1,"playable":48.90277993281108,"score":48.90277993281108},"GB2-03":{"attempts":1,"playable":57.457245401265936,"score":57.457245401265936},"GB2-04":{"attempts":1,"playable":45.49109922101121,"score":45.49109922101121},"GB2-05":{"attempts":1,"playable":43.765649087864375,"score":43.765649087864375},"GB2-06":{"attempts":1,"playable":60.061514276627314,"score":60.061514276627314},"GB2-07":{"attempts":1,"playable":36.55145307533581,"score":36.55145307533581},"GB2-08":{"attempts":1,"playable":41.24430512376548,"score":41.24430512376548}},"none":{"GB2-01":{"attempts":1,"playable":42.206272671740486,"score":42.206272671740486},"GB2-02":{"attempts":1,"playable":41.94491643039368,"score":41.94491643039368},"GB2-03":{"attempts":1,"playable":55.45410010952195,"score":55.45410010952195},"GB2-04":{"attempts":1,"playable":37.9308583096144,"score":37.9308583096144},"GB2-05":{"attempts":1,"playable":59.83263251779442,"score":59.83263251779442},"GB2-06":{"attempts":1,"playable":81.5289454586105,"score":81.5289454586105},"GB2-07":{"attempts":1,"playable":39.39201726487513,"score":39.39201726487513},"GB2-08":{"attempts":1,"playable":49.9055192455227,"score":49.9055192455227}}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-10-31T16:53:32Z","match_totals_all":{"draws":2905,"losses":4303,"wins":5062},"match_totals_tracks":{"highest":{"draws":815,"losses":887,"wins":2388},"medium":{"draws":976,"losses":1873,"wins":1241},"none":{"draws":1114,"losses":1543,"wins":1433}},"model_slug":"qwen-qwen3-8-max-0902","official_rank_by_reasoning":{"highest":17,"medium":47,"none":22},"overall":{"max":92.40190828557452,"mean":55.41313294349275,"min":26.316261127613792},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":76.6106405694137,"GB2-02":49.6375012766101,"GB2-03":71.57780906043338,"GB2-04":84.6217405965923,"GB2-05":92.40190828557452,"GB2-06":64.31928435320305,"GB2-07":76.3385285884776,"GB2-08":46.422208659153405},"per_game_all":{"GB2-01":48.37772478958933,"GB2-02":46.82839921327162,"GB2-03":61.49638485707376,"GB2-04":56.01456604240597,"GB2-05":65.33339663041112,"GB2-06":68.63658136281362,"GB2-07":50.76066630956285,"GB2-08":45.85734434281386},"per_game_match_totals_all":{"GB2-01":{"draws":306,"losses":675,"wins":567},"GB2-02":{"draws":1040,"losses":270,"wins":130},"GB2-03":{"draws":275,"losses":490,"wins":723},"GB2-04":{"draws":709,"losses":324,"wins":461},"GB2-05":{"draws":0,"losses":569,"wins":1021},"GB2-06":{"draws":97,"losses":471,"wins":938},"GB2-07":{"draws":0,"losses":815,"wins":775},"GB2-08":{"draws":478,"losses":689,"wins":447}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":130,"wins":384},"GB2-02":{"draws":330,"losses":85,"wins":65},"GB2-03":{"draws":93,"losses":111,"wins":292},"GB2-04":{"draws":89,"losses":37,"wins":372},"GB2-05":{"draws":0,"losses":41,"wins":489},"GB2-06":{"draws":52,"losses":171,"wins":279},"GB2-07":{"draws":0,"losses":130,"wins":400},"GB2-08":{"draws":249,"losses":182,"wins":107}},"medium":{"GB2-01":{"draws":95,"losses":341,"wins":80},"GB2-02":{"draws":353,"losses":77,"wins":50},"GB2-03":{"draws":90,"losses":185,"wins":221},"GB2-04":{"draws":320,"losses":120,"wins":58},"GB2-05":{"draws":0,"losses":306,"wins":224},"GB2-06":{"draws":16,"losses":212,"wins":274},"GB2-07":{"draws":0,"losses":350,"wins":180},"GB2-08":{"draws":102,"losses":282,"wins":154}},"none":{"GB2-01":{"draws":209,"losses":204,"wins":103},"GB2-02":{"draws":357,"losses":108,"wins":15},"GB2-03":{"draws":92,"losses":194,"wins":210},"GB2-04":{"draws":300,"losses":167,"wins":31},"GB2-05":{"draws":0,"losses":222,"wins":308},"GB2-06":{"draws":29,"losses":88,"wins":385},"GB2-07":{"draws":0,"losses":335,"wins":195},"GB2-08":{"draws":127,"losses":225,"wins":186}}},"per_game_raw_elo_all":{"GB2-01":1459.0162214694117,"GB2-02":1447.4389215647816,"GB2-03":1541.8415914224322,"GB2-04":1547.0047033261606,"GB2-05":1760.9417263444793,"GB2-06":1737.9191626165164,"GB2-07":1472.2025147671484,"GB2-08":1337.4593208590188},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1751.7125235315461,"GB2-02":1469.1396449017009,"GB2-03":1647.8368965146492,"GB2-04":1820.3177420785278,"GB2-05":2360.6681427205285,"GB2-06":1652.9353020212845,"GB2-07":1822.5512784886669,"GB2-08":1343.276931152785},"medium":{"GB2-01":1230.6326138174784,"GB2-02":1463.4621107359083,"GB2-03":1498.1295227049418,"GB2-04":1439.9179531399868,"GB2-05":1359.4742126058347,"GB2-06":1579.9036620946044,"GB2-07":1279.000280251939,"GB2-08":1283.7065223004918},"none":{"GB2-01":1394.7035270592103,"GB2-02":1409.7150090567357,"GB2-03":1479.5583550477058,"GB2-04":1380.7784147599664,"GB2-05":1562.6828237070747,"GB2-06":1980.9185237336596,"GB2-07":1315.0559855608392,"GB2-08":1385.39450912378}},"per_game_tracks":{"highest":{"GB2-01":76.6106405694137,"GB2-02":49.6375012766101,"GB2-03":71.57780906043338,"GB2-04":84.6217405965923,"GB2-05":92.40190828557452,"GB2-06":64.31928435320305,"GB2-07":76.3385285884776,"GB2-08":46.422208659153405},"medium":{"GB2-01":26.316261127613792,"GB2-02":48.90277993281108,"GB2-03":57.457245401265936,"GB2-04":45.49109922101121,"GB2-05":43.765649087864375,"GB2-06":60.061514276627314,"GB2-07":36.55145307533581,"GB2-08":41.24430512376548},"none":{"GB2-01":42.206272671740486,"GB2-02":41.94491643039368,"GB2-03":55.45410010952195,"GB2-04":37.9308583096144,"GB2-05":59.83263251779442,"GB2-06":81.5289454586105,"GB2-07":39.39201726487513,"GB2-08":49.9055192455227}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":19,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:07:49Z","reasoning":{"highest":70.24120267368225,"medium":44.97378840578687,"none":51.02440775100915},"reasoning_agg":{"highest":{"max":92.40190828557452,"mean":70.24120267368225,"min":46.422208659153405},"medium":{"max":60.061514276627314,"mean":44.97378840578687,"min":26.316261127613792},"none":{"max":81.5289454586105,"mean":51.02440775100915,"min":37.9308583096144}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.267414267895383},"working_program_strength":{"all":55.41313294349275,"highest":70.24120267368225,"medium":44.97378840578687,"none":51.02440775100915}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:6761d8d2ef5e7731","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":12.15224},"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":0.7687025000000001}},"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":0.7687025},"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":55.22058182006023,"highest":63.641076951767516,"medium":55.19946139561091,"none":46.82120711280228},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":91.13460546083282,"score":91.13460546083282},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.94281021300134,"score":28.62854014200089},"GB2-03":{"attempts":3,"playable":40.496446074611384,"score":40.496446074611384},"GB2-04":{"attempts":3,"playable":42.85664878190346,"score":42.85664878190346},"GB2-05":{"attempts":3,"playable":73.08142255668417,"score":73.08142255668417},"GB2-06":{"attempts":3,"playable":73.85134385447866,"score":73.85134385447866},"GB2-07":{"attempts":3,"playable":46.697426503939035,"score":46.697426503939035},"GB2-08":{"attempts":3,"playable":45.018221186031475,"score":45.018221186031475}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":95.24684945533983,"score":95.24684945533983},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.42644358426692,"score":44.42644358426692},"GB2-04":{"attempts":1,"playable":56.411660955116936,"score":56.411660955116936},"GB2-05":{"attempts":1,"playable":86.0321664811842,"score":86.0321664811842},"GB2-06":{"attempts":1,"playable":81.61967477554526,"score":81.61967477554526},"GB2-07":{"attempts":1,"playable":77.72188078652425,"score":77.72188078652425},"GB2-08":{"attempts":1,"playable":67.6699395761627,"score":67.6699395761627}},"medium":{"GB2-01":{"attempts":1,"playable":97.50072570324825,"score":97.50072570324825},"GB2-02":{"attempts":1,"playable":46.58945983591505,"score":46.58945983591505},"GB2-03":{"attempts":1,"playable":44.42644358426692,"score":44.42644358426692},"GB2-04":{"attempts":1,"playable":32.69055565321784,"score":32.69055565321784},"GB2-05":{"attempts":1,"playable":71.4850270328087,"score":71.4850270328087},"GB2-06":{"attempts":1,"playable":76.62896100280021,"score":76.62896100280021},"GB2-07":{"attempts":1,"playable":33.88199520119422,"score":33.88199520119422},"GB2-08":{"attempts":1,"playable":38.392523151436066,"score":38.392523151436066}},"none":{"GB2-01":{"attempts":1,"playable":80.65624122391038,"score":80.65624122391038},"GB2-02":{"attempts":1,"playable":39.29616059008762,"score":39.29616059008762},"GB2-03":{"attempts":1,"playable":32.636451055300306,"score":32.636451055300306},"GB2-04":{"attempts":1,"playable":39.46772973737559,"score":39.46772973737559},"GB2-05":{"attempts":1,"playable":61.7270741560596,"score":61.7270741560596},"GB2-06":{"attempts":1,"playable":63.30539578509047,"score":63.30539578509047},"GB2-07":{"attempts":1,"playable":28.488403524098622,"score":28.488403524098622},"GB2-08":{"attempts":1,"playable":28.992200830495662,"score":28.992200830495662}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-10-31T16:10:51Z","match_totals_all":{"draws":2470,"losses":3993,"wins":5327},"match_totals_tracks":{"highest":{"draws":490,"losses":798,"wins":2322},"medium":{"draws":983,"losses":1424,"wins":1683},"none":{"draws":997,"losses":1771,"wins":1322}},"model_slug":"gpt-5-4","official_rank_by_reasoning":{"highest":29,"medium":28,"none":28},"overall":{"max":97.50072570324825,"mean":55.22058182006023,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":95.24684945533983,"GB2-03":44.42644358426692,"GB2-04":56.411660955116936,"GB2-05":86.0321664811842,"GB2-06":81.61967477554526,"GB2-07":77.72188078652425,"GB2-08":67.6699395761627},"per_game_all":{"GB2-01":91.13460546083282,"GB2-03":40.496446074611384,"GB2-04":42.85664878190346,"GB2-05":73.08142255668417,"GB2-06":73.85134385447866,"GB2-07":46.697426503939035,"GB2-08":45.018221186031475},"per_game_match_totals_all":{"GB2-01":{"draws":71,"losses":115,"wins":1362},"GB2-02":{"draws":715,"losses":206,"wins":39},"GB2-03":{"draws":542,"losses":667,"wins":279},"GB2-04":{"draws":820,"losses":468,"wins":206},"GB2-05":{"draws":0,"losses":451,"wins":1139},"GB2-06":{"draws":60,"losses":404,"wins":1042},"GB2-07":{"draws":0,"losses":878,"wins":712},"GB2-08":{"draws":262,"losses":804,"wins":548}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":13,"losses":21,"wins":482},"GB2-03":{"draws":146,"losses":221,"wins":129},"GB2-04":{"draws":260,"losses":96,"wins":142},"GB2-05":{"draws":0,"losses":79,"wins":451},"GB2-06":{"draws":36,"losses":84,"wins":382},"GB2-07":{"draws":0,"losses":122,"wins":408},"GB2-08":{"draws":35,"losses":175,"wins":328}},"medium":{"GB2-01":{"draws":7,"losses":10,"wins":499},"GB2-02":{"draws":369,"losses":80,"wins":31},"GB2-03":{"draws":224,"losses":182,"wins":90},"GB2-04":{"draws":257,"losses":214,"wins":27},"GB2-05":{"draws":0,"losses":160,"wins":370},"GB2-06":{"draws":17,"losses":121,"wins":364},"GB2-07":{"draws":0,"losses":364,"wins":166},"GB2-08":{"draws":109,"losses":293,"wins":136}},"none":{"GB2-01":{"draws":51,"losses":84,"wins":381},"GB2-02":{"draws":346,"losses":126,"wins":8},"GB2-03":{"draws":172,"losses":264,"wins":60},"GB2-04":{"draws":303,"losses":158,"wins":37},"GB2-05":{"draws":0,"losses":212,"wins":318},"GB2-06":{"draws":7,"losses":199,"wins":296},"GB2-07":{"draws":0,"losses":392,"wins":138},"GB2-08":{"draws":118,"losses":336,"wins":84}}},"per_game_raw_elo_all":{"GB2-01":2088.441346349389,"GB2-03":1347.2881445546384,"GB2-04":1418.6497749151677,"GB2-05":1807.082565765036,"GB2-06":1833.2564582282478,"GB2-07":1421.3978449968974,"GB2-08":1349.8330061233858},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2159.427885104411,"GB2-03":1382.0658139922884,"GB2-04":1525.1245977886197,"GB2-05":2094.750766063771,"GB2-06":1982.825283781877,"GB2-07":1848.0880599399707,"GB2-08":1650.366745499416},"medium":{"GB2-01":2297.707389298962,"GB2-02":1445.6240603819788,"GB2-03":1382.0658139922884,"GB2-04":1337.8390290734724,"GB2-05":1738.1352690474566,"GB2-06":1881.6829357033098,"GB2-07":1244.4639543763963,"GB2-08":1251.8602811242963},"none":{"GB2-01":1808.1887646447933,"GB2-02":1388.971008389102,"GB2-03":1277.7328056793388,"GB2-04":1392.9856978834107,"GB2-05":1588.3616621838803,"GB2-06":1635.2611551995572,"GB2-07":1171.6415206743254,"GB2-08":1147.271991746445}},"per_game_tracks":{"highest":{"GB2-01":95.24684945533983,"GB2-03":44.42644358426692,"GB2-04":56.411660955116936,"GB2-05":86.0321664811842,"GB2-06":81.61967477554526,"GB2-07":77.72188078652425,"GB2-08":67.6699395761627},"medium":{"GB2-01":97.50072570324825,"GB2-02":46.58945983591505,"GB2-03":44.42644358426692,"GB2-04":32.69055565321784,"GB2-05":71.4850270328087,"GB2-06":76.62896100280021,"GB2-07":33.88199520119422,"GB2-08":38.392523151436066},"none":{"GB2-01":80.65624122391038,"GB2-02":39.29616059008762,"GB2-03":32.636451055300306,"GB2-04":39.46772973737559,"GB2-05":61.7270741560596,"GB2-06":63.30539578509047,"GB2-07":28.488403524098622,"GB2-08":28.992200830495662}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:01:17Z","reasoning":{"highest":63.641076951767516,"medium":55.19946139561091,"none":46.82120711280228},"reasoning_agg":{"highest":{"max":95.24684945533983,"mean":63.641076951767516,"min":0.0},"medium":{"max":97.50072570324825,"mean":55.19946139561091,"min":32.69055565321784},"none":{"max":80.65624122391038,"mean":46.82120711280228,"min":28.488403524098622}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":16.81986983896524},"working_program_strength":{"all":58.251109293953924,"highest":72.73265937344858,"medium":55.19946139561091,"none":46.82120711280228}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:0e40c4e24db66bc0","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":0.818811367247394},"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":3.4542268568195333}},"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":5.470887999999999},"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":54.69930127019899,"highest":68.77458241970672,"medium":43.93046446681053,"none":51.39285692407972},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":49.43693255444782,"score":49.43693255444782},"GB2-02":{"attempts":3,"playable":48.96294097429897,"score":48.96294097429897},"GB2-03":{"attempts":3,"playable":58.6114822485009,"score":58.6114822485009},"GB2-04":{"attempts":3,"playable":43.989421507090746,"score":43.989421507090746},"GB2-05":{"attempts":3,"playable":51.67578154111019,"score":51.67578154111019},"GB2-06":{"attempts":3,"playable":63.73425896978628,"score":63.73425896978628},"GB2-07":{"attempts":3,"playable":48.72115166390271,"score":48.72115166390271},"GB2-08":{"attempts":3,"playable":72.4624407024543,"score":72.4624407024543}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":58.64459698895617,"score":58.64459698895617},"GB2-02":{"attempts":1,"playable":53.7184008357533,"score":53.7184008357533},"GB2-03":{"attempts":1,"playable":81.74448926014766,"score":81.74448926014766},"GB2-04":{"attempts":1,"playable":46.914897134092485,"score":46.914897134092485},"GB2-05":{"attempts":1,"playable":69.062853558927,"score":69.062853558927},"GB2-06":{"attempts":1,"playable":80.5308618775055,"score":80.5308618775055},"GB2-07":{"attempts":1,"playable":69.54648189537367,"score":69.54648189537367},"GB2-08":{"attempts":1,"playable":90.03407780689795,"score":90.03407780689795}},"medium":{"GB2-01":{"attempts":1,"playable":53.191793593389924,"score":53.191793593389924},"GB2-02":{"attempts":1,"playable":43.84772061297107,"score":43.84772061297107},"GB2-03":{"attempts":1,"playable":43.59593934605393,"score":43.59593934605393},"GB2-04":{"attempts":1,"playable":38.44338198008019,"score":38.44338198008019},"GB2-05":{"attempts":1,"playable":50.48844938435943,"score":50.48844938435943},"GB2-06":{"attempts":1,"playable":46.81318268661005,"score":46.81318268661005},"GB2-07":{"attempts":1,"playable":32.34852825246026,"score":32.34852825246026},"GB2-08":{"attempts":1,"playable":42.7147198785594,"score":42.7147198785594}},"none":{"GB2-01":{"attempts":1,"playable":36.47440708099738,"score":36.47440708099738},"GB2-02":{"attempts":1,"playable":49.32270147417252,"score":49.32270147417252},"GB2-03":{"attempts":1,"playable":50.49401813930111,"score":50.49401813930111},"GB2-04":{"attempts":1,"playable":46.60998540709956,"score":46.60998540709956},"GB2-05":{"attempts":1,"playable":35.476041680044155,"score":35.476041680044155},"GB2-06":{"attempts":1,"playable":63.8587323452433,"score":63.8587323452433},"GB2-07":{"attempts":1,"playable":44.268444843874185,"score":44.268444843874185},"GB2-08":{"attempts":1,"playable":84.63852442190554,"score":84.63852442190554}}},"id":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-10-31T16:57:25Z","match_totals_all":{"draws":3037,"losses":4299,"wins":4934},"match_totals_tracks":{"highest":{"draws":833,"losses":923,"wins":2334},"medium":{"draws":1217,"losses":1792,"wins":1081},"none":{"draws":987,"losses":1584,"wins":1519}},"model_slug":"qwen-qwen3-8-2-4t-a95b","official_rank_by_reasoning":{"highest":20,"medium":50,"none":20},"overall":{"max":90.03407780689795,"mean":54.69930127019899,"min":32.34852825246026},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.64459698895617,"GB2-02":53.7184008357533,"GB2-03":81.74448926014766,"GB2-04":46.914897134092485,"GB2-05":69.062853558927,"GB2-06":80.5308618775055,"GB2-07":69.54648189537367,"GB2-08":90.03407780689795},"per_game_all":{"GB2-01":49.43693255444782,"GB2-02":48.96294097429897,"GB2-03":58.6114822485009,"GB2-04":43.989421507090746,"GB2-05":51.67578154111019,"GB2-06":63.73425896978628,"GB2-07":48.72115166390271,"GB2-08":72.4624407024543},"per_game_match_totals_all":{"GB2-01":{"draws":599,"losses":515,"wins":434},"GB2-02":{"draws":1053,"losses":233,"wins":154},"GB2-03":{"draws":226,"losses":552,"wins":710},"GB2-04":{"draws":946,"losses":389,"wins":159},"GB2-05":{"draws":0,"losses":793,"wins":797},"GB2-06":{"draws":88,"losses":553,"wins":865},"GB2-07":{"draws":0,"losses":850,"wins":740},"GB2-08":{"draws":125,"losses":414,"wins":1075}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":151,"losses":149,"wins":216},"GB2-02":{"draws":335,"losses":63,"wins":82},"GB2-03":{"draws":13,"losses":96,"wins":387},"GB2-04":{"draws":300,"losses":123,"wins":75},"GB2-05":{"draws":0,"losses":173,"wins":357},"GB2-06":{"draws":34,"losses":91,"wins":377},"GB2-07":{"draws":0,"losses":169,"wins":361},"GB2-08":{"draws":0,"losses":59,"wins":479}},"medium":{"GB2-01":{"draws":261,"losses":122,"wins":133},"GB2-02":{"draws":359,"losses":98,"wins":23},"GB2-03":{"draws":158,"losses":219,"wins":119},"GB2-04":{"draws":291,"losses":169,"wins":38},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":23,"losses":278,"wins":201},"GB2-07":{"draws":0,"losses":372,"wins":158},"GB2-08":{"draws":125,"losses":263,"wins":150}},"none":{"GB2-01":{"draws":187,"losses":244,"wins":85},"GB2-02":{"draws":359,"losses":72,"wins":49},"GB2-03":{"draws":55,"losses":237,"wins":204},"GB2-04":{"draws":355,"losses":97,"wins":46},"GB2-05":{"draws":0,"losses":349,"wins":181},"GB2-06":{"draws":31,"losses":184,"wins":287},"GB2-07":{"draws":0,"losses":309,"wins":221},"GB2-08":{"draws":0,"losses":92,"wins":446}}},"per_game_raw_elo_all":{"GB2-01":1463.51759111658,"GB2-02":1464.0363741392587,"GB2-03":1536.5721064217298,"GB2-04":1428.1103911905575,"GB2-05":1463.9739211742626,"GB2-06":1657.7873262398589,"GB2-07":1437.0485202151751,"GB2-08":1832.5361341752985},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1552.4334946414656,"GB2-02":1500.932452325665,"GB2-03":1799.8442437185358,"GB2-04":1450.9100565191686,"GB2-05":1697.3119563896635,"GB2-06":1960.1412723912283,"GB2-07":1710.8918594757934,"GB2-08":2176.8100254169876},"medium":{"GB2-01":1499.4763473972707,"GB2-02":1424.470731628572,"GB2-03":1374.8634526243216,"GB2-04":1384.8644620300422,"GB2-05":1443.294433757351,"GB2-06":1368.3362032832251,"GB2-07":1224.23902052255,"GB2-08":1300.3426614643788},"none":{"GB2-01":1338.6429313110034,"GB2-02":1466.7059384635393,"GB2-03":1435.0086229223323,"GB2-04":1448.5566550224619,"GB2-05":1251.3153733757733,"GB2-06":1644.8845030451234,"GB2-07":1376.0146806471826,"GB2-08":2020.455715644529}},"per_game_tracks":{"highest":{"GB2-01":58.64459698895617,"GB2-02":53.7184008357533,"GB2-03":81.74448926014766,"GB2-04":46.914897134092485,"GB2-05":69.062853558927,"GB2-06":80.5308618775055,"GB2-07":69.54648189537367,"GB2-08":90.03407780689795},"medium":{"GB2-01":53.191793593389924,"GB2-02":43.84772061297107,"GB2-03":43.59593934605393,"GB2-04":38.44338198008019,"GB2-05":50.48844938435943,"GB2-06":46.81318268661005,"GB2-07":32.34852825246026,"GB2-08":42.7147198785594},"none":{"GB2-01":36.47440708099738,"GB2-02":49.32270147417252,"GB2-03":50.49401813930111,"GB2-04":46.60998540709956,"GB2-05":35.476041680044155,"GB2-06":63.8587323452433,"GB2-07":44.268444843874185,"GB2-08":84.63852442190554}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":21,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:55:09Z","reasoning":{"highest":68.77458241970672,"medium":43.93046446681053,"none":51.39285692407972},"reasoning_agg":{"highest":{"max":90.03407780689795,"mean":68.77458241970672,"min":46.914897134092485},"medium":{"max":53.191793593389924,"mean":43.93046446681053,"min":32.34852825246026},"none":{"max":84.63852442190554,"mean":51.39285692407972,"min":35.476041680044155}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":24.84411795289619},"working_program_strength":{"all":54.69930127019899,"highest":68.77458241970672,"medium":43.93046446681053,"none":51.39285692407972}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:9e10a6aabf043ef4","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":0.21121389000000002},"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":0.028788054}},"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":0.21121389000000002}},"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":0.39273128399999996},"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":53.84081007907505,"highest":69.64579961836183,"medium":55.85909786439987,"none":36.017532754463424},"economics_best_value":{"per_model":{"highest":true},"per_setting":{"highest":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.15089794116533,"score":59.15089794116533},"GB2-02":{"attempts":3,"playable":52.46380595850639,"score":52.46380595850639},"GB2-03":{"attempts":3,"playable":54.40989251189387,"score":54.40989251189387},"GB2-04":{"attempts":3,"playable":50.96568177281849,"score":50.96568177281849},"GB2-05":{"attempts":3,"playable":55.525695563358774,"score":55.525695563358774},"GB2-06":{"attempts":3,"playable":62.81688207246742,"score":62.81688207246742},"GB2-07":{"attempts":3,"playable":56.97086075432656,"score":56.97086075432656},"GB2-08":{"attempts":3,"playable":38.422764058063514,"score":38.422764058063514}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.48932556917271,"score":63.48932556917271},"GB2-02":{"attempts":1,"playable":57.361233204659236,"score":57.361233204659236},"GB2-03":{"attempts":1,"playable":60.240155213920865,"score":60.240155213920865},"GB2-04":{"attempts":1,"playable":74.78092291318734,"score":74.78092291318734},"GB2-05":{"attempts":1,"playable":82.56811149319687,"score":82.56811149319687},"GB2-06":{"attempts":1,"playable":82.34545479017686,"score":82.34545479017686},"GB2-07":{"attempts":1,"playable":75.81898482243845,"score":75.81898482243845},"GB2-08":{"attempts":1,"playable":60.56220894014235,"score":60.56220894014235}},"medium":{"GB2-01":{"attempts":1,"playable":68.1161334836176,"score":68.1161334836176},"GB2-02":{"attempts":1,"playable":58.191087380303316,"score":58.191087380303316},"GB2-03":{"attempts":1,"playable":54.951350928960075,"score":54.951350928960075},"GB2-04":{"attempts":1,"playable":38.750784944954475,"score":38.750784944954475},"GB2-05":{"attempts":1,"playable":53.7407087937457,"score":53.7407087937457},"GB2-06":{"attempts":1,"playable":76.99195183059857,"score":76.99195183059857},"GB2-07":{"attempts":1,"playable":69.72174524050753,"score":69.72174524050753},"GB2-08":{"attempts":1,"playable":26.40902031251176,"score":26.40902031251176}},"none":{"GB2-01":{"attempts":1,"playable":45.84723477070569,"score":45.84723477070569},"GB2-02":{"attempts":1,"playable":41.83909729055662,"score":41.83909729055662},"GB2-03":{"attempts":1,"playable":48.03817139280068,"score":48.03817139280068},"GB2-04":{"attempts":1,"playable":39.36533746031366,"score":39.36533746031366},"GB2-05":{"attempts":1,"playable":30.268266403133776,"score":30.268266403133776},"GB2-06":{"attempts":1,"playable":29.11323959662685,"score":29.11323959662685},"GB2-07":{"attempts":1,"playable":25.37185220003368,"score":25.37185220003368},"GB2-08":{"attempts":1,"playable":28.297062921536437,"score":28.297062921536437}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T16:48:53Z","match_totals_all":{"draws":2937,"losses":4474,"wins":4859},"match_totals_tracks":{"highest":{"draws":675,"losses":986,"wins":2429},"medium":{"draws":1141,"losses":1327,"wins":1622},"none":{"draws":1121,"losses":2161,"wins":808}},"model_slug":"deepseek-deepseek-v4-1-flash","official_rank_by_reasoning":{"highest":18,"medium":27,"none":50},"overall":{"max":82.56811149319687,"mean":53.84081007907505,"min":25.37185220003368},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":27,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.48932556917271,"GB2-02":57.361233204659236,"GB2-03":60.240155213920865,"GB2-04":74.78092291318734,"GB2-05":82.56811149319687,"GB2-06":82.34545479017686,"GB2-07":75.81898482243845,"GB2-08":60.56220894014235},"per_game_all":{"GB2-01":59.15089794116533,"GB2-02":52.46380595850639,"GB2-03":54.40989251189387,"GB2-04":50.96568177281849,"GB2-05":55.525695563358774,"GB2-06":62.81688207246742,"GB2-07":56.97086075432656,"GB2-08":38.422764058063514},"per_game_match_totals_all":{"GB2-01":{"draws":472,"losses":429,"wins":647},"GB2-02":{"draws":988,"losses":215,"wins":237},"GB2-03":{"draws":312,"losses":579,"wins":597},"GB2-04":{"draws":734,"losses":389,"wins":371},"GB2-05":{"draws":0,"losses":729,"wins":861},"GB2-06":{"draws":70,"losses":566,"wins":870},"GB2-07":{"draws":0,"losses":709,"wins":881},"GB2-08":{"draws":361,"losses":858,"wins":395}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":189,"wins":306},"GB2-02":{"draws":294,"losses":66,"wins":120},"GB2-03":{"draws":56,"losses":188,"wins":252},"GB2-04":{"draws":156,"losses":55,"wins":287},"GB2-05":{"draws":0,"losses":99,"wins":431},"GB2-06":{"draws":28,"losses":84,"wins":390},"GB2-07":{"draws":0,"losses":133,"wins":397},"GB2-08":{"draws":120,"losses":172,"wins":246}},"medium":{"GB2-01":{"draws":289,"losses":31,"wins":196},"GB2-02":{"draws":312,"losses":53,"wins":115},"GB2-03":{"draws":147,"losses":169,"wins":180},"GB2-04":{"draws":260,"losses":183,"wins":55},"GB2-05":{"draws":0,"losses":254,"wins":276},"GB2-06":{"draws":29,"losses":113,"wins":360},"GB2-07":{"draws":0,"losses":168,"wins":362},"GB2-08":{"draws":104,"losses":356,"wins":78}},"none":{"GB2-01":{"draws":162,"losses":209,"wins":145},"GB2-02":{"draws":382,"losses":96,"wins":2},"GB2-03":{"draws":109,"losses":222,"wins":165},"GB2-04":{"draws":318,"losses":151,"wins":29},"GB2-05":{"draws":0,"losses":376,"wins":154},"GB2-06":{"draws":13,"losses":369,"wins":120},"GB2-07":{"draws":0,"losses":408,"wins":122},"GB2-08":{"draws":137,"losses":330,"wins":71}}},"per_game_raw_elo_all":{"GB2-01":1560.4157696900613,"GB2-02":1491.8410497472335,"GB2-03":1471.0376861983984,"GB2-04":1490.6196914825484,"GB2-05":1548.753115992661,"GB2-06":1662.2032767227618,"GB2-07":1551.2123788249344,"GB2-08":1262.8057680119284},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1601.2700073299602,"GB2-02":1529.9497065995815,"GB2-03":1524.6935765610983,"GB2-04":1692.3749127810497,"GB2-05":1984.8272848123574,"GB2-06":1998.19722603948,"GB2-07":1813.2641791423544,"GB2-08":1531.5893678265147},"medium":{"GB2-01":1650.4543019634448,"GB2-02":1536.6819795581337,"GB2-03":1474.958279104272,"GB2-04":1387.3077138216152,"GB2-05":1483.9577685982936,"GB2-06":1888.8299748444838,"GB2-07":1713.5586734966937,"GB2-08":1117.4883298488596},"none":{"GB2-01":1429.5229997767788,"GB2-02":1408.8914630839859,"GB2-03":1413.4612029298248,"GB2-04":1392.1764478449802,"GB2-05":1177.474294567331,"GB2-06":1099.582629284321,"GB2-07":1126.8142838357548,"GB2-08":1139.3396063604114}},"per_game_tracks":{"highest":{"GB2-01":63.48932556917271,"GB2-02":57.361233204659236,"GB2-03":60.240155213920865,"GB2-04":74.78092291318734,"GB2-05":82.56811149319687,"GB2-06":82.34545479017686,"GB2-07":75.81898482243845,"GB2-08":60.56220894014235},"medium":{"GB2-01":68.1161334836176,"GB2-02":58.191087380303316,"GB2-03":54.951350928960075,"GB2-04":38.750784944954475,"GB2-05":53.7407087937457,"GB2-06":76.99195183059857,"GB2-07":69.72174524050753,"GB2-08":26.40902031251176},"none":{"GB2-01":45.84723477070569,"GB2-02":41.83909729055662,"GB2-03":48.03817139280068,"GB2-04":39.36533746031366,"GB2-05":30.268266403133776,"GB2-06":29.11323959662685,"GB2-07":25.37185220003368,"GB2-08":28.297062921536437}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":22,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:02:43Z","reasoning":{"highest":69.64579961836183,"medium":55.85909786439987,"none":36.017532754463424},"reasoning_agg":{"highest":{"max":82.56811149319687,"mean":69.64579961836183,"min":57.361233204659236},"medium":{"max":76.99195183059857,"mean":55.85909786439987,"min":26.40902031251176},"none":{"max":48.03817139280068,"mean":36.017532754463424,"min":25.37185220003368}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":33.62826686389841},"working_program_strength":{"all":53.84081007907505,"highest":69.64579961836183,"medium":55.85909786439987,"none":36.017532754463424}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:813f8bca2684fd6a","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":1.1471405},"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":0.376168},"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":0.376168},"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":1.1471405000000001}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.2224195,"mean":0.071446625,"median":0.04824225,"min":0.01939525,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":18,"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":27,"run_count":24,"total":1.7147189999999999},"codegen_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":53.753023112448,"highest":59.687398037310224,"medium":59.25035866418701,"none":42.32131263584674},"first_seen_at":null,"game_gaps":{"medium":{"GB2-06":"too_slow"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":67.88678857425356,"score":67.88678857425356},"GB2-02":{"attempts":3,"playable":45.9531065027507,"score":45.9531065027507},"GB2-03":{"attempts":3,"playable":53.04876444798185,"score":53.04876444798185},"GB2-04":{"attempts":3,"playable":47.692429796718216,"score":47.692429796718216},"GB2-05":{"attempts":3,"playable":54.49070585303863,"score":54.49070585303863},"GB2-06":{"attempts":2,"playable":23.597643512464437,"score":23.597643512464437},"GB2-07":{"attempts":3,"playable":57.89433217546059,"score":57.89433217546059},"GB2-08":{"attempts":3,"playable":67.57617565300843,"score":67.57617565300843}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.56275519228566,"score":80.56275519228566},"GB2-02":{"attempts":1,"playable":48.90277993281108,"score":48.90277993281108},"GB2-03":{"attempts":1,"playable":60.931884665538774,"score":60.931884665538774},"GB2-04":{"attempts":1,"playable":49.14768578617863,"score":49.14768578617863},"GB2-05":{"attempts":1,"playable":61.537849515819474,"score":61.537849515819474},"GB2-06":{"attempts":1,"playable":27.15413219770637,"score":27.15413219770637},"GB2-07":{"attempts":1,"playable":74.7785410427387,"score":74.7785410427387},"GB2-08":{"attempts":1,"playable":74.48355596540314,"score":74.48355596540314}},"medium":{"GB2-01":{"attempts":1,"playable":85.83077725700464,"score":85.83077725700464},"GB2-02":{"attempts":1,"playable":46.8000184261714,"score":46.8000184261714},"GB2-03":{"attempts":1,"playable":51.41053102099297,"score":51.41053102099297},"GB2-04":{"attempts":1,"playable":45.694634454271224,"score":45.694634454271224},"GB2-05":{"attempts":1,"playable":50.296840376304885,"score":50.296840376304885},"GB2-07":{"attempts":1,"playable":64.25793860596862,"score":64.25793860596862},"GB2-08":{"attempts":1,"playable":70.46177050859534,"score":70.46177050859534}},"none":{"GB2-01":{"attempts":1,"playable":37.266833273470354,"score":37.266833273470354},"GB2-02":{"attempts":1,"playable":42.156521149269636,"score":42.156521149269636},"GB2-03":{"attempts":1,"playable":46.80387765741382,"score":46.80387765741382},"GB2-04":{"attempts":1,"playable":48.23496914970478,"score":48.23496914970478},"GB2-05":{"attempts":1,"playable":51.63742766699152,"score":51.63742766699152},"GB2-06":{"attempts":1,"playable":20.041154827222503,"score":20.041154827222503},"GB2-07":{"attempts":1,"playable":34.64651687767444,"score":34.64651687767444},"GB2-08":{"attempts":1,"playable":57.78320048502683,"score":57.78320048502683}}},"id":"meta/muse-spark-1.2","is_recent_addition":false,"last_measured_at":"2026-10-31T17:00:58Z","match_totals_all":{"draws":2429,"losses":4501,"wins":4838},"match_totals_tracks":{"highest":{"draws":703,"losses":1376,"wins":2011},"medium":{"draws":783,"losses":1140,"wins":1665},"none":{"draws":943,"losses":1985,"wins":1162}},"model_slug":"meta-muse-spark-1-2","official_rank_by_reasoning":{"highest":33,"medium":24,"none":35},"overall":{"max":85.83077725700464,"mean":53.753023112448,"min":20.041154827222503},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":28,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.56275519228566,"GB2-02":48.90277993281108,"GB2-03":60.931884665538774,"GB2-04":49.14768578617863,"GB2-05":61.537849515819474,"GB2-06":27.15413219770637,"GB2-07":74.7785410427387,"GB2-08":74.48355596540314},"per_game_all":{"GB2-01":67.88678857425356,"GB2-02":45.9531065027507,"GB2-03":53.04876444798185,"GB2-04":47.692429796718216,"GB2-05":54.49070585303863,"GB2-07":57.89433217546059,"GB2-08":67.57617565300843},"per_game_match_totals_all":{"GB2-01":{"draws":192,"losses":429,"wins":927},"GB2-02":{"draws":1083,"losses":261,"wins":96},"GB2-03":{"draws":194,"losses":658,"wins":636},"GB2-04":{"draws":907,"losses":354,"wins":233},"GB2-05":{"draws":0,"losses":750,"wins":840},"GB2-06":{"draws":22,"losses":790,"wins":192},"GB2-07":{"draws":0,"losses":698,"wins":892},"GB2-08":{"draws":31,"losses":561,"wins":1022}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":109,"wins":405},"GB2-02":{"draws":373,"losses":67,"wins":40},"GB2-03":{"draws":19,"losses":203,"wins":274},"GB2-04":{"draws":280,"losses":122,"wins":96},"GB2-05":{"draws":0,"losses":213,"wins":317},"GB2-06":{"draws":19,"losses":375,"wins":108},"GB2-07":{"draws":0,"losses":139,"wins":391},"GB2-08":{"draws":10,"losses":148,"wins":380}},"medium":{"GB2-01":{"draws":23,"losses":70,"wins":423},"GB2-02":{"draws":361,"losses":83,"wins":36},"GB2-03":{"draws":106,"losses":207,"wins":183},"GB2-04":{"draws":272,"losses":143,"wins":83},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-07":{"draws":0,"losses":199,"wins":331},"GB2-08":{"draws":21,"losses":166,"wins":351}},"none":{"GB2-01":{"draws":167,"losses":250,"wins":99},"GB2-02":{"draws":349,"losses":111,"wins":20},"GB2-03":{"draws":69,"losses":248,"wins":179},"GB2-04":{"draws":355,"losses":89,"wins":54},"GB2-05":{"draws":0,"losses":265,"wins":265},"GB2-06":{"draws":3,"losses":415,"wins":84},"GB2-07":{"draws":0,"losses":360,"wins":170},"GB2-08":{"draws":0,"losses":247,"wins":291}}},"per_game_raw_elo_all":{"GB2-01":1682.5730219103082,"GB2-02":1440.689842888315,"GB2-03":1459.0948180232328,"GB2-04":1456.9155365509826,"GB2-05":1494.7598115754245,"GB2-07":1561.188506370021,"GB2-08":1658.9573021573706},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1806.7963799660702,"GB2-02":1463.4621107359083,"GB2-03":1531.4584502490088,"GB2-04":1468.1553837885967,"GB2-05":1585.7624068820985,"GB2-06":1069.608543691734,"GB2-07":1795.1098777098696,"GB2-08":1783.8618333623099},"medium":{"GB2-01":1894.394152057132,"GB2-02":1447.2466416479112,"GB2-03":1443.1194896378474,"GB2-04":1441.4899786406954,"GB2-05":1440.911421880583,"GB2-07":1634.0213815379739,"GB2-08":1702.7127176520203},"none":{"GB2-01":1346.5285337077225,"GB2-02":1411.3607762811257,"GB2-03":1402.706514182842,"GB2-04":1461.1012472236557,"GB2-05":1457.6056059635916,"GB2-06":956.8806419470943,"GB2-07":1254.4342598622202,"GB2-08":1490.2973554577814}},"per_game_tracks":{"highest":{"GB2-01":80.56275519228566,"GB2-02":48.90277993281108,"GB2-03":60.931884665538774,"GB2-04":49.14768578617863,"GB2-05":61.537849515819474,"GB2-06":27.15413219770637,"GB2-07":74.7785410427387,"GB2-08":74.48355596540314},"medium":{"GB2-01":85.83077725700464,"GB2-02":46.8000184261714,"GB2-03":51.41053102099297,"GB2-04":45.694634454271224,"GB2-05":50.296840376304885,"GB2-07":64.25793860596862,"GB2-08":70.46177050859534},"none":{"GB2-01":37.266833273470354,"GB2-02":42.156521149269636,"GB2-03":46.80387765741382,"GB2-04":48.23496914970478,"GB2-05":51.63742766699152,"GB2-06":20.041154827222503,"GB2-07":34.64651687767444,"GB2-08":57.78320048502683}},"program_outcomes":{"all":{"counted_attempts":23,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":1,"worked_after_repair":1,"worked_first_time":22,"working":23},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":7,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":1,"worked_after_repair":0,"worked_first_time":7,"working":7},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:08:49Z","reasoning":{"highest":59.687398037310224,"medium":59.25035866418701,"none":42.32131263584674},"reasoning_agg":{"highest":{"max":80.56275519228566,"mean":59.687398037310224,"min":27.15413219770637},"medium":{"max":85.83077725700464,"mean":59.25035866418701,"min":45.694634454271224},"none":{"max":57.78320048502683,"mean":42.32131263584674,"min":20.041154827222503}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.366085401463486},"working_program_strength":{"all":53.753023112448,"highest":59.687398037310224,"medium":59.25035866418701,"none":42.32131263584674}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:3df3f49bc7c18786","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":0.969381525},"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":1.0866157440000002},"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":1.0866157440000002},"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":2.183515394},"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":52.88880105996333,"highest":63.57074978754593,"medium":50.979608725996655,"none":44.11604466634739},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":51.46029963488402,"score":51.46029963488402},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":60.86003888007763,"score":40.573359253385085},"GB2-03":{"attempts":3,"playable":59.29738056117474,"score":59.29738056117474},"GB2-04":{"attempts":3,"playable":44.19237409072059,"score":44.19237409072059},"GB2-05":{"attempts":3,"playable":57.75334093337013,"score":57.75334093337013},"GB2-06":{"attempts":3,"playable":60.088913403849034,"score":60.088913403849034},"GB2-07":{"attempts":3,"playable":60.64172232692536,"score":60.64172232692536},"GB2-08":{"attempts":3,"playable":49.10301827539768,"score":49.10301827539768}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":55.04487857893879,"score":55.04487857893879},"GB2-02":{"attempts":1,"playable":78.61189504242573,"score":78.61189504242573},"GB2-03":{"attempts":1,"playable":72.52329448993513,"score":72.52329448993513},"GB2-04":{"attempts":1,"playable":56.21085512612917,"score":56.21085512612917},"GB2-05":{"attempts":1,"playable":70.36882624206335,"score":70.36882624206335},"GB2-06":{"attempts":1,"playable":80.7123377754222,"score":80.7123377754222},"GB2-07":{"attempts":1,"playable":67.79033809792271,"score":67.79033809792271},"GB2-08":{"attempts":1,"playable":27.303572947530373,"score":27.303572947530373}},"medium":{"GB2-01":{"attempts":1,"playable":52.80128063373155,"score":52.80128063373155},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":41.19809502778741,"score":41.19809502778741},"GB2-04":{"attempts":1,"playable":35.15934859310481,"score":35.15934859310481},"GB2-05":{"attempts":1,"playable":52.4027471736876,"score":52.4027471736876},"GB2-06":{"attempts":1,"playable":60.34071391970887,"score":60.34071391970887},"GB2-07":{"attempts":1,"playable":77.20347169483242,"score":77.20347169483242},"GB2-08":{"attempts":1,"playable":88.7312127651206,"score":88.7312127651206}},"none":{"GB2-01":{"attempts":1,"playable":46.534739691981706,"score":46.534739691981706},"GB2-02":{"attempts":1,"playable":43.108182717729534,"score":43.108182717729534},"GB2-03":{"attempts":1,"playable":64.17075216580167,"score":64.17075216580167},"GB2-04":{"attempts":1,"playable":41.20691855292778,"score":41.20691855292778},"GB2-05":{"attempts":1,"playable":50.48844938435943,"score":50.48844938435943},"GB2-06":{"attempts":1,"playable":39.21368851641602,"score":39.21368851641602},"GB2-07":{"attempts":1,"playable":36.93135718802093,"score":36.93135718802093},"GB2-08":{"attempts":1,"playable":31.27426911354207,"score":31.27426911354207}}},"id":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-10-31T16:30:32Z","match_totals_all":{"draws":2442,"losses":4326,"wins":5022},"match_totals_tracks":{"highest":{"draws":851,"losses":1161,"wins":2078},"medium":{"draws":566,"losses":1283,"wins":1761},"none":{"draws":1025,"losses":1882,"wins":1183}},"model_slug":"tencent-hy4-preview","official_rank_by_reasoning":{"highest":30,"medium":37,"none":31},"overall":{"max":88.7312127651206,"mean":52.88880105996333,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":29,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.04487857893879,"GB2-02":78.61189504242573,"GB2-03":72.52329448993513,"GB2-04":56.21085512612917,"GB2-05":70.36882624206335,"GB2-06":80.7123377754222,"GB2-07":67.79033809792271,"GB2-08":27.303572947530373},"per_game_all":{"GB2-01":51.46029963488402,"GB2-03":59.29738056117474,"GB2-04":44.19237409072059,"GB2-05":57.75334093337013,"GB2-06":60.088913403849034,"GB2-07":60.64172232692536,"GB2-08":49.10301827539768},"per_game_match_totals_all":{"GB2-01":{"draws":360,"losses":604,"wins":584},"GB2-02":{"draws":515,"losses":132,"wins":313},"GB2-03":{"draws":434,"losses":441,"wins":613},"GB2-04":{"draws":847,"losses":435,"wins":212},"GB2-05":{"draws":0,"losses":698,"wins":892},"GB2-06":{"draws":32,"losses":637,"wins":837},"GB2-07":{"draws":0,"losses":652,"wins":938},"GB2-08":{"draws":254,"losses":727,"wins":633}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":244,"losses":121,"wins":151},"GB2-02":{"draws":129,"losses":44,"wins":307},"GB2-03":{"draws":49,"losses":128,"wins":319},"GB2-04":{"draws":260,"losses":97,"wins":141},"GB2-05":{"draws":0,"losses":166,"wins":364},"GB2-06":{"draws":22,"losses":96,"wins":384},"GB2-07":{"draws":0,"losses":179,"wins":351},"GB2-08":{"draws":147,"losses":330,"wins":61}},"medium":{"GB2-01":{"draws":33,"losses":238,"wins":245},"GB2-03":{"draws":267,"losses":176,"wins":53},"GB2-04":{"draws":261,"losses":200,"wins":37},"GB2-05":{"draws":0,"losses":261,"wins":269},"GB2-06":{"draws":5,"losses":216,"wins":281},"GB2-07":{"draws":0,"losses":125,"wins":405},"GB2-08":{"draws":0,"losses":67,"wins":471}},"none":{"GB2-01":{"draws":83,"losses":245,"wins":188},"GB2-02":{"draws":386,"losses":88,"wins":6},"GB2-03":{"draws":118,"losses":137,"wins":241},"GB2-04":{"draws":326,"losses":138,"wins":34},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":5,"losses":325,"wins":172},"GB2-07":{"draws":0,"losses":348,"wins":182},"GB2-08":{"draws":107,"losses":330,"wins":101}}},"per_game_raw_elo_all":{"GB2-01":1483.03552005168,"GB2-03":1525.9771097926948,"GB2-04":1429.513501496047,"GB2-05":1543.132578775816,"GB2-06":1600.322070648752,"GB2-07":1602.2895300759956,"GB2-08":1478.8104110717866},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1517.3063710122312,"GB2-02":1736.0526468824346,"GB2-03":1659.7245306542486,"GB2-04":1523.5175579700833,"GB2-05":1718.9370867685318,"GB2-06":1963.8932729925625,"GB2-07":1684.6378168658414,"GB2-08":1127.9023930879916},"medium":{"GB2-01":1495.734888237959,"GB2-03":1354.0360943044507,"GB2-04":1358.3664906967392,"GB2-05":1467.1662158015656,"GB2-06":1584.5991976130485,"GB2-07":1838.3726848533627,"GB2-08":2135.5373033124847},"none":{"GB2-01":1436.06530090485,"GB2-02":1418.7464884796957,"GB2-03":1564.1707044193852,"GB2-04":1406.6564558213183,"GB2-05":1443.294433757351,"GB2-06":1252.4737413406456,"GB2-07":1283.8580885087822,"GB2-08":1172.9915368148831}},"per_game_tracks":{"highest":{"GB2-01":55.04487857893879,"GB2-02":78.61189504242573,"GB2-03":72.52329448993513,"GB2-04":56.21085512612917,"GB2-05":70.36882624206335,"GB2-06":80.7123377754222,"GB2-07":67.79033809792271,"GB2-08":27.303572947530373},"medium":{"GB2-01":52.80128063373155,"GB2-03":41.19809502778741,"GB2-04":35.15934859310481,"GB2-05":52.4027471736876,"GB2-06":60.34071391970887,"GB2-07":77.20347169483242,"GB2-08":88.7312127651206},"none":{"GB2-01":46.534739691981706,"GB2-02":43.108182717729534,"GB2-03":64.17075216580167,"GB2-04":41.20691855292778,"GB2-05":50.48844938435943,"GB2-06":39.21368851641602,"GB2-07":36.93135718802093,"GB2-08":31.27426911354207}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":3,"worked_first_time":20,"working":23},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:58:44Z","reasoning":{"highest":63.57074978754593,"medium":50.97960872599666,"none":44.11604466634739},"reasoning_agg":{"highest":{"max":80.7123377754222,"mean":63.57074978754593,"min":27.303572947530373},"medium":{"max":88.7312127651206,"mean":50.97960872599666,"min":0.0},"none":{"max":64.17075216580167,"mean":44.11604466634739,"min":31.27426911354207}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":19.454705121198536},"working_program_strength":{"all":55.31640147548698,"highest":63.57074978754593,"medium":58.2624099725676,"none":44.11604466634739}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:5584160e53b73374","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":8.014536975},"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":4.1696877},"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":0.8934513000000002}},"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":52.42748932522003,"highest":64.71122098645768,"medium":52.26538630701934,"none":40.305860682183074},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":53.32664235601575,"score":53.32664235601575},"GB2-02":{"attempts":6,"failed_attempts":1,"playable":44.27129202609572,"score":38.02275119948211},"GB2-03":{"attempts":6,"playable":58.126219037671596,"score":58.126219037671596},"GB2-04":{"attempts":6,"playable":49.06796923861071,"score":49.06796923861071},"GB2-05":{"attempts":6,"playable":67.10819181310181,"score":67.10819181310181},"GB2-06":{"attempts":6,"playable":63.489024313167924,"score":63.489024313167924},"GB2-07":{"attempts":6,"playable":49.133337035578016,"score":49.133337035578016},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":52.86055454865291,"score":41.14577960813235}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":56.105399423520836,"score":56.105399423520836},"GB2-02":{"attempts":2,"playable":55.072163665130006,"score":55.072163665130006},"GB2-03":{"attempts":2,"playable":69.19672898306219,"score":69.19672898306219},"GB2-04":{"attempts":2,"playable":63.77436185217144,"score":63.77436185217144},"GB2-05":{"attempts":2,"playable":83.85510550332549,"score":83.85510550332549},"GB2-06":{"attempts":2,"playable":82.32587355860474,"score":82.32587355860474},"GB2-07":{"attempts":2,"playable":51.379612986493754,"score":51.379612986493754},"GB2-08":{"attempts":2,"playable":55.980521919352995,"score":55.980521919352995}},"medium":{"GB2-01":{"attempts":2,"playable":72.36839272007468,"score":72.36839272007468},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":37.49124495968166,"score":18.74562247984083},"GB2-03":{"attempts":2,"playable":48.51163358631278,"score":48.51163358631278},"GB2-04":{"attempts":2,"playable":41.05083067041674,"score":41.05083067041674},"GB2-05":{"attempts":2,"playable":69.8605605587716,"score":69.8605605587716},"GB2-06":{"attempts":2,"playable":83.93165827716074,"score":83.93165827716074},"GB2-07":{"attempts":2,"playable":48.5100673420157,"score":48.5100673420157},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":70.28864964312334,"score":35.14432482156167}},"none":{"GB2-01":{"attempts":2,"playable":31.506134924451736,"score":31.506134924451736},"GB2-02":{"attempts":2,"playable":40.250467453475494,"score":40.250467453475494},"GB2-03":{"attempts":2,"playable":56.67029454363981,"score":56.67029454363981},"GB2-04":{"attempts":2,"playable":42.37871519324394,"score":42.37871519324394},"GB2-05":{"attempts":2,"playable":47.60890937720836,"score":47.60890937720836},"GB2-06":{"attempts":2,"playable":24.20954110373831,"score":24.20954110373831},"GB2-07":{"attempts":2,"playable":47.51033077822458,"score":47.51033077822458},"GB2-08":{"attempts":2,"playable":32.31249208348238,"score":32.31249208348238}}},"id":"google/gemini-3.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T17:05:01Z","match_totals_all":{"draws":4896,"losses":8704,"wins":9922},"match_totals_tracks":{"highest":{"draws":1486,"losses":2319,"wins":4375},"medium":{"draws":1366,"losses":2331,"wins":3465},"none":{"draws":2044,"losses":4054,"wins":2082}},"model_slug":"google-gemini-3-6-flash","official_rank_by_reasoning":{"highest":26,"medium":34,"none":44},"overall":{"max":83.93165827716074,"mean":52.42748932522003,"min":18.74562247984083},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.105399423520836,"GB2-02":55.072163665130006,"GB2-03":69.19672898306219,"GB2-04":63.77436185217144,"GB2-05":83.85510550332549,"GB2-06":82.32587355860474,"GB2-07":51.379612986493754,"GB2-08":55.980521919352995},"per_game_all":{"GB2-01":53.32664235601575,"GB2-02":44.27129202609572,"GB2-03":58.126219037671596,"GB2-04":49.06796923861071,"GB2-05":67.10819181310181,"GB2-06":63.489024313167924,"GB2-07":49.133337035578016,"GB2-08":52.86055454865291},"per_game_match_totals_all":{"GB2-01":{"draws":701,"losses":1149,"wins":1246},"GB2-02":{"draws":1642,"losses":523,"wins":235},"GB2-03":{"draws":312,"losses":1196,"wins":1468},"GB2-04":{"draws":1765,"losses":689,"wins":534},"GB2-05":{"draws":0,"losses":1084,"wins":2096},"GB2-06":{"draws":108,"losses":1115,"wins":1789},"GB2-07":{"draws":0,"losses":1693,"wins":1487},"GB2-08":{"draws":368,"losses":1255,"wins":1067}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":248,"losses":350,"wins":434},"GB2-02":{"draws":575,"losses":160,"wins":225},"GB2-03":{"draws":52,"losses":314,"wins":626},"GB2-04":{"draws":465,"losses":145,"wins":386},"GB2-05":{"draws":0,"losses":181,"wins":879},"GB2-06":{"draws":12,"losses":190,"wins":802},"GB2-07":{"draws":0,"losses":541,"wins":519},"GB2-08":{"draws":134,"losses":438,"wins":504}},"medium":{"GB2-01":{"draws":269,"losses":166,"wins":597},"GB2-02":{"draws":335,"losses":140,"wins":5},"GB2-03":{"draws":85,"losses":502,"wins":405},"GB2-04":{"draws":611,"losses":298,"wins":87},"GB2-05":{"draws":0,"losses":331,"wins":729},"GB2-06":{"draws":37,"losses":160,"wins":807},"GB2-07":{"draws":0,"losses":571,"wins":489},"GB2-08":{"draws":29,"losses":163,"wins":346}},"none":{"GB2-01":{"draws":184,"losses":633,"wins":215},"GB2-02":{"draws":732,"losses":223,"wins":5},"GB2-03":{"draws":175,"losses":380,"wins":437},"GB2-04":{"draws":689,"losses":246,"wins":61},"GB2-05":{"draws":0,"losses":572,"wins":488},"GB2-06":{"draws":59,"losses":765,"wins":180},"GB2-07":{"draws":0,"losses":581,"wins":479},"GB2-08":{"draws":205,"losses":654,"wins":217}}},"per_game_raw_elo_all":{"GB2-01":1535.297200718874,"GB2-02":1428.2822054261753,"GB2-03":1511.3079135079754,"GB2-04":1470.8168470384044,"GB2-05":1768.1464675348443,"GB2-06":1689.1434030272956,"GB2-07":1437.4459413772822,"GB2-08":1465.8030157979035},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1534.0831267963504,"GB2-02":1513.731811851333,"GB2-03":1619.2985243122996,"GB2-04":1591.4217492032526,"GB2-05":2067.1015615046326,"GB2-06":2015.2049239017347,"GB2-07":1464.7745604388897,"GB2-08":1513.6356501949513},"medium":{"GB2-01":1784.3402740956303,"GB2-02":1374.6367233029687,"GB2-03":1422.6083006354488,"GB2-04":1405.321755634422,"GB2-05":1829.8784226633957,"GB2-06":2033.4414316438329,"GB2-07":1429.9663463007382,"GB2-08":1699.3710699716894},"none":{"GB2-01":1287.4682012646413,"GB2-02":1396.478081124225,"GB2-03":1492.016915576178,"GB2-04":1415.707036277538,"GB2-05":1407.4594184365044,"GB2-06":1018.7838535363193,"GB2-07":1417.596917392219,"GB2-08":1184.4023272270697}},"per_game_tracks":{"highest":{"GB2-01":56.105399423520836,"GB2-02":55.072163665130006,"GB2-03":69.19672898306219,"GB2-04":63.77436185217144,"GB2-05":83.85510550332549,"GB2-06":82.32587355860474,"GB2-07":51.379612986493754,"GB2-08":55.980521919352995},"medium":{"GB2-01":72.36839272007468,"GB2-02":37.49124495968166,"GB2-03":48.51163358631278,"GB2-04":41.05083067041674,"GB2-05":69.8605605587716,"GB2-06":83.93165827716074,"GB2-07":48.5100673420157,"GB2-08":70.28864964312334},"none":{"GB2-01":31.506134924451736,"GB2-02":40.250467453475494,"GB2-03":56.67029454363981,"GB2-04":42.37871519324394,"GB2-05":47.60890937720836,"GB2-06":24.20954110373831,"GB2-07":47.51033077822458,"GB2-08":32.31249208348238}},"program_outcomes":{"all":{"counted_attempts":48,"failed":2,"infra_excluded":5,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":8,"worked_first_time":38,"working":46},"highest":{"counted_attempts":16,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":12,"working":16},"medium":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":14,"working":14},"none":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":12,"working":16}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:09:27Z","reasoning":{"highest":64.71122098645768,"medium":52.26538630701934,"none":40.305860682183074},"reasoning_agg":{"highest":{"max":83.85510550332549,"mean":64.71122098645768,"min":51.379612986493754},"medium":{"max":83.93165827716074,"mean":52.26538630701934,"min":18.74562247984083},"none":{"max":56.67029454363981,"mean":40.305860682183074,"min":24.20954110373831}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":24.405360304274602},"working_program_strength":{"all":54.6729037961118,"highest":64.71122098645768,"medium":59.001629719694655,"none":40.305860682183074}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:d7417423be731139","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":52.394920955333475,"highest":68.32697411265718,"medium":47.5561393052534,"none":41.30164944808984},"economics_best_value":{"per_model":{"medium":true,"none":true},"per_setting":{"medium":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":54.498834161600904,"score":47.56869051393559},"GB2-02":{"attempts":8,"playable":55.70067993956048,"score":55.70067993956048},"GB2-03":{"attempts":23,"failed_attempts":3,"playable":58.093657675370785,"score":52.12992748033535},"GB2-04":{"attempts":9,"playable":59.35886779577286,"score":59.35886779577286},"GB2-05":{"attempts":9,"playable":54.59496115497269,"score":54.59496115497269},"GB2-06":{"attempts":8,"playable":46.35561359867878,"score":46.35561359867878},"GB2-07":{"attempts":9,"playable":50.748324131302496,"score":50.748324131302496},"GB2-08":{"attempts":9,"failed_attempts":1,"playable":56.20424001872848,"score":52.702303028109576}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":3,"playable":58.59113475134728,"score":58.59113475134728},"GB2-02":{"attempts":2,"playable":73.90873177865188,"score":73.90873177865188},"GB2-03":{"attempts":5,"playable":71.04069273988907,"score":71.04069273988907},"GB2-04":{"attempts":3,"playable":71.298445377025,"score":71.298445377025},"GB2-05":{"attempts":3,"playable":62.57780615420692,"score":62.57780615420692},"GB2-06":{"attempts":3,"playable":68.86683715925902,"score":68.86683715925902},"GB2-07":{"attempts":3,"playable":66.75137072683911,"score":66.75137072683911},"GB2-08":{"attempts":3,"playable":73.58077421403918,"score":73.58077421403918}},"medium":{"GB2-01":{"attempts":3,"failed_attempts":1,"playable":62.37129282898785,"score":41.5808618859919},"GB2-02":{"attempts":3,"playable":50.0505138374372,"score":50.0505138374372},"GB2-03":{"attempts":9,"failed_attempts":2,"playable":57.78043497973329,"score":44.94033831757034},"GB2-04":{"attempts":3,"playable":57.37423732268082,"score":57.37423732268082},"GB2-05":{"attempts":3,"playable":49.325364888517576,"score":49.325364888517576},"GB2-06":{"attempts":2,"playable":27.930384379730707,"score":27.930384379730707},"GB2-07":{"attempts":3,"playable":45.73290088352252,"score":45.73290088352252},"GB2-08":{"attempts":3,"playable":63.51451292657618,"score":63.51451292657618}},"none":{"GB2-01":{"attempts":3,"playable":42.53407490446759,"score":42.53407490446759},"GB2-02":{"attempts":3,"playable":43.14279420259237,"score":43.14279420259237},"GB2-03":{"attempts":9,"failed_attempts":1,"playable":45.45984530648998,"score":40.40875138354665},"GB2-04":{"attempts":3,"playable":49.403920687612754,"score":49.403920687612754},"GB2-05":{"attempts":3,"playable":51.88171242219358,"score":51.88171242219358},"GB2-06":{"attempts":3,"playable":42.26961925704659,"score":42.26961925704659},"GB2-07":{"attempts":3,"playable":39.76070078354585,"score":39.76070078354585},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":31.517432915570048,"score":21.011621943713365}}},"id":"stealth/ox-alpha","is_recent_addition":false,"last_measured_at":"2026-10-31T17:12:55Z","match_totals_all":{"draws":8041,"losses":15165,"wins":17024},"match_totals_tracks":{"highest":{"draws":1268,"losses":3700,"wins":7814},"medium":{"draws":2734,"losses":5155,"wins":5347},"none":{"draws":4039,"losses":6310,"wins":3863}},"model_slug":"stealth-ox-alpha","official_rank_by_reasoning":{"highest":21,"medium":45,"none":40},"overall":{"max":73.90873177865188,"mean":52.394920955333475,"min":21.011621943713365},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.59113475134728,"GB2-02":73.90873177865188,"GB2-03":71.04069273988907,"GB2-04":71.298445377025,"GB2-05":62.57780615420692,"GB2-06":68.86683715925902,"GB2-07":66.75137072683911,"GB2-08":73.58077421403918},"per_game_all":{"GB2-01":54.49883416160091,"GB2-02":55.70067993956048,"GB2-03":58.093657675370785,"GB2-04":59.35886779577286,"GB2-05":54.59496115497269,"GB2-06":46.35561359867878,"GB2-07":50.748324131302496,"GB2-08":56.20424001872848},"per_game_match_totals_all":{"GB2-01":{"draws":658,"losses":1675,"wins":1795},"GB2-02":{"draws":2500,"losses":600,"wins":740},"GB2-03":{"draws":1876,"losses":3748,"wins":4296},"GB2-04":{"draws":2369,"losses":711,"wins":1402},"GB2-05":{"draws":0,"losses":2244,"wins":2526},"GB2-06":{"draws":115,"losses":2132,"wins":1769},"GB2-07":{"draws":0,"losses":2438,"wins":2332},"GB2-08":{"draws":523,"losses":1617,"wins":2164}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":73,"losses":637,"wins":838},"GB2-02":{"draws":353,"losses":87,"wins":520},"GB2-03":{"draws":141,"losses":721,"wins":1618},"GB2-04":{"draws":564,"losses":168,"wins":762},"GB2-05":{"draws":0,"losses":622,"wins":968},"GB2-06":{"draws":72,"losses":473,"wins":961},"GB2-07":{"draws":0,"losses":554,"wins":1036},"GB2-08":{"draws":65,"losses":438,"wins":1111}},"medium":{"GB2-01":{"draws":217,"losses":302,"wins":513},"GB2-02":{"draws":1042,"losses":223,"wins":175},"GB2-03":{"draws":385,"losses":1394,"wins":1693},"GB2-04":{"draws":871,"losses":228,"wins":395},"GB2-05":{"draws":0,"losses":831,"wins":759},"GB2-06":{"draws":20,"losses":742,"wins":242},"GB2-07":{"draws":0,"losses":891,"wins":699},"GB2-08":{"draws":199,"losses":544,"wins":871}},"none":{"GB2-01":{"draws":368,"losses":736,"wins":444},"GB2-02":{"draws":1105,"losses":290,"wins":45},"GB2-03":{"draws":1350,"losses":1633,"wins":985},"GB2-04":{"draws":934,"losses":315,"wins":245},"GB2-05":{"draws":0,"losses":791,"wins":799},"GB2-06":{"draws":23,"losses":917,"wins":566},"GB2-07":{"draws":0,"losses":993,"wins":597},"GB2-08":{"draws":259,"losses":635,"wins":182}}},"per_game_raw_elo_all":{"GB2-01":1513.791265387841,"GB2-02":1526.8986883706955,"GB2-03":1528.6621661900033,"GB2-04":1560.9900811128812,"GB2-05":1498.6524540449493,"GB2-06":1367.8502817949968,"GB2-07":1454.1958442460827,"GB2-08":1519.6046109462059},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1555.070899328034,"GB2-02":1689.224447541475,"GB2-03":1675.567257471282,"GB2-04":1679.3870150592304,"GB2-05":1605.9749061488935,"GB2-06":1768.4271039071882,"GB2-07":1674.3607500631213,"GB2-08":1789.5964974411065},"medium":{"GB2-01":1590.3840753575287,"GB2-02":1472.4705591819084,"GB2-03":1519.745397631023,"GB2-04":1533.1966197815955,"GB2-05":1428.8923736196382,"GB2-06":1035.099634594943,"GB2-07":1384.0215483479772,"GB2-08":1593.9335536475166},"none":{"GB2-01":1395.9188214779595,"GB2-02":1419.0010583887024,"GB2-03":1390.673843467705,"GB2-04":1470.386608497818,"GB2-05":1461.0900823663162,"GB2-06":1300.0241068828593,"GB2-07":1304.20523432715,"GB2-08":1175.2837817499942}},"per_game_tracks":{"highest":{"GB2-01":58.59113475134728,"GB2-02":73.90873177865188,"GB2-03":71.04069273988907,"GB2-04":71.298445377025,"GB2-05":62.57780615420692,"GB2-06":68.86683715925902,"GB2-07":66.75137072683911,"GB2-08":73.58077421403918},"medium":{"GB2-01":62.37129282898785,"GB2-02":50.0505138374372,"GB2-03":57.78043497973329,"GB2-04":57.37423732268082,"GB2-05":49.325364888517576,"GB2-06":27.930384379730707,"GB2-07":45.73290088352252,"GB2-08":63.51451292657618},"none":{"GB2-01":42.534074904467595,"GB2-02":43.14279420259238,"GB2-03":45.45984530648998,"GB2-04":49.403920687612754,"GB2-05":51.88171242219358,"GB2-06":42.26961925704659,"GB2-07":39.76070078354585,"GB2-08":31.517432915570048}},"program_outcomes":{"all":{"counted_attempts":84,"failed":5,"infra_excluded":5,"success_rate":0.9404761904761905,"too_slow":1,"worked_after_repair":17,"worked_first_time":62,"working":79},"highest":{"counted_attempts":25,"failed":0,"infra_excluded":5,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":22,"working":25},"medium":{"counted_attempts":29,"failed":3,"infra_excluded":0,"success_rate":0.896551724137931,"too_slow":1,"worked_after_repair":5,"worked_first_time":21,"working":26},"none":{"counted_attempts":30,"failed":2,"infra_excluded":0,"success_rate":0.9333333333333333,"too_slow":0,"worked_after_repair":9,"worked_first_time":19,"working":28}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T02:07:13Z","reasoning":{"highest":68.32697411265718,"medium":47.5561393052534,"none":41.30164944808984},"reasoning_agg":{"highest":{"max":73.90873177865188,"mean":68.32697411265718,"min":58.59113475134728},"medium":{"max":63.51451292657618,"mean":47.5561393052534,"min":27.930384379730707},"none":{"max":51.88171242219358,"mean":41.30164944808984,"min":21.011621943713365}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.025324664567343},"working_program_strength":{"all":54.444397309498434,"highest":68.32697411265718,"medium":51.75995525589826,"none":43.24626255993985}},{"canonical_public_row_identity":"publication-row.v1:overall:fireworks-ember-1:652066c0cab2100d","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":0.582672}},"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":4.113816},"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":52.368066004671995,"highest":65.01865590199031,"medium":54.65813924762252,"none":37.42740286440315},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":59.69008483456546,"score":59.69008483456546},"GB2-02":{"attempts":3,"playable":44.33959288179739,"score":44.33959288179739},"GB2-03":{"attempts":3,"playable":60.093474499829334,"score":60.093474499829334},"GB2-04":{"attempts":3,"playable":44.929246648308236,"score":44.929246648308236},"GB2-05":{"attempts":3,"playable":44.28068250305737,"score":44.28068250305737},"GB2-06":{"attempts":3,"playable":52.16650170956141,"score":52.16650170956141},"GB2-07":{"attempts":3,"playable":59.066032675832766,"score":59.066032675832766},"GB2-08":{"attempts":3,"playable":54.378912284424,"score":54.378912284424}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":77.0834990709238,"score":77.0834990709238},"GB2-02":{"attempts":1,"playable":42.57959551045286,"score":42.57959551045286},"GB2-03":{"attempts":1,"playable":81.20394090368762,"score":81.20394090368762},"GB2-04":{"attempts":1,"playable":40.593409787871586,"score":40.593409787871586},"GB2-05":{"attempts":1,"playable":63.239030366158865,"score":63.239030366158865},"GB2-06":{"attempts":1,"playable":52.04227040564263,"score":52.04227040564263},"GB2-07":{"attempts":1,"playable":75.81898482243845,"score":75.81898482243845},"GB2-08":{"attempts":1,"playable":87.5885163487467,"score":87.5885163487467}},"medium":{"GB2-01":{"attempts":1,"playable":51.23787998671576,"score":51.23787998671576},"GB2-02":{"attempts":1,"playable":45.008686771732854,"score":45.008686771732854},"GB2-03":{"attempts":1,"playable":62.50685252669661,"score":62.50685252669661},"GB2-04":{"attempts":1,"playable":53.191874906884294,"score":53.191874906884294},"GB2-05":{"attempts":1,"playable":47.803186700778895,"score":47.803186700778895},"GB2-06":{"attempts":1,"playable":57.350223892964856,"score":57.350223892964856},"GB2-07":{"attempts":1,"playable":64.25793860596862,"score":64.25793860596862},"GB2-08":{"attempts":1,"playable":55.908470589238334,"score":55.908470589238334}},"none":{"GB2-01":{"attempts":1,"playable":50.74887544605683,"score":50.74887544605683},"GB2-02":{"attempts":1,"playable":45.43049636320644,"score":45.43049636320644},"GB2-03":{"attempts":1,"playable":36.569630069103766,"score":36.569630069103766},"GB2-04":{"attempts":1,"playable":41.002455250168815,"score":41.002455250168815},"GB2-05":{"attempts":1,"playable":21.79983044223438,"score":21.79983044223438},"GB2-06":{"attempts":1,"playable":47.10701083007673,"score":47.10701083007673},"GB2-07":{"attempts":1,"playable":37.12117459909125,"score":37.12117459909125},"GB2-08":{"attempts":1,"playable":19.639749915286977,"score":19.639749915286977}}},"id":"fireworks/ember-1","is_recent_addition":false,"last_measured_at":"2026-10-31T17:13:07Z","match_totals_all":{"draws":2978,"losses":4628,"wins":4664},"match_totals_tracks":{"highest":{"draws":714,"losses":1138,"wins":2238},"medium":{"draws":1055,"losses":1429,"wins":1606},"none":{"draws":1209,"losses":2061,"wins":820}},"model_slug":"fireworks-ember-1","official_rank_by_reasoning":{"highest":25,"medium":30,"none":49},"overall":{"max":87.5885163487467,"mean":52.368066004671995,"min":19.639749915286977},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":77.0834990709238,"GB2-02":42.57959551045286,"GB2-03":81.20394090368762,"GB2-04":40.593409787871586,"GB2-05":63.239030366158865,"GB2-06":52.04227040564263,"GB2-07":75.81898482243845,"GB2-08":87.5885163487467},"per_game_all":{"GB2-01":59.69008483456546,"GB2-02":44.33959288179739,"GB2-03":60.093474499829334,"GB2-04":44.929246648308236,"GB2-05":44.28068250305737,"GB2-06":52.16650170956141,"GB2-07":59.066032675832766,"GB2-08":54.378912284424},"per_game_match_totals_all":{"GB2-01":{"draws":466,"losses":423,"wins":659},"GB2-02":{"draws":1071,"losses":290,"wins":79},"GB2-03":{"draws":295,"losses":494,"wins":699},"GB2-04":{"draws":898,"losses":399,"wins":197},"GB2-05":{"draws":0,"losses":909,"wins":681},"GB2-06":{"draws":46,"losses":762,"wins":698},"GB2-07":{"draws":0,"losses":679,"wins":911},"GB2-08":{"draws":202,"losses":672,"wins":740}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":9,"losses":124,"wins":383},"GB2-02":{"draws":363,"losses":102,"wins":15},"GB2-03":{"draws":15,"losses":98,"wins":383},"GB2-04":{"draws":312,"losses":148,"wins":38},"GB2-05":{"draws":0,"losses":204,"wins":326},"GB2-06":{"draws":13,"losses":256,"wins":233},"GB2-07":{"draws":0,"losses":133,"wins":397},"GB2-08":{"draws":2,"losses":73,"wins":463}},"medium":{"GB2-01":{"draws":257,"losses":134,"wins":125},"GB2-02":{"draws":358,"losses":93,"wins":29},"GB2-03":{"draws":41,"losses":184,"wins":271},"GB2-04":{"draws":304,"losses":90,"wins":104},"GB2-05":{"draws":0,"losses":285,"wins":245},"GB2-06":{"draws":11,"losses":229,"wins":262},"GB2-07":{"draws":0,"losses":199,"wins":331},"GB2-08":{"draws":84,"losses":215,"wins":239}},"none":{"GB2-01":{"draws":200,"losses":165,"wins":151},"GB2-02":{"draws":350,"losses":95,"wins":35},"GB2-03":{"draws":239,"losses":212,"wins":45},"GB2-04":{"draws":282,"losses":161,"wins":55},"GB2-05":{"draws":0,"losses":420,"wins":110},"GB2-06":{"draws":22,"losses":277,"wins":203},"GB2-07":{"draws":0,"losses":347,"wins":183},"GB2-08":{"draws":116,"losses":384,"wins":38}}},"per_game_raw_elo_all":{"GB2-01":1571.632109003427,"GB2-02":1428.258423076527,"GB2-03":1550.1599133466032,"GB2-04":1435.508836788674,"GB2-05":1353.7734068769178,"GB2-06":1452.5020763950408,"GB2-07":1577.855409828396,"GB2-08":1532.853646731185},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1757.9589746635788,"GB2-02":1414.6472416588617,"GB2-03":1789.9888498661494,"GB2-04":1401.8490903366605,"GB2-05":1609.439648339289,"GB2-06":1449.7115821825626,"GB2-07":1813.2641791423544,"GB2-08":2101.503866071876},"medium":{"GB2-01":1480.7988666800647,"GB2-02":1433.4372473501935,"GB2-03":1547.1384736505327,"GB2-04":1499.6214408722062,"GB2-05":1409.9295608538664,"GB2-06":1534.9333376337713,"GB2-07":1634.0213815379739,"GB2-08":1463.8425842112165},"none":{"GB2-01":1476.1384856666382,"GB2-02":1436.6907802205253,"GB2-03":1313.3524165231274,"GB2-04":1405.055979157156,"GB2-05":1041.9510114375978,"GB2-06":1372.8613093687889,"GB2-07":1286.2806688048604,"GB2-08":1033.2144899104628}},"per_game_tracks":{"highest":{"GB2-01":77.0834990709238,"GB2-02":42.57959551045286,"GB2-03":81.20394090368762,"GB2-04":40.593409787871586,"GB2-05":63.239030366158865,"GB2-06":52.04227040564263,"GB2-07":75.81898482243845,"GB2-08":87.5885163487467},"medium":{"GB2-01":51.23787998671576,"GB2-02":45.008686771732854,"GB2-03":62.50685252669661,"GB2-04":53.191874906884294,"GB2-05":47.803186700778895,"GB2-06":57.350223892964856,"GB2-07":64.25793860596862,"GB2-08":55.908470589238334},"none":{"GB2-01":50.74887544605683,"GB2-02":45.43049636320644,"GB2-03":36.569630069103766,"GB2-04":41.002455250168815,"GB2-05":21.79983044223438,"GB2-06":47.10701083007673,"GB2-07":37.12117459909125,"GB2-08":19.639749915286977}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#6720FF","provider_company":"Fireworks AI","provider_key":"fireworks","provider_text_color":"#f8fafc","rank_movement":-2,"rank_movement_baseline_at":"2026-10-26T02:06:27Z","reasoning":{"highest":65.01865590199031,"medium":54.65813924762252,"none":37.42740286440315},"reasoning_agg":{"highest":{"max":87.5885163487467,"mean":65.01865590199031,"min":40.593409787871586},"medium":{"max":64.25793860596862,"mean":54.65813924762252,"min":45.008686771732854},"none":{"max":50.74887544605683,"mean":37.42740286440315,"min":19.639749915286977}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.591253037587165},"working_program_strength":{"all":52.368066004671995,"highest":65.01865590199031,"medium":54.65813924762252,"none":37.42740286440315}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:5a2ef8bbc04cd5c2","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":1.2628249999999999}},"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":1.7435250000000002},"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":10.456240000000003},"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":51.44133161153667,"highest":63.98779339867241,"medium":47.64643547410424,"none":42.689765961833345},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed"},"none":{"GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":55.50569495106681,"score":55.50569495106681},"GB2-02":{"attempts":3,"playable":53.59062342158205,"score":53.59062342158205},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":31.13864109929948,"score":10.379547033099827},"GB2-04":{"attempts":3,"playable":51.55078041892682,"score":51.55078041892682},"GB2-05":{"attempts":3,"playable":39.83948564719659,"score":39.83948564719659},"GB2-06":{"attempts":3,"playable":70.68032154689469,"score":70.68032154689469},"GB2-07":{"attempts":3,"playable":65.6757502012325,"score":65.6757502012325},"GB2-08":{"attempts":3,"playable":64.308449672294,"score":64.308449672294}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":68.78861511489926,"score":68.78861511489926},"GB2-02":{"attempts":1,"playable":79.10732431662915,"score":79.10732431662915},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":70.39936886775291,"score":70.39936886775291},"GB2-05":{"attempts":1,"playable":48.76286631738985,"score":48.76286631738985},"GB2-06":{"attempts":1,"playable":82.52688068061835,"score":82.52688068061835},"GB2-07":{"attempts":1,"playable":76.85763611916,"score":76.85763611916},"GB2-08":{"attempts":1,"playable":85.45965577292978,"score":85.45965577292978}},"medium":{"GB2-01":{"attempts":1,"playable":41.417467546983815,"score":41.417467546983815},"GB2-02":{"attempts":1,"playable":42.26230666890257,"score":42.26230666890257},"GB2-03":{"attempts":1,"playable":31.13864109929948,"score":31.13864109929948},"GB2-04":{"attempts":1,"playable":42.33074786119691,"score":42.33074786119691},"GB2-05":{"attempts":1,"playable":48.187142229883186,"score":48.187142229883186},"GB2-06":{"attempts":1,"playable":80.16790540991097,"score":80.16790540991097},"GB2-07":{"attempts":1,"playable":67.96624444842745,"score":67.96624444842745},"GB2-08":{"attempts":1,"playable":27.70102852822946,"score":27.70102852822946}},"none":{"GB2-01":{"attempts":1,"playable":56.31100219131735,"score":56.31100219131735},"GB2-02":{"attempts":1,"playable":39.40223927921443,"score":39.40223927921443},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.922224527830636,"score":41.922224527830636},"GB2-05":{"attempts":1,"playable":22.568448394316732,"score":22.568448394316732},"GB2-06":{"attempts":1,"playable":49.34617855015477,"score":49.34617855015477},"GB2-07":{"attempts":1,"playable":52.203370036110066,"score":52.203370036110066},"GB2-08":{"attempts":1,"playable":79.76466471572279,"score":79.76466471572279}}},"id":"claude-opus-4-8","is_recent_addition":false,"last_measured_at":"2026-10-31T16:57:51Z","match_totals_all":{"draws":2349,"losses":3985,"wins":4944},"match_totals_tracks":{"highest":{"draws":477,"losses":786,"wins":2331},"medium":{"draws":1083,"losses":1681,"wins":1326},"none":{"draws":789,"losses":1518,"wins":1287}},"model_slug":"claude-opus-4-8","official_rank_by_reasoning":{"highest":28,"medium":44,"none":34},"overall":{"max":85.45965577292978,"mean":51.44133161153667,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":68.78861511489926,"GB2-02":79.10732431662915,"GB2-04":70.39936886775291,"GB2-05":48.76286631738985,"GB2-06":82.52688068061835,"GB2-07":76.85763611916,"GB2-08":85.45965577292978},"per_game_all":{"GB2-01":55.50569495106681,"GB2-02":53.59062342158205,"GB2-04":51.55078041892682,"GB2-05":39.83948564719659,"GB2-06":70.68032154689469,"GB2-07":65.6757502012325,"GB2-08":64.308449672294},"per_game_match_totals_all":{"GB2-01":{"draws":256,"losses":593,"wins":699},"GB2-02":{"draws":901,"losses":239,"wins":300},"GB2-03":{"draws":152,"losses":281,"wins":63},"GB2-04":{"draws":855,"losses":321,"wins":318},"GB2-05":{"draws":0,"losses":979,"wins":611},"GB2-06":{"draws":49,"losses":459,"wins":998},"GB2-07":{"draws":0,"losses":571,"wins":1019},"GB2-08":{"draws":136,"losses":542,"wins":936}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":68,"losses":138,"wins":310},"GB2-02":{"draws":180,"losses":16,"wins":284},"GB2-04":{"draws":205,"losses":53,"wins":240},"GB2-05":{"draws":0,"losses":280,"wins":250},"GB2-06":{"draws":24,"losses":85,"wins":393},"GB2-07":{"draws":0,"losses":127,"wins":403},"GB2-08":{"draws":0,"losses":87,"wins":451}},"medium":{"GB2-01":{"draws":75,"losses":275,"wins":166},"GB2-02":{"draws":386,"losses":92,"wins":2},"GB2-03":{"draws":152,"losses":281,"wins":63},"GB2-04":{"draws":327,"losses":132,"wins":39},"GB2-05":{"draws":0,"losses":283,"wins":247},"GB2-06":{"draws":8,"losses":106,"wins":388},"GB2-07":{"draws":0,"losses":178,"wins":352},"GB2-08":{"draws":135,"losses":334,"wins":69}},"none":{"GB2-01":{"draws":113,"losses":180,"wins":223},"GB2-02":{"draws":335,"losses":131,"wins":14},"GB2-04":{"draws":323,"losses":136,"wins":39},"GB2-05":{"draws":0,"losses":416,"wins":114},"GB2-06":{"draws":17,"losses":268,"wins":217},"GB2-07":{"draws":0,"losses":266,"wins":264},"GB2-08":{"draws":1,"losses":121,"wins":416}}},"per_game_raw_elo_all":{"GB2-01":1524.851793104479,"GB2-02":1514.7846736787499,"GB2-04":1491.617559153161,"GB2-05":1297.2634708780927,"GB2-06":1787.4187268538644,"GB2-07":1664.7884725979304,"GB2-08":1691.77554127701},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1657.8777927227104,"GB2-02":1742.3632223576947,"GB2-04":1647.1823248205353,"GB2-05":1421.8520667387847,"GB2-06":2002.0746851424374,"GB2-07":1831.9904731342028,"GB2-08":2042.195387585595},"medium":{"GB2-01":1387.1009273604425,"GB2-02":1412.183013994855,"GB2-03":1263.7745672826443,"GB2-04":1415.4267734701657,"GB2-05":1414.7005801900393,"GB2-06":1952.6692785597977,"GB2-07":1687.2312968863844,"GB2-08":1132.4931402427565},"none":{"GB2-01":1529.576659230284,"GB2-02":1389.8077846837,"GB2-04":1412.2435791687822,"GB2-05":1055.2377657054535,"GB2-06":1407.512216859358,"GB2-07":1475.1436477732045,"GB2-08":1900.638096002678}},"per_game_tracks":{"highest":{"GB2-01":68.78861511489926,"GB2-02":79.10732431662915,"GB2-04":70.39936886775291,"GB2-05":48.76286631738985,"GB2-06":82.52688068061835,"GB2-07":76.85763611916,"GB2-08":85.45965577292978},"medium":{"GB2-01":41.417467546983815,"GB2-02":42.26230666890257,"GB2-03":31.13864109929948,"GB2-04":42.33074786119691,"GB2-05":48.187142229883186,"GB2-06":80.16790540991097,"GB2-07":67.96624444842745,"GB2-08":27.70102852822946},"none":{"GB2-01":56.31100219131735,"GB2-02":39.40223927921443,"GB2-04":41.922224527830636,"GB2-05":22.568448394316732,"GB2-06":49.34617855015477,"GB2-07":52.203370036110066,"GB2-08":79.76466471572279}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":6,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":1,"worked_first_time":21,"working":22},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":6,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:58:18Z","reasoning":{"highest":63.98779339867241,"medium":47.64643547410424,"none":42.689765961833345},"reasoning_agg":{"highest":{"max":85.45965577292978,"mean":63.98779339867241,"min":0.0},"medium":{"max":80.16790540991097,"mean":47.64643547410424,"min":27.70102852822946},"none":{"max":79.76466471572279,"mean":42.689765961833345,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":21.298027436839064},"working_program_strength":{"all":56.52121539060837,"highest":73.12890674133989,"medium":47.64643547410424,"none":48.788303956380965}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:43de48784439f899","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":1.5865090123478311},"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":2.164549388465127}},"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":4.982416500000001},"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":50.945350076008985,"highest":64.07813205985005,"medium":57.107340222693495,"none":31.6505779454834},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":71.11394708871856,"score":71.11394708871856},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":48.7676102734024,"score":42.16521607904195},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":54.68483256403973,"score":50.77413901062881},"GB2-04":{"attempts":4,"playable":45.96093827890837,"score":45.96093827890837},"GB2-05":{"attempts":4,"playable":45.11590721650722,"score":45.11590721650722},"GB2-06":{"attempts":4,"playable":62.73998444499039,"score":62.73998444499039},"GB2-07":{"attempts":4,"playable":49.98558621597636,"score":49.98558621597636},"GB2-08":{"attempts":4,"playable":39.70708227330015,"score":39.70708227330015}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":90.48626674304325,"score":90.48626674304325},"GB2-02":{"attempts":1,"playable":62.735143417049954,"score":62.735143417049954},"GB2-03":{"attempts":1,"playable":70.34280388731447,"score":70.34280388731447},"GB2-04":{"attempts":1,"playable":41.30913525559276,"score":41.30913525559276},"GB2-05":{"attempts":1,"playable":52.02015563577708,"score":52.02015563577708},"GB2-06":{"attempts":1,"playable":74.81367179220813,"score":74.81367179220813},"GB2-07":{"attempts":1,"playable":52.02065654100442,"score":52.02065654100442},"GB2-08":{"attempts":1,"playable":68.89722320681024,"score":68.89722320681024}},"medium":{"GB2-01":{"attempts":1,"playable":73.38132061676976,"score":73.38132061676976},"GB2-02":{"attempts":1,"playable":43.95332223699452,"score":43.95332223699452},"GB2-03":{"attempts":1,"playable":70.24753248433919,"score":70.24753248433919},"GB2-04":{"attempts":1,"playable":54.60231532523223,"score":54.60231532523223},"GB2-05":{"attempts":1,"playable":67.19089355992637,"score":67.19089355992637},"GB2-06":{"attempts":1,"playable":73.99647511043496,"score":73.99647511043496},"GB2-07":{"attempts":1,"playable":52.750997379978756,"score":52.750997379978756},"GB2-08":{"attempts":1,"playable":20.73586506787219,"score":20.73586506787219}},"none":{"GB2-01":{"attempts":2,"playable":49.47425390634268,"score":49.47425390634268},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":39.61436516616272,"score":19.80718258308136},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":23.4641613204655,"score":11.73208066023275},"GB2-04":{"attempts":2,"playable":41.97136425590014,"score":41.97136425590014},"GB2-05":{"attempts":2,"playable":16.136672453818193,"score":16.136672453818193},"GB2-06":{"attempts":2,"playable":39.40980643232808,"score":39.40980643232808},"GB2-07":{"attempts":2,"playable":45.18510472694593,"score":45.18510472694593},"GB2-08":{"attempts":2,"playable":29.48815854521804,"score":29.48815854521804}}},"id":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T17:14:21Z","match_totals_all":{"draws":2984,"losses":6681,"wins":5719},"match_totals_tracks":{"highest":{"draws":670,"losses":1227,"wins":2193},"medium":{"draws":812,"losses":1445,"wins":1833},"none":{"draws":1502,"losses":4009,"wins":1693}},"model_slug":"google-gemini-3-5-flash","official_rank_by_reasoning":{"highest":27,"medium":26,"none":57},"overall":{"max":90.48626674304325,"mean":50.945350076008985,"min":11.73208066023275},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":34,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.48626674304325,"GB2-02":62.735143417049954,"GB2-03":70.34280388731447,"GB2-04":41.30913525559276,"GB2-05":52.02015563577708,"GB2-06":74.81367179220813,"GB2-07":52.02065654100442,"GB2-08":68.89722320681024},"per_game_all":{"GB2-01":71.11394708871856,"GB2-02":48.7676102734024,"GB2-03":54.68483256403973,"GB2-04":45.96093827890837,"GB2-05":45.11590721650722,"GB2-06":62.73998444499039,"GB2-07":49.98558621597636,"GB2-08":39.70708227330015},"per_game_match_totals_all":{"GB2-01":{"draws":220,"losses":636,"wins":1208},"GB2-02":{"draws":1019,"losses":252,"wins":169},"GB2-03":{"draws":156,"losses":643,"wins":689},"GB2-04":{"draws":1188,"losses":536,"wins":268},"GB2-05":{"draws":0,"losses":1345,"wins":775},"GB2-06":{"draws":13,"losses":919,"wins":1076},"GB2-07":{"draws":0,"losses":1137,"wins":983},"GB2-08":{"draws":388,"losses":1213,"wins":551}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":45,"wins":450},"GB2-02":{"draws":256,"losses":59,"wins":165},"GB2-03":{"draws":42,"losses":143,"wins":311},"GB2-04":{"draws":273,"losses":164,"wins":61},"GB2-05":{"draws":0,"losses":263,"wins":267},"GB2-06":{"draws":3,"losses":138,"wins":361},"GB2-07":{"draws":0,"losses":267,"wins":263},"GB2-08":{"draws":75,"losses":148,"wins":315}},"medium":{"GB2-01":{"draws":14,"losses":141,"wins":361},"GB2-02":{"draws":402,"losses":76,"wins":2},"GB2-03":{"draws":43,"losses":143,"wins":310},"GB2-04":{"draws":280,"losses":95,"wins":123},"GB2-05":{"draws":0,"losses":183,"wins":347},"GB2-06":{"draws":4,"losses":142,"wins":356},"GB2-07":{"draws":0,"losses":263,"wins":267},"GB2-08":{"draws":69,"losses":402,"wins":67}},"none":{"GB2-01":{"draws":185,"losses":450,"wins":397},"GB2-02":{"draws":361,"losses":117,"wins":2},"GB2-03":{"draws":71,"losses":357,"wins":68},"GB2-04":{"draws":635,"losses":277,"wins":84},"GB2-05":{"draws":0,"losses":899,"wins":161},"GB2-06":{"draws":6,"losses":639,"wins":359},"GB2-07":{"draws":0,"losses":607,"wins":453},"GB2-08":{"draws":244,"losses":663,"wins":169}}},"per_game_raw_elo_all":{"GB2-01":1724.0130189149822,"GB2-02":1463.8042715643387,"GB2-03":1483.7114294098353,"GB2-04":1443.5821989558908,"GB2-05":1354.9655441353596,"GB2-06":1644.8443863282573,"GB2-07":1447.3985544953268,"GB2-08":1291.1773334770803},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1996.4912234501794,"GB2-02":1574.6462110967022,"GB2-03":1632.7921411129842,"GB2-04":1407.4559789406449,"GB2-05":1462.3833882812357,"GB2-06":1846.3229213904563,"GB2-07":1472.8369084852372,"GB2-08":1672.9723506990806},"medium":{"GB2-01":1711.0374266036065,"GB2-02":1425.2872169323223,"GB2-03":1631.6528692052575,"GB2-04":1510.7284810354554,"GB2-05":1667.6926763956014,"GB2-06":1830.5983909763434,"GB2-07":1482.0687617361943,"GB2-08":1047.726839393967},"none":{"GB2-01":1464.5104066911608,"GB2-02":1391.4793866639916,"GB2-03":1186.689277911264,"GB2-04":1412.5621368915724,"GB2-05":934.8205677292412,"GB2-06":1257.6118466179723,"GB2-07":1387.2899932645491,"GB2-08":1152.832810338193}},"per_game_tracks":{"highest":{"GB2-01":90.48626674304325,"GB2-02":62.735143417049954,"GB2-03":70.34280388731447,"GB2-04":41.30913525559276,"GB2-05":52.02015563577708,"GB2-06":74.81367179220813,"GB2-07":52.02065654100442,"GB2-08":68.89722320681024},"medium":{"GB2-01":73.38132061676976,"GB2-02":43.95332223699452,"GB2-03":70.24753248433919,"GB2-04":54.60231532523223,"GB2-05":67.19089355992637,"GB2-06":73.99647511043496,"GB2-07":52.750997379978756,"GB2-08":20.73586506787219},"none":{"GB2-01":49.47425390634268,"GB2-02":39.61436516616272,"GB2-03":23.4641613204655,"GB2-04":41.97136425590014,"GB2-05":16.136672453818193,"GB2-06":39.40980643232808,"GB2-07":45.18510472694593,"GB2-08":29.48815854521804}},"program_outcomes":{"all":{"counted_attempts":32,"failed":2,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":8,"worked_first_time":22,"working":30},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":11,"working":14}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:55:21Z","reasoning":{"highest":64.07813205985005,"medium":57.107340222693495,"none":31.6505779454834},"reasoning_agg":{"highest":{"max":90.48626674304325,"mean":64.07813205985005,"min":41.30913525559276},"medium":{"max":73.99647511043496,"mean":57.107340222693495,"min":20.73586506787219},"none":{"max":49.47425390634268,"mean":31.6505779454834,"min":11.73208066023275}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":32.42755411436665},"working_program_strength":{"all":52.259486044480404,"highest":64.07813205985005,"medium":57.107340222693495,"none":35.59298585089766}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:5f41df3bb03edf57","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":0.957684}},"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":0.9576840000000001},"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":6.452750000000002},"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":50.79887447384647,"highest":52.09199745739988,"medium":51.02073218383535,"none":49.28389378030418},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":34.007412898960624,"score":34.007412898960624},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":44.99475754624954,"score":36.337718810806535},"GB2-03":{"attempts":3,"playable":50.929899370393116,"score":50.929899370393116},"GB2-04":{"attempts":3,"playable":48.935873685798676,"score":48.935873685798676},"GB2-05":{"attempts":3,"playable":68.83218479097428,"score":68.83218479097428},"GB2-06":{"attempts":3,"playable":41.73279508069024,"score":41.73279508069024},"GB2-07":{"attempts":3,"playable":63.2770355278791,"score":63.2770355278791},"GB2-08":{"attempts":3,"playable":62.338075625269134,"score":62.338075625269134}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":32.70210541123022,"score":32.70210541123022},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":51.94223241265799,"score":25.971116206328993},"GB2-03":{"attempts":1,"playable":57.457245401265936,"score":57.457245401265936},"GB2-04":{"attempts":1,"playable":67.15851433650127,"score":67.15851433650127},"GB2-05":{"attempts":1,"playable":47.803186700778895,"score":47.803186700778895},"GB2-06":{"attempts":1,"playable":52.23368881261252,"score":52.23368881261252},"GB2-07":{"attempts":1,"playable":78.0672634342842,"score":78.0672634342842},"GB2-08":{"attempts":1,"playable":55.34285935619696,"score":55.34285935619696}},"medium":{"GB2-01":{"attempts":1,"playable":42.40338587264386,"score":42.40338587264386},"GB2-02":{"attempts":1,"playable":42.57959551045286,"score":42.57959551045286},"GB2-03":{"attempts":1,"playable":56.75758203208009,"score":56.75758203208009},"GB2-04":{"attempts":1,"playable":38.03338146812662,"score":38.03338146812662},"GB2-05":{"attempts":1,"playable":68.12775047654978,"score":68.12775047654978},"GB2-06":{"attempts":1,"playable":50.11968411044939,"score":50.11968411044939},"GB2-07":{"attempts":1,"playable":39.76924601114534,"score":39.76924601114534},"GB2-08":{"attempts":1,"playable":70.37523198923483,"score":70.37523198923483}},"none":{"GB2-01":{"attempts":1,"playable":26.9167474130078,"score":26.9167474130078},"GB2-02":{"attempts":1,"playable":40.462444715637766,"score":40.462444715637766},"GB2-03":{"attempts":1,"playable":38.574870677833346,"score":38.574870677833346},"GB2-04":{"attempts":1,"playable":41.61572525276816,"score":41.61572525276816},"GB2-05":{"attempts":1,"playable":90.56561719559417,"score":90.56561719559417},"GB2-06":{"attempts":1,"playable":22.845012319008795,"score":22.845012319008795},"GB2-07":{"attempts":1,"playable":71.99459713820777,"score":71.99459713820777},"GB2-08":{"attempts":1,"playable":61.29613553037561,"score":61.29613553037561}}},"id":"qwen/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-10-31T17:02:38Z","match_totals_all":{"draws":2893,"losses":4718,"wins":4659},"match_totals_tracks":{"highest":{"draws":812,"losses":1518,"wins":1760},"medium":{"draws":1027,"losses":1588,"wins":1475},"none":{"draws":1054,"losses":1612,"wins":1424}},"model_slug":"qwen-qwen3-8-max","official_rank_by_reasoning":{"highest":42,"medium":36,"none":24},"overall":{"max":90.56561719559417,"mean":50.79887447384647,"min":22.845012319008795},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.70210541123022,"GB2-02":51.94223241265799,"GB2-03":57.457245401265936,"GB2-04":67.15851433650127,"GB2-05":47.803186700778895,"GB2-06":52.23368881261252,"GB2-07":78.0672634342842,"GB2-08":55.34285935619696},"per_game_all":{"GB2-01":34.007412898960624,"GB2-02":44.99475754624954,"GB2-03":50.929899370393116,"GB2-04":48.935873685798676,"GB2-05":68.83218479097428,"GB2-06":41.73279508069024,"GB2-07":63.2770355278791,"GB2-08":62.338075625269134},"per_game_match_totals_all":{"GB2-01":{"draws":381,"losses":859,"wins":308},"GB2-02":{"draws":1072,"losses":280,"wins":88},"GB2-03":{"draws":297,"losses":637,"wins":554},"GB2-04":{"draws":837,"losses":369,"wins":288},"GB2-05":{"draws":0,"losses":515,"wins":1075},"GB2-06":{"draws":66,"losses":905,"wins":535},"GB2-07":{"draws":0,"losses":608,"wins":982},"GB2-08":{"draws":240,"losses":545,"wins":829}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":97,"losses":308,"wins":111},"GB2-02":{"draws":344,"losses":67,"wins":69},"GB2-03":{"draws":36,"losses":212,"wins":248},"GB2-04":{"draws":198,"losses":73,"wins":227},"GB2-05":{"draws":0,"losses":285,"wins":245},"GB2-06":{"draws":29,"losses":247,"wins":226},"GB2-07":{"draws":0,"losses":120,"wins":410},"GB2-08":{"draws":108,"losses":206,"wins":224}},"medium":{"GB2-01":{"draws":167,"losses":224,"wins":125},"GB2-02":{"draws":377,"losses":95,"wins":8},"GB2-03":{"draws":97,"losses":185,"wins":214},"GB2-04":{"draws":327,"losses":153,"wins":18},"GB2-05":{"draws":0,"losses":178,"wins":352},"GB2-06":{"draws":21,"losses":262,"wins":219},"GB2-07":{"draws":0,"losses":333,"wins":197},"GB2-08":{"draws":38,"losses":158,"wins":342}},"none":{"GB2-01":{"draws":117,"losses":327,"wins":72},"GB2-02":{"draws":351,"losses":118,"wins":11},"GB2-03":{"draws":164,"losses":240,"wins":92},"GB2-04":{"draws":312,"losses":143,"wins":43},"GB2-05":{"draws":0,"losses":52,"wins":478},"GB2-06":{"draws":16,"losses":396,"wins":90},"GB2-07":{"draws":0,"losses":155,"wins":375},"GB2-08":{"draws":94,"losses":181,"wins":263}}},"per_game_raw_elo_all":{"GB2-01":1311.4545329413884,"GB2-02":1433.2719934315176,"GB2-03":1440.2729427089723,"GB2-04":1469.315334822518,"GB2-05":1788.6690730285354,"GB2-06":1291.54974849405,"GB2-07":1641.1628777184949,"GB2-08":1566.6827113663558},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1300.2544533180153,"GB2-02":1487.0276201273186,"GB2-03":1498.1295227049418,"GB2-04":1616.4971654311112,"GB2-05":1409.9295608538664,"GB2-06":1452.7313482450813,"GB2-07":1854.6646313978765,"GB2-08":1456.0638036528178},"medium":{"GB2-01":1396.5992391721854,"GB2-02":1414.6472416588617,"GB2-03":1491.5961665835152,"GB2-04":1381.5970609308883,"GB2-05":1682.3272624441393,"GB2-06":1419.5598893613528,"GB2-07":1319.8044557408518,"GB2-08":1701.040739666035},"none":{"GB2-01":1237.5099063339642,"GB2-02":1398.1411185083725,"GB2-03":1331.0931388384595,"GB2-04":1409.8517781055543,"GB2-05":2273.750395787601,"GB2-06":1002.3580078757155,"GB2-07":1749.0195460167556,"GB2-08":1542.9435907802144}},"per_game_tracks":{"highest":{"GB2-01":32.70210541123022,"GB2-02":51.94223241265799,"GB2-03":57.457245401265936,"GB2-04":67.15851433650127,"GB2-05":47.803186700778895,"GB2-06":52.23368881261252,"GB2-07":78.0672634342842,"GB2-08":55.34285935619696},"medium":{"GB2-01":42.40338587264386,"GB2-02":42.57959551045286,"GB2-03":56.75758203208009,"GB2-04":38.03338146812662,"GB2-05":68.12775047654978,"GB2-06":50.11968411044939,"GB2-07":39.76924601114534,"GB2-08":70.37523198923483},"none":{"GB2-01":26.9167474130078,"GB2-02":40.462444715637766,"GB2-03":38.574870677833346,"GB2-04":41.61572525276816,"GB2-05":90.56561719559417,"GB2-06":22.845012319008795,"GB2-07":71.99459713820777,"GB2-08":61.29613553037561}},"program_outcomes":{"all":{"counted_attempts":25,"failed":1,"infra_excluded":3,"success_rate":0.96,"too_slow":1,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":9,"failed":1,"infra_excluded":3,"success_rate":0.8888888888888888,"too_slow":1,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T02:05:00Z","reasoning":{"highest":52.09199745739988,"medium":51.02073218383535,"none":49.28389378030418},"reasoning_agg":{"highest":{"max":78.0672634342842,"mean":52.09199745739988,"min":25.971116206328993},"medium":{"max":70.37523198923483,"mean":51.02073218383535,"min":38.03338146812662},"none":{"max":90.56561719559417,"mean":49.28389378030418,"min":22.845012319008795}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":2.808103677095694},"working_program_strength":{"all":51.88100431577684,"highest":55.338386983191,"medium":51.02073218383535,"none":49.28389378030418}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:41dd219b4919f08f","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":3.542855},"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":26.56635},"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":50.769599063074736,"highest":61.48585084242007,"medium":53.209588567059555,"none":37.61335777974458},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed"},"none":{"GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":65.70410856666086,"score":65.70410856666086},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":48.82163440140356,"score":32.547756267602374},"GB2-03":{"attempts":3,"playable":43.17462984026427,"score":43.17462984026427},"GB2-04":{"attempts":3,"playable":39.43198379350792,"score":39.43198379350792},"GB2-05":{"attempts":3,"playable":68.80427424588488,"score":68.80427424588488},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":55.74173479553931,"score":37.16115653035954},"GB2-07":{"attempts":3,"playable":62.10727163267887,"score":62.10727163267887},"GB2-08":{"attempts":3,"playable":57.22561162763919,"score":57.22561162763919}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":80.93650547362301,"score":80.93650547362301},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":50.90165767680046,"score":50.90165767680046},"GB2-04":{"attempts":1,"playable":37.00774047066414,"score":37.00774047066414},"GB2-05":{"attempts":1,"playable":77.19174638354706,"score":77.19174638354706},"GB2-06":{"attempts":1,"playable":81.0752827102861,"score":81.0752827102861},"GB2-07":{"attempts":1,"playable":87.00937946262356,"score":87.00937946262356},"GB2-08":{"attempts":1,"playable":77.76449456181625,"score":77.76449456181625}},"medium":{"GB2-01":{"attempts":1,"playable":64.9379402396438,"score":64.9379402396438},"GB2-02":{"attempts":1,"playable":55.69835237241343,"score":55.69835237241343},"GB2-03":{"attempts":1,"playable":39.20603325373902,"score":39.20603325373902},"GB2-04":{"attempts":1,"playable":39.67248565709144,"score":39.67248565709144},"GB2-05":{"attempts":1,"playable":77.00960774567534,"score":77.00960774567534},"GB2-06":{"attempts":1,"playable":30.408186880792513,"score":30.408186880792513},"GB2-07":{"attempts":1,"playable":61.05423536891878,"score":61.05423536891878},"GB2-08":{"attempts":1,"playable":57.689867018202115,"score":57.689867018202115}},"none":{"GB2-01":{"attempts":1,"playable":51.23787998671576,"score":51.23787998671576},"GB2-02":{"attempts":1,"playable":41.94491643039368,"score":41.94491643039368},"GB2-03":{"attempts":1,"playable":39.41619859025332,"score":39.41619859025332},"GB2-04":{"attempts":1,"playable":41.61572525276816,"score":41.61572525276816},"GB2-05":{"attempts":1,"playable":52.21146860843226,"score":52.21146860843226},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":38.25820006649426,"score":38.25820006649426},"GB2-08":{"attempts":1,"playable":36.22247330289921,"score":36.22247330289921}}},"id":"gpt-5.5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:04:19Z","match_totals_all":{"draws":3031,"losses":3744,"wins":4513},"match_totals_tracks":{"highest":{"draws":627,"losses":814,"wins":2169},"medium":{"draws":1111,"losses":1449,"wins":1530},"none":{"draws":1293,"losses":1481,"wins":814}},"model_slug":"gpt-5-5","official_rank_by_reasoning":{"highest":32,"medium":32,"none":48},"overall":{"max":87.00937946262356,"mean":50.769599063074736,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":80.93650547362301,"GB2-03":50.90165767680046,"GB2-04":37.00774047066414,"GB2-05":77.19174638354706,"GB2-06":81.0752827102861,"GB2-07":87.00937946262356,"GB2-08":77.76449456181625},"per_game_all":{"GB2-01":65.70410856666086,"GB2-03":43.17462984026427,"GB2-04":39.43198379350792,"GB2-05":68.80427424588488,"GB2-07":62.10727163267887,"GB2-08":57.22561162763919},"per_game_match_totals_all":{"GB2-01":{"draws":717,"losses":204,"wins":627},"GB2-02":{"draws":689,"losses":163,"wins":108},"GB2-03":{"draws":441,"losses":679,"wins":368},"GB2-04":{"draws":870,"losses":494,"wins":130},"GB2-05":{"draws":0,"losses":521,"wins":1069},"GB2-06":{"draws":25,"losses":462,"wins":517},"GB2-07":{"draws":0,"losses":626,"wins":964},"GB2-08":{"draws":289,"losses":595,"wins":730}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":126,"losses":45,"wins":345},"GB2-03":{"draws":147,"losses":189,"wins":160},"GB2-04":{"draws":283,"losses":180,"wins":35},"GB2-05":{"draws":0,"losses":129,"wins":401},"GB2-06":{"draws":20,"losses":95,"wins":387},"GB2-07":{"draws":0,"losses":68,"wins":462},"GB2-08":{"draws":51,"losses":108,"wins":379}},"medium":{"GB2-01":{"draws":280,"losses":52,"wins":184},"GB2-02":{"draws":304,"losses":69,"wins":107},"GB2-03":{"draws":164,"losses":237,"wins":95},"GB2-04":{"draws":281,"losses":168,"wins":49},"GB2-05":{"draws":0,"losses":130,"wins":400},"GB2-06":{"draws":5,"losses":367,"wins":130},"GB2-07":{"draws":0,"losses":217,"wins":313},"GB2-08":{"draws":77,"losses":209,"wins":252}},"none":{"GB2-01":{"draws":311,"losses":107,"wins":98},"GB2-02":{"draws":385,"losses":94,"wins":1},"GB2-03":{"draws":130,"losses":253,"wins":113},"GB2-04":{"draws":306,"losses":146,"wins":46},"GB2-05":{"draws":0,"losses":262,"wins":268},"GB2-07":{"draws":0,"losses":341,"wins":189},"GB2-08":{"draws":161,"losses":278,"wins":99}}},"per_game_raw_elo_all":{"GB2-01":1636.5139011021577,"GB2-03":1371.241562431717,"GB2-04":1392.6101868959915,"GB2-05":1720.0465510099086,"GB2-07":1654.1826864745035,"GB2-08":1523.9365755496835},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1812.3917316280233,"GB2-03":1438.6106602472048,"GB2-04":1373.3764008492406,"GB2-05":1849.674753198548,"GB2-06":1971.4307386265998,"GB2-07":2071.7142135648055,"GB2-08":1855.0111703419004},"medium":{"GB2-01":1616.3511049983854,"GB2-02":1516.605954046972,"GB2-03":1336.6359952180958,"GB2-04":1394.6023817331804,"GB2-05":1845.690779556564,"GB2-06":1119.2793214866817,"GB2-07":1590.100765610494,"GB2-08":1488.9548488132646},"none":{"GB2-01":1480.7988666800647,"GB2-02":1409.7150090567357,"GB2-03":1338.4780318298508,"GB2-04":1409.8517781055543,"GB2-05":1464.7741202746147,"GB2-07":1300.7330802482106,"GB2-08":1227.8437074938859}},"per_game_tracks":{"highest":{"GB2-01":80.93650547362301,"GB2-03":50.90165767680046,"GB2-04":37.00774047066414,"GB2-05":77.19174638354706,"GB2-06":81.0752827102861,"GB2-07":87.00937946262356,"GB2-08":77.76449456181625},"medium":{"GB2-01":64.9379402396438,"GB2-02":55.69835237241343,"GB2-03":39.20603325373902,"GB2-04":39.67248565709144,"GB2-05":77.00960774567534,"GB2-06":30.408186880792513,"GB2-07":61.05423536891878,"GB2-08":57.689867018202115},"none":{"GB2-01":51.23787998671576,"GB2-02":41.94491643039368,"GB2-03":39.41619859025332,"GB2-04":41.61572525276816,"GB2-05":52.21146860843226,"GB2-07":38.25820006649426,"GB2-08":36.22247330289921}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":1,"worked_first_time":21,"working":22},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-26T01:51:19Z","reasoning":{"highest":61.48585084242007,"medium":53.209588567059555,"none":37.61335777974458},"reasoning_agg":{"highest":{"max":87.00937946262356,"mean":61.48585084242007,"min":0.0},"medium":{"max":77.00960774567534,"mean":53.209588567059555,"min":30.408186880792513},"none":{"max":52.21146860843226,"mean":37.61335777974458,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":23.87249306267549},"working_program_strength":{"all":55.48860899746353,"highest":70.26954381990865,"medium":53.209588567059555,"none":42.98669460542238}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:970abfe5e8c98e0e","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":3.34216},"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":0.97393}},"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":1.42452},"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":0.97393},"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":11.203784999999996},"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":49.05842184159014,"highest":50.31770346771243,"medium":48.81896058536168,"none":48.03860147169633},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":47.27232375683064,"score":47.27232375683064},"GB2-02":{"attempts":5,"playable":44.04124332178994,"score":44.04124332178994},"GB2-03":{"attempts":4,"playable":47.64173981512861,"score":47.64173981512861},"GB2-04":{"attempts":5,"playable":43.71794555783112,"score":43.71794555783112},"GB2-05":{"attempts":5,"playable":46.51999518508625,"score":46.51999518508625},"GB2-06":{"attempts":5,"playable":48.51449128088777,"score":48.51449128088777},"GB2-07":{"attempts":5,"playable":45.71351687683395,"score":45.71351687683395},"GB2-08":{"attempts":5,"playable":69.0461189383329,"score":69.0461189383329}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":49.878888549794226,"score":49.878888549794226},"GB2-02":{"attempts":2,"playable":43.63642974783079,"score":43.63642974783079},"GB2-03":{"attempts":1,"playable":50.69789789139602,"score":50.69789789139602},"GB2-04":{"attempts":2,"playable":41.308815217157026,"score":41.308815217157026},"GB2-05":{"attempts":2,"playable":47.317045563989126,"score":47.317045563989126},"GB2-06":{"attempts":2,"playable":52.39851014372575,"score":52.39851014372575},"GB2-07":{"attempts":2,"playable":55.53216475903501,"score":55.53216475903501},"GB2-08":{"attempts":2,"playable":61.771875868771474,"score":61.771875868771474}},"medium":{"GB2-01":{"attempts":2,"playable":47.46711650822858,"score":47.46711650822858},"GB2-02":{"attempts":2,"playable":44.11168934594367,"score":44.11168934594367},"GB2-03":{"attempts":2,"playable":49.567882932112624,"score":49.567882932112624},"GB2-04":{"attempts":2,"playable":41.204279563323276,"score":41.204279563323276},"GB2-05":{"attempts":2,"playable":45.20798687055452,"score":45.20798687055452},"GB2-06":{"attempts":2,"playable":47.21583036915254,"score":47.21583036915254},"GB2-07":{"attempts":2,"playable":49.25985761900657,"score":49.25985761900657},"GB2-08":{"attempts":2,"playable":66.51704147457166,"score":66.51704147457166}},"none":{"GB2-01":{"attempts":1,"playable":44.4709662124691,"score":44.4709662124691},"GB2-02":{"attempts":1,"playable":44.37561087159538,"score":44.37561087159538},"GB2-03":{"attempts":1,"playable":42.6594386218772,"score":42.6594386218772},"GB2-04":{"attempts":1,"playable":48.64074189301308,"score":48.64074189301308},"GB2-05":{"attempts":1,"playable":47.03495312071511,"score":47.03495312071511},"GB2-06":{"attempts":1,"playable":45.929133329784996,"score":45.929133329784996},"GB2-07":{"attempts":1,"playable":32.34852825246026,"score":32.34852825246026},"GB2-08":{"attempts":1,"playable":78.84943947165557,"score":78.84943947165557}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-10-31T16:28:46Z","match_totals_all":{"draws":5079,"losses":8060,"wins":6815},"match_totals_tracks":{"highest":{"draws":1786,"losses":3100,"wins":2798},"medium":{"draws":2157,"losses":3307,"wins":2716},"none":{"draws":1136,"losses":1653,"wins":1301}},"model_slug":"claude-opus-4-5","official_rank_by_reasoning":{"highest":43,"medium":41,"none":27},"overall":{"max":78.84943947165557,"mean":49.05842184159014,"min":32.34852825246026},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.878888549794226,"GB2-02":43.63642974783079,"GB2-03":50.69789789139602,"GB2-04":41.308815217157026,"GB2-05":47.317045563989126,"GB2-06":52.39851014372575,"GB2-07":55.53216475903501,"GB2-08":61.771875868771474},"per_game_all":{"GB2-01":47.27232375683064,"GB2-02":44.04124332178994,"GB2-03":47.64173981512861,"GB2-04":43.71794555783112,"GB2-05":46.51999518508625,"GB2-06":48.51449128088777,"GB2-07":45.71351687683395,"GB2-08":69.0461189383329},"per_game_match_totals_all":{"GB2-01":{"draws":837,"losses":978,"wins":765},"GB2-02":{"draws":1879,"losses":445,"wins":76},"GB2-03":{"draws":484,"losses":862,"wins":638},"GB2-04":{"draws":1583,"losses":676,"wins":231},"GB2-05":{"draws":0,"losses":1461,"wins":1189},"GB2-06":{"draws":65,"losses":1357,"wins":1088},"GB2-07":{"draws":0,"losses":1431,"wins":1219},"GB2-08":{"draws":231,"losses":850,"wins":1609}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":229,"losses":422,"wins":381},"GB2-02":{"draws":756,"losses":179,"wins":25},"GB2-03":{"draws":75,"losses":226,"wins":195},"GB2-04":{"draws":588,"losses":307,"wins":101},"GB2-05":{"draws":0,"losses":575,"wins":485},"GB2-06":{"draws":28,"losses":507,"wins":469},"GB2-07":{"draws":0,"losses":495,"wins":565},"GB2-08":{"draws":110,"losses":389,"wins":577}},"medium":{"GB2-01":{"draws":372,"losses":377,"wins":283},"GB2-02":{"draws":753,"losses":176,"wins":31},"GB2-03":{"draws":236,"losses":420,"wins":336},"GB2-04":{"draws":670,"losses":267,"wins":59},"GB2-05":{"draws":0,"losses":597,"wins":463},"GB2-06":{"draws":27,"losses":561,"wins":416},"GB2-07":{"draws":0,"losses":564,"wins":496},"GB2-08":{"draws":99,"losses":345,"wins":632}},"none":{"GB2-01":{"draws":236,"losses":179,"wins":101},"GB2-02":{"draws":370,"losses":90,"wins":20},"GB2-03":{"draws":173,"losses":216,"wins":107},"GB2-04":{"draws":325,"losses":102,"wins":71},"GB2-05":{"draws":0,"losses":289,"wins":241},"GB2-06":{"draws":10,"losses":289,"wins":203},"GB2-07":{"draws":0,"losses":372,"wins":158},"GB2-08":{"draws":22,"losses":116,"wins":400}}},"per_game_raw_elo_all":{"GB2-01":1443.9590039334623,"GB2-02":1425.965607688594,"GB2-03":1410.1690071694711,"GB2-04":1426.0692893919925,"GB2-05":1393.8642890765939,"GB2-06":1395.2312198916943,"GB2-07":1393.7621454097896,"GB2-08":1707.237242826819},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1470.8172183142224,"GB2-02":1422.83543070606,"GB2-03":1436.8091198215277,"GB2-04":1407.4410387947053,"GB2-05":1403.7009844518288,"GB2-06":1455.969903399086,"GB2-07":1518.7492943656137,"GB2-08":1591.0019220298052},"medium":{"GB2-01":1444.6570093907542,"GB2-02":1426.5110826488674,"GB2-03":1426.9598574531926,"GB2-04":1406.5306370852525,"GB2-05":1377.5158486476694,"GB2-06":1374.975758617989,"GB2-07":1438.298121341205,"GB2-08":1651.1709950559593},"none":{"GB2-01":1416.4027840954104,"GB2-02":1428.5503097108551,"GB2-03":1366.7380442336928,"GB2-04":1464.2361922960195,"GB2-05":1400.3760341302834,"GB2-06":1354.7479976580082,"GB2-07":1224.23902052255,"GB2-08":1879.5388113946929}},"per_game_tracks":{"highest":{"GB2-01":49.878888549794226,"GB2-02":43.63642974783079,"GB2-03":50.69789789139602,"GB2-04":41.308815217157026,"GB2-05":47.317045563989126,"GB2-06":52.39851014372575,"GB2-07":55.53216475903501,"GB2-08":61.771875868771474},"medium":{"GB2-01":47.46711650822858,"GB2-02":44.11168934594367,"GB2-03":49.567882932112624,"GB2-04":41.204279563323276,"GB2-05":45.20798687055452,"GB2-06":47.21583036915254,"GB2-07":49.25985761900657,"GB2-08":66.51704147457166},"none":{"GB2-01":44.4709662124691,"GB2-02":44.37561087159538,"GB2-03":42.6594386218772,"GB2-04":48.64074189301308,"GB2-05":47.03495312071511,"GB2-06":45.929133329784996,"GB2-07":32.34852825246026,"GB2-08":78.84943947165557}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T02:08:04Z","reasoning":{"highest":50.31770346771243,"medium":48.81896058536168,"none":48.03860147169633},"reasoning_agg":{"highest":{"max":61.771875868771474,"mean":50.31770346771243,"min":41.308815217157026},"medium":{"max":66.51704147457166,"mean":48.81896058536168,"min":41.204279563323276},"none":{"max":78.84943947165557,"mean":48.03860147169633,"min":32.34852825246026}},"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":2.279101996016095},"working_program_strength":{"all":49.05842184159014,"highest":50.31770346771243,"medium":48.81896058536168,"none":48.03860147169633}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:f8c582a5decbb683","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":0.0306889},"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":0.030688900000000005},"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":0.025451049999999996},"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":48.901284698897086,"highest":57.79629883139616,"medium":43.72506358771962,"none":45.182491677575484},"economics_best_value":{"per_model":{"all":true,"highest":true,"none":true}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":39.05402108438846,"score":39.05402108438846},"GB2-02":{"attempts":3,"playable":50.913895271840495,"score":50.913895271840495},"GB2-03":{"attempts":3,"playable":49.3949198941289,"score":49.3949198941289},"GB2-04":{"attempts":3,"playable":53.27361200189613,"score":53.27361200189613},"GB2-05":{"attempts":3,"playable":46.95270112105751,"score":46.95270112105751},"GB2-06":{"attempts":3,"playable":64.6878026388465,"score":64.6878026388465},"GB2-07":{"attempts":3,"playable":42.1821354229969,"score":42.1821354229969},"GB2-08":{"attempts":3,"playable":44.75119015602181,"score":44.75119015602181}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":29.813733336483228,"score":29.813733336483228},"GB2-02":{"attempts":1,"playable":63.14645910415441,"score":63.14645910415441},"GB2-03":{"attempts":1,"playable":50.49401813930111,"score":50.49401813930111},"GB2-04":{"attempts":1,"playable":65.08490988904798,"score":65.08490988904798},"GB2-05":{"attempts":1,"playable":53.93170144168089,"score":53.93170144168089},"GB2-06":{"attempts":1,"playable":85.78961219087726,"score":85.78961219087726},"GB2-07":{"attempts":1,"playable":39.20326986217805,"score":39.20326986217805},"GB2-08":{"attempts":1,"playable":74.90668668744632,"score":74.90668668744632}},"medium":{"GB2-01":{"attempts":1,"playable":39.04763309437765,"score":39.04763309437765},"GB2-02":{"attempts":1,"playable":45.2196158397717,"score":45.2196158397717},"GB2-03":{"attempts":1,"playable":51.91865031777808,"score":51.91865031777808},"GB2-04":{"attempts":1,"playable":50.059410995398345,"score":50.059410995398345},"GB2-05":{"attempts":1,"playable":50.871572098016436,"score":50.871572098016436},"GB2-06":{"attempts":1,"playable":35.9127469404134,"score":35.9127469404134},"GB2-07":{"attempts":1,"playable":53.84395280924377,"score":53.84395280924377},"GB2-08":{"attempts":1,"playable":22.926926606757565,"score":22.926926606757565}},"none":{"GB2-01":{"attempts":1,"playable":48.30069682230449,"score":48.30069682230449},"GB2-02":{"attempts":1,"playable":44.37561087159538,"score":44.37561087159538},"GB2-03":{"attempts":1,"playable":45.7720912253075,"score":45.7720912253075},"GB2-04":{"attempts":1,"playable":44.67651512124206,"score":44.67651512124206},"GB2-05":{"attempts":1,"playable":36.05482982347519,"score":36.05482982347519},"GB2-06":{"attempts":1,"playable":72.36104878524885,"score":72.36104878524885},"GB2-07":{"attempts":1,"playable":33.499183597568866,"score":33.499183597568866},"GB2-08":{"attempts":1,"playable":36.419957173861576,"score":36.419957173861576}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-10-31T16:50:37Z","match_totals_all":{"draws":2985,"losses":5081,"wins":4204},"match_totals_tracks":{"highest":{"draws":561,"losses":1541,"wins":1988},"medium":{"draws":1111,"losses":1850,"wins":1129},"none":{"draws":1313,"losses":1690,"wins":1087}},"model_slug":"gpt-6-luna","official_rank_by_reasoning":{"highest":36,"medium":51,"none":30},"overall":{"max":85.78961219087726,"mean":48.901284698897086,"min":22.926926606757565},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.813733336483228,"GB2-02":63.14645910415441,"GB2-03":50.49401813930111,"GB2-04":65.08490988904798,"GB2-05":53.93170144168089,"GB2-06":85.78961219087726,"GB2-07":39.20326986217805,"GB2-08":74.90668668744632},"per_game_all":{"GB2-01":39.05402108438846,"GB2-02":50.913895271840495,"GB2-03":49.3949198941289,"GB2-04":53.27361200189613,"GB2-05":46.95270112105751,"GB2-06":64.6878026388465,"GB2-07":42.1821354229969,"GB2-08":44.75119015602181},"per_game_match_totals_all":{"GB2-01":{"draws":470,"losses":738,"wins":340},"GB2-02":{"draws":1054,"losses":204,"wins":182},"GB2-03":{"draws":209,"losses":705,"wins":574},"GB2-04":{"draws":838,"losses":305,"wins":351},"GB2-05":{"draws":0,"losses":868,"wins":722},"GB2-06":{"draws":65,"losses":543,"wins":898},"GB2-07":{"draws":0,"losses":959,"wins":631},"GB2-08":{"draws":349,"losses":759,"wins":506}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":370,"wins":144},"GB2-02":{"draws":274,"losses":48,"wins":158},"GB2-03":{"draws":25,"losses":252,"wins":219},"GB2-04":{"draws":231,"losses":67,"wins":200},"GB2-05":{"draws":0,"losses":253,"wins":277},"GB2-06":{"draws":24,"losses":67,"wins":411},"GB2-07":{"draws":0,"losses":336,"wins":194},"GB2-08":{"draws":5,"losses":148,"wins":385}},"medium":{"GB2-01":{"draws":191,"losses":229,"wins":96},"GB2-02":{"draws":394,"losses":74,"wins":12},"GB2-03":{"draws":99,"losses":208,"wins":189},"GB2-04":{"draws":285,"losses":115,"wins":98},"GB2-05":{"draws":0,"losses":269,"wins":261},"GB2-06":{"draws":21,"losses":333,"wins":148},"GB2-07":{"draws":0,"losses":257,"wins":273},"GB2-08":{"draws":121,"losses":365,"wins":52}},"none":{"GB2-01":{"draws":277,"losses":139,"wins":100},"GB2-02":{"draws":386,"losses":82,"wins":12},"GB2-03":{"draws":85,"losses":245,"wins":166},"GB2-04":{"draws":322,"losses":123,"wins":53},"GB2-05":{"draws":0,"losses":346,"wins":184},"GB2-06":{"draws":20,"losses":143,"wins":339},"GB2-07":{"draws":0,"losses":366,"wins":164},"GB2-08":{"draws":223,"losses":246,"wins":69}}},"per_game_raw_elo_all":{"GB2-01":1362.1884821575252,"GB2-02":1480.602343171098,"GB2-03":1425.461812143756,"GB2-04":1502.21354565266,"GB2-05":1397.8701412479359,"GB2-06":1692.286774442755,"GB2-07":1349.355684806271,"GB2-08":1366.1336823059821},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1269.6421924718459,"GB2-02":1578.1923036560681,"GB2-03":1435.0086229223323,"GB2-04":1597.8047359674877,"GB2-05":1486.3645196312343,"GB2-06":2074.8376929825386,"GB2-07":1312.6770979199257,"GB2-08":1792.7879361186422},"medium":{"GB2-01":1364.0706806609492,"GB2-02":1435.0644161463706,"GB2-03":1447.6362191253234,"GB2-04":1475.21373130322,"GB2-05":1448.0619313761215,"GB2-06":1202.554592589771,"GB2-07":1495.9453348788488,"GB2-08":1075.5874185817797},"none":{"GB2-01":1452.8525733397812,"GB2-02":1428.5503097108551,"GB2-03":1393.7405943836134,"GB2-04":1433.6221696872722,"GB2-05":1259.183972736452,"GB2-06":1799.4680377559553,"GB2-07":1239.444621620038,"GB2-08":1230.025692217525}},"per_game_tracks":{"highest":{"GB2-01":29.813733336483228,"GB2-02":63.14645910415441,"GB2-03":50.49401813930111,"GB2-04":65.08490988904798,"GB2-05":53.93170144168089,"GB2-06":85.78961219087726,"GB2-07":39.20326986217805,"GB2-08":74.90668668744632},"medium":{"GB2-01":39.04763309437765,"GB2-02":45.2196158397717,"GB2-03":51.91865031777808,"GB2-04":50.059410995398345,"GB2-05":50.871572098016436,"GB2-06":35.9127469404134,"GB2-07":53.84395280924377,"GB2-08":22.926926606757565},"none":{"GB2-01":48.30069682230449,"GB2-02":44.37561087159538,"GB2-03":45.7720912253075,"GB2-04":44.67651512124206,"GB2-05":36.05482982347519,"GB2-06":72.36104878524885,"GB2-07":33.499183597568866,"GB2-08":36.419957173861576}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-26T01:39:32Z","reasoning":{"highest":57.79629883139616,"medium":43.72506358771962,"none":45.182491677575484},"reasoning_agg":{"highest":{"max":85.78961219087726,"mean":57.79629883139616,"min":29.813733336483228},"medium":{"max":53.84395280924377,"mean":43.72506358771962,"min":22.926926606757565},"none":{"max":72.36104878524885,"mean":45.182491677575484,"min":33.499183597568866}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":14.07123524367654},"working_program_strength":{"all":48.901284698897086,"highest":57.79629883139616,"medium":43.72506358771962,"none":45.182491677575484}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:5efa63052d7fe040","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":3.7157460000000007},"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":2.3233296},"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":2.3233295999999997},"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":3.715746}},"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":48.758065198663324,"highest":45.16508781125245,"medium":49.60595099933734,"none":51.50315678540019},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":42.46147807126206,"score":42.46147807126206},"GB2-02":{"attempts":3,"playable":42.33261905128048,"score":42.33261905128048},"GB2-03":{"attempts":3,"playable":64.60430313909148,"score":64.60430313909148},"GB2-04":{"attempts":3,"playable":48.73675478966762,"score":48.73675478966762},"GB2-05":{"attempts":3,"playable":56.33601821461366,"score":56.33601821461366},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":52.10037721979937,"score":34.73358481319958},"GB2-07":{"attempts":3,"playable":48.72275970936434,"score":48.72275970936434},"GB2-08":{"attempts":3,"playable":52.137003800827415,"score":52.137003800827415}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":6.581131738139788,"score":6.581131738139788},"GB2-02":{"attempts":1,"playable":43.21386575739794,"score":43.21386575739794},"GB2-03":{"attempts":1,"playable":77.64964133334368,"score":77.64964133334368},"GB2-04":{"attempts":1,"playable":52.889287590724535,"score":52.889287590724535},"GB2-05":{"attempts":1,"playable":62.2944454030853,"score":62.2944454030853},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":93.67555408383942,"score":93.67555408383942},"GB2-08":{"attempts":1,"playable":25.01677658348891,"score":25.01677658348891}},"medium":{"GB2-01":{"attempts":1,"playable":69.07662824198081,"score":69.07662824198081},"GB2-02":{"attempts":1,"playable":41.733267003257794,"score":41.733267003257794},"GB2-03":{"attempts":1,"playable":66.79272456079305,"score":66.79272456079305},"GB2-04":{"attempts":1,"playable":47.42285187369465,"score":47.42285187369465},"GB2-05":{"attempts":1,"playable":51.44601327330756,"score":51.44601327330756},"GB2-06":{"attempts":1,"playable":56.40976300495131,"score":56.40976300495131},"GB2-07":{"attempts":1,"playable":24.39247214407316,"score":24.39247214407316},"GB2-08":{"attempts":1,"playable":39.57388789264043,"score":39.57388789264043}},"none":{"GB2-01":{"attempts":1,"playable":51.72667423366556,"score":51.72667423366556},"GB2-02":{"attempts":1,"playable":42.050724393185696,"score":42.050724393185696},"GB2-03":{"attempts":1,"playable":49.37054352313771,"score":49.37054352313771},"GB2-04":{"attempts":1,"playable":45.898124904583696,"score":45.898124904583696},"GB2-05":{"attempts":1,"playable":55.267595967448116,"score":55.267595967448116},"GB2-06":{"attempts":1,"playable":47.79099143464743,"score":47.79099143464743},"GB2-07":{"attempts":1,"playable":28.100252900180433,"score":28.100252900180433},"GB2-08":{"attempts":1,"playable":91.8203469263529,"score":91.8203469263529}}},"id":"moonshotai/kimi-k3","is_recent_addition":false,"last_measured_at":"2026-10-31T17:13:07Z","match_totals_all":{"draws":2785,"losses":4634,"wins":4349},"match_totals_tracks":{"highest":{"draws":810,"losses":1384,"wins":1394},"medium":{"draws":1000,"losses":1671,"wins":1419},"none":{"draws":975,"losses":1579,"wins":1536}},"model_slug":"moonshotai-kimi-k3","official_rank_by_reasoning":{"highest":48,"medium":40,"none":19},"overall":{"max":93.67555408383942,"mean":48.758065198663324,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":6.581131738139788,"GB2-02":43.21386575739794,"GB2-03":77.64964133334368,"GB2-04":52.889287590724535,"GB2-05":62.2944454030853,"GB2-07":93.67555408383942,"GB2-08":25.01677658348891},"per_game_all":{"GB2-01":42.46147807126206,"GB2-02":42.33261905128048,"GB2-03":64.60430313909148,"GB2-04":48.73675478966762,"GB2-05":56.33601821461366,"GB2-07":48.72275970936434,"GB2-08":52.137003800827415},"per_game_match_totals_all":{"GB2-01":{"draws":359,"losses":737,"wins":452},"GB2-02":{"draws":1066,"losses":321,"wins":53},"GB2-03":{"draws":199,"losses":478,"wins":811},"GB2-04":{"draws":816,"losses":384,"wins":294},"GB2-05":{"draws":0,"losses":721,"wins":869},"GB2-06":{"draws":40,"losses":504,"wins":460},"GB2-07":{"draws":0,"losses":837,"wins":753},"GB2-08":{"draws":305,"losses":652,"wins":657}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":482,"wins":26},"GB2-02":{"draws":339,"losses":111,"wins":30},"GB2-03":{"draws":34,"losses":108,"wins":354},"GB2-04":{"draws":249,"losses":119,"wins":130},"GB2-05":{"draws":0,"losses":209,"wins":321},"GB2-07":{"draws":0,"losses":30,"wins":500},"GB2-08":{"draws":180,"losses":325,"wins":33}},"medium":{"GB2-01":{"draws":89,"losses":126,"wins":301},"GB2-02":{"draws":353,"losses":111,"wins":16},"GB2-03":{"draws":73,"losses":146,"wins":277},"GB2-04":{"draws":339,"losses":101,"wins":58},"GB2-05":{"draws":0,"losses":266,"wins":264},"GB2-06":{"draws":21,"losses":229,"wins":252},"GB2-07":{"draws":0,"losses":413,"wins":117},"GB2-08":{"draws":125,"losses":279,"wins":134}},"none":{"GB2-01":{"draws":262,"losses":129,"wins":125},"GB2-02":{"draws":374,"losses":99,"wins":7},"GB2-03":{"draws":92,"losses":224,"wins":180},"GB2-04":{"draws":228,"losses":164,"wins":106},"GB2-05":{"draws":0,"losses":246,"wins":284},"GB2-06":{"draws":19,"losses":275,"wins":208},"GB2-07":{"draws":0,"losses":394,"wins":136},"GB2-08":{"draws":0,"losses":48,"wins":490}}},"per_game_raw_elo_all":{"GB2-01":1346.1526721042862,"GB2-02":1412.7236051220877,"GB2-03":1582.800450879978,"GB2-04":1465.0472503033295,"GB2-05":1518.2353479843525,"GB2-07":1545.293859407908,"GB2-08":1535.056109506693},"per_game_raw_elo_tracks":{"highest":{"GB2-01":891.9139492911097,"GB2-02":1419.565240150129,"GB2-03":1731.127873625623,"GB2-04":1497.2496813540433,"GB2-05":1596.2051697162965,"GB2-07":2357.5266223096623,"GB2-08":1101.0232981232552},"medium":{"GB2-01":1661.0819821719267,"GB2-02":1408.0674645093268,"GB2-03":1592.1517421738135,"GB2-04":1454.8307276395326,"GB2-05":1455.2183523519536,"GB2-06":1519.5833865722352,"GB2-07":1112.165040920254,"GB2-08":1264.9991284747014},"none":{"GB2-01":1485.4620848498218,"GB2-02":1410.538110706807,"GB2-03":1425.1217368404978,"GB2-04":1443.0613419164122,"GB2-05":1503.2825218848077,"GB2-06":1383.4134027675511,"GB2-07":1166.1899149938083,"GB2-08":2239.145901922122}},"per_game_tracks":{"highest":{"GB2-01":6.581131738139788,"GB2-02":43.21386575739794,"GB2-03":77.64964133334368,"GB2-04":52.889287590724535,"GB2-05":62.2944454030853,"GB2-07":93.67555408383942,"GB2-08":25.01677658348891},"medium":{"GB2-01":69.07662824198081,"GB2-02":41.733267003257794,"GB2-03":66.79272456079305,"GB2-04":47.42285187369465,"GB2-05":51.44601327330756,"GB2-06":56.40976300495131,"GB2-07":24.39247214407316,"GB2-08":39.57388789264043},"none":{"GB2-01":51.72667423366556,"GB2-02":42.050724393185696,"GB2-03":49.37054352313771,"GB2-04":45.898124904583696,"GB2-05":55.267595967448116,"GB2-06":47.79099143464743,"GB2-07":28.100252900180433,"GB2-08":91.8203469263529}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":2,"worked_first_time":21,"working":23},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:07:49Z","reasoning":{"highest":45.165087811252455,"medium":49.60595099933734,"none":51.50315678540019},"reasoning_agg":{"highest":{"max":93.67555408383942,"mean":45.165087811252455,"min":0.0},"medium":{"max":69.07662824198081,"mean":49.60595099933734,"min":24.39247214407316},"none":{"max":91.8203469263529,"mean":51.50315678540019,"min":28.100252900180433}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.338068974147738},"working_program_strength":{"all":50.908783665865826,"highest":51.61724321285994,"medium":49.60595099933734,"none":51.50315678540019}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:9d4d43e629397128","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":2.80795},"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":0.5249900000000001},"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":0.49337000000000003},"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":2.8079499999999995}},"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":48.202904241114446,"highest":56.57588266522936,"medium":44.09406156837473,"none":43.93876848973923},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":53.0998075754401,"score":53.0998075754401},"GB2-02":{"attempts":3,"playable":42.86126861369669,"score":42.86126861369669},"GB2-03":{"attempts":3,"playable":53.14322789161016,"score":53.14322789161016},"GB2-04":{"attempts":3,"playable":47.27772719710823,"score":47.27772719710823},"GB2-05":{"attempts":3,"playable":40.34270730146167,"score":40.34270730146167},"GB2-06":{"attempts":3,"playable":38.313122981307004,"score":38.313122981307004},"GB2-07":{"attempts":3,"playable":51.4303070133254,"score":51.4303070133254},"GB2-08":{"attempts":3,"playable":59.15506535496625,"score":59.15506535496625}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.77923582154035,"score":63.77923582154035},"GB2-02":{"attempts":1,"playable":41.94491643039368,"score":41.94491643039368},"GB2-03":{"attempts":1,"playable":61.030570766665925,"score":61.030570766665925},"GB2-04":{"attempts":1,"playable":52.99016356608194,"score":52.99016356608194},"GB2-05":{"attempts":1,"playable":54.69529851452448,"score":54.69529851452448},"GB2-06":{"attempts":1,"playable":28.353709998269295,"score":28.353709998269295},"GB2-07":{"attempts":1,"playable":68.14208507734556,"score":68.14208507734556},"GB2-08":{"attempts":1,"playable":81.67108114701365,"score":81.67108114701365}},"medium":{"GB2-01":{"attempts":1,"playable":46.04370742161869,"score":46.04370742161869},"GB2-02":{"attempts":1,"playable":43.742107265297825,"score":43.742107265297825},"GB2-03":{"attempts":1,"playable":42.24247734975924,"score":42.24247734975924},"GB2-04":{"attempts":1,"playable":45.18571291473545,"score":45.18571291473545},"GB2-05":{"attempts":1,"playable":42.9955172115003,"score":42.9955172115003},"GB2-06":{"attempts":1,"playable":38.59965355641884,"score":38.59965355641884},"GB2-07":{"attempts":1,"playable":50.73925750338751,"score":50.73925750338751},"GB2-08":{"attempts":1,"playable":43.20405932427992,"score":43.20405932427992}},"none":{"GB2-01":{"attempts":1,"playable":49.47647948316126,"score":49.47647948316126},"GB2-02":{"attempts":1,"playable":42.89678214539853,"score":42.89678214539853},"GB2-03":{"attempts":1,"playable":56.1566355584053,"score":56.1566355584053},"GB2-04":{"attempts":1,"playable":43.6573051105073,"score":43.6573051105073},"GB2-05":{"attempts":1,"playable":23.337306178360244,"score":23.337306178360244},"GB2-06":{"attempts":1,"playable":47.98600538923288,"score":47.98600538923288},"GB2-07":{"attempts":1,"playable":35.40957845924309,"score":35.40957845924309},"GB2-08":{"attempts":1,"playable":52.59005559360518,"score":52.59005559360518}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:04:37Z","match_totals_all":{"draws":2904,"losses":5198,"wins":4168},"match_totals_tracks":{"highest":{"draws":835,"losses":1437,"wins":1818},"medium":{"draws":1083,"losses":1849,"wins":1158},"none":{"draws":986,"losses":1912,"wins":1192}},"model_slug":"claude-sonnet-5","official_rank_by_reasoning":{"highest":37,"medium":48,"none":32},"overall":{"max":81.67108114701365,"mean":48.202904241114446,"min":23.337306178360244},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":40,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.77923582154035,"GB2-02":41.94491643039368,"GB2-03":61.030570766665925,"GB2-04":52.99016356608194,"GB2-05":54.69529851452448,"GB2-06":28.353709998269295,"GB2-07":68.14208507734556,"GB2-08":81.67108114701365},"per_game_all":{"GB2-01":53.0998075754401,"GB2-02":42.86126861369669,"GB2-03":53.14322789161016,"GB2-04":47.27772719710823,"GB2-05":40.34270730146167,"GB2-06":38.313122981307004,"GB2-07":51.4303070133254,"GB2-08":59.15506535496625},"per_game_match_totals_all":{"GB2-01":{"draws":249,"losses":634,"wins":665},"GB2-02":{"draws":1133,"losses":280,"wins":27},"GB2-03":{"draws":328,"losses":589,"wins":571},"GB2-04":{"draws":923,"losses":352,"wins":219},"GB2-05":{"draws":0,"losses":971,"wins":619},"GB2-06":{"draws":18,"losses":984,"wins":504},"GB2-07":{"draws":0,"losses":807,"wins":783},"GB2-08":{"draws":253,"losses":581,"wins":780}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":171,"wins":291},"GB2-02":{"draws":377,"losses":98,"wins":5},"GB2-03":{"draws":106,"losses":159,"wins":231},"GB2-04":{"draws":290,"losses":98,"wins":110},"GB2-05":{"draws":0,"losses":249,"wins":281},"GB2-06":{"draws":8,"losses":375,"wins":119},"GB2-07":{"draws":0,"losses":177,"wins":353},"GB2-08":{"draws":0,"losses":110,"wins":428}},"medium":{"GB2-01":{"draws":106,"losses":236,"wins":174},"GB2-02":{"draws":384,"losses":86,"wins":10},"GB2-03":{"draws":119,"losses":245,"wins":132},"GB2-04":{"draws":317,"losses":123,"wins":58},"GB2-05":{"draws":0,"losses":310,"wins":220},"GB2-06":{"draws":3,"losses":329,"wins":170},"GB2-07":{"draws":0,"losses":274,"wins":256},"GB2-08":{"draws":154,"losses":246,"wins":138}},"none":{"GB2-01":{"draws":89,"losses":227,"wins":200},"GB2-02":{"draws":372,"losses":96,"wins":12},"GB2-03":{"draws":103,"losses":185,"wins":208},"GB2-04":{"draws":316,"losses":131,"wins":51},"GB2-05":{"draws":0,"losses":412,"wins":118},"GB2-06":{"draws":7,"losses":280,"wins":215},"GB2-07":{"draws":0,"losses":356,"wins":174},"GB2-08":{"draws":99,"losses":225,"wins":214}}},"per_game_raw_elo_all":{"GB2-01":1499.896778075389,"GB2-02":1416.8256221502804,"GB2-03":1460.524142319836,"GB2-04":1453.776554649019,"GB2-05":1304.6894100895888,"GB2-06":1239.1987527617996,"GB2-07":1470.2861055525455,"GB2-08":1557.0752450887933},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.2677343725293,"GB2-02":1409.7150090567357,"GB2-03":1532.4293789965454,"GB2-04":1498.0399755077942,"GB2-05":1496.0156958918906,"GB2-06":1087.9912692565476,"GB2-07":1689.8315387799694,"GB2-08":1945.8845635517453},"medium":{"GB2-01":1431.3932671843856,"GB2-02":1423.6539460087445,"GB2-03":1363.1174415539253,"GB2-04":1437.5585577046293,"GB2-05":1349.7472828235834,"GB2-06":1243.178061591187,"GB2-07":1456.7076650056456,"GB2-08":1305.9215663490384},"none":{"GB2-01":1464.0293326692517,"GB2-02":1417.1079113853616,"GB2-03":1486.0256064090374,"GB2-04":1425.731130734633,"GB2-05":1068.3052515532927,"GB2-06":1386.4269274376643,"GB2-07":1264.3191128720216,"GB2-08":1419.4196053655965}},"per_game_tracks":{"highest":{"GB2-01":63.77923582154035,"GB2-02":41.94491643039368,"GB2-03":61.030570766665925,"GB2-04":52.99016356608194,"GB2-05":54.69529851452448,"GB2-06":28.353709998269295,"GB2-07":68.14208507734556,"GB2-08":81.67108114701365},"medium":{"GB2-01":46.04370742161869,"GB2-02":43.742107265297825,"GB2-03":42.24247734975924,"GB2-04":45.18571291473545,"GB2-05":42.9955172115003,"GB2-06":38.59965355641884,"GB2-07":50.73925750338751,"GB2-08":43.20405932427992},"none":{"GB2-01":49.47647948316126,"GB2-02":42.89678214539853,"GB2-03":56.1566355584053,"GB2-04":43.6573051105073,"GB2-05":23.337306178360244,"GB2-06":47.98600538923288,"GB2-07":35.40957845924309,"GB2-08":52.59005559360518}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":24,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:07:41Z","reasoning":{"highest":56.57588266522936,"medium":44.09406156837473,"none":43.93876848973923},"reasoning_agg":{"highest":{"max":81.67108114701365,"mean":56.57588266522936,"min":28.353709998269295},"medium":{"max":50.73925750338751,"mean":44.09406156837473,"min":38.59965355641884},"none":{"max":56.1566355584053,"mean":43.93876848973923,"min":23.337306178360244}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.637114175490126},"working_program_strength":{"all":48.202904241114446,"highest":56.57588266522936,"medium":44.09406156837473,"none":43.93876848973923}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-3:bc6950a0d4411105","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003},"medium":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.0224273}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.046827143749999994,"median":0.045572185,"min":0.02463971,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":7},"recorded_attempt_count":11,"run_count":8,"total":0.37461715000000007},"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":0.0094142,"mean":0.0028034124999999997,"median":0.001882025,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.022427299999999997},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.04598051,"mean":0.037044270000000004,"median":0.03605392,"min":0.02439431,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":11,"run_count":8,"total":0.29635416000000003}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.08221237,"mean":0.028891608750000006,"median":0.03513247,"min":0.0015762,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":24},"recorded_attempt_count":31,"run_count":24,"total":0.6933986099999999},"codegen_latency_ms":{"attempt_count":24,"max_ms":377102,"mean_ms":133492.94444444444,"min_ms":3791,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319339,"mean_ms":217388.6,"min_ms":142770,"run_count":5},"medium":{"attempt_count":7,"max_ms":377102,"mean_ms":248372.6,"min_ms":146739,"run_count":5},"none":{"attempt_count":9,"max_ms":30086,"mean_ms":9258.375,"min_ms":3791,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":230653,"output_mean":79571.75,"output_min":2342,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":129270,"output_mean":102689.5,"output_min":67386,"run_count":8},"medium":{"attempt_count":11,"output_max":230653,"output_mean":130579.0,"output_min":68315,"run_count":8},"none":{"attempt_count":9,"output_max":22506,"output_mean":5446.75,"output_min":2342,"run_count":8}},"display_name":"Mercury 3","economics":{"all":47.84274863967004,"highest":59.58172086017735,"medium":44.99838422375987,"none":38.948140835072905},"first_seen_at":null,"game_gaps":{"highest":{"GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-07":"infra_excluded"},"medium":{"GB2-01":"infra_excluded","GB2-03":"failed","GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-06":"infra_excluded"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":31,"effective_max_output_tokens":[131072],"finish_reason_observations":24,"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,"requested_max_output_token_observations":31,"requested_max_output_tokens":[131072],"total_output_tokens":1909722,"total_reasoning_output_tokens":1808452,"total_visible_output_tokens":101270,"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":"unknown_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":"inception","provider_model":"inception/mercury-3","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":3,"evaluated_cells":4,"failed_game_aliases":["GB2-03"],"first_pass_admitted":2,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"admitted":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":1}},"infra_excluded_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"infra_failures_excluded":4,"model_code_failure_rate":0.25,"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":1,"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":5,"evaluated_cells":5,"first_pass_admitted":2,"first_pass_rate":0.4,"game_attempts":{"GB2-01":{"admitted":1},"GB2-02":{"admitted":1},"GB2-03":{"admitted":1},"GB2-04":{"infra_failures_excluded":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":["GB2-04","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":3,"repaired_rate":0.6}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":42.47583456402555,"score":42.47583456402555},"GB2-02":{"attempts":3,"playable":44.409558987105875,"score":44.409558987105875},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":48.01091746038051,"score":32.00727830692034},"GB2-04":{"attempts":1,"playable":40.69568594533089,"score":40.69568594533089},"GB2-05":{"attempts":1,"playable":25.260560217696167,"score":25.260560217696167},"GB2-06":{"attempts":2,"playable":73.21083030075091,"score":73.21083030075091},"GB2-07":{"attempts":2,"playable":55.69688884408028,"score":55.69688884408028},"GB2-08":{"attempts":3,"playable":50.50446747123009,"score":50.50446747123009}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":50.063915845315755,"score":50.063915845315755},"GB2-02":{"attempts":1,"playable":44.16449018927223,"score":44.16449018927223},"GB2-03":{"attempts":1,"playable":62.21220095299298,"score":62.21220095299298},"GB2-06":{"attempts":1,"playable":79.62346402908678,"score":79.62346402908678},"GB2-08":{"attempts":1,"playable":61.84453328421896,"score":61.84453328421896}},"medium":{"GB2-02":{"attempts":1,"playable":46.37885098681369,"score":46.37885098681369},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":77.8945940905917,"score":77.8945940905917},"GB2-08":{"attempts":1,"playable":55.7200918176341,"score":55.7200918176341}},"none":{"GB2-01":{"attempts":1,"playable":34.887753282735346,"score":34.887753282735346},"GB2-02":{"attempts":1,"playable":42.68533578523171,"score":42.68533578523171},"GB2-03":{"attempts":1,"playable":33.80963396776804,"score":33.80963396776804},"GB2-04":{"attempts":1,"playable":40.69568594533089,"score":40.69568594533089},"GB2-05":{"attempts":1,"playable":25.260560217696167,"score":25.260560217696167},"GB2-06":{"attempts":1,"playable":66.79819657241505,"score":66.79819657241505},"GB2-07":{"attempts":1,"playable":33.499183597568866,"score":33.499183597568866},"GB2-08":{"attempts":1,"playable":33.948777311837205,"score":33.948777311837205}}},"id":"inception/mercury-3","is_recent_addition":false,"last_measured_at":"2026-10-27T02:35:43Z","match_totals_all":{"draws":2052,"losses":3305,"wins":2813},"match_totals_tracks":{"highest":{"draws":727,"losses":725,"wins":1080},"medium":{"draws":335,"losses":477,"wins":736},"none":{"draws":990,"losses":2103,"wins":997}},"model_slug":"inception-mercury-3","official_rank_by_reasoning":{"none":47},"overall":{"max":79.62346402908678,"mean":47.84274863967004,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":41,"overall_ranking_status":"partial","per_game":{"GB2-01":50.063915845315755,"GB2-02":44.16449018927223,"GB2-03":62.21220095299298,"GB2-06":79.62346402908678,"GB2-08":61.84453328421896},"per_game_all":{"GB2-02":44.409558987105875,"GB2-08":50.50446747123009},"per_game_match_totals_all":{"GB2-01":{"draws":438,"losses":395,"wins":199},"GB2-02":{"draws":1053,"losses":298,"wins":89},"GB2-03":{"draws":227,"losses":437,"wins":328},"GB2-04":{"draws":323,"losses":142,"wins":33},"GB2-05":{"draws":0,"losses":402,"wins":128},"GB2-06":{"draws":11,"losses":291,"wins":702},"GB2-07":{"draws":0,"losses":487,"wins":573},"GB2-08":{"draws":0,"losses":853,"wins":761}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":259,"losses":139,"wins":118},"GB2-02":{"draws":348,"losses":102,"wins":30},"GB2-03":{"draws":114,"losses":149,"wins":233},"GB2-06":{"draws":6,"losses":110,"wins":386},"GB2-08":{"draws":0,"losses":225,"wins":313}},"medium":{"GB2-02":{"draws":335,"losses":98,"wins":47},"GB2-07":{"draws":0,"losses":121,"wins":409},"GB2-08":{"draws":0,"losses":258,"wins":280}},"none":{"GB2-01":{"draws":179,"losses":256,"wins":81},"GB2-02":{"draws":370,"losses":98,"wins":12},"GB2-03":{"draws":113,"losses":288,"wins":95},"GB2-04":{"draws":323,"losses":142,"wins":33},"GB2-05":{"draws":0,"losses":402,"wins":128},"GB2-06":{"draws":5,"losses":181,"wins":316},"GB2-07":{"draws":0,"losses":366,"wins":164},"GB2-08":{"draws":0,"losses":370,"wins":168}}},"per_game_raw_elo_all":{"GB2-02":1428.796075376059,"GB2-08":1405.1721334490376},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1469.6172757010147,"GB2-02":1426.9193175815556,"GB2-03":1544.1740448733933,"GB2-06":1941.5372305518047,"GB2-08":1551.5568405292938},"medium":{"GB2-02":1444.001059081438,"GB2-07":1851.366085692725,"GB2-08":1461.2417906403437},"none":{"GB2-01":1322.6817882620485,"GB2-02":1415.4678494651837,"GB2-03":1288.4976564205856,"GB2-04":1402.6515736907934,"GB2-05":1100.080265896353,"GB2-06":1696.913351161495,"GB2-07":1239.444621620038,"GB2-08":1202.7177691774748}},"per_game_tracks":{"highest":{"GB2-01":50.063915845315755,"GB2-02":44.16449018927223,"GB2-03":62.21220095299298,"GB2-06":79.62346402908678,"GB2-08":61.84453328421896},"medium":{"GB2-02":46.37885098681369,"GB2-07":77.8945940905917,"GB2-08":55.7200918176341},"none":{"GB2-01":34.887753282735346,"GB2-02":42.68533578523171,"GB2-03":33.80963396776804,"GB2-04":40.69568594533089,"GB2-05":25.260560217696167,"GB2-06":66.79819657241505,"GB2-07":33.499183597568866,"GB2-08":33.948777311837205}},"program_outcomes":{"all":{"counted_attempts":17,"failed":1,"infra_excluded":7,"success_rate":0.9411764705882353,"too_slow":0,"worked_after_repair":5,"worked_first_time":11,"working":16},"highest":{"counted_attempts":5,"failed":0,"infra_excluded":3,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":2,"working":5},"medium":{"counted_attempts":4,"failed":1,"infra_excluded":4,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":2,"working":3},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":59.58172086017735,"medium":44.99838422375987,"none":38.948140835072905},"reasoning_agg":{"highest":{"max":79.62346402908678,"mean":59.58172086017735,"min":44.16449018927223},"medium":{"max":77.8945940905917,"mean":44.99838422375987,"min":0.0},"none":{"max":66.79819657241505,"mean":38.948140835072905,"min":25.260560217696167}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":20.633580025104443},"working_program_strength":{"all":52.8425691089767,"highest":59.58172086017735,"medium":59.99784563167983,"none":38.948140835072905}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:2dd7e8c0505d81be","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":3.0672337499999998},"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":0.7756987500000001},"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":0.77569875},"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":0.6137425000000001},"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":47.266211393665536,"highest":55.178430625589755,"medium":50.79333414056768,"none":35.82686941483916},"first_seen_at":null,"game_gaps":{"none":{"GB2-05":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":67.99031692181711,"score":67.99031692181711},"GB2-02":{"attempts":3,"playable":49.887119553203554,"score":49.887119553203554},"GB2-03":{"attempts":3,"playable":34.72948920570698,"score":34.72948920570698},"GB2-04":{"attempts":3,"playable":43.52092723435848,"score":43.52092723435848},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":56.98132217306416,"score":37.98754811537611},"GB2-06":{"attempts":3,"playable":53.36272890593377,"score":53.36272890593377},"GB2-07":{"attempts":3,"playable":44.99105631280137,"score":44.99105631280137},"GB2-08":{"attempts":3,"playable":45.66050490012689,"score":45.66050490012689}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":72.14094859655616,"score":72.14094859655616},"GB2-02":{"attempts":1,"playable":59.433818621899206,"score":59.433818621899206},"GB2-03":{"attempts":1,"playable":36.569630069103766,"score":36.569630069103766},"GB2-04":{"attempts":1,"playable":42.33074786119691,"score":42.33074786119691},"GB2-05":{"attempts":1,"playable":55.64893258926082,"score":55.64893258926082},"GB2-06":{"attempts":1,"playable":80.16790540991097,"score":80.16790540991097},"GB2-07":{"attempts":1,"playable":44.268444843874185,"score":44.268444843874185},"GB2-08":{"attempts":1,"playable":50.867017012915994,"score":50.867017012915994}},"medium":{"GB2-01":{"attempts":1,"playable":77.27247993583588,"score":77.27247993583588},"GB2-02":{"attempts":1,"playable":45.95748358281864,"score":45.95748358281864},"GB2-03":{"attempts":1,"playable":34.23544025107207,"score":34.23544025107207},"GB2-04":{"attempts":1,"playable":43.759274382090815,"score":43.759274382090815},"GB2-05":{"attempts":1,"playable":58.31371175686749,"score":58.31371175686749},"GB2-06":{"attempts":1,"playable":42.452171217178645,"score":42.452171217178645},"GB2-07":{"attempts":1,"playable":61.05423536891878,"score":61.05423536891878},"GB2-08":{"attempts":1,"playable":43.30187662975916,"score":43.30187662975916}},"none":{"GB2-01":{"attempts":1,"playable":54.55752223305929,"score":54.55752223305929},"GB2-02":{"attempts":1,"playable":44.27005645489282,"score":44.27005645489282},"GB2-03":{"attempts":1,"playable":33.38339729694511,"score":33.38339729694511},"GB2-04":{"attempts":1,"playable":44.47275945978772,"score":44.47275945978772},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":37.46811009071168,"score":37.46811009071168},"GB2-07":{"attempts":1,"playable":29.65048872561117,"score":29.65048872561117},"GB2-08":{"attempts":1,"playable":42.8126210577055,"score":42.8126210577055}}},"id":"gpt-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-10-31T16:37:24Z","match_totals_all":{"draws":3003,"losses":4736,"wins":4001},"match_totals_tracks":{"highest":{"draws":912,"losses":1475,"wins":1703},"medium":{"draws":990,"losses":1612,"wins":1488},"none":{"draws":1101,"losses":1649,"wins":810}},"model_slug":"gpt-5-6-terra","official_rank_by_reasoning":{"highest":41,"medium":38,"none":51},"overall":{"max":80.16790540991097,"mean":47.266211393665536,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":42,"overall_ranking_status":"ranked","per_game":{"GB2-01":72.14094859655616,"GB2-02":59.433818621899206,"GB2-03":36.569630069103766,"GB2-04":42.33074786119691,"GB2-05":55.64893258926082,"GB2-06":80.16790540991097,"GB2-07":44.268444843874185,"GB2-08":50.867017012915994},"per_game_all":{"GB2-01":67.99031692181711,"GB2-02":49.887119553203554,"GB2-03":34.72948920570698,"GB2-04":43.52092723435848,"GB2-06":53.36272890593377,"GB2-07":44.99105631280137,"GB2-08":45.66050490012689},"per_game_match_totals_all":{"GB2-01":{"draws":243,"losses":406,"wins":899},"GB2-02":{"draws":1038,"losses":227,"wins":175},"GB2-03":{"draws":547,"losses":747,"wins":194},"GB2-04":{"draws":904,"losses":417,"wins":173},"GB2-05":{"draws":0,"losses":474,"wins":586},"GB2-06":{"draws":59,"losses":728,"wins":719},"GB2-07":{"draws":0,"losses":912,"wins":678},"GB2-08":{"draws":212,"losses":825,"wins":577}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":71,"losses":119,"wins":326},"GB2-02":{"draws":266,"losses":70,"wins":144},"GB2-03":{"draws":151,"losses":256,"wins":89},"GB2-04":{"draws":325,"losses":133,"wins":40},"GB2-05":{"draws":0,"losses":244,"wins":286},"GB2-06":{"draws":24,"losses":98,"wins":380},"GB2-07":{"draws":0,"losses":309,"wins":221},"GB2-08":{"draws":75,"losses":246,"wins":217}},"medium":{"GB2-01":{"draws":3,"losses":126,"wins":387},"GB2-02":{"draws":383,"losses":76,"wins":21},"GB2-03":{"draws":227,"losses":229,"wins":40},"GB2-04":{"draws":251,"losses":163,"wins":84},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":33,"losses":295,"wins":174},"GB2-07":{"draws":0,"losses":217,"wins":313},"GB2-08":{"draws":93,"losses":276,"wins":169}},"none":{"GB2-01":{"draws":169,"losses":161,"wins":186},"GB2-02":{"draws":389,"losses":81,"wins":10},"GB2-03":{"draws":169,"losses":262,"wins":65},"GB2-04":{"draws":328,"losses":121,"wins":49},"GB2-06":{"draws":2,"losses":335,"wins":165},"GB2-07":{"draws":0,"losses":386,"wins":144},"GB2-08":{"draws":44,"losses":303,"wins":191}}},"per_game_raw_elo_all":{"GB2-01":1656.4298032136596,"GB2-02":1471.7853545050912,"GB2-03":1296.7756863345928,"GB2-04":1424.664761104128,"GB2-06":1493.452221845351,"GB2-07":1384.6282171776795,"GB2-08":1335.3008751297023},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1696.2069628183126,"GB2-02":1546.867553206834,"GB2-03":1313.3524165231274,"GB2-04":1415.4267734701657,"GB2-05":1508.142285086807,"GB2-06":1952.6692785597977,"GB2-07":1376.0146806471826,"GB2-08":1397.4060576605052},"medium":{"GB2-01":1760.4787881849734,"GB2-02":1440.7535619430269,"GB2-03":1292.3723789344708,"GB2-04":1426.521473408679,"GB2-05":1542.5835968148824,"GB2-06":1301.6256465425981,"GB2-07":1590.100765610494,"GB2-08":1307.0395776250073},"none":{"GB2-01":1512.6036586376931,"GB2-02":1427.7349483654125,"GB2-03":1284.6022635461804,"GB2-04":1432.046036433539,"GB2-06":1226.0617404336572,"GB2-07":1187.769205275362,"GB2-08":1301.4569901035943}},"per_game_tracks":{"highest":{"GB2-01":72.14094859655616,"GB2-02":59.433818621899206,"GB2-03":36.569630069103766,"GB2-04":42.33074786119691,"GB2-05":55.64893258926082,"GB2-06":80.16790540991097,"GB2-07":44.268444843874185,"GB2-08":50.867017012915994},"medium":{"GB2-01":77.27247993583588,"GB2-02":45.95748358281864,"GB2-03":34.23544025107207,"GB2-04":43.759274382090815,"GB2-05":58.31371175686749,"GB2-06":42.452171217178645,"GB2-07":61.05423536891878,"GB2-08":43.30187662975916},"none":{"GB2-01":54.55752223305929,"GB2-02":44.27005645489282,"GB2-03":33.38339729694511,"GB2-04":44.47275945978772,"GB2-06":37.46811009071168,"GB2-07":29.65048872561117,"GB2-08":42.8126210577055}},"program_outcomes":{"all":{"counted_attempts":24,"failed":1,"infra_excluded":0,"success_rate":0.9583333333333334,"too_slow":0,"worked_after_repair":3,"worked_first_time":20,"working":23},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:54:15Z","reasoning":{"highest":55.178430625589755,"medium":50.79333414056768,"none":35.82686941483916},"reasoning_agg":{"highest":{"max":80.16790540991097,"mean":55.178430625589755,"min":36.569630069103766},"medium":{"max":77.27247993583588,"mean":50.79333414056768,"min":34.23544025107207},"none":{"max":54.55752223305929,"mean":35.82686941483916,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":19.351561210750596},"working_program_strength":{"all":48.97225279437216,"highest":55.178430625589755,"medium":50.79333414056768,"none":40.94499361695904}},{"canonical_public_row_identity":"publication-row.v1:overall:gemini-3-1-pro-preview:a324d82792c47394","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":0.6420659999999999},"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":0.3670399999999999}},"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":0.36704000000000003},"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":2.592372}},"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":3.601478000000001},"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":46.14367491198055,"highest":66.5149499749952,"medium":42.12655644473854,"none":29.789518316207882},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":50.14632067383881,"score":50.14632067383881},"GB2-02":{"attempts":3,"playable":43.38970979151887,"score":43.38970979151887},"GB2-03":{"attempts":3,"playable":53.75060628147787,"score":53.75060628147787},"GB2-04":{"attempts":3,"playable":56.71909493453715,"score":56.71909493453715},"GB2-05":{"attempts":3,"playable":39.59760245210348,"score":39.59760245210348},"GB2-06":{"attempts":3,"playable":21.285890802333174,"score":21.285890802333174},"GB2-07":{"attempts":3,"playable":57.054539706549214,"score":57.054539706549214},"GB2-08":{"attempts":3,"playable":47.20563465348575,"score":47.20563465348575}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.42856770392736,"score":74.42856770392736},"GB2-02":{"attempts":1,"playable":43.108182717729534,"score":43.108182717729534},"GB2-03":{"attempts":1,"playable":66.30912685890443,"score":66.30912685890443},"GB2-04":{"attempts":1,"playable":81.21420724865548,"score":81.21420724865548},"GB2-05":{"attempts":1,"playable":85.17622827719016,"score":85.17622827719016},"GB2-06":{"attempts":1,"playable":19.250927977020314,"score":19.250927977020314},"GB2-07":{"attempts":1,"playable":75.1255605082591,"score":75.1255605082591},"GB2-08":{"attempts":1,"playable":87.50679850827528,"score":87.50679850827528}},"medium":{"GB2-01":{"attempts":1,"playable":35.086217559685224,"score":35.086217559685224},"GB2-02":{"attempts":1,"playable":44.37561087159538,"score":44.37561087159538},"GB2-03":{"attempts":1,"playable":66.59939335930642,"score":66.59939335930642},"GB2-04":{"attempts":1,"playable":45.99985326266107,"score":45.99985326266107},"GB2-05":{"attempts":1,"playable":17.57586010525059,"score":17.57586010525059},"GB2-06":{"attempts":1,"playable":29.2214964360282,"score":29.2214964360282},"GB2-07":{"attempts":1,"playable":71.6455864673154,"score":71.6455864673154},"GB2-08":{"attempts":1,"playable":26.508433496066036,"score":26.508433496066036}},"none":{"GB2-01":{"attempts":1,"playable":40.924176757903865,"score":40.924176757903865},"GB2-02":{"attempts":1,"playable":42.68533578523171,"score":42.68533578523171},"GB2-03":{"attempts":1,"playable":28.34329862622276,"score":28.34329862622276},"GB2-04":{"attempts":1,"playable":42.9432242922949,"score":42.9432242922949},"GB2-05":{"attempts":1,"playable":16.040718973869694,"score":16.040718973869694},"GB2-06":{"attempts":1,"playable":15.385247993951005,"score":15.385247993951005},"GB2-07":{"attempts":1,"playable":24.39247214407316,"score":24.39247214407316},"GB2-08":{"attempts":1,"playable":27.601671956115936,"score":27.601671956115936}}},"id":"gemini-3.1-pro-preview","is_recent_addition":false,"last_measured_at":"2026-10-31T17:13:11Z","match_totals_all":{"draws":2670,"losses":5513,"wins":4087},"match_totals_tracks":{"highest":{"draws":545,"losses":1151,"wins":2394},"medium":{"draws":1062,"losses":1931,"wins":1097},"none":{"draws":1063,"losses":2431,"wins":596}},"model_slug":"gemini-3-1-pro-preview","official_rank_by_reasoning":{"highest":23,"medium":53,"none":63},"overall":{"max":87.50679850827528,"mean":46.14367491198055,"min":15.385247993951005},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":43,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.42856770392736,"GB2-02":43.108182717729534,"GB2-03":66.30912685890443,"GB2-04":81.21420724865548,"GB2-05":85.17622827719016,"GB2-06":19.250927977020314,"GB2-07":75.1255605082591,"GB2-08":87.50679850827528},"per_game_all":{"GB2-01":50.14632067383881,"GB2-02":43.38970979151887,"GB2-03":53.75060628147787,"GB2-04":56.71909493453715,"GB2-05":39.59760245210348,"GB2-06":21.285890802333174,"GB2-07":57.054539706549214,"GB2-08":47.20563465348575},"per_game_match_totals_all":{"GB2-01":{"draws":280,"losses":662,"wins":606},"GB2-02":{"draws":1156,"losses":261,"wins":23},"GB2-03":{"draws":279,"losses":599,"wins":610},"GB2-04":{"draws":685,"losses":327,"wins":482},"GB2-05":{"draws":0,"losses":976,"wins":614},"GB2-06":{"draws":16,"losses":1224,"wins":266},"GB2-07":{"draws":0,"losses":707,"wins":883},"GB2-08":{"draws":254,"losses":757,"wins":603}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":132,"wins":363},"GB2-02":{"draws":384,"losses":89,"wins":7},"GB2-03":{"draws":26,"losses":172,"wins":298},"GB2-04":{"draws":111,"losses":44,"wins":343},"GB2-05":{"draws":0,"losses":84,"wins":446},"GB2-06":{"draws":2,"losses":419,"wins":81},"GB2-07":{"draws":0,"losses":137,"wins":393},"GB2-08":{"draws":1,"losses":74,"wins":463}},"medium":{"GB2-01":{"draws":173,"losses":258,"wins":85},"GB2-02":{"draws":382,"losses":84,"wins":14},"GB2-03":{"draws":97,"losses":135,"wins":264},"GB2-04":{"draws":275,"losses":140,"wins":83},"GB2-05":{"draws":0,"losses":442,"wins":88},"GB2-06":{"draws":12,"losses":369,"wins":121},"GB2-07":{"draws":0,"losses":157,"wins":373},"GB2-08":{"draws":123,"losses":346,"wins":69}},"none":{"GB2-01":{"draws":86,"losses":272,"wins":158},"GB2-02":{"draws":390,"losses":88,"wins":2},"GB2-03":{"draws":156,"losses":292,"wins":48},"GB2-04":{"draws":299,"losses":143,"wins":56},"GB2-05":{"draws":0,"losses":450,"wins":80},"GB2-06":{"draws":2,"losses":436,"wins":64},"GB2-07":{"draws":0,"losses":413,"wins":117},"GB2-08":{"draws":130,"losses":337,"wins":71}}},"per_game_raw_elo_all":{"GB2-01":1476.9675784325243,"GB2-02":1420.9215492185783,"GB2-03":1471.2821577584698,"GB2-04":1544.7820923319352,"GB2-05":1321.2392570143866,"GB2-06":973.5058762692137,"GB2-07":1552.2426933837312,"GB2-08":1449.7116710186376},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1723.878866846735,"GB2-02":1418.7464884796957,"GB2-03":1586.8747435027167,"GB2-04":1770.3095593592518,"GB2-05":2065.6173481900605,"GB2-06":943.6894116742686,"GB2-07":1801.1020519165997,"GB2-08":2099.135916380825},"medium":{"GB2-01":1324.6918147071542,"GB2-02":1428.5503097108551,"GB2-03":1590.0353991388072,"GB2-04":1443.8467916489367,"GB2-05":964.3288186170732,"GB2-06":1101.2322019645903,"GB2-07":1743.4609873143393,"GB2-08":1118.6515909051082},"none":{"GB2-01":1382.3320537436832,"GB2-02":1415.4678494651837,"GB2-03":1236.9363306338853,"GB2-04":1420.1899259876172,"GB2-05":933.7716042360264,"GB2-06":875.5960151687821,"GB2-07":1112.165040920254,"GB2-08":1131.34750576998}},"per_game_tracks":{"highest":{"GB2-01":74.42856770392736,"GB2-02":43.108182717729534,"GB2-03":66.30912685890443,"GB2-04":81.21420724865548,"GB2-05":85.17622827719016,"GB2-06":19.250927977020314,"GB2-07":75.1255605082591,"GB2-08":87.50679850827528},"medium":{"GB2-01":35.086217559685224,"GB2-02":44.37561087159538,"GB2-03":66.59939335930642,"GB2-04":45.99985326266107,"GB2-05":17.57586010525059,"GB2-06":29.2214964360282,"GB2-07":71.6455864673154,"GB2-08":26.508433496066036},"none":{"GB2-01":40.924176757903865,"GB2-02":42.68533578523171,"GB2-03":28.34329862622276,"GB2-04":42.9432242922949,"GB2-05":16.040718973869694,"GB2-06":15.385247993951005,"GB2-07":24.39247214407316,"GB2-08":27.601671956115936}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":20,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:54:15Z","reasoning":{"highest":66.5149499749952,"medium":42.12655644473854,"none":29.789518316207882},"reasoning_agg":{"highest":{"max":87.50679850827528,"mean":66.5149499749952,"min":19.250927977020314},"medium":{"max":71.6455864673154,"mean":42.12655644473854,"min":17.57586010525059},"none":{"max":42.9432242922949,"mean":29.789518316207882,"min":15.385247993951005}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":36.72543165878732},"working_program_strength":{"all":46.14367491198055,"highest":66.5149499749952,"medium":42.12655644473854,"none":29.789518316207882}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:80b09fce73ac6d39","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":1.4469687303},"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":0.013816857666666668,"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":0.20593804350000003},"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":0.013816857666666668,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168},"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":44.86291677580647,"highest":45.55294625254986,"medium":47.829677744958104,"none":41.20612632991145},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":40.54563289685931,"score":40.54563289685931},"GB2-02":{"attempts":6,"playable":50.479688152397635,"score":50.479688152397635},"GB2-03":{"attempts":6,"playable":36.00616539674908,"score":36.00616539674908},"GB2-04":{"attempts":6,"playable":49.90990834620467,"score":49.90990834620467},"GB2-05":{"attempts":6,"playable":49.46089370318375,"score":49.46089370318375},"GB2-06":{"attempts":6,"playable":55.79136555354625,"score":55.79136555354625},"GB2-07":{"attempts":6,"playable":38.92313048913715,"score":38.92313048913715},"GB2-08":{"attempts":6,"playable":37.786549668373944,"score":37.786549668373944}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":54.069952914790306,"score":54.069952914790306},"GB2-02":{"attempts":1,"playable":61.91159206865199,"score":61.91159206865199},"GB2-03":{"attempts":1,"playable":37.09828752235075,"score":37.09828752235075},"GB2-04":{"attempts":1,"playable":58.416412573028,"score":58.416412573028},"GB2-05":{"attempts":1,"playable":58.88364509325174,"score":58.88364509325174},"GB2-06":{"attempts":1,"playable":42.35186430476081,"score":42.35186430476081},"GB2-07":{"attempts":1,"playable":10.153152420309118,"score":10.153152420309118},"GB2-08":{"attempts":1,"playable":41.53866312325621,"score":41.53866312325621}},"medium":{"GB2-01":{"attempts":2,"playable":39.12420829247724,"score":39.12420829247724},"GB2-02":{"attempts":2,"playable":48.6774415304111,"score":48.6774415304111},"GB2-03":{"attempts":2,"playable":30.592136200568348,"score":30.592136200568348},"GB2-04":{"attempts":2,"playable":48.09802931356302,"score":48.09802931356302},"GB2-05":{"attempts":2,"playable":53.93079350037165,"score":53.93079350037165},"GB2-06":{"attempts":2,"playable":78.66656044290741,"score":78.66656044290741},"GB2-07":{"attempts":2,"playable":58.92957242041351,"score":58.92957242041351},"GB2-08":{"attempts":2,"playable":24.618680258952594,"score":24.618680258952594}},"none":{"GB2-01":{"attempts":3,"playable":28.442737483310395,"score":28.442737483310395},"GB2-02":{"attempts":3,"playable":40.85003085812979,"score":40.85003085812979},"GB2-03":{"attempts":3,"playable":40.328072467328155,"score":40.328072467328155},"GB2-04":{"attempts":3,"playable":43.215283152023005,"score":43.215283152023005},"GB2-05":{"attempts":3,"playable":35.56824251592788,"score":35.56824251592788},"GB2-06":{"attempts":3,"playable":46.355671912970514,"score":46.355671912970514},"GB2-07":{"attempts":3,"playable":47.68666662668884,"score":47.68666662668884},"GB2-08":{"attempts":3,"playable":47.20230562291302,"score":47.20230562291302}}},"id":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-10-31T16:20:24Z","match_totals_all":{"draws":6261,"losses":11144,"wins":7135},"match_totals_tracks":{"highest":{"draws":993,"losses":1842,"wins":1255},"medium":{"draws":2193,"losses":3347,"wins":2640},"none":{"draws":3075,"losses":5955,"wins":3240}},"model_slug":"z-ai-glm-5-2","official_rank_by_reasoning":{"highest":46,"medium":43,"none":41},"overall":{"max":78.66656044290741,"mean":44.86291677580647,"min":10.153152420309118},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":54.069952914790306,"GB2-02":61.91159206865199,"GB2-03":37.09828752235075,"GB2-04":58.416412573028,"GB2-05":58.88364509325174,"GB2-06":42.35186430476081,"GB2-07":10.153152420309118,"GB2-08":41.53866312325621},"per_game_all":{"GB2-01":40.54563289685931,"GB2-02":50.479688152397635,"GB2-03":36.00616539674908,"GB2-04":49.90990834620467,"GB2-05":49.46089370318376,"GB2-06":55.791365553546235,"GB2-07":38.92313048913715,"GB2-08":37.786549668373944},"per_game_match_totals_all":{"GB2-01":{"draws":765,"losses":1647,"wins":684},"GB2-02":{"draws":2060,"losses":545,"wins":275},"GB2-03":{"draws":1091,"losses":1443,"wins":442},"GB2-04":{"draws":1695,"losses":776,"wins":517},"GB2-05":{"draws":0,"losses":1778,"wins":1402},"GB2-06":{"draws":84,"losses":1372,"wins":1556},"GB2-07":{"draws":0,"losses":1811,"wins":1369},"GB2-08":{"draws":566,"losses":1772,"wins":890}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":184,"losses":156,"wins":176},"GB2-02":{"draws":238,"losses":72,"wins":170},"GB2-03":{"draws":176,"losses":241,"wins":79},"GB2-04":{"draws":242,"losses":95,"wins":161},"GB2-05":{"draws":0,"losses":227,"wins":303},"GB2-06":{"draws":18,"losses":303,"wins":181},"GB2-07":{"draws":0,"losses":484,"wins":46},"GB2-08":{"draws":135,"losses":264,"wins":139}},"medium":{"GB2-01":{"draws":280,"losses":508,"wins":244},"GB2-02":{"draws":716,"losses":151,"wins":93},"GB2-03":{"draws":414,"losses":512,"wins":66},"GB2-04":{"draws":572,"losses":248,"wins":176},"GB2-05":{"draws":0,"losses":506,"wins":554},"GB2-06":{"draws":31,"losses":221,"wins":752},"GB2-07":{"draws":0,"losses":457,"wins":603},"GB2-08":{"draws":180,"losses":744,"wins":152}},"none":{"GB2-01":{"draws":301,"losses":983,"wins":264},"GB2-02":{"draws":1106,"losses":322,"wins":12},"GB2-03":{"draws":501,"losses":690,"wins":297},"GB2-04":{"draws":881,"losses":433,"wins":180},"GB2-05":{"draws":0,"losses":1045,"wins":545},"GB2-06":{"draws":35,"losses":848,"wins":623},"GB2-07":{"draws":0,"losses":870,"wins":720},"GB2-08":{"draws":251,"losses":764,"wins":599}}},"per_game_raw_elo_all":{"GB2-01":1374.808846042459,"GB2-02":1476.876088012349,"GB2-03":1307.4055873568032,"GB2-04":1474.6309457432108,"GB2-05":1423.0611556744552,"GB2-06":1534.0749125905297,"GB2-07":1274.0469571936085,"GB2-08":1268.9730254035715},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1507.9089828507726,"GB2-02":1567.606907214877,"GB2-03":1318.0513311098725,"GB2-04":1541.3165079054347,"GB2-05":1550.0797257240467,"GB2-06":1300.0993239955587,"GB2-07":837.2131571753969,"GB2-08":1287.0227509173365},"medium":{"GB2-01":1363.230937658643,"GB2-02":1461.8846523110094,"GB2-03":1258.0122715005912,"GB2-04":1460.2746015326998,"GB2-05":1486.4211497960814,"GB2-06":1929.0453459294563,"GB2-07":1564.903804673505,"GB2-08":1096.1690976042405},"none":{"GB2-01":1253.2866176179616,"GB2-02":1401.136704511161,"GB2-03":1346.1531594599458,"GB2-04":1422.3017277914976,"GB2-05":1232.682591503238,"GB2-06":1373.0800678465741,"GB2-07":1420.0239097319236,"GB2-08":1423.7272276891372}},"per_game_tracks":{"highest":{"GB2-01":54.069952914790306,"GB2-02":61.91159206865199,"GB2-03":37.09828752235075,"GB2-04":58.416412573028,"GB2-05":58.88364509325174,"GB2-06":42.35186430476081,"GB2-07":10.153152420309118,"GB2-08":41.53866312325621},"medium":{"GB2-01":39.12420829247724,"GB2-02":48.6774415304111,"GB2-03":30.592136200568348,"GB2-04":48.09802931356302,"GB2-05":53.93079350037165,"GB2-06":78.66656044290741,"GB2-07":58.92957242041351,"GB2-08":24.618680258952594},"none":{"GB2-01":28.4427374833104,"GB2-02":40.85003085812979,"GB2-03":40.328072467328155,"GB2-04":43.215283152023005,"GB2-05":35.568242515927885,"GB2-06":46.35567191297051,"GB2-07":47.68666662668884,"GB2-08":47.20230562291302}},"program_outcomes":{"all":{"counted_attempts":48,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":22,"worked_first_time":26,"working":48},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"medium":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":10,"worked_first_time":6,"working":16},"none":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":11,"worked_first_time":13,"working":24}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T02:09:54Z","reasoning":{"highest":45.55294625254986,"medium":47.829677744958104,"none":41.20612632991145},"reasoning_agg":{"highest":{"max":61.91159206865199,"mean":45.55294625254986,"min":10.153152420309118},"medium":{"max":78.66656044290741,"mean":47.829677744958104,"min":24.618680258952594},"none":{"max":47.68666662668884,"mean":41.20612632991145,"min":28.442737483310395}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":6.623551415046656},"working_program_strength":{"all":44.86291677580647,"highest":45.55294625254986,"medium":47.829677744958104,"none":41.20612632991145}},{"canonical_public_row_identity":"publication-row.v1:overall:reflection-beam-1-0-501b-a23b:1c1eb87c5ea986b7","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":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.227669},"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":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595}},"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":0.01932975,"mean":0.010711218750000001,"median":0.008422124999999999,"min":0.00683925,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.08568975000000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.013563249999999999,"mean":0.0084324375,"median":0.007856624999999999,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.0674595},"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":0.04917425,"mean":0.028458624999999998,"median":0.0242415,"min":0.016261,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.22766899999999998}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.04917425,"mean":0.015867427083333333,"median":0.01165575,"min":0.0040545,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":36},"recorded_attempt_count":36,"run_count":24,"total":0.38081824999999997},"codegen_latency_ms":{"attempt_count":36,"max_ms":225177,"mean_ms":82986.79166666667,"min_ms":14518,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":225177,"mean_ms":159627.75,"min_ms":89322,"run_count":8},"medium":{"attempt_count":11,"max_ms":118131,"mean_ms":55222.125,"min_ms":14518,"run_count":8},"none":{"attempt_count":14,"max_ms":72565,"mean_ms":34110.5,"min_ms":18316,"run_count":8}},"codegen_output_tokens":{"attempt_count":36,"output_max":44106,"output_mean":12952.291666666666,"output_min":2213,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":44106,"output_mean":25586.0,"output_min":14383,"run_count":8},"medium":{"attempt_count":11,"output_max":15405,"output_mean":8034.75,"output_min":4457,"run_count":8},"none":{"attempt_count":14,"output_max":8725,"output_mean":5236.125,"output_min":2213,"run_count":8}},"display_name":"Beam 1.0 501B A23B","economics":{"all":44.732946639834516,"highest":55.59820633762745,"medium":37.73256124477107,"none":40.86807233710503},"first_seen_at":null,"game_gaps":{"medium":{"GB2-01":"failed"},"none":{"GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":36,"effective_max_output_tokens":[131072],"finish_reason_observations":36,"finish_reasons":["stop"],"indexed_attempts":36,"output_token_observations":36,"provider_post_attempt_observations":36,"provider_post_attempts":36,"reasoning_token_observations":36,"reconciliation_get_attempt_observations":36,"requested_max_output_token_observations":36,"requested_max_output_tokens":[131072],"total_output_tokens":310855,"total_reasoning_output_tokens":208237,"total_visible_output_tokens":102618,"visible_token_observations":36},"generation_policy":{"generation_policy":"quality_generation_policy","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":"other","provider_model":"reflection/beam-1.0-501b-a23b","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":["GB2-01"],"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},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"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":{"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":4,"repaired_rate":0.5},"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,"failed_attempts":1,"playable":33.95406253793937,"score":22.63604169195958},"GB2-02":{"attempts":3,"playable":43.19022953853021,"score":43.19022953853021},"GB2-03":{"attempts":3,"playable":53.963806699307575,"score":53.963806699307575},"GB2-04":{"attempts":3,"playable":46.98986659696872,"score":46.98986659696872},"GB2-05":{"attempts":3,"playable":52.050920470459744,"score":52.050920470459744},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":65.1890461382992,"score":43.45936409219947},"GB2-07":{"attempts":3,"playable":26.914500759477136,"score":26.914500759477136},"GB2-08":{"attempts":3,"playable":68.6588432697737,"score":68.6588432697737}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":24.91360999309,"score":24.91360999309},"GB2-02":{"attempts":1,"playable":50.16189544042474,"score":50.16189544042474},"GB2-03":{"attempts":1,"playable":78.56762844837525,"score":78.56762844837525},"GB2-04":{"attempts":1,"playable":61.11286829372216,"score":61.11286829372216},"GB2-05":{"attempts":1,"playable":53.167511411143785,"score":53.167511411143785},"GB2-06":{"attempts":1,"playable":74.72288482555444,"score":74.72288482555444},"GB2-07":{"attempts":1,"playable":39.20326986217805,"score":39.20326986217805},"GB2-08":{"attempts":1,"playable":62.9359824265312,"score":62.9359824265312}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":33.87287483548217,"score":33.87287483548217},"GB2-03":{"attempts":1,"playable":39.41619859025332,"score":39.41619859025332},"GB2-04":{"attempts":1,"playable":40.08188224812344,"score":40.08188224812344},"GB2-05":{"attempts":1,"playable":41.06900138198107,"score":41.06900138198107},"GB2-06":{"attempts":1,"playable":55.65520745104395,"score":55.65520745104395},"GB2-07":{"attempts":1,"playable":31.38707999594424,"score":31.38707999594424},"GB2-08":{"attempts":1,"playable":60.37824545534032,"score":60.37824545534032}},"none":{"GB2-01":{"attempts":1,"playable":42.994515082788745,"score":42.994515082788745},"GB2-02":{"attempts":1,"playable":45.535918339683725,"score":45.535918339683725},"GB2-03":{"attempts":1,"playable":43.90759305929414,"score":43.90759305929414},"GB2-04":{"attempts":1,"playable":39.77484924906058,"score":39.77484924906058},"GB2-05":{"attempts":1,"playable":61.91624861825438,"score":61.91624861825438},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":10.153152420309118,"score":10.153152420309118},"GB2-08":{"attempts":1,"playable":82.66230192744956,"score":82.66230192744956}}},"id":"reflection/beam-1.0-501b-a23b","is_recent_addition":false,"last_measured_at":"2026-10-27T23:46:14Z","match_totals_all":{"draws":2497,"losses":4769,"wins":3986},"match_totals_tracks":{"highest":{"draws":725,"losses":1555,"wins":1810},"medium":{"draws":779,"losses":1733,"wins":1062},"none":{"draws":993,"losses":1481,"wins":1114}},"model_slug":"reflection-beam-1-0-501b-a23b","official_rank_by_reasoning":{"highest":40,"medium":59,"none":43},"overall":{"max":82.66230192744956,"mean":44.732946639834516,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":24.91360999309,"GB2-02":50.16189544042474,"GB2-03":78.56762844837525,"GB2-04":61.11286829372216,"GB2-05":53.167511411143785,"GB2-06":74.72288482555444,"GB2-07":39.20326986217805,"GB2-08":62.9359824265312},"per_game_all":{"GB2-02":43.19022953853021,"GB2-03":53.963806699307575,"GB2-04":46.98986659696872,"GB2-05":52.050920470459744,"GB2-07":26.914500759477136,"GB2-08":68.6588432697737},"per_game_match_totals_all":{"GB2-01":{"draws":344,"losses":528,"wins":160},"GB2-02":{"draws":963,"losses":360,"wins":117},"GB2-03":{"draws":325,"losses":572,"wins":591},"GB2-04":{"draws":826,"losses":404,"wins":264},"GB2-05":{"draws":0,"losses":788,"wins":802},"GB2-06":{"draws":39,"losses":364,"wins":601},"GB2-07":{"draws":0,"losses":1197,"wins":393},"GB2-08":{"draws":0,"losses":556,"wins":1058}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":328,"wins":53},"GB2-02":{"draws":325,"losses":85,"wins":70},"GB2-03":{"draws":38,"losses":101,"wins":357},"GB2-04":{"draws":199,"losses":103,"wins":196},"GB2-05":{"draws":0,"losses":257,"wins":273},"GB2-06":{"draws":28,"losses":126,"wins":348},"GB2-07":{"draws":0,"losses":336,"wins":194},"GB2-08":{"draws":0,"losses":219,"wins":319}},"medium":{"GB2-02":{"draws":281,"losses":184,"wins":15},"GB2-03":{"draws":178,"losses":229,"wins":89},"GB2-04":{"draws":309,"losses":152,"wins":37},"GB2-05":{"draws":0,"losses":320,"wins":210},"GB2-06":{"draws":11,"losses":238,"wins":253},"GB2-07":{"draws":0,"losses":377,"wins":153},"GB2-08":{"draws":0,"losses":233,"wins":305}},"none":{"GB2-01":{"draws":209,"losses":200,"wins":107},"GB2-02":{"draws":357,"losses":91,"wins":32},"GB2-03":{"draws":109,"losses":242,"wins":145},"GB2-04":{"draws":318,"losses":149,"wins":31},"GB2-05":{"draws":0,"losses":211,"wins":319},"GB2-07":{"draws":0,"losses":484,"wins":46},"GB2-08":{"draws":0,"losses":104,"wins":434}}},"per_game_raw_elo_all":{"GB2-02":1418.6327894249062,"GB2-03":1487.1638923795824,"GB2-04":1452.279280728649,"GB2-05":1464.3034661045415,"GB2-07":1120.4247946654596,"GB2-08":1689.3290434331157},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1214.2313756116114,"GB2-02":1473.1979831137442,"GB2-03":1745.447333380417,"GB2-04":1563.599298324822,"GB2-05":1476.7502978796356,"GB2-06":1844.5702748517965,"GB2-07":1312.6770979199257,"GB2-08":1569.037466115339},"medium":{"GB2-02":1345.1967059564006,"GB2-03":1338.4780318298508,"GB2-04":1397.828712008195,"GB2-05":1325.1916627373264,"GB2-06":1507.352604304492,"GB2-07":1211.3841289010559,"GB2-08":1528.7738326216377},"none":{"GB2-01":1402.2754511651833,"GB2-02":1437.5036792045744,"GB2-03":1377.5663119284786,"GB2-04":1395.4098318529295,"GB2-05":1590.968437696663,"GB2-07":837.2131571753969,"GB2-08":1970.1758315623706}},"per_game_tracks":{"highest":{"GB2-01":24.91360999309,"GB2-02":50.16189544042474,"GB2-03":78.56762844837525,"GB2-04":61.11286829372216,"GB2-05":53.167511411143785,"GB2-06":74.72288482555444,"GB2-07":39.20326986217805,"GB2-08":62.9359824265312},"medium":{"GB2-02":33.87287483548217,"GB2-03":39.41619859025332,"GB2-04":40.08188224812344,"GB2-05":41.06900138198107,"GB2-06":55.65520745104395,"GB2-07":31.38707999594424,"GB2-08":60.37824545534032},"none":{"GB2-01":42.994515082788745,"GB2-02":45.535918339683725,"GB2-03":43.90759305929414,"GB2-04":39.77484924906058,"GB2-05":61.91624861825438,"GB2-07":10.153152420309118,"GB2-08":82.66230192744956}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":9,"worked_first_time":13,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":4,"worked_first_time":3,"working":7}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-2,"rank_movement_baseline_at":"2026-10-24T18:07:57Z","reasoning":{"highest":55.59820633762745,"medium":37.73256124477107,"none":40.86807233710503},"reasoning_agg":{"highest":{"max":78.56762844837525,"mean":55.59820633762745,"min":24.91360999309},"medium":{"max":60.37824545534032,"mean":37.73256124477107,"min":0.0},"none":{"max":82.66230192744956,"mean":40.86807233710503,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":17.865645092856383},"working_program_strength":{"all":48.475833953257194,"highest":55.59820633762745,"medium":43.12292713688122,"none":46.7063683852629}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:84c92d6f9c4c6c41","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":1.17256164828},"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":0.9884523218399999},"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":1.1725616482799999}},"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":2.3773764379600006},"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":43.853621646468035,"highest":55.96702381641266,"medium":47.11229398606076,"none":28.481547136930686},"first_seen_at":null,"game_gaps":{"none":{"GB2-02":"failed","GB2-05":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":43.566241222229785,"score":43.566241222229785},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.8415221220411,"score":28.5610147480274},"GB2-03":{"attempts":3,"playable":47.7938554249748,"score":47.7938554249748},"GB2-04":{"attempts":3,"playable":40.309215445350446,"score":40.309215445350446},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.67408552901576,"score":39.782723686010506},"GB2-06":{"attempts":3,"playable":55.83731171973998,"score":55.83731171973998},"GB2-07":{"attempts":3,"playable":58.92301016242228,"score":58.92301016242228},"GB2-08":{"attempts":3,"playable":36.05560076298911,"score":36.05560076298911}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":43.58532995518017,"score":43.58532995518017},"GB2-02":{"attempts":1,"playable":45.00868677173283,"score":45.00868677173283},"GB2-03":{"attempts":1,"playable":64.36585113532635,"score":64.36585113532635},"GB2-04":{"attempts":1,"playable":43.555325214966615,"score":43.555325214966615},"GB2-05":{"attempts":1,"playable":74.81270014849274,"score":74.81270014849274},"GB2-06":{"attempts":1,"playable":66.15673996249593,"score":66.15673996249593},"GB2-07":{"attempts":1,"playable":79.27476718220218,"score":79.27476718220218},"GB2-08":{"attempts":1,"playable":30.97679016090451,"score":30.97679016090451}},"medium":{"GB2-01":{"attempts":1,"playable":51.53118177573665,"score":51.53118177573665},"GB2-02":{"attempts":1,"playable":40.67435747234936,"score":40.67435747234936},"GB2-03":{"attempts":1,"playable":42.763608030337295,"score":42.763608030337295},"GB2-04":{"attempts":1,"playable":33.205276451308166,"score":33.205276451308166},"GB2-05":{"attempts":1,"playable":44.53547090953879,"score":44.53547090953879},"GB2-06":{"attempts":1,"playable":39.62182001331107,"score":39.62182001331107},"GB2-07":{"attempts":1,"playable":74.08387133123723,"score":74.08387133123723},"GB2-08":{"attempts":1,"playable":50.48276590466756,"score":50.48276590466756}},"none":{"GB2-01":{"attempts":1,"playable":35.58221193577253,"score":35.58221193577253},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.25210710926078,"score":36.25210710926078},"GB2-04":{"attempts":1,"playable":44.16704466977656,"score":44.16704466977656},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":61.73337518341293,"score":61.73337518341293},"GB2-07":{"attempts":1,"playable":23.41039197382741,"score":23.41039197382741},"GB2-08":{"attempts":1,"playable":26.707246223395252,"score":26.707246223395252}}},"id":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-10-31T16:40:28Z","match_totals_all":{"draws":2483,"losses":4892,"wins":3885},"match_totals_tracks":{"highest":{"draws":774,"losses":1498,"wins":1818},"medium":{"draws":919,"losses":1792,"wins":1379},"none":{"draws":790,"losses":1602,"wins":688}},"model_slug":"deepseek-deepseek-v4-pro-0813","official_rank_by_reasoning":{"highest":39,"medium":46,"none":68},"overall":{"max":79.27476718220218,"mean":43.853621646468035,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":46,"overall_ranking_status":"ranked","per_game":{"GB2-01":43.58532995518017,"GB2-02":45.00868677173283,"GB2-03":64.36585113532635,"GB2-04":43.555325214966615,"GB2-05":74.81270014849274,"GB2-06":66.15673996249593,"GB2-07":79.27476718220218,"GB2-08":30.97679016090451},"per_game_all":{"GB2-01":43.566241222229785,"GB2-03":47.7938554249748,"GB2-04":40.309215445350446,"GB2-06":55.83731171973998,"GB2-07":58.92301016242228,"GB2-08":36.05560076298911},"per_game_match_totals_all":{"GB2-01":{"draws":403,"losses":703,"wins":442},"GB2-02":{"draws":713,"losses":208,"wins":39},"GB2-03":{"draws":284,"losses":688,"wins":516},"GB2-04":{"draws":792,"losses":520,"wins":182},"GB2-05":{"draws":0,"losses":444,"wins":616},"GB2-06":{"draws":17,"losses":715,"wins":774},"GB2-07":{"draws":0,"losses":674,"wins":916},"GB2-08":{"draws":274,"losses":940,"wins":400}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":294,"wins":207},"GB2-02":{"draws":372,"losses":86,"wins":22},"GB2-03":{"draws":26,"losses":182,"wins":288},"GB2-04":{"draws":245,"losses":167,"wins":86},"GB2-05":{"draws":0,"losses":142,"wins":388},"GB2-06":{"draws":8,"losses":183,"wins":311},"GB2-07":{"draws":0,"losses":113,"wins":417},"GB2-08":{"draws":108,"losses":331,"wins":99}},"medium":{"GB2-01":{"draws":286,"losses":118,"wins":112},"GB2-02":{"draws":341,"losses":122,"wins":17},"GB2-03":{"draws":40,"losses":282,"wins":174},"GB2-04":{"draws":184,"losses":248,"wins":66},"GB2-05":{"draws":0,"losses":302,"wins":228},"GB2-06":{"draws":7,"losses":322,"wins":173},"GB2-07":{"draws":0,"losses":143,"wins":387},"GB2-08":{"draws":61,"losses":255,"wins":222}},"none":{"GB2-01":{"draws":102,"losses":291,"wins":123},"GB2-03":{"draws":218,"losses":224,"wins":54},"GB2-04":{"draws":363,"losses":105,"wins":30},"GB2-06":{"draws":2,"losses":210,"wins":290},"GB2-07":{"draws":0,"losses":418,"wins":112},"GB2-08":{"draws":105,"losses":354,"wins":79}}},"per_game_raw_elo_all":{"GB2-01":1407.076869802994,"GB2-03":1414.788724688581,"GB2-04":1398.930321982794,"GB2-06":1517.4323118155553,"GB2-07":1586.2729558170874,"GB2-08":1227.739696484183},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1407.9364676788973,"GB2-02":1433.4372473501933,"GB2-03":1566.202256514467,"GB2-04":1424.9404875183757,"GB2-05":1800.0633202931351,"GB2-06":1685.4291285276659,"GB2-07":1878.369336440685,"GB2-08":1169.662164758129},"medium":{"GB2-01":1483.5964086275437,"GB2-02":1399.8007400236527,"GB2-03":1367.6422411761382,"GB2-04":1342.1705014646939,"GB2-05":1369.1555005582923,"GB2-06":1258.6557781753804,"GB2-07":1783.2916722497234,"GB2-08":1392.5835487834167},"none":{"GB2-01":1329.6977331025412,"GB2-03":1310.5216763751378,"GB2-04":1429.6799769653126,"GB2-06":1608.21202874362,"GB2-07":1097.1578587608537,"GB2-08":1120.9733759110031}},"per_game_tracks":{"highest":{"GB2-01":43.58532995518017,"GB2-02":45.00868677173283,"GB2-03":64.36585113532635,"GB2-04":43.555325214966615,"GB2-05":74.81270014849274,"GB2-06":66.15673996249593,"GB2-07":79.27476718220218,"GB2-08":30.97679016090451},"medium":{"GB2-01":51.53118177573665,"GB2-02":40.67435747234936,"GB2-03":42.763608030337295,"GB2-04":33.205276451308166,"GB2-05":44.53547090953879,"GB2-06":39.62182001331107,"GB2-07":74.08387133123723,"GB2-08":50.48276590466756},"none":{"GB2-01":35.58221193577253,"GB2-03":36.25210710926078,"GB2-04":44.16704466977656,"GB2-06":61.73337518341293,"GB2-07":23.41039197382741,"GB2-08":26.707246223395252}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":4,"worked_first_time":18,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T00:22:44Z","reasoning":{"highest":55.96702381641266,"medium":47.11229398606076,"none":28.481547136930686},"reasoning_agg":{"highest":{"max":79.27476718220218,"mean":55.96702381641266,"min":30.97679016090451},"medium":{"max":74.08387133123723,"mean":47.11229398606076,"min":33.205276451308166},"none":{"max":61.73337518341293,"mean":28.481547136930686,"min":0.0}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":27.485476679481977},"working_program_strength":{"all":47.01823799501589,"highest":55.96702381641266,"medium":47.11229398606076,"none":37.97539618257425}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:201663eb3d6fa183","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":0.9135725942490001},"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":0.20237245442100002}},"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":0.202372454421},"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":0.913572594249}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640002},"codegen_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":43.513183636014105,"highest":48.666370259348135,"medium":53.65578416006933,"none":28.217396488624857},"first_seen_at":null,"game_gaps":{"none":{"GB2-02":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":39.654697270377184,"score":39.654697270377184},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.46907880944907,"score":28.31271920629938},"GB2-03":{"attempts":3,"playable":39.87812148467649,"score":39.87812148467649},"GB2-04":{"attempts":3,"playable":45.1175696683076,"score":45.1175696683076},"GB2-05":{"attempts":3,"playable":42.92351732701986,"score":42.92351732701986},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":63.655757627191406,"score":42.43717175146094},"GB2-07":{"attempts":3,"playable":67.0006522709049,"score":67.0006522709049},"GB2-08":{"attempts":3,"playable":42.7810201090665,"score":42.7810201090665}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.61682850303232,"score":27.61682850303232},"GB2-02":{"attempts":1,"playable":45.535918339683725,"score":45.535918339683725},"GB2-03":{"attempts":1,"playable":47.2157771060164,"score":47.2157771060164},"GB2-04":{"attempts":1,"playable":45.99985326266107,"score":45.99985326266107},"GB2-05":{"attempts":1,"playable":45.112618737377,"score":45.112618737377},"GB2-06":{"attempts":1,"playable":78.35309349857275,"score":78.35309349857275},"GB2-07":{"attempts":1,"playable":74.7785410427387,"score":74.7785410427387},"GB2-08":{"attempts":1,"playable":24.718331584703076,"score":24.718331584703076}},"medium":{"GB2-01":{"attempts":1,"playable":62.23199982825813,"score":62.23199982825813},"GB2-02":{"attempts":1,"playable":39.40223927921443,"score":39.40223927921443},"GB2-03":{"attempts":1,"playable":30.28042113507212,"score":30.28042113507212},"GB2-04":{"attempts":1,"playable":44.2689604016478,"score":44.2689604016478},"GB2-05":{"attempts":1,"playable":49.14653902255498,"score":49.14653902255498},"GB2-06":{"attempts":1,"playable":48.95842175581007,"score":48.95842175581007},"GB2-07":{"attempts":1,"playable":71.47099297422929,"score":71.47099297422929},"GB2-08":{"attempts":1,"playable":83.4866988837679,"score":83.4866988837679}},"none":{"GB2-01":{"attempts":1,"playable":29.115263479841108,"score":29.115263479841108},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":42.138166212940966,"score":42.138166212940966},"GB2-04":{"attempts":1,"playable":45.083895340613935,"score":45.083895340613935},"GB2-05":{"attempts":1,"playable":34.5113942211276,"score":34.5113942211276},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":54.75242279574671,"score":54.75242279574671},"GB2-08":{"attempts":1,"playable":20.138029858728544,"score":20.138029858728544}}},"id":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-10-31T16:38:21Z","match_totals_all":{"draws":2574,"losses":4869,"wins":3845},"match_totals_tracks":{"highest":{"draws":998,"losses":1685,"wins":1407},"medium":{"draws":810,"losses":1560,"wins":1720},"none":{"draws":766,"losses":1624,"wins":718}},"model_slug":"deepseek-deepseek-v4-pro","official_rank_by_reasoning":{"highest":45,"medium":31,"none":69},"overall":{"max":83.4866988837679,"mean":43.513183636014105,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":47,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.61682850303232,"GB2-02":45.535918339683725,"GB2-03":47.2157771060164,"GB2-04":45.99985326266107,"GB2-05":45.112618737377,"GB2-06":78.35309349857275,"GB2-07":74.7785410427387,"GB2-08":24.718331584703076},"per_game_all":{"GB2-01":39.654697270377184,"GB2-03":39.87812148467649,"GB2-04":45.1175696683076,"GB2-05":42.92351732701986,"GB2-07":67.0006522709049,"GB2-08":42.7810201090665},"per_game_match_totals_all":{"GB2-01":{"draws":213,"losses":856,"wins":479},"GB2-02":{"draws":702,"losses":217,"wins":41},"GB2-03":{"draws":447,"losses":723,"wins":318},"GB2-04":{"draws":941,"losses":375,"wins":178},"GB2-05":{"draws":0,"losses":931,"wins":659},"GB2-06":{"draws":17,"losses":390,"wins":597},"GB2-07":{"draws":0,"losses":549,"wins":1041},"GB2-08":{"draws":254,"losses":828,"wins":532}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":42,"losses":361,"wins":113},"GB2-02":{"draws":355,"losses":92,"wins":33},"GB2-03":{"draws":177,"losses":192,"wins":127},"GB2-04":{"draws":295,"losses":130,"wins":73},"GB2-05":{"draws":0,"losses":299,"wins":231},"GB2-06":{"draws":12,"losses":114,"wins":376},"GB2-07":{"draws":0,"losses":139,"wins":391},"GB2-08":{"draws":117,"losses":358,"wins":63}},"medium":{"GB2-01":{"draws":38,"losses":187,"wins":291},"GB2-02":{"draws":347,"losses":125,"wins":8},"GB2-03":{"draws":108,"losses":307,"wins":81},"GB2-04":{"draws":312,"losses":130,"wins":56},"GB2-05":{"draws":0,"losses":278,"wins":252},"GB2-06":{"draws":5,"losses":276,"wins":221},"GB2-07":{"draws":0,"losses":158,"wins":372},"GB2-08":{"draws":0,"losses":99,"wins":439}},"none":{"GB2-01":{"draws":133,"losses":308,"wins":75},"GB2-03":{"draws":162,"losses":224,"wins":110},"GB2-04":{"draws":334,"losses":115,"wins":49},"GB2-05":{"draws":0,"losses":354,"wins":176},"GB2-07":{"draws":0,"losses":252,"wins":278},"GB2-08":{"draws":137,"losses":371,"wins":30}}},"per_game_raw_elo_all":{"GB2-01":1365.2821194361152,"GB2-03":1341.3852574929447,"GB2-04":1437.0291387423738,"GB2-05":1347.024075982683,"GB2-07":1681.1162229663987,"GB2-08":1376.0473787436051},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1245.4274738101321,"GB2-02":1437.5036792045744,"GB2-03":1406.2913491295394,"GB2-04":1443.8467916489367,"GB2-05":1376.3900671420768,"GB2-06":1915.8829475659388,"GB2-07":1795.1098777098696,"GB2-08":1097.4478533115548},"medium":{"GB2-01":1588.378376420268,"GB2-02":1389.8077846837,"GB2-03":1255.653130623046,"GB2-04":1430.4689204585834,"GB2-05":1426.6174784059447,"GB2-06":1401.4888125235404,"GB2-07":1740.696635355058,"GB2-08":1990.8293744484677},"none":{"GB2-01":1262.0405080779456,"GB2-03":1362.2112927262483,"GB2-04":1436.7717041196013,"GB2-05":1238.0646824000276,"GB2-07":1507.542155834269,"GB2-08":1039.8649084707927}},"per_game_tracks":{"highest":{"GB2-01":27.61682850303232,"GB2-02":45.535918339683725,"GB2-03":47.2157771060164,"GB2-04":45.99985326266107,"GB2-05":45.112618737377,"GB2-06":78.35309349857275,"GB2-07":74.7785410427387,"GB2-08":24.718331584703076},"medium":{"GB2-01":62.23199982825813,"GB2-02":39.40223927921443,"GB2-03":30.28042113507212,"GB2-04":44.2689604016478,"GB2-05":49.14653902255498,"GB2-06":48.95842175581007,"GB2-07":71.47099297422929,"GB2-08":83.4866988837679},"none":{"GB2-01":29.115263479841108,"GB2-03":42.138166212940966,"GB2-04":45.083895340613935,"GB2-05":34.5113942211276,"GB2-07":54.75242279574671,"GB2-08":20.138029858728544}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":9,"worked_first_time":13,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":4,"worked_first_time":4,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:40:16Z","reasoning":{"highest":48.666370259348135,"medium":53.65578416006933,"none":28.217396488624857},"reasoning_agg":{"highest":{"max":78.35309349857275,"mean":48.666370259348135,"min":24.718331584703076},"medium":{"max":83.4866988837679,"mean":53.65578416006933,"min":30.28042113507212},"none":{"max":54.75242279574671,"mean":28.217396488624857,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":25.438387671444474},"working_program_strength":{"all":46.64844991252798,"highest":48.666370259348135,"medium":53.65578416006933,"none":37.623195318166474}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:01830fcec5780cc2","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":0.779305}},"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":0.7793049999999999},"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":4.455918750000001},"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":43.030839236643864,"highest":48.89148896563599,"medium":38.76415214513826,"none":41.43687659915735},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed"},"none":{"GB2-04":"too_slow","GB2-06":"too_slow"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":43.84870271327113,"score":43.84870271327113},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.46088821717183,"score":26.973925478114552},"GB2-03":{"attempts":3,"playable":28.434294553719443,"score":28.434294553719443},"GB2-04":{"attempts":2,"playable":41.35903677067774,"score":41.35903677067774},"GB2-05":{"attempts":3,"playable":61.75155724547941,"score":61.75155724547941},"GB2-06":{"attempts":2,"playable":59.633448644842744,"score":59.633448644842744},"GB2-07":{"attempts":3,"playable":52.099603979349645,"score":52.099603979349645},"GB2-08":{"attempts":3,"playable":36.18572191343154,"score":36.18572191343154}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":39.73936899061798,"score":39.73936899061798},"GB2-02":{"attempts":1,"playable":42.26230666890257,"score":42.26230666890257},"GB2-03":{"attempts":1,"playable":37.30955847897335,"score":37.30955847897335},"GB2-04":{"attempts":1,"playable":39.77484924906058,"score":39.77484924906058},"GB2-05":{"attempts":1,"playable":75.91363551983989,"score":75.91363551983989},"GB2-06":{"attempts":1,"playable":69.63034362209171,"score":69.63034362209171},"GB2-07":{"attempts":1,"playable":52.750997379978756,"score":52.750997379978756},"GB2-08":{"attempts":1,"playable":33.75085181562314,"score":33.75085181562314}},"medium":{"GB2-01":{"attempts":1,"playable":21.196096072488395,"score":21.196096072488395},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.995170094660647,"score":31.995170094660647},"GB2-04":{"attempts":1,"playable":42.9432242922949,"score":42.9432242922949},"GB2-05":{"attempts":1,"playable":61.537849515819474,"score":61.537849515819474},"GB2-06":{"attempts":1,"playable":49.636553667593766,"score":49.636553667593766},"GB2-07":{"attempts":1,"playable":62.83704619097238,"score":62.83704619097238},"GB2-08":{"attempts":1,"playable":39.967277327276534,"score":39.967277327276534}},"none":{"GB2-01":{"attempts":1,"playable":70.61064307670702,"score":70.61064307670702},"GB2-02":{"attempts":1,"playable":38.65946976544109,"score":38.65946976544109},"GB2-03":{"attempts":1,"playable":15.998155087524344,"score":15.998155087524344},"GB2-05":{"attempts":1,"playable":47.803186700778895,"score":47.803186700778895},"GB2-07":{"attempts":1,"playable":40.71076836709781,"score":40.71076836709781},"GB2-08":{"attempts":1,"playable":34.83903659739497,"score":34.83903659739497}}},"id":"gpt-5","is_recent_addition":false,"last_measured_at":"2026-10-31T16:41:54Z","match_totals_all":{"draws":2331,"losses":4978,"wins":3481},"match_totals_tracks":{"highest":{"draws":1086,"losses":1637,"wins":1367},"medium":{"draws":646,"losses":1771,"wins":1193},"none":{"draws":599,"losses":1570,"wins":921}},"model_slug":"gpt-5","official_rank_by_reasoning":{"highest":44,"medium":57,"none":39},"overall":{"max":75.91363551983989,"mean":43.030839236643864,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game":{"GB2-01":39.73936899061798,"GB2-02":42.26230666890257,"GB2-03":37.30955847897335,"GB2-04":39.77484924906058,"GB2-05":75.91363551983989,"GB2-06":69.63034362209171,"GB2-07":52.750997379978756,"GB2-08":33.75085181562314},"per_game_all":{"GB2-01":43.84870271327113,"GB2-03":28.434294553719443,"GB2-05":61.75155724547941,"GB2-07":52.099603979349645,"GB2-08":36.18572191343154},"per_game_match_totals_all":{"GB2-01":{"draws":207,"losses":794,"wins":547},"GB2-02":{"draws":706,"losses":234,"wins":20},"GB2-03":{"draws":419,"losses":898,"wins":171},"GB2-04":{"draws":595,"losses":303,"wins":98},"GB2-05":{"draws":0,"losses":634,"wins":956},"GB2-06":{"draws":18,"losses":434,"wins":552},"GB2-07":{"draws":0,"losses":798,"wins":792},"GB2-08":{"draws":386,"losses":883,"wins":345}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":86,"losses":278,"wins":152},"GB2-02":{"draws":360,"losses":105,"wins":15},"GB2-03":{"draws":154,"losses":251,"wins":91},"GB2-04":{"draws":330,"losses":143,"wins":25},"GB2-05":{"draws":0,"losses":136,"wins":394},"GB2-06":{"draws":4,"losses":166,"wins":332},"GB2-07":{"draws":0,"losses":263,"wins":267},"GB2-08":{"draws":152,"losses":295,"wins":91}},"medium":{"GB2-01":{"draws":64,"losses":382,"wins":70},"GB2-03":{"draws":192,"losses":257,"wins":47},"GB2-04":{"draws":265,"losses":160,"wins":73},"GB2-05":{"draws":0,"losses":213,"wins":317},"GB2-06":{"draws":14,"losses":268,"wins":220},"GB2-07":{"draws":0,"losses":207,"wins":323},"GB2-08":{"draws":111,"losses":284,"wins":143}},"none":{"GB2-01":{"draws":57,"losses":134,"wins":325},"GB2-02":{"draws":346,"losses":129,"wins":5},"GB2-03":{"draws":73,"losses":390,"wins":33},"GB2-05":{"draws":0,"losses":285,"wins":245},"GB2-07":{"draws":0,"losses":328,"wins":202},"GB2-08":{"draws":123,"losses":304,"wins":111}}},"per_game_raw_elo_all":{"GB2-01":1405.7528797440116,"GB2-03":1229.0126472435331,"GB2-05":1606.0274056096775,"GB2-07":1476.0112694616955,"GB2-08":1227.4925769065192},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1370.8261574533628,"GB2-02":1412.183013994855,"GB2-03":1319.9245224373358,"GB2-04":1395.4098318529295,"GB2-05":1822.3902490930673,"GB2-06":1748.473755241612,"GB2-07":1482.0687617361943,"GB2-08":1200.5271691821474},"medium":{"GB2-01":1168.0152859503405,"GB2-03":1271.7881639573811,"GB2-04":1420.1899259876172,"GB2-05":1585.7624068820985,"GB2-06":1412.029799626772,"GB2-07":1614.3402644200523,"GB2-08":1269.3894299549863},"none":{"GB2-01":1678.4171958283316,"GB2-02":1383.9361117360347,"GB2-03":1095.3252553358823,"GB2-05":1409.9295608538664,"GB2-07":1331.6247822288399,"GB2-08":1212.561131582424}},"per_game_tracks":{"highest":{"GB2-01":39.73936899061798,"GB2-02":42.26230666890257,"GB2-03":37.30955847897335,"GB2-04":39.77484924906058,"GB2-05":75.91363551983989,"GB2-06":69.63034362209171,"GB2-07":52.750997379978756,"GB2-08":33.75085181562314},"medium":{"GB2-01":21.196096072488395,"GB2-03":31.995170094660647,"GB2-04":42.9432242922949,"GB2-05":61.537849515819474,"GB2-06":49.636553667593766,"GB2-07":62.83704619097238,"GB2-08":39.967277327276534},"none":{"GB2-01":70.61064307670702,"GB2-02":38.65946976544109,"GB2-03":15.998155087524344,"GB2-05":47.803186700778895,"GB2-07":40.71076836709781,"GB2-08":34.83903659739497}},"program_outcomes":{"all":{"counted_attempts":22,"failed":1,"infra_excluded":0,"success_rate":0.9545454545454546,"too_slow":2,"worked_after_repair":5,"worked_first_time":16,"working":21},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7},"none":{"counted_attempts":6,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":2,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.89148896563599,"medium":38.76415214513826,"none":41.43687659915735},"reasoning_agg":{"highest":{"max":75.91363551983989,"mean":48.89148896563599,"min":33.75085181562314},"medium":{"max":62.83704619097238,"mean":38.76415214513826,"min":0.0},"none":{"max":70.61064307670702,"mean":41.43687659915735,"min":15.998155087524344}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":10.127336820497732},"working_program_strength":{"all":44.87675124355522,"highest":48.89148896563599,"medium":44.3018881658723,"none":41.43687659915735}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:61e59d89d21ca0b8","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":0.24666659999999999},"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":0.0367878}},"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":0.05054444999999999},"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":0.24666659999999996}},"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":0.33399884999999996},"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":41.841263585233236,"highest":56.16863150458305,"medium":43.95790491816642,"none":25.39725433295024},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":51.351233961445615,"score":51.351233961445615},"GB2-02":{"attempts":3,"playable":43.70624953629721,"score":43.70624953629721},"GB2-03":{"attempts":3,"playable":38.597776892219805,"score":38.597776892219805},"GB2-04":{"attempts":3,"playable":41.81069461909322,"score":41.81069461909322},"GB2-05":{"attempts":3,"playable":40.093700497413074,"score":40.093700497413074},"GB2-06":{"attempts":3,"playable":52.18520583990908,"score":52.18520583990908},"GB2-07":{"attempts":3,"playable":38.803231157933865,"score":38.803231157933865},"GB2-08":{"attempts":3,"playable":28.182016177554004,"score":28.182016177554004}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":81.40294929716667,"score":81.40294929716667},"GB2-02":{"attempts":1,"playable":45.2196158397717,"score":45.2196158397717},"GB2-03":{"attempts":1,"playable":41.616186518873356,"score":41.616186518873356},"GB2-04":{"attempts":1,"playable":38.750784944954475,"score":38.750784944954475},"GB2-05":{"attempts":1,"playable":51.254565677257055,"score":51.254565677257055},"GB2-06":{"attempts":1,"playable":84.06849553857809,"score":84.06849553857809},"GB2-07":{"attempts":1,"playable":72.69192288473282,"score":72.69192288473282},"GB2-08":{"attempts":1,"playable":34.344531335330196,"score":34.344531335330196}},"medium":{"GB2-01":{"attempts":1,"playable":46.534739691981706,"score":46.534739691981706},"GB2-02":{"attempts":1,"playable":43.31953725866707,"score":43.31953725866707},"GB2-03":{"attempts":1,"playable":44.2189893368531,"score":44.2189893368531},"GB2-04":{"attempts":1,"playable":47.93051396737071,"score":47.93051396737071},"GB2-05":{"attempts":1,"playable":44.53547090953879,"score":44.53547090953879},"GB2-06":{"attempts":1,"playable":54.7091671416833,"score":54.7091671416833},"GB2-07":{"attempts":1,"playable":28.8761579159805,"score":28.8761579159805},"GB2-08":{"attempts":1,"playable":41.53866312325621,"score":41.53866312325621}},"none":{"GB2-01":{"attempts":1,"playable":26.116012895188472,"score":26.116012895188472},"GB2-02":{"attempts":1,"playable":42.57959551045286,"score":42.57959551045286},"GB2-03":{"attempts":1,"playable":29.958154820932968,"score":29.958154820932968},"GB2-04":{"attempts":1,"playable":38.750784944954475,"score":38.750784944954475},"GB2-05":{"attempts":1,"playable":24.491064905443373,"score":24.491064905443373},"GB2-06":{"attempts":1,"playable":17.777954839465853,"score":17.777954839465853},"GB2-07":{"attempts":1,"playable":14.841612673088273,"score":14.841612673088273},"GB2-08":{"attempts":1,"playable":8.66285407407561,"score":8.66285407407561}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-10-31T17:01:37Z","match_totals_all":{"draws":3212,"losses":5806,"wins":3252},"match_totals_tracks":{"highest":{"draws":1045,"losses":1349,"wins":1696},"medium":{"draws":1093,"losses":1855,"wins":1142},"none":{"draws":1074,"losses":2602,"wins":414}},"model_slug":"gpt-5-6-luna","official_rank_by_reasoning":{"highest":38,"medium":49,"none":75},"overall":{"max":84.06849553857809,"mean":41.841263585233236,"min":8.66285407407561},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":81.40294929716667,"GB2-02":45.2196158397717,"GB2-03":41.616186518873356,"GB2-04":38.750784944954475,"GB2-05":51.254565677257055,"GB2-06":84.06849553857809,"GB2-07":72.69192288473282,"GB2-08":34.344531335330196},"per_game_all":{"GB2-01":51.351233961445615,"GB2-02":43.70624953629721,"GB2-03":38.597776892219805,"GB2-04":41.81069461909322,"GB2-05":40.093700497413074,"GB2-06":52.18520583990908,"GB2-07":38.803231157933865,"GB2-08":28.182016177554004},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":697,"wins":682},"GB2-02":{"draws":1125,"losses":272,"wins":43},"GB2-03":{"draws":582,"losses":674,"wins":232},"GB2-04":{"draws":952,"losses":418,"wins":124},"GB2-05":{"draws":0,"losses":975,"wins":615},"GB2-06":{"draws":61,"losses":733,"wins":712},"GB2-07":{"draws":0,"losses":1002,"wins":588},"GB2-08":{"draws":323,"losses":1035,"wins":256}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":105,"wins":410},"GB2-02":{"draws":356,"losses":93,"wins":31},"GB2-03":{"draws":211,"losses":202,"wins":83},"GB2-04":{"draws":296,"losses":165,"wins":37},"GB2-05":{"draws":0,"losses":267,"wins":263},"GB2-06":{"draws":33,"losses":72,"wins":397},"GB2-07":{"draws":0,"losses":151,"wins":379},"GB2-08":{"draws":148,"losses":294,"wins":96}},"medium":{"GB2-01":{"draws":67,"losses":253,"wins":196},"GB2-02":{"draws":382,"losses":89,"wins":9},"GB2-03":{"draws":156,"losses":217,"wins":123},"GB2-04":{"draws":346,"losses":95,"wins":57},"GB2-05":{"draws":0,"losses":302,"wins":228},"GB2-06":{"draws":17,"losses":240,"wins":245},"GB2-07":{"draws":0,"losses":390,"wins":140},"GB2-08":{"draws":125,"losses":269,"wins":144}},"none":{"GB2-01":{"draws":101,"losses":339,"wins":76},"GB2-02":{"draws":387,"losses":90,"wins":3},"GB2-03":{"draws":215,"losses":255,"wins":26},"GB2-04":{"draws":310,"losses":158,"wins":30},"GB2-05":{"draws":0,"losses":406,"wins":124},"GB2-06":{"draws":11,"losses":421,"wins":70},"GB2-07":{"draws":0,"losses":461,"wins":69},"GB2-08":{"draws":50,"losses":472,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1494.6237213183383,"GB2-02":1423.3651007616766,"GB2-03":1330.1729267122416,"GB2-04":1411.1218130762218,"GB2-05":1303.1684583513654,"GB2-06":1482.10421431357,"GB2-07":1294.5806656269958,"GB2-08":1112.6946206754762},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1819.48517519801,"GB2-02":1435.0644161463706,"GB2-03":1357.674110852893,"GB2-04":1387.3077138216152,"GB2-05":1452.83205566894,"GB2-06":2035.6673719643463,"GB2-07":1760.2614753592288,"GB2-08":1207.095230032408},"medium":{"GB2-01":1436.06530090485,"GB2-02":1420.3836444797973,"GB2-03":1380.266751887756,"GB2-04":1458.7500115854355,"GB2-05":1369.1555005582923,"GB2-06":1492.1184828843188,"GB2-07":1177.054352166737,"GB2-08":1287.0227509173365},"none":{"GB2-01":1228.3206878521548,"GB2-02":1414.6472416588617,"GB2-03":1252.5779173960755,"GB2-04":1387.3077138216152,"GB2-05":1087.5178188268642,"GB2-06":918.526788092045,"GB2-07":946.4261693550213,"GB2-08":843.965881076684}},"per_game_tracks":{"highest":{"GB2-01":81.40294929716667,"GB2-02":45.2196158397717,"GB2-03":41.616186518873356,"GB2-04":38.750784944954475,"GB2-05":51.254565677257055,"GB2-06":84.06849553857809,"GB2-07":72.69192288473282,"GB2-08":34.344531335330196},"medium":{"GB2-01":46.534739691981706,"GB2-02":43.31953725866707,"GB2-03":44.2189893368531,"GB2-04":47.93051396737071,"GB2-05":44.53547090953879,"GB2-06":54.7091671416833,"GB2-07":28.8761579159805,"GB2-08":41.53866312325621},"none":{"GB2-01":26.116012895188472,"GB2-02":42.57959551045286,"GB2-03":29.958154820932968,"GB2-04":38.750784944954475,"GB2-05":24.491064905443373,"GB2-06":17.777954839465853,"GB2-07":14.841612673088273,"GB2-08":8.66285407407561}},"program_outcomes":{"all":{"counted_attempts":24,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":23,"working":24},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:54:42Z","reasoning":{"highest":56.16863150458305,"medium":43.95790491816642,"none":25.39725433295024},"reasoning_agg":{"highest":{"max":84.06849553857809,"mean":56.16863150458305,"min":34.344531335330196},"medium":{"max":54.7091671416833,"mean":43.95790491816642,"min":28.8761579159805},"none":{"max":42.57959551045286,"mean":25.39725433295024,"min":8.66285407407561}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":30.771377171632807},"working_program_strength":{"all":41.841263585233236,"highest":56.16863150458305,"medium":43.95790491816642,"none":25.39725433295024}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3-1-flash:c73463359f716332","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":35},"recorded_attempt_count":35,"run_count":24,"total":0.0},"codegen_latency_ms":{"attempt_count":35,"max_ms":926386,"mean_ms":167464.70833333334,"min_ms":7440,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":12,"max_ms":926386,"mean_ms":393879.0,"min_ms":180915,"run_count":8},"medium":{"attempt_count":12,"max_ms":181663,"mean_ms":86858.125,"min_ms":40176,"run_count":8},"none":{"attempt_count":11,"max_ms":29718,"mean_ms":21657.0,"min_ms":7440,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":73160,"output_mean":16631.416666666668,"output_min":1375,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":12,"output_max":73160,"output_mean":36727.625,"output_min":23210,"run_count":8},"medium":{"attempt_count":12,"output_max":16723,"output_mean":9745.875,"output_min":4629,"run_count":8},"none":{"attempt_count":11,"output_max":6152,"output_mean":3420.75,"output_min":1375,"run_count":8}},"display_name":"Minimax M3.1 Flash","economics":{"all":38.07824890666645,"highest":39.99000085005289,"medium":42.68216338420152,"none":31.56258248574495},"economics_best_value":{"per_model":{"all":true,"highest":true}},"first_seen_at":null,"game_gaps":{"highest":{"GB2-08":"failed"},"medium":{"GB2-02":"failed"},"none":{"GB2-08":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":35,"effective_max_output_tokens":[524288],"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,"requested_max_output_token_observations":35,"requested_max_output_tokens":[524288],"total_output_tokens":399154,"total_reasoning_output_tokens":282019,"total_visible_output_tokens":117135,"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":524288,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"minimax","provider_model":"minimax/minimax-m3.1-flash","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":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":{"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},"baseline":{"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},"intensive":{"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}},"headline_games_all":{"GB2-01":{"attempts":3,"playable":37.98583312119988,"score":37.98583312119988},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.415659916398184,"score":27.610439944265455},"GB2-03":{"attempts":3,"playable":34.808134198490144,"score":34.808134198490144},"GB2-04":{"attempts":3,"playable":39.7063188491256,"score":39.7063188491256},"GB2-05":{"attempts":3,"playable":48.93371083764294,"score":48.93371083764294},"GB2-06":{"attempts":3,"playable":51.2025026504763,"score":51.2025026504763},"GB2-07":{"attempts":3,"playable":54.64879721434139,"score":54.64879721434139},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":29.190763313369704,"score":9.7302544377899}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":14.931048783826306,"score":14.931048783826306},"GB2-02":{"attempts":1,"playable":41.09805282953857,"score":41.09805282953857},"GB2-03":{"attempts":1,"playable":48.961115008185836,"score":48.961115008185836},"GB2-04":{"attempts":1,"playable":39.67248565709144,"score":39.67248565709144},"GB2-05":{"attempts":1,"playable":72.78312368067063,"score":72.78312368067063},"GB2-06":{"attempts":1,"playable":32.22701951372749,"score":32.22701951372749},"GB2-07":{"attempts":1,"playable":70.24716132738281,"score":70.24716132738281},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":68.1161334836176,"score":68.1161334836176},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":31.7811969323352,"score":31.7811969323352},"GB2-04":{"attempts":1,"playable":38.750784944954475,"score":38.750784944954475},"GB2-05":{"attempts":1,"playable":50.48844938435943,"score":50.48844938435943},"GB2-06":{"attempts":1,"playable":51.65898604074648,"score":51.65898604074648},"GB2-07":{"attempts":1,"playable":71.47099297422929,"score":71.47099297422929},"GB2-08":{"attempts":1,"playable":29.190763313369704,"score":29.190763313369704}},"none":{"GB2-01":{"attempts":1,"playable":30.910317096155747,"score":30.910317096155747},"GB2-02":{"attempts":1,"playable":41.733267003257794,"score":41.733267003257794},"GB2-03":{"attempts":1,"playable":23.68209065494941,"score":23.68209065494941},"GB2-04":{"attempts":1,"playable":40.69568594533089,"score":40.69568594533089},"GB2-05":{"attempts":1,"playable":23.52955944789878,"score":23.52955944789878},"GB2-06":{"attempts":1,"playable":69.72150239695492,"score":69.72150239695492},"GB2-07":{"attempts":1,"playable":22.22823734141206,"score":22.22823734141206},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"minimax/minimax-m3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-27T23:46:14Z","match_totals_all":{"draws":2213,"losses":5169,"wins":3332},"match_totals_tracks":{"highest":{"draws":790,"losses":1600,"wins":1162},"medium":{"draws":500,"losses":1680,"wins":1430},"none":{"draws":923,"losses":1889,"wins":740}},"model_slug":"minimax-minimax-m3-1-flash","official_rank_by_reasoning":{"highest":50,"medium":52,"none":58},"overall":{"max":72.78312368067063,"mean":38.07824890666645,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["unknown_capability_evidence"],"overall_official_rank":50,"overall_ranking_status":"partial","per_game":{"GB2-01":14.931048783826306,"GB2-02":41.09805282953857,"GB2-03":48.961115008185836,"GB2-04":39.67248565709144,"GB2-05":72.78312368067063,"GB2-06":32.22701951372749,"GB2-07":70.24716132738281},"per_game_all":{"GB2-01":37.98583312119988,"GB2-03":34.808134198490144,"GB2-04":39.7063188491256,"GB2-05":48.93371083764294,"GB2-06":51.2025026504763,"GB2-07":54.64879721434139},"per_game_match_totals_all":{"GB2-01":{"draws":136,"losses":918,"wins":494},"GB2-02":{"draws":726,"losses":215,"wins":19},"GB2-03":{"draws":387,"losses":824,"wins":277},"GB2-04":{"draws":946,"losses":452,"wins":96},"GB2-05":{"draws":0,"losses":835,"wins":755},"GB2-06":{"draws":18,"losses":784,"wins":704},"GB2-07":{"draws":0,"losses":747,"wins":843},"GB2-08":{"draws":0,"losses":394,"wins":144}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":26,"losses":432,"wins":58},"GB2-02":{"draws":349,"losses":116,"wins":15},"GB2-03":{"draws":94,"losses":225,"wins":177},"GB2-04":{"draws":315,"losses":151,"wins":32},"GB2-05":{"draws":0,"losses":153,"wins":377},"GB2-06":{"draws":6,"losses":358,"wins":138},"GB2-07":{"draws":0,"losses":165,"wins":365}},"medium":{"GB2-01":{"draws":81,"losses":135,"wins":300},"GB2-03":{"draws":112,"losses":298,"wins":86},"GB2-04":{"draws":296,"losses":165,"wins":37},"GB2-05":{"draws":0,"losses":271,"wins":259},"GB2-06":{"draws":11,"losses":259,"wins":232},"GB2-07":{"draws":0,"losses":158,"wins":372},"GB2-08":{"draws":0,"losses":394,"wins":144}},"none":{"GB2-01":{"draws":29,"losses":351,"wins":136},"GB2-02":{"draws":377,"losses":99,"wins":4},"GB2-03":{"draws":181,"losses":301,"wins":14},"GB2-04":{"draws":335,"losses":136,"wins":27},"GB2-05":{"draws":0,"losses":411,"wins":119},"GB2-06":{"draws":1,"losses":167,"wins":334},"GB2-07":{"draws":0,"losses":424,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1336.1421109679886,"GB2-03":1293.4592548810635,"GB2-04":1394.8538897485296,"GB2-05":1425.408887526116,"GB2-06":1446.892490775673,"GB2-07":1513.6435152646973},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1076.5602399608579,"GB2-02":1403.1135005757899,"GB2-03":1421.5318211727383,"GB2-04":1394.6023817331804,"GB2-05":1761.3931189703812,"GB2-06":1146.8462180004135,"GB2-07":1721.6081919139383},"medium":{"GB2-01":1650.4543019634448,"GB2-03":1269.7943923913806,"GB2-04":1387.3077138216152,"GB2-05":1443.294433757351,"GB2-06":1443.67515372938,"GB2-07":1740.696635355058,"GB2-08":1149.5283151279227},"none":{"GB2-01":1281.4117909796635,"GB2-02":1408.0674645093268,"GB2-03":1189.0515510790715,"GB2-04":1402.6515736907934,"GB2-05":1071.539109850615,"GB2-06":1750.1561005972253,"GB2-07":1078.6257185250956}},"per_game_tracks":{"highest":{"GB2-01":14.931048783826306,"GB2-02":41.09805282953857,"GB2-03":48.961115008185836,"GB2-04":39.67248565709144,"GB2-05":72.78312368067063,"GB2-06":32.22701951372749,"GB2-07":70.24716132738281},"medium":{"GB2-01":68.1161334836176,"GB2-03":31.7811969323352,"GB2-04":38.750784944954475,"GB2-05":50.48844938435943,"GB2-06":51.65898604074648,"GB2-07":71.47099297422929,"GB2-08":29.190763313369704},"none":{"GB2-01":30.910317096155747,"GB2-02":41.733267003257794,"GB2-03":23.68209065494941,"GB2-04":40.69568594533089,"GB2-05":23.52955944789878,"GB2-06":69.72150239695492,"GB2-07":22.22823734141206}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":14,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.99000085005289,"medium":42.68216338420152,"none":31.56258248574495},"reasoning_agg":{"highest":{"max":72.78312368067063,"mean":39.99000085005289,"min":0.0},"medium":{"max":71.47099297422929,"mean":42.68216338420152,"min":0.0},"none":{"max":69.72150239695492,"mean":31.56258248574495,"min":0.0}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":11.119580898456572},"working_program_strength":{"all":43.51799875047595,"highest":45.70285811434616,"medium":48.77961529623031,"none":36.07152284085137}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:9ca1a99e9c27624e","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":0.08840574999999999,"min":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552},"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":0.39097600000000005},"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":0.08840574999999999,"min":0.07737849999999999,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":40},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.927552}},"codegen_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":36.26754281898222,"highest":32.117649718272226,"medium":34.38243631086787,"none":42.30254242780657},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"too_slow","GB2-04":"failed"},"medium":{"GB2-02":"failed","GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":45.38150416502546,"score":40.313262338251825},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":42.47384387943976,"score":21.23692193971988},"GB2-03":{"attempts":6,"failed_attempts":4,"playable":39.14443977405829,"score":16.98033907731549},"GB2-04":{"attempts":6,"failed_attempts":4,"playable":42.789047828620284,"score":28.526031885746857},"GB2-05":{"attempts":6,"playable":48.398626946299636,"score":48.398626946299636},"GB2-06":{"attempts":6,"playable":45.11605868709938,"score":45.11605868709938},"GB2-07":{"attempts":6,"playable":47.08208372305241,"score":47.08208372305241},"GB2-08":{"attempts":6,"failed_attempts":1,"playable":42.85204509444142,"score":38.86010869485486}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":4,"failed_attempts":1,"playable":60.818901921283704,"score":45.61417644096278},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":36.463816421560146,"score":9.115954105390037},"GB2-04":{"attempts":4,"failed_attempts":4,"score":0.0},"GB2-05":{"attempts":4,"playable":49.02199259171564,"score":49.02199259171564},"GB2-06":{"attempts":4,"playable":41.82607797402924,"score":41.82607797402924},"GB2-07":{"attempts":4,"playable":43.31791931952877,"score":43.31791931952877},"GB2-08":{"attempts":4,"failed_attempts":1,"playable":47.90323679503882,"score":35.92742759627912}},"medium":{"GB2-01":{"attempts":1,"playable":37.46484698008998,"score":37.46484698008998},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":41.30913525559276,"score":41.30913525559276},"GB2-05":{"attempts":1,"playable":44.72787497387571,"score":44.72787497387571},"GB2-06":{"attempts":1,"playable":45.63357720964464,"score":45.63357720964464},"GB2-07":{"attempts":1,"playable":58.72506198745043,"score":58.72506198745043},"GB2-08":{"attempts":1,"playable":47.19899408028943,"score":47.19899408028943}},"none":{"GB2-01":{"attempts":1,"playable":37.86076359370269,"score":37.86076359370269},"GB2-02":{"attempts":1,"playable":42.47384387943976,"score":42.47384387943976},"GB2-03":{"attempts":1,"playable":41.82506312655644,"score":41.82506312655644},"GB2-04":{"attempts":1,"playable":44.2689604016478,"score":44.2689604016478},"GB2-05":{"attempts":1,"playable":51.44601327330756,"score":51.44601327330756},"GB2-06":{"attempts":1,"playable":47.888520877624266,"score":47.888520877624266},"GB2-07":{"attempts":1,"playable":39.20326986217805,"score":39.20326986217805},"GB2-08":{"attempts":1,"playable":33.45390440799602,"score":33.45390440799602}}},"id":"o3","is_recent_addition":false,"last_measured_at":"2026-10-31T17:14:21Z","match_totals_all":{"draws":2185,"losses":8610,"wins":6315},"match_totals_tracks":{"highest":{"draws":528,"losses":5211,"wins":4167},"medium":{"draws":550,"losses":1487,"wins":1077},"none":{"draws":1107,"losses":1912,"wins":1071}},"model_slug":"o3","official_rank_by_reasoning":{"highest":59,"medium":63,"none":36},"overall":{"max":58.72506198745043,"mean":36.26754281898222,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.818901921283704,"GB2-03":36.463816421560146,"GB2-05":49.02199259171564,"GB2-06":41.82607797402924,"GB2-07":43.31791931952877,"GB2-08":47.90323679503882},"per_game_all":{"GB2-01":45.38150416502546,"GB2-05":48.398626946299636,"GB2-06":45.11605868709938,"GB2-07":47.08208372305241,"GB2-08":42.85204509444142},"per_game_match_totals_all":{"GB2-01":{"draws":299,"losses":1153,"wins":1128},"GB2-02":{"draws":380,"losses":94,"wins":6},"GB2-03":{"draws":261,"losses":508,"wins":223},"GB2-04":{"draws":597,"losses":288,"wins":111},"GB2-05":{"draws":0,"losses":1681,"wins":1499},"GB2-06":{"draws":44,"losses":1807,"wins":1161},"GB2-07":{"draws":0,"losses":1820,"wins":1360},"GB2-08":{"draws":604,"losses":1259,"wins":827}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":157,"losses":561,"wins":830},"GB2-03":{"draws":128,"losses":268,"wins":100},"GB2-05":{"draws":0,"losses":1114,"wins":1006},"GB2-06":{"draws":11,"losses":1244,"wins":753},"GB2-07":{"draws":0,"losses":1254,"wins":866},"GB2-08":{"draws":232,"losses":770,"wins":612}},"medium":{"GB2-01":{"draws":99,"losses":283,"wins":134},"GB2-04":{"draws":333,"losses":134,"wins":31},"GB2-05":{"draws":0,"losses":301,"wins":229},"GB2-06":{"draws":25,"losses":283,"wins":194},"GB2-07":{"draws":0,"losses":230,"wins":300},"GB2-08":{"draws":93,"losses":256,"wins":189}},"none":{"GB2-01":{"draws":43,"losses":309,"wins":164},"GB2-02":{"draws":380,"losses":94,"wins":6},"GB2-03":{"draws":133,"losses":240,"wins":123},"GB2-04":{"draws":264,"losses":154,"wins":80},"GB2-05":{"draws":0,"losses":266,"wins":264},"GB2-06":{"draws":8,"losses":280,"wins":214},"GB2-07":{"draws":0,"losses":336,"wins":194},"GB2-08":{"draws":279,"losses":233,"wins":26}}},"per_game_raw_elo_all":{"GB2-01":1425.6596216351438,"GB2-05":1417.238368502163,"GB2-06":1342.4631215869822,"GB2-07":1411.5572728404397,"GB2-08":1317.1516333468567},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1576.082747962748,"GB2-03":1312.409809235894,"GB2-05":1424.9273702874611,"GB2-06":1292.2555760888486,"GB2-07":1362.9084750174197,"GB2-08":1401.7182292097095},"medium":{"GB2-01":1348.4908820895039,"GB2-04":1407.4559789406449,"GB2-05":1371.5693828670737,"GB2-06":1350.2135596176918,"GB2-07":1559.0862455839742,"GB2-08":1352.4980396632952},"none":{"GB2-01":1352.40523485318,"GB2-02":1413.8262385455776,"GB2-03":1359.4903073217008,"GB2-04":1430.4689204585834,"GB2-05":1455.2183523519536,"GB2-06":1384.920229054406,"GB2-07":1312.6770979199257,"GB2-08":1197.238631167565}},"per_game_tracks":{"highest":{"GB2-01":60.818901921283704,"GB2-03":36.463816421560146,"GB2-05":49.02199259171564,"GB2-06":41.82607797402924,"GB2-07":43.31791931952877,"GB2-08":47.90323679503882},"medium":{"GB2-01":37.46484698008998,"GB2-04":41.30913525559276,"GB2-05":44.72787497387571,"GB2-06":45.63357720964464,"GB2-07":58.72506198745043,"GB2-08":47.19899408028943},"none":{"GB2-01":37.86076359370269,"GB2-02":42.47384387943976,"GB2-03":41.82506312655644,"GB2-04":44.2689604016478,"GB2-05":51.44601327330756,"GB2-06":47.888520877624266,"GB2-07":39.20326986217805,"GB2-08":33.45390440799602}},"program_outcomes":{"all":{"counted_attempts":44,"failed":11,"infra_excluded":0,"success_rate":0.75,"too_slow":4,"worked_after_repair":1,"worked_first_time":32,"working":33},"highest":{"counted_attempts":28,"failed":9,"infra_excluded":0,"success_rate":0.6785714285714286,"too_slow":4,"worked_after_repair":0,"worked_first_time":19,"working":19},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":0,"worked_first_time":6,"working":6},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":0,"rank_movement_baseline_at":"2026-10-26T02:08:04Z","reasoning":{"highest":32.117649718272226,"medium":34.38243631086787,"none":42.30254242780657},"reasoning_agg":{"highest":{"max":49.02199259171564,"mean":32.117649718272226,"min":0.0},"medium":{"max":58.72506198745043,"mean":34.38243631086787,"min":0.0},"none":{"max":51.44601327330756,"mean":42.30254242780657,"min":33.45390440799602}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":10.184892709534346},"working_program_strength":{"all":44.90148278205215,"highest":46.558657503859386,"medium":45.84324841449049,"none":42.30254242780657}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:083de56cd94240a4","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":0.4057700000000001},"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":0.428104},"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":0.40576999999999996}},"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":1.0014830000000001},"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":36.25240249322843,"highest":43.0496502204162,"medium":40.11721941624721,"none":25.590337843021892},"first_seen_at":null,"game_gaps":{"medium":{"GB2-07":"failed"},"none":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":38.72399487020597,"score":38.72399487020597},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":40.40923256882927,"score":26.93948837921951},"GB2-03":{"attempts":3,"playable":42.37386116698077,"score":42.37386116698077},"GB2-04":{"attempts":3,"playable":40.660178541949335,"score":40.660178541949335},"GB2-05":{"attempts":3,"playable":38.36695890780499,"score":38.36695890780499},"GB2-06":{"attempts":3,"playable":17.42779785812212,"score":17.42779785812212},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":37.235218881121135,"score":24.823479254080755},"GB2-08":{"attempts":3,"playable":60.70346096746399,"score":60.70346096746399}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":41.417467546983815,"score":41.417467546983815},"GB2-02":{"attempts":1,"playable":41.09805282953857,"score":41.09805282953857},"GB2-03":{"attempts":1,"playable":41.51170590378346,"score":41.51170590378346},"GB2-04":{"attempts":1,"playable":38.34089571965341,"score":38.34089571965341},"GB2-05":{"attempts":1,"playable":49.91352862098098,"score":49.91352862098098},"GB2-06":{"attempts":1,"playable":20.491745124685572,"score":20.491745124685572},"GB2-07":{"attempts":1,"playable":45.01338529965386,"score":45.01338529965386},"GB2-08":{"attempts":1,"playable":66.6104207180499,"score":66.6104207180499}},"medium":{"GB2-01":{"attempts":1,"playable":50.944502493562524,"score":50.944502493562524},"GB2-02":{"attempts":1,"playable":39.720412308119975,"score":39.720412308119975},"GB2-03":{"attempts":1,"playable":39.941124573431644,"score":39.941124573431644},"GB2-04":{"attempts":1,"playable":41.10469187570221,"score":41.10469187570221},"GB2-05":{"attempts":1,"playable":48.379078488230974,"score":48.379078488230974},"GB2-06":{"attempts":1,"playable":14.240894817070036,"score":14.240894817070036},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":86.6070507738603,"score":86.6070507738603}},"none":{"GB2-01":{"attempts":1,"playable":23.810014570071576,"score":23.810014570071576},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":45.6687530237272,"score":45.6687530237272},"GB2-04":{"attempts":1,"playable":42.534948030492394,"score":42.534948030492394},"GB2-05":{"attempts":1,"playable":16.808269614203017,"score":16.808269614203017},"GB2-06":{"attempts":1,"playable":17.550753632610753,"score":17.550753632610753},"GB2-07":{"attempts":1,"playable":29.45705246258841,"score":29.45705246258841},"GB2-08":{"attempts":1,"playable":28.892911410481766,"score":28.892911410481766}}},"id":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-10-31T16:45:39Z","match_totals_all":{"draws":2657,"losses":5711,"wins":2892},"match_totals_tracks":{"highest":{"draws":1126,"losses":1855,"wins":1109},"medium":{"draws":830,"losses":1567,"wins":1163},"none":{"draws":701,"losses":2289,"wins":620}},"model_slug":"bytedance-seed-seed-2-0-code","official_rank_by_reasoning":{"highest":49,"medium":56,"none":74},"overall":{"max":86.6070507738603,"mean":36.25240249322843,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":52,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.417467546983815,"GB2-02":41.09805282953857,"GB2-03":41.51170590378346,"GB2-04":38.34089571965341,"GB2-05":49.91352862098098,"GB2-06":20.491745124685572,"GB2-07":45.01338529965386,"GB2-08":66.6104207180499},"per_game_all":{"GB2-01":38.72399487020597,"GB2-03":42.37386116698077,"GB2-04":40.660178541949335,"GB2-05":38.36695890780499,"GB2-06":17.42779785812212,"GB2-08":60.70346096746399},"per_game_match_totals_all":{"GB2-01":{"draws":391,"losses":782,"wins":375},"GB2-02":{"draws":711,"losses":232,"wins":17},"GB2-03":{"draws":335,"losses":744,"wins":409},"GB2-04":{"draws":984,"losses":419,"wins":91},"GB2-05":{"draws":0,"losses":1002,"wins":588},"GB2-06":{"draws":8,"losses":1280,"wins":218},"GB2-07":{"draws":0,"losses":692,"wins":368},"GB2-08":{"draws":228,"losses":560,"wins":826}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":207,"losses":209,"wins":100},"GB2-02":{"draws":363,"losses":109,"wins":8},"GB2-03":{"draws":134,"losses":241,"wins":121},"GB2-04":{"draws":316,"losses":157,"wins":25},"GB2-05":{"draws":0,"losses":274,"wins":256},"GB2-06":{"draws":3,"losses":413,"wins":86},"GB2-07":{"draws":0,"losses":305,"wins":225},"GB2-08":{"draws":103,"losses":147,"wins":288}},"medium":{"GB2-01":{"draws":68,"losses":230,"wins":218},"GB2-02":{"draws":348,"losses":123,"wins":9},"GB2-03":{"draws":99,"losses":266,"wins":131},"GB2-04":{"draws":313,"losses":145,"wins":40},"GB2-05":{"draws":0,"losses":282,"wins":248},"GB2-06":{"draws":2,"losses":441,"wins":59},"GB2-08":{"draws":0,"losses":80,"wins":458}},"none":{"GB2-01":{"draws":116,"losses":343,"wins":57},"GB2-03":{"draws":102,"losses":237,"wins":157},"GB2-04":{"draws":355,"losses":117,"wins":26},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":3,"losses":426,"wins":73},"GB2-07":{"draws":0,"losses":387,"wins":143},"GB2-08":{"draws":125,"losses":333,"wins":80}}},"per_game_raw_elo_all":{"GB2-01":1355.3549122709358,"GB2-03":1364.2268280260753,"GB2-04":1402.3070384044586,"GB2-05":1267.4884734835448,"GB2-06":910.9240351113882,"GB2-08":1617.0267707722653},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1387.1009273604425,"GB2-02":1403.1135005757899,"GB2-03":1356.7653234457705,"GB2-04":1384.0486717878937,"GB2-05":1436.1463790786563,"GB2-06":964.3192131966683,"GB2-07":1385.2807647890952,"GB2-08":1631.3616689706437},"medium":{"GB2-01":1478.0023461061749,"GB2-02":1392.314230671829,"GB2-03":1343.0716808962252,"GB2-04":1405.856458424986,"GB2-05":1417.0849859830746,"GB2-06":853.8833046144762,"GB2-08":2073.5764374410696},"none":{"GB2-01":1200.9614633461897,"GB2-03":1392.8434797362308,"GB2-04":1417.015985000496,"GB2-05":949.234055388904,"GB2-06":914.5695875230206,"GB2-07":1185.1039262016661,"GB2-08":1146.1422059050826}},"per_game_tracks":{"highest":{"GB2-01":41.417467546983815,"GB2-02":41.09805282953857,"GB2-03":41.51170590378346,"GB2-04":38.34089571965341,"GB2-05":49.91352862098098,"GB2-06":20.491745124685572,"GB2-07":45.01338529965386,"GB2-08":66.6104207180499},"medium":{"GB2-01":50.944502493562524,"GB2-02":39.720412308119975,"GB2-03":39.941124573431644,"GB2-04":41.10469187570221,"GB2-05":48.379078488230974,"GB2-06":14.240894817070036,"GB2-08":86.6070507738603},"none":{"GB2-01":23.810014570071576,"GB2-03":45.6687530237272,"GB2-04":42.534948030492394,"GB2-05":16.808269614203017,"GB2-06":17.550753632610753,"GB2-07":29.45705246258841,"GB2-08":28.892911410481766}},"program_outcomes":{"all":{"counted_attempts":24,"failed":2,"infra_excluded":0,"success_rate":0.9166666666666666,"too_slow":0,"worked_after_repair":8,"worked_first_time":14,"working":22},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":5,"worked_first_time":2,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#111418","rank_movement":-2,"rank_movement_baseline_at":"2026-10-26T02:02:43Z","reasoning":{"highest":43.0496502204162,"medium":40.11721941624721,"none":25.590337843021892},"reasoning_agg":{"highest":{"max":66.6104207180499,"mean":43.0496502204162,"min":20.491745124685572},"medium":{"max":86.6070507738603,"mean":40.11721941624721,"min":0.0},"none":{"max":45.6687530237272,"mean":25.590337843021892,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":17.459312377394305},"working_program_strength":{"all":39.381333791288874,"highest":43.0496502204162,"medium":45.84825076142538,"none":29.24610039202502}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:4a7f433abdec3d0b","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":0.16008749804},"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":34.83157639217308,"highest":37.354105993471975,"medium":35.16982569797398,"none":31.970797485073298},"first_seen_at":null,"game_gaps":{"highest":{"GB2-05":"failed"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":24.933128314190256,"score":24.933128314190256},"GB2-02":{"attempts":5,"playable":41.413324741629,"score":41.413324741629},"GB2-03":{"attempts":4,"playable":38.018798417372345,"score":38.018798417372345},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":41.436613576973784,"score":27.624409051315855},"GB2-05":{"attempts":5,"failed_attempts":1,"playable":35.230160942591986,"score":23.48677396172799},"GB2-06":{"attempts":5,"playable":54.975795582297586,"score":54.975795582297586},"GB2-07":{"attempts":5,"playable":27.93567945654787,"score":27.93567945654787},"GB2-08":{"attempts":5,"playable":40.26470161230377,"score":40.26470161230377}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":15.84331711118899,"score":15.84331711118899},"GB2-02":{"attempts":1,"playable":42.89678214539853,"score":42.89678214539853},"GB2-03":{"attempts":1,"playable":34.66081498134423,"score":34.66081498134423},"GB2-04":{"attempts":1,"playable":42.12650662185929,"score":42.12650662185929},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":82.16402033648322,"score":82.16402033648322},"GB2-07":{"attempts":1,"playable":39.01443369396503,"score":39.01443369396503},"GB2-08":{"attempts":1,"playable":42.12697305753646,"score":42.12697305753646}},"medium":{"GB2-01":{"attempts":3,"playable":38.263537979121544,"score":38.263537979121544},"GB2-02":{"attempts":3,"playable":39.82161897527511,"score":39.82161897527511},"GB2-03":{"attempts":2,"playable":44.309823266364845,"score":44.309823266364845},"GB2-04":{"attempts":2,"playable":40.746720532088275,"score":40.746720532088275},"GB2-05":{"attempts":3,"playable":25.54006417502328,"score":25.54006417502328},"GB2-06":{"attempts":3,"playable":25.97706085662414,"score":25.97706085662414},"GB2-07":{"attempts":3,"playable":25.5380459368718,"score":25.5380459368718},"GB2-08":{"attempts":3,"playable":41.161733862422814,"score":41.161733862422814}},"none":{"GB2-01":{"attempts":1,"playable":20.692529852260233,"score":20.692529852260233},"GB2-02":{"attempts":1,"playable":41.52157310421335,"score":41.52157310421335},"GB2-03":{"attempts":1,"playable":35.085757004407945,"score":35.085757004407945},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":44.92025771016069,"score":44.92025771016069},"GB2-06":{"attempts":1,"playable":56.78630555378539,"score":56.78630555378539},"GB2-07":{"attempts":1,"playable":19.254558738806775,"score":19.254558738806775},"GB2-08":{"attempts":1,"playable":37.50539791695202,"score":37.50539791695202}}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T15:55:37Z","match_totals_all":{"draws":4313,"losses":9985,"wins":4130},"match_totals_tracks":{"highest":{"draws":1060,"losses":1594,"wins":906},"medium":{"draws":2531,"losses":6380,"wins":2365},"none":{"draws":722,"losses":2011,"wins":859}},"model_slug":"deepseek-deepseek-v4-flash","official_rank_by_reasoning":{"highest":51,"medium":61,"none":55},"overall":{"max":82.16402033648322,"mean":34.83157639217308,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":53,"overall_ranking_status":"ranked","per_game":{"GB2-01":15.84331711118899,"GB2-02":42.89678214539853,"GB2-03":34.66081498134423,"GB2-04":42.12650662185929,"GB2-06":82.16402033648322,"GB2-07":39.01443369396503,"GB2-08":42.12697305753646},"per_game_all":{"GB2-01":24.933128314190256,"GB2-02":41.413324741629,"GB2-03":38.018798417372345,"GB2-06":54.975795582297586,"GB2-07":27.935679456547874,"GB2-08":40.26470161230377},"per_game_match_totals_all":{"GB2-01":{"draws":403,"losses":1638,"wins":539},"GB2-02":{"draws":1788,"losses":566,"wins":46},"GB2-03":{"draws":564,"losses":986,"wins":434},"GB2-04":{"draws":980,"losses":413,"wins":101},"GB2-05":{"draws":0,"losses":1502,"wins":618},"GB2-06":{"draws":51,"losses":1471,"wins":988},"GB2-07":{"draws":0,"losses":1995,"wins":655},"GB2-08":{"draws":527,"losses":1414,"wins":749}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":105,"losses":388,"wins":23},"GB2-02":{"draws":348,"losses":108,"wins":24},"GB2-03":{"draws":145,"losses":268,"wins":83},"GB2-04":{"draws":295,"losses":149,"wins":54},"GB2-06":{"draws":34,"losses":82,"wins":386},"GB2-07":{"draws":0,"losses":337,"wins":193},"GB2-08":{"draws":133,"losses":262,"wins":143}},"medium":{"GB2-01":{"draws":189,"losses":888,"wins":471},"GB2-02":{"draws":1061,"losses":359,"wins":20},"GB2-03":{"draws":282,"losses":448,"wins":262},"GB2-04":{"draws":685,"losses":264,"wins":47},"GB2-05":{"draws":0,"losses":1202,"wins":388},"GB2-06":{"draws":12,"losses":1154,"wins":340},"GB2-07":{"draws":0,"losses":1219,"wins":371},"GB2-08":{"draws":302,"losses":846,"wins":466}},"none":{"GB2-01":{"draws":109,"losses":362,"wins":45},"GB2-02":{"draws":379,"losses":99,"wins":2},"GB2-03":{"draws":137,"losses":270,"wins":89},"GB2-05":{"draws":0,"losses":300,"wins":230},"GB2-06":{"draws":5,"losses":235,"wins":262},"GB2-07":{"draws":0,"losses":439,"wins":91},"GB2-08":{"draws":92,"losses":306,"wins":140}}},"per_game_raw_elo_all":{"GB2-01":1198.2134010641012,"GB2-02":1405.4542862591763,"GB2-03":1325.7835227470907,"GB2-06":1518.52967274144,"GB2-07":1148.9776014997585,"GB2-08":1276.5449595461505},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1091.3432476333248,"GB2-02":1417.1079113853616,"GB2-03":1296.2273223999146,"GB2-04":1413.8359909467022,"GB2-06":1994.3339459586132,"GB2-07":1310.2950079875257,"GB2-08":1293.6711381926302},"medium":{"GB2-01":1341.9100457524855,"GB2-02":1392.8368711195974,"GB2-03":1381.0598942681477,"GB2-04":1403.047471417995,"GB2-05":1060.1559903791142,"GB2-06":1035.5402977825054,"GB2-07":1107.319963383645,"GB2-08":1293.934866722147},"none":{"GB2-01":1161.3869098064936,"GB2-02":1406.4180762725705,"GB2-03":1300.0633515732097,"GB2-05":1373.9808741948384,"GB2-06":1525.7147744832014,"GB2-07":1029.3178331281047,"GB2-08":1242.0288737236742}},"per_game_tracks":{"highest":{"GB2-01":15.84331711118899,"GB2-02":42.89678214539853,"GB2-03":34.66081498134423,"GB2-04":42.12650662185929,"GB2-06":82.16402033648322,"GB2-07":39.01443369396503,"GB2-08":42.12697305753646},"medium":{"GB2-01":38.263537979121544,"GB2-02":39.82161897527511,"GB2-03":44.309823266364845,"GB2-04":40.746720532088275,"GB2-05":25.54006417502328,"GB2-06":25.97706085662414,"GB2-07":25.538045936871807,"GB2-08":41.161733862422814},"none":{"GB2-01":20.692529852260233,"GB2-02":41.52157310421335,"GB2-03":35.085757004407945,"GB2-05":44.92025771016069,"GB2-06":56.78630555378539,"GB2-07":19.254558738806775,"GB2-08":37.50539791695202}},"program_outcomes":{"all":{"counted_attempts":38,"failed":2,"infra_excluded":2,"success_rate":0.9473684210526315,"too_slow":0,"worked_after_repair":11,"worked_first_time":25,"working":36},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"medium":{"counted_attempts":22,"failed":0,"infra_excluded":2,"success_rate":1.0,"too_slow":0,"worked_after_repair":7,"worked_first_time":15,"working":22},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":6,"working":7}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:04:59Z","reasoning":{"highest":37.354105993471975,"medium":35.16982569797398,"none":31.970797485073298},"reasoning_agg":{"highest":{"max":82.16402033648322,"mean":37.354105993471975,"min":0.0},"medium":{"max":44.309823266364845,"mean":35.16982569797398,"min":25.5380459368718},"none":{"max":56.78630555378539,"mean":31.970797485073298,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":5.383308508398677},"working_program_strength":{"all":38.13276227210381,"highest":42.690406849682255,"medium":35.16982569797398,"none":36.538054268655195}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:9d4b0d52a83b422c","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":1.565521045},"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":0.35846965},"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":0.3584696499999999},"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":34.62512592314123,"highest":45.41430983558118,"medium":40.90544829243823,"none":17.555619641404284},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-08":"failed"},"none":{"GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":50.90719303013315,"score":50.90719303013315},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":42.10362277122766,"score":28.06908184748511},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":46.42865236261341,"score":30.952434908408943},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":55.634054308812026,"score":37.089369539208015},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":59.263376915299325,"score":39.508917943532886},"GB2-06":{"attempts":3,"playable":40.23255845105445,"score":40.23255845105445},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":49.64093068715969,"score":33.093953791439795},"GB2-08":{"attempts":3,"failed_attempts":2,"playable":51.4424936216026,"score":17.147497873867533}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":74.71379107428876,"score":74.71379107428876},"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":71.08390138056203,"score":71.08390138056203},"GB2-05":{"attempts":1,"playable":59.263376915299325,"score":59.263376915299325},"GB2-06":{"attempts":1,"playable":28.571026312969234,"score":28.571026312969234},"GB2-07":{"attempts":1,"playable":78.23988937992755,"score":78.23988937992755},"GB2-08":{"attempts":1,"playable":51.4424936216026,"score":51.4424936216026}},"medium":{"GB2-01":{"attempts":1,"playable":53.09417802302067,"score":53.09417802302067},"GB2-02":{"attempts":1,"playable":42.156521149269636,"score":42.156521149269636},"GB2-03":{"attempts":1,"playable":49.67730324695518,"score":49.67730324695518},"GB2-04":{"attempts":1,"playable":40.18420723706202,"score":40.18420723706202},"GB2-05":{"attempts":1,"playable":59.263376915299325,"score":59.263376915299325},"GB2-06":{"attempts":1,"playable":61.82602777350721,"score":61.82602777350721},"GB2-07":{"attempts":1,"playable":21.04197199439183,"score":21.04197199439183},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":1,"playable":24.91360999309,"score":24.91360999309},"GB2-02":{"attempts":1,"playable":42.050724393185696,"score":42.050724393185696},"GB2-03":{"attempts":1,"playable":43.18000147827165,"score":43.18000147827165},"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":30.300621266686917,"score":30.300621266686917},"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":"2026-10-31T16:49:19Z","match_totals_all":{"draws":1875,"losses":3688,"wins":3097},"match_totals_tracks":{"highest":{"draws":239,"losses":1176,"wins":1699},"medium":{"draws":1005,"losses":1476,"wins":1071},"none":{"draws":631,"losses":1036,"wins":327}},"model_slug":"qwen-qwen3-8-27b","official_rank_by_reasoning":{"highest":47,"medium":54},"overall":{"max":78.23988937992755,"mean":34.62512592314123,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":54,"overall_ranking_status":"partial","per_game":{"GB2-01":74.71379107428876,"GB2-04":71.08390138056203,"GB2-05":59.263376915299325,"GB2-06":28.571026312969234,"GB2-07":78.23988937992755,"GB2-08":51.4424936216026},"per_game_all":{"GB2-01":50.90719303013315,"GB2-06":40.23255845105445},"per_game_match_totals_all":{"GB2-01":{"draws":265,"losses":657,"wins":626},"GB2-02":{"draws":759,"losses":192,"wins":9},"GB2-03":{"draws":273,"losses":432,"wins":287},"GB2-04":{"draws":468,"losses":224,"wins":304},"GB2-05":{"draws":0,"losses":450,"wins":610},"GB2-06":{"draws":47,"losses":935,"wins":524},"GB2-07":{"draws":0,"losses":549,"wins":511},"GB2-08":{"draws":63,"losses":249,"wins":226}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":10,"losses":136,"wins":370},"GB2-04":{"draws":154,"losses":75,"wins":269},"GB2-05":{"draws":0,"losses":225,"wins":305},"GB2-06":{"draws":12,"losses":372,"wins":118},"GB2-07":{"draws":0,"losses":119,"wins":411},"GB2-08":{"draws":63,"losses":249,"wins":226}},"medium":{"GB2-01":{"draws":114,"losses":196,"wins":206},"GB2-02":{"draws":381,"losses":95,"wins":4},"GB2-03":{"draws":173,"losses":182,"wins":141},"GB2-04":{"draws":314,"losses":149,"wins":35},"GB2-05":{"draws":0,"losses":225,"wins":305},"GB2-06":{"draws":23,"losses":199,"wins":280},"GB2-07":{"draws":0,"losses":430,"wins":100}},"none":{"GB2-01":{"draws":141,"losses":325,"wins":50},"GB2-02":{"draws":378,"losses":97,"wins":5},"GB2-03":{"draws":100,"losses":250,"wins":146},"GB2-06":{"draws":12,"losses":364,"wins":126}}},"per_game_raw_elo_all":{"GB2-01":1480.067692685219,"GB2-06":1272.9171724510422},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1727.4310572193417,"GB2-04":1653.9321783574517,"GB2-05":1555.1038674535155,"GB2-06":1091.3111703169504,"GB2-07":1857.9841572219423,"GB2-08":1404.6860333914676},"medium":{"GB2-01":1498.540645224704,"GB2-02":1411.3607762811257,"GB2-03":1427.8158144681556,"GB2-04":1398.6338753812252,"GB2-05":1555.1038674535155,"GB2-06":1609.7944923077862,"GB2-07":1059.4550719934277},"none":{"GB2-01":1214.2313756116114,"GB2-02":1410.538110706807,"GB2-03":1371.2554782985903,"GB2-06":1117.6458547283905}},"per_game_tracks":{"highest":{"GB2-01":74.71379107428876,"GB2-04":71.08390138056203,"GB2-05":59.263376915299325,"GB2-06":28.571026312969234,"GB2-07":78.23988937992755,"GB2-08":51.4424936216026},"medium":{"GB2-01":53.09417802302067,"GB2-02":42.156521149269636,"GB2-03":49.67730324695518,"GB2-04":40.18420723706202,"GB2-05":59.263376915299325,"GB2-06":61.82602777350721,"GB2-07":21.04197199439183},"none":{"GB2-01":24.91360999309,"GB2-02":42.050724393185696,"GB2-03":43.18000147827165,"GB2-06":30.300621266686917}},"program_outcomes":{"all":{"counted_attempts":24,"failed":7,"infra_excluded":0,"success_rate":0.7083333333333334,"too_slow":0,"worked_after_repair":6,"worked_first_time":11,"working":17},"highest":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"none":{"counted_attempts":8,"failed":4,"infra_excluded":0,"success_rate":0.5,"too_slow":0,"worked_after_repair":2,"worked_first_time":2,"working":4}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.41430983558118,"medium":40.90544829243823,"none":17.555619641404284},"reasoning_agg":{"highest":{"max":78.23988937992755,"mean":45.41430983558118,"min":0.0},"medium":{"max":61.82602777350721,"mean":40.90544829243823,"min":0.0},"none":{"max":43.18000147827165,"mean":17.555619641404284,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":27.858690194176894},"working_program_strength":{"all":47.47091205323445,"highest":60.55241311410824,"medium":46.74908376278655,"none":35.11123928280857}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-space-bunny-alpha:4a1adab13c9db1f6","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":33.4057341720241,"highest":36.7991949927594,"medium":35.76951573923582,"none":27.648491784077066},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":56.57888988937127,"score":37.71925992624751},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":41.83882416999572,"score":27.89254944666381},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":40.95514647629603,"score":27.30343098419735},"GB2-04":{"attempts":3,"playable":40.863870206010766,"score":40.863870206010766},"GB2-05":{"attempts":3,"playable":34.07760018094285,"score":34.07760018094285},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":48.49051020788136,"score":32.327006805254236},"GB2-07":{"attempts":3,"playable":45.58531834331861,"score":45.58531834331861},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.21525622533646,"score":21.47683748355764}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":63.77923582154035,"score":63.77923582154035},"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":38.34089571965341,"score":38.34089571965341},"GB2-05":{"attempts":1,"playable":45.68956779529827,"score":45.68956779529827},"GB2-06":{"attempts":1,"playable":38.59965355641884,"score":38.59965355641884},"GB2-07":{"attempts":1,"playable":74.43131236751287,"score":74.43131236751287},"GB2-08":{"attempts":1,"playable":33.55289468165149,"score":33.55289468165149}},"medium":{"GB2-01":{"attempts":1,"playable":49.37854395720218,"score":49.37854395720218},"GB2-02":{"attempts":1,"playable":42.57959551045286,"score":42.57959551045286},"GB2-03":{"attempts":1,"playable":46.081932046417926,"score":46.081932046417926},"GB2-04":{"attempts":1,"playable":40.593409787871586,"score":40.593409787871586},"GB2-05":{"attempts":1,"playable":12.970088553099016,"score":12.970088553099016},"GB2-06":{"attempts":1,"playable":58.38136685934386,"score":58.38136685934386},"GB2-07":{"attempts":1,"playable":36.171189199499125,"score":36.171189199499125},"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":41.09805282953857,"score":41.09805282953857},"GB2-03":{"attempts":1,"playable":35.82836090617413,"score":35.82836090617413},"GB2-04":{"attempts":1,"playable":43.6573051105073,"score":43.6573051105073},"GB2-05":{"attempts":1,"playable":43.573144194431265,"score":43.573144194431265},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.153453462943826,"score":26.153453462943826},"GB2-08":{"attempts":1,"playable":30.87761776902143,"score":30.87761776902143}}},"id":"stealth/space-bunny-alpha","is_recent_addition":false,"last_measured_at":"2026-10-31T17:02:37Z","match_totals_all":{"draws":2386,"losses":4663,"wins":2689},"match_totals_tracks":{"highest":{"draws":541,"losses":1382,"wins":1191},"medium":{"draws":905,"losses":1740,"wins":907},"none":{"draws":940,"losses":1541,"wins":591}},"model_slug":"stealth-space-bunny-alpha","official_rank_by_reasoning":{"highest":52,"medium":60,"none":71},"overall":{"max":74.43131236751287,"mean":33.4057341720241,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":55,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.77923582154035,"GB2-04":38.34089571965341,"GB2-05":45.68956779529827,"GB2-06":38.59965355641884,"GB2-07":74.43131236751287,"GB2-08":33.55289468165149},"per_game_all":{"GB2-04":40.863870206010766,"GB2-05":34.07760018094285,"GB2-07":45.58531834331861},"per_game_match_totals_all":{"GB2-01":{"draws":248,"losses":346,"wins":438},"GB2-02":{"draws":750,"losses":199,"wins":11},"GB2-03":{"draws":220,"losses":511,"wins":261},"GB2-04":{"draws":944,"losses":436,"wins":114},"GB2-05":{"draws":0,"losses":1069,"wins":521},"GB2-06":{"draws":7,"losses":556,"wins":441},"GB2-07":{"draws":0,"losses":897,"wins":693},"GB2-08":{"draws":217,"losses":649,"wins":210}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":154,"losses":121,"wins":241},"GB2-04":{"draws":292,"losses":169,"wins":37},"GB2-05":{"draws":0,"losses":296,"wins":234},"GB2-06":{"draws":3,"losses":329,"wins":170},"GB2-07":{"draws":0,"losses":141,"wins":389},"GB2-08":{"draws":92,"losses":326,"wins":120}},"medium":{"GB2-01":{"draws":94,"losses":225,"wins":197},"GB2-02":{"draws":377,"losses":95,"wins":8},"GB2-03":{"draws":104,"losses":234,"wins":158},"GB2-04":{"draws":326,"losses":141,"wins":31},"GB2-05":{"draws":0,"losses":466,"wins":64},"GB2-06":{"draws":4,"losses":227,"wins":271},"GB2-07":{"draws":0,"losses":352,"wins":178}},"none":{"GB2-02":{"draws":373,"losses":104,"wins":3},"GB2-03":{"draws":116,"losses":277,"wins":103},"GB2-04":{"draws":326,"losses":126,"wins":46},"GB2-05":{"draws":0,"losses":307,"wins":223},"GB2-07":{"draws":0,"losses":404,"wins":126},"GB2-08":{"draws":125,"losses":323,"wins":90}}},"per_game_raw_elo_all":{"GB2-04":1403.8762976197293,"GB2-05":1202.6888168978103,"GB2-07":1400.5321855097234},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1604.2677343725293,"GB2-04":1384.0486717878937,"GB2-05":1383.604783185163,"GB2-06":1243.178061591187,"GB2-07":1789.1738220452762,"GB2-08":1198.335180251218},"medium":{"GB2-01":1463.0980589393355,"GB2-02":1414.6472416588617,"GB2-03":1396.4312548374248,"GB2-04":1401.8490903366605,"GB2-05":867.414678083607,"GB2-06":1551.906163909403,"GB2-07":1274.1250091356533},"none":{"GB2-02":1403.1135005757899,"GB2-03":1306.7334023375029,"GB2-04":1425.731130734633,"GB2-05":1357.0469894246605,"GB2-07":1138.29772534824,"GB2-08":1168.5508887210021}},"per_game_tracks":{"highest":{"GB2-01":63.77923582154035,"GB2-04":38.34089571965341,"GB2-05":45.68956779529827,"GB2-06":38.59965355641884,"GB2-07":74.43131236751287,"GB2-08":33.55289468165149},"medium":{"GB2-01":49.37854395720218,"GB2-02":42.57959551045286,"GB2-03":46.081932046417926,"GB2-04":40.593409787871586,"GB2-05":12.970088553099016,"GB2-06":58.38136685934386,"GB2-07":36.171189199499125},"none":{"GB2-02":41.09805282953857,"GB2-03":35.82836090617413,"GB2-04":43.6573051105073,"GB2-05":43.573144194431265,"GB2-07":26.153453462943826,"GB2-08":30.87761776902143}},"program_outcomes":{"all":{"counted_attempts":24,"failed":5,"infra_excluded":0,"success_rate":0.7916666666666666,"too_slow":0,"worked_after_repair":12,"worked_first_time":7,"working":19},"highest":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:09:58Z","reasoning":{"highest":36.7991949927594,"medium":35.76951573923582,"none":27.648491784077066},"reasoning_agg":{"highest":{"max":74.43131236751287,"mean":36.7991949927594,"min":0.0},"medium":{"max":58.38136685934386,"mean":35.76951573923582,"min":0.0},"none":{"max":43.6573051105073,"mean":27.648491784077066,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":9.150703208682337},"working_program_strength":{"all":42.26989853163621,"highest":49.0655933236792,"medium":40.879446559126656,"none":36.86465571210275}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:fcc83610427dff10","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":0.27157109999999995}},"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":0.6081093},"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":32.817348074439046,"highest":32.636067274895694,"medium":26.780531661300905,"none":39.03544528712054},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.69025423298972,"score":31.826014996614205},"GB2-02":{"attempts":6,"failed_attempts":2,"playable":42.84223788715732,"score":28.17359101667998},"GB2-03":{"attempts":6,"failed_attempts":1,"playable":48.17763644007715,"score":39.05263088470229},"GB2-04":{"attempts":6,"playable":43.53149656792517,"score":43.53149656792517},"GB2-05":{"attempts":6,"playable":15.144579694395327,"score":15.144579694395327},"GB2-06":{"attempts":6,"playable":36.79976060895595,"score":36.79976060895595},"GB2-07":{"attempts":6,"failed_attempts":1,"playable":42.559049970772385,"score":39.08507465641832},"GB2-08":{"attempts":6,"playable":28.925636169821114,"score":28.925636169821114}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":35.18543541825313,"score":17.592717709126564},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.586684031984916,"score":22.293342015992458},"GB2-03":{"attempts":2,"playable":47.69716231284809,"score":47.69716231284809},"GB2-04":{"attempts":2,"playable":40.13240437418439,"score":40.13240437418439},"GB2-05":{"attempts":2,"playable":17.95975568612141,"score":17.95975568612141},"GB2-06":{"attempts":2,"playable":40.99584541729873,"score":40.99584541729873},"GB2-07":{"attempts":2,"playable":44.73023851962753,"score":44.73023851962753},"GB2-08":{"attempts":2,"playable":29.687072163966366,"score":29.687072163966366}},"medium":{"GB2-01":{"attempts":2,"playable":40.97351471913097,"score":40.97351471913097},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.42519719087914,"score":21.71259859543957},"GB2-03":{"attempts":2,"playable":42.08571367513417,"score":42.08571367513417},"GB2-04":{"attempts":2,"playable":42.68738581686847,"score":42.68738581686847},"GB2-05":{"attempts":2,"playable":15.560997574146384,"score":15.560997574146384},"GB2-06":{"attempts":2,"playable":13.151215239080937,"score":13.151215239080937},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":20.843851886124355,"score":10.421925943062178},"GB2-08":{"attempts":2,"playable":27.650901727544568,"score":27.650901727544568}},"none":{"GB2-01":{"attempts":2,"playable":36.91181256158508,"score":36.91181256158508},"GB2-02":{"attempts":2,"playable":40.51483243860791,"score":40.51483243860791},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":54.75003333224918,"score":27.37501666612459},"GB2-04":{"attempts":2,"playable":47.774699512722655,"score":47.774699512722655},"GB2-05":{"attempts":2,"playable":11.912985822918188,"score":11.912985822918188},"GB2-06":{"attempts":2,"playable":56.252221170488184,"score":56.252221170488184},"GB2-07":{"attempts":2,"playable":62.10305950656526,"score":62.10305950656526},"GB2-08":{"attempts":2,"playable":29.438934617952413,"score":29.438934617952413}}},"id":"google/gemini-3.5-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-31T17:07:30Z","match_totals_all":{"draws":5000,"losses":11604,"wins":4896},"match_totals_tracks":{"highest":{"draws":1348,"losses":3622,"wins":1676},"medium":{"draws":1794,"losses":4243,"wins":1133},"none":{"draws":1858,"losses":3739,"wins":2087}},"model_slug":"google-gemini-3-5-flash-lite","official_rank_by_reasoning":{"highest":57,"medium":71,"none":46},"overall":{"max":62.10305950656526,"mean":32.817348074439046,"min":10.421925943062178},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":56,"overall_ranking_status":"ranked","per_game":{"GB2-01":35.18543541825313,"GB2-02":44.586684031984916,"GB2-03":47.69716231284809,"GB2-04":40.13240437418439,"GB2-05":17.95975568612141,"GB2-06":40.99584541729873,"GB2-07":44.73023851962753,"GB2-08":29.687072163966366},"per_game_all":{"GB2-01":37.69025423298972,"GB2-02":42.84223788715732,"GB2-03":48.17763644007715,"GB2-04":43.53149656792517,"GB2-05":15.144579694395327,"GB2-06":36.79976060895595,"GB2-07":42.559049970772385,"GB2-08":28.925636169821114},"per_game_match_totals_all":{"GB2-01":{"draws":464,"losses":1412,"wins":704},"GB2-02":{"draws":1490,"losses":395,"wins":35},"GB2-03":{"draws":548,"losses":1135,"wins":797},"GB2-04":{"draws":1839,"losses":818,"wins":331},"GB2-05":{"draws":0,"losses":2728,"wins":452},"GB2-06":{"draws":26,"losses":1987,"wins":999},"GB2-07":{"draws":0,"losses":1465,"wins":1185},"GB2-08":{"draws":633,"losses":1664,"wins":393}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":100,"losses":294,"wins":122},"GB2-02":{"draws":354,"losses":97,"wins":29},"GB2-03":{"draws":148,"losses":481,"wins":363},"GB2-04":{"draws":593,"losses":316,"wins":87},"GB2-05":{"draws":0,"losses":880,"wins":180},"GB2-06":{"draws":16,"losses":618,"wins":370},"GB2-07":{"draws":0,"losses":613,"wins":447},"GB2-08":{"draws":137,"losses":323,"wins":78}},"medium":{"GB2-01":{"draws":169,"losses":545,"wins":318},"GB2-02":{"draws":395,"losses":82,"wins":3},"GB2-03":{"draws":313,"losses":454,"wins":225},"GB2-04":{"draws":657,"losses":259,"wins":80},"GB2-05":{"draws":0,"losses":905,"wins":155},"GB2-06":{"draws":5,"losses":891,"wins":108},"GB2-07":{"draws":0,"losses":431,"wins":99},"GB2-08":{"draws":255,"losses":676,"wins":145}},"none":{"GB2-01":{"draws":195,"losses":573,"wins":264},"GB2-02":{"draws":741,"losses":216,"wins":3},"GB2-03":{"draws":87,"losses":200,"wins":209},"GB2-04":{"draws":589,"losses":243,"wins":164},"GB2-05":{"draws":0,"losses":943,"wins":117},"GB2-06":{"draws":5,"losses":478,"wins":521},"GB2-07":{"draws":0,"losses":421,"wins":639},"GB2-08":{"draws":241,"losses":665,"wins":170}}},"per_game_raw_elo_all":{"GB2-01":1350.250844310548,"GB2-02":1416.635786314965,"GB2-03":1415.5684973459445,"GB2-04":1424.6471387442953,"GB2-05":911.5444018220591,"GB2-06":1211.4598014922879,"GB2-07":1349.928745692823,"GB2-08":1146.4304716234296},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1325.6951655540474,"GB2-02":1430.18025472401,"GB2-03":1411.8292013455207,"GB2-04":1398.1945901826316,"GB2-05":971.4954401209724,"GB2-06":1284.4890623119518,"GB2-07":1381.7507451098681,"GB2-08":1155.1510025556995},"medium":{"GB2-01":1382.8095018297138,"GB2-02":1421.2017093686945,"GB2-03":1361.753792753799,"GB2-04":1418.1825775187795,"GB2-05":923.8211737977601,"GB2-06":832.2539614726261,"GB2-07":1056.1922921444643,"GB2-08":1131.7977259924073},"none":{"GB2-01":1342.2478655478826,"GB2-02":1398.5253948521902,"GB2-03":1473.122497938513,"GB2-04":1457.5642485314745,"GB2-05":839.3165915474449,"GB2-06":1517.6363806922861,"GB2-07":1611.8431998241363,"GB2-08":1152.342686322182}},"per_game_tracks":{"highest":{"GB2-01":35.18543541825313,"GB2-02":44.586684031984916,"GB2-03":47.69716231284809,"GB2-04":40.13240437418439,"GB2-05":17.95975568612141,"GB2-06":40.99584541729873,"GB2-07":44.73023851962753,"GB2-08":29.687072163966366},"medium":{"GB2-01":40.97351471913097,"GB2-02":43.42519719087914,"GB2-03":42.08571367513417,"GB2-04":42.68738581686847,"GB2-05":15.560997574146384,"GB2-06":13.151215239080937,"GB2-07":20.843851886124355,"GB2-08":27.650901727544568},"none":{"GB2-01":36.91181256158508,"GB2-02":40.51483243860791,"GB2-03":54.75003333224918,"GB2-04":47.774699512722655,"GB2-05":11.912985822918188,"GB2-06":56.252221170488184,"GB2-07":62.10305950656526,"GB2-08":29.438934617952413}},"program_outcomes":{"all":{"counted_attempts":48,"failed":5,"infra_excluded":0,"success_rate":0.8958333333333334,"too_slow":0,"worked_after_repair":7,"worked_first_time":36,"working":43},"highest":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":1,"worked_first_time":13,"working":14},"medium":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":14,"working":14},"none":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":6,"worked_first_time":9,"working":15}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:09:49Z","reasoning":{"highest":32.636067274895694,"medium":26.780531661300905,"none":39.03544528712054},"reasoning_agg":{"highest":{"max":47.69716231284809,"mean":32.636067274895694,"min":17.592717709126564},"medium":{"max":42.68738581686847,"mean":26.780531661300905,"min":10.421925943062178},"none":{"max":62.10305950656526,"mean":39.03544528712054,"min":11.912985822918188}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"reasoning_variance":12.254913625819633},"working_program_strength":{"all":36.958831446511766,"highest":37.62182474053557,"medium":30.79734722861362,"none":42.45732237038611}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:08b1f95dc978089f","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":0.38761485000000007},"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":0.07206399999999999}},"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":0.5373186},"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":31.260092137291497,"highest":35.285489261608575,"medium":29.024956139161695,"none":29.46983101110422},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":21.479267716886806,"score":21.479267716886806},"GB2-02":{"attempts":3,"playable":41.980003187722076,"score":41.980003187722076},"GB2-03":{"attempts":3,"playable":47.416952003032726,"score":47.416952003032726},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":43.69078487770835,"score":36.61864269552498},"GB2-05":{"attempts":3,"playable":19.066832736232417,"score":19.066832736232417},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":29.51972290067989,"score":23.783190103709448},"GB2-07":{"attempts":3,"playable":35.48308147103602,"score":35.48308147103602},"GB2-08":{"attempts":3,"playable":24.252767184187487,"score":24.252767184187487}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":33.19925604696922,"score":33.19925604696922},"GB2-02":{"attempts":1,"playable":42.050724393185696,"score":42.050724393185696},"GB2-03":{"attempts":1,"playable":45.46198984747758,"score":45.46198984747758},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":42.432853093100235,"score":21.216426546550117},"GB2-05":{"attempts":1,"playable":41.647118049470414,"score":41.647118049470414},"GB2-06":{"attempts":1,"playable":54.139971920217015,"score":54.139971920217015},"GB2-07":{"attempts":1,"playable":18.65653983913404,"score":18.65653983913404},"GB2-08":{"attempts":1,"playable":25.911887449864494,"score":25.911887449864494}},"medium":{"GB2-01":{"attempts":1,"playable":9.43855349356319,"score":9.43855349356319},"GB2-02":{"attempts":1,"playable":42.68533578523171,"score":42.68533578523171},"GB2-03":{"attempts":1,"playable":39.73123781446718,"score":39.73123781446718},"GB2-04":{"attempts":1,"playable":44.88022715793401,"score":44.88022715793401},"GB2-05":{"attempts":1,"playable":10.088749860741556,"score":10.088749860741556},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.437096610489274,"score":8.718548305244637},"GB2-07":{"attempts":1,"playable":56.02076305699269,"score":56.02076305699269},"GB2-08":{"attempts":1,"playable":20.6362336391186,"score":20.6362336391186}},"none":{"GB2-01":{"attempts":1,"playable":21.799993610128006,"score":21.799993610128006},"GB2-02":{"attempts":1,"playable":41.20394938474883,"score":41.20394938474883},"GB2-03":{"attempts":1,"playable":57.057628347153425,"score":57.057628347153425},"GB2-04":{"attempts":1,"playable":43.759274382090815,"score":43.759274382090815},"GB2-05":{"attempts":1,"playable":5.4646302984852815,"score":5.4646302984852815},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.982100171333386,"score":8.491050085666693},"GB2-07":{"attempts":1,"playable":31.77194151698134,"score":31.77194151698134},"GB2-08":{"attempts":1,"playable":26.21018046357936,"score":26.21018046357936}}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-10-31T17:05:04Z","match_totals_all":{"draws":3186,"losses":6938,"wins":2146},"match_totals_tracks":{"highest":{"draws":1086,"losses":2102,"wins":902},"medium":{"draws":999,"losses":2446,"wins":645},"none":{"draws":1101,"losses":2390,"wins":599}},"model_slug":"thinkingmachines-inkling-small","official_rank_by_reasoning":{"highest":54,"medium":69,"none":65},"overall":{"max":57.057628347153425,"mean":31.260092137291497,"min":5.4646302984852815},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":57,"overall_ranking_status":"ranked","per_game":{"GB2-01":33.19925604696922,"GB2-02":42.050724393185696,"GB2-03":45.46198984747758,"GB2-04":42.432853093100235,"GB2-05":41.647118049470414,"GB2-06":54.139971920217015,"GB2-07":18.65653983913404,"GB2-08":25.911887449864494},"per_game_all":{"GB2-01":21.479267716886806,"GB2-02":41.980003187722076,"GB2-03":47.416952003032726,"GB2-04":43.69078487770835,"GB2-05":19.066832736232417,"GB2-06":29.51972290067989,"GB2-07":35.48308147103602,"GB2-08":24.252767184187487},"per_game_match_totals_all":{"GB2-01":{"draws":262,"losses":1106,"wins":180},"GB2-02":{"draws":1154,"losses":282,"wins":4},"GB2-03":{"draws":443,"losses":616,"wins":429},"GB2-04":{"draws":953,"losses":390,"wins":151},"GB2-05":{"draws":0,"losses":1303,"wins":287},"GB2-06":{"draws":13,"losses":1103,"wins":390},"GB2-07":{"draws":0,"losses":1062,"wins":528},"GB2-08":{"draws":361,"losses":1076,"wins":177}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":140,"losses":284,"wins":92},"GB2-02":{"draws":388,"losses":92,"wins":0},"GB2-03":{"draws":94,"losses":242,"wins":160},"GB2-04":{"draws":312,"losses":139,"wins":47},"GB2-05":{"draws":0,"losses":317,"wins":213},"GB2-06":{"draws":11,"losses":246,"wins":245},"GB2-07":{"draws":0,"losses":442,"wins":88},"GB2-08":{"draws":141,"losses":340,"wins":57}},"medium":{"GB2-01":{"draws":60,"losses":442,"wins":14},"GB2-02":{"draws":390,"losses":88,"wins":2},"GB2-03":{"draws":131,"losses":251,"wins":114},"GB2-04":{"draws":304,"losses":131,"wins":63},"GB2-05":{"draws":0,"losses":481,"wins":49},"GB2-06":{"draws":0,"losses":428,"wins":74},"GB2-07":{"draws":0,"losses":245,"wins":285},"GB2-08":{"draws":114,"losses":380,"wins":44}},"none":{"GB2-01":{"draws":62,"losses":380,"wins":74},"GB2-02":{"draws":376,"losses":102,"wins":2},"GB2-03":{"draws":218,"losses":123,"wins":155},"GB2-04":{"draws":337,"losses":120,"wins":41},"GB2-05":{"draws":0,"losses":505,"wins":25},"GB2-06":{"draws":2,"losses":429,"wins":71},"GB2-07":{"draws":0,"losses":375,"wins":155},"GB2-08":{"draws":106,"losses":356,"wins":76}}},"per_game_raw_elo_all":{"GB2-01":1150.2173679042098,"GB2-02":1409.9821168920055,"GB2-03":1408.8921595542524,"GB2-04":1425.9801399024127,"GB2-05":923.6442980259316,"GB2-06":1100.0500613582792,"GB2-07":1253.0806721887473,"GB2-08":1091.0765114010946},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1305.405715988427,"GB2-02":1410.538110706807,"GB2-03":1391.048859846729,"GB2-04":1416.221571985123,"GB2-05":1332.5976242535264,"GB2-06":1483.0036322572723,"GB2-07":1018.8543750137417,"GB2-08":1111.647445335111},"medium":{"GB2-01":969.4100830707903,"GB2-02":1415.4678494651837,"GB2-03":1341.2361328645734,"GB2-04":1435.1973743134367,"GB2-05":795.8923682808904,"GB2-06":912.5816257177894,"GB2-07":1523.840393604955,"GB2-08":1046.4251291853873},"none":{"GB2-01":1175.836304653412,"GB2-02":1403.9403905040265,"GB2-03":1494.3914859514548,"GB2-04":1426.521473408679,"GB2-05":642.4429015433774,"GB2-06":904.5649260997758,"GB2-07":1216.5472479475452,"GB2-08":1115.156959682786}},"per_game_tracks":{"highest":{"GB2-01":33.19925604696922,"GB2-02":42.050724393185696,"GB2-03":45.46198984747758,"GB2-04":42.432853093100235,"GB2-05":41.647118049470414,"GB2-06":54.139971920217015,"GB2-07":18.65653983913404,"GB2-08":25.911887449864494},"medium":{"GB2-01":9.43855349356319,"GB2-02":42.68533578523171,"GB2-03":39.73123781446718,"GB2-04":44.88022715793401,"GB2-05":10.088749860741556,"GB2-06":17.437096610489274,"GB2-07":56.02076305699269,"GB2-08":20.6362336391186},"none":{"GB2-01":21.799993610128006,"GB2-02":41.20394938474883,"GB2-03":57.057628347153425,"GB2-04":43.759274382090815,"GB2-05":5.4646302984852815,"GB2-06":16.982100171333386,"GB2-07":31.77194151698134,"GB2-08":26.21018046357936}},"program_outcomes":{"all":{"counted_attempts":27,"failed":3,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":1,"worked_after_repair":9,"worked_first_time":15,"working":24},"highest":{"counted_attempts":9,"failed":1,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":1,"worked_after_repair":2,"worked_first_time":6,"working":8},"medium":{"counted_attempts":9,"failed":1,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":0,"worked_after_repair":4,"worked_first_time":4,"working":8},"none":{"counted_attempts":9,"failed":1,"infra_excluded":0,"success_rate":0.8888888888888888,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:58:44Z","reasoning":{"highest":35.285489261608575,"medium":29.024956139161695,"none":29.46983101110422},"reasoning_agg":{"highest":{"max":54.139971920217015,"mean":35.285489261608575,"min":18.65653983913404},"medium":{"max":56.02076305699269,"mean":29.024956139161695,"min":8.718548305244637},"none":{"max":57.057628347153425,"mean":29.46983101110422,"min":5.4646302984852815}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":6.26053312244688},"working_program_strength":{"all":32.86117650968572,"highest":37.93754257992733,"medium":30.11477467731727,"none":30.531212271812556}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:812775d72ec59271","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":0.05850166}},"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":0.06659801000000001},"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":0.15725572000000002}},"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":30.000855412297057,"highest":35.60909927565693,"medium":31.25665076912552,"none":23.136816192108714},"first_seen_at":null,"game_gaps":{"highest":{"GB2-06":"failed"},"none":{"GB2-02":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":29.99482450570633,"score":29.99482450570633},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":43.16098966813884,"score":28.77399311209256},"GB2-03":{"attempts":3,"playable":40.83877199476999,"score":40.83877199476999},"GB2-04":{"attempts":3,"playable":45.99684347999795,"score":45.99684347999795},"GB2-05":{"attempts":3,"playable":23.042213836175737,"score":23.042213836175737},"GB2-06":{"attempts":3,"failed_attempts":2,"playable":17.437096610489274,"score":5.812365536829758},"GB2-07":{"attempts":3,"playable":37.28464544591679,"score":37.28464544591679},"GB2-08":{"attempts":3,"playable":28.26318538688732,"score":28.26318538688732}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":31.70706559479027,"score":31.70706559479027},"GB2-02":{"attempts":1,"playable":42.89678214539853,"score":42.89678214539853},"GB2-03":{"attempts":1,"playable":37.94271117028376,"score":37.94271117028376},"GB2-04":{"attempts":1,"playable":49.14768578617863,"score":49.14768578617863},"GB2-05":{"attempts":1,"playable":45.88183823045958,"score":45.88183823045958},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":47.60963911417833,"score":47.60963911417833},"GB2-08":{"attempts":1,"playable":29.687072163966366,"score":29.687072163966366}},"medium":{"GB2-01":{"attempts":1,"playable":22.001200676107132,"score":22.001200676107132},"GB2-02":{"attempts":1,"playable":43.42519719087914,"score":43.42519719087914},"GB2-03":{"attempts":1,"playable":39.83619514464155,"score":39.83619514464155},"GB2-04":{"attempts":1,"playable":45.287519438848605,"score":45.287519438848605},"GB2-05":{"attempts":1,"playable":15.465058417539462,"score":15.465058417539462},"GB2-06":{"attempts":1,"playable":17.437096610489274,"score":17.437096610489274},"GB2-07":{"attempts":1,"playable":37.31090238059962,"score":37.31090238059962},"GB2-08":{"attempts":1,"playable":29.290036293899348,"score":29.290036293899348}},"none":{"GB2-01":{"attempts":1,"playable":36.27620724622159,"score":36.27620724622159},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":44.73740966938467,"score":44.73740966938467},"GB2-04":{"attempts":1,"playable":43.555325214966615,"score":43.555325214966615},"GB2-05":{"attempts":1,"playable":7.77974486052818,"score":7.77974486052818},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":26.93339484297241,"score":26.93339484297241},"GB2-08":{"attempts":1,"playable":25.81244770279624,"score":25.81244770279624}}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-10-31T11:20:56Z","match_totals_all":{"draws":2879,"losses":5900,"wins":2007},"match_totals_tracks":{"highest":{"draws":1136,"losses":1640,"wins":812},"medium":{"draws":1088,"losses":2363,"wins":639},"none":{"draws":655,"losses":1897,"wins":556}},"model_slug":"meta-muse-glimmer-30b","official_rank_by_reasoning":{"highest":53,"medium":67,"none":78},"overall":{"max":49.14768578617863,"mean":30.000855412297057,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.70706559479027,"GB2-02":42.89678214539853,"GB2-03":37.94271117028376,"GB2-04":49.14768578617863,"GB2-05":45.88183823045958,"GB2-07":47.60963911417833,"GB2-08":29.687072163966366},"per_game_all":{"GB2-01":29.99482450570633,"GB2-03":40.83877199476999,"GB2-04":45.99684347999795,"GB2-05":23.042213836175737,"GB2-07":37.28464544591679,"GB2-08":28.26318538688732},"per_game_match_totals_all":{"GB2-01":{"draws":320,"losses":950,"wins":278},"GB2-02":{"draws":787,"losses":168,"wins":5},"GB2-03":{"draws":453,"losses":707,"wins":328},"GB2-04":{"draws":983,"losses":341,"wins":170},"GB2-05":{"draws":0,"losses":1241,"wins":349},"GB2-06":{"draws":0,"losses":428,"wins":74},"GB2-07":{"draws":0,"losses":1037,"wins":553},"GB2-08":{"draws":336,"losses":1028,"wins":250}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":294,"wins":87},"GB2-02":{"draws":388,"losses":88,"wins":4},"GB2-03":{"draws":158,"losses":246,"wins":92},"GB2-04":{"draws":288,"losses":118,"wins":92},"GB2-05":{"draws":0,"losses":295,"wins":235},"GB2-07":{"draws":0,"losses":291,"wins":239},"GB2-08":{"draws":167,"losses":308,"wins":63}},"medium":{"GB2-01":{"draws":90,"losses":365,"wins":61},"GB2-02":{"draws":399,"losses":80,"wins":1},"GB2-03":{"draws":130,"losses":251,"wins":115},"GB2-04":{"draws":342,"losses":110,"wins":46},"GB2-05":{"draws":0,"losses":453,"wins":77},"GB2-06":{"draws":0,"losses":428,"wins":74},"GB2-07":{"draws":0,"losses":346,"wins":184},"GB2-08":{"draws":127,"losses":330,"wins":81}},"none":{"GB2-01":{"draws":95,"losses":291,"wins":130},"GB2-03":{"draws":165,"losses":210,"wins":121},"GB2-04":{"draws":353,"losses":113,"wins":32},"GB2-05":{"draws":0,"losses":493,"wins":37},"GB2-07":{"draws":0,"losses":400,"wins":130},"GB2-08":{"draws":42,"losses":390,"wins":106}}},"per_game_raw_elo_all":{"GB2-01":1268.3070455117831,"GB2-03":1350.8134547461646,"GB2-04":1443.8136946485383,"GB2-05":1011.9331323326246,"GB2-07":1285.2906493437245,"GB2-08":1138.7600279576454},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1289.8465660972165,"GB2-02":1417.1079113853616,"GB2-03":1325.523416968002,"GB2-04":1468.1553837885967,"GB2-05":1386.0057106266663,"GB2-07":1417.5850630264756,"GB2-08":1155.1510025556995},"medium":{"GB2-01":1178.412471367913,"GB2-02":1421.2017093686945,"GB2-03":1342.1542188662136,"GB2-04":1438.3452126386428,"GB2-05":921.9119325295997,"GB2-06":912.5816257177894,"GB2-07":1288.6991507137955,"GB2-08":1150.6548883863798},"none":{"GB2-01":1336.66209907022,"GB2-03":1384.7627284042778,"GB2-04":1424.9404875183757,"GB2-05":727.881753841608,"GB2-07":1149.587734290902,"GB2-08":1110.4741929308568}},"per_game_tracks":{"highest":{"GB2-01":31.70706559479027,"GB2-02":42.89678214539853,"GB2-03":37.94271117028376,"GB2-04":49.14768578617863,"GB2-05":45.88183823045958,"GB2-07":47.60963911417833,"GB2-08":29.687072163966366},"medium":{"GB2-01":22.001200676107132,"GB2-02":43.42519719087914,"GB2-03":39.83619514464155,"GB2-04":45.287519438848605,"GB2-05":15.465058417539462,"GB2-06":17.437096610489274,"GB2-07":37.31090238059962,"GB2-08":29.290036293899348},"none":{"GB2-01":36.27620724622159,"GB2-03":44.73740966938467,"GB2-04":43.555325214966615,"GB2-05":7.77974486052818,"GB2-07":26.93339484297241,"GB2-08":25.81244770279624}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":14,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6}},"provider_color":"#0467DF","provider_company":"Meta","provider_key":"meta","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T01:59:42Z","reasoning":{"highest":35.60909927565693,"medium":31.25665076912552,"none":23.136816192108714},"reasoning_agg":{"highest":{"max":49.14768578617863,"mean":35.60909927565693,"min":0.0},"medium":{"max":45.287519438848605,"mean":31.25665076912552,"min":15.465058417539462},"none":{"max":44.73740966938467,"mean":23.136816192108714,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":12.472283083548216},"working_program_strength":{"all":34.267284161054704,"highest":40.69611345789364,"medium":31.25665076912552,"none":30.849088256144952}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:1529f6ddff8e9ba9","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":0.009085673},"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":0.009855891},"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":0.059539762}},"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":29.90843425040693,"highest":35.21632311420778,"medium":30.456089888510526,"none":24.05288974850248},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"},"none":{"GB2-04":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":38.50084492032479,"score":25.667229946883193},"GB2-02":{"attempts":3,"playable":43.10799475098716,"score":43.10799475098716},"GB2-03":{"attempts":3,"playable":39.5946964244357,"score":39.5946964244357},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":40.48935602369981,"score":26.992904015799876},"GB2-05":{"attempts":3,"playable":29.93983034258821,"score":29.93983034258821},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.16953318087073,"score":16.779688787247153},"GB2-07":{"attempts":3,"playable":27.996247082958373,"score":27.996247082958373},"GB2-08":{"attempts":3,"playable":29.188882652355776,"score":29.188882652355776}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.84772061297107,"score":43.84772061297107},"GB2-03":{"attempts":1,"playable":46.59775293801674,"score":46.59775293801674},"GB2-04":{"attempts":1,"playable":42.432853093100235,"score":42.432853093100235},"GB2-05":{"attempts":1,"playable":58.31371175686749,"score":58.31371175686749},"GB2-06":{"attempts":1,"playable":23.513347639552677,"score":23.513347639552677},"GB2-07":{"attempts":1,"playable":34.26443917732915,"score":34.26443917732915},"GB2-08":{"attempts":1,"playable":32.76075969582489,"score":32.76075969582489}},"medium":{"GB2-01":{"attempts":1,"playable":35.978837160291505,"score":35.978837160291505},"GB2-02":{"attempts":1,"playable":42.36808092226087,"score":42.36808092226087},"GB2-03":{"attempts":1,"playable":35.82836090617413,"score":35.82836090617413},"GB2-04":{"attempts":1,"playable":38.54585895429939,"score":38.54585895429939},"GB2-05":{"attempts":1,"playable":15.656946317856486,"score":15.656946317856486},"GB2-06":{"attempts":1,"playable":26.825718722188785,"score":26.825718722188785},"GB2-07":{"attempts":1,"playable":21.04197199439183,"score":21.04197199439183},"GB2-08":{"attempts":1,"playable":27.402944130621222,"score":27.402944130621222}},"none":{"GB2-01":{"attempts":1,"playable":41.02285268035807,"score":41.02285268035807},"GB2-02":{"attempts":1,"playable":43.108182717729534,"score":43.108182717729534},"GB2-03":{"attempts":1,"playable":36.35797542911624,"score":36.35797542911624},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":15.848832953040649,"score":15.848832953040649},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":28.682330077154134,"score":28.682330077154134},"GB2-08":{"attempts":1,"playable":27.402944130621222,"score":27.402944130621222}}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-10-31T17:00:51Z","match_totals_all":{"draws":2751,"losses":5967,"wins":2036},"match_totals_tracks":{"highest":{"draws":942,"losses":1754,"wins":878},"medium":{"draws":1057,"losses":2416,"wins":617},"none":{"draws":752,"losses":1797,"wins":541}},"model_slug":"openai-gpt-oss-120b","official_rank_by_reasoning":{"highest":55,"medium":68,"none":77},"overall":{"max":58.31371175686749,"mean":29.90843425040693,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":59,"overall_ranking_status":"ranked","per_game":{"GB2-02":43.84772061297107,"GB2-03":46.59775293801674,"GB2-04":42.432853093100235,"GB2-05":58.31371175686749,"GB2-06":23.513347639552677,"GB2-07":34.26443917732915,"GB2-08":32.76075969582489},"per_game_all":{"GB2-02":43.10799475098716,"GB2-03":39.5946964244357,"GB2-05":29.93983034258821,"GB2-07":27.996247082958373,"GB2-08":29.188882652355776},"per_game_match_totals_all":{"GB2-01":{"draws":179,"losses":565,"wins":288},"GB2-02":{"draws":1156,"losses":265,"wins":19},"GB2-03":{"draws":356,"losses":773,"wins":359},"GB2-04":{"draws":650,"losses":284,"wins":62},"GB2-05":{"draws":0,"losses":1133,"wins":457},"GB2-06":{"draws":8,"losses":783,"wins":213},"GB2-07":{"draws":0,"losses":1183,"wins":407},"GB2-08":{"draws":402,"losses":981,"wins":231}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":379,"losses":88,"wins":13},"GB2-03":{"draws":117,"losses":225,"wins":154},"GB2-04":{"draws":326,"losses":132,"wins":40},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":2,"losses":400,"wins":100},"GB2-07":{"draws":0,"losses":362,"wins":168},"GB2-08":{"draws":118,"losses":317,"wins":103}},"medium":{"GB2-01":{"draws":94,"losses":293,"wins":129},"GB2-02":{"draws":381,"losses":94,"wins":5},"GB2-03":{"draws":122,"losses":274,"wins":100},"GB2-04":{"draws":324,"losses":152,"wins":22},"GB2-05":{"draws":0,"losses":452,"wins":78},"GB2-06":{"draws":6,"losses":383,"wins":113},"GB2-07":{"draws":0,"losses":430,"wins":100},"GB2-08":{"draws":130,"losses":338,"wins":70}},"none":{"GB2-01":{"draws":85,"losses":272,"wins":159},"GB2-02":{"draws":396,"losses":83,"wins":1},"GB2-03":{"draws":117,"losses":274,"wins":105},"GB2-05":{"draws":0,"losses":451,"wins":79},"GB2-07":{"draws":0,"losses":391,"wins":139},"GB2-08":{"draws":154,"losses":326,"wins":58}}},"per_game_raw_elo_all":{"GB2-02":1418.7406840467318,"GB2-03":1339.704510709559,"GB2-05":1132.7731516912697,"GB2-07":1161.0893255031363,"GB2-08":1149.2184867843273},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1424.470731628572,"GB2-03":1400.9138966471864,"GB2-04":1416.221571985123,"GB2-05":1542.5835968148824,"GB2-06":1012.9565023504189,"GB2-07":1249.4602094486913,"GB2-08":1189.5511554619081},"medium":{"GB2-01":1333.683461542984,"GB2-02":1413.004832031928,"GB2-03":1306.7334023375029,"GB2-04":1385.6795600510386,"GB2-05":925.891425671282,"GB2-06":1064.5566682965773,"GB2-07":1059.4550719934277,"GB2-08":1129.052152445537},"none":{"GB2-01":1383.2869499157443,"GB2-02":1418.7464884796957,"GB2-03":1311.4662331439877,"GB2-05":929.8444325876443,"GB2-07":1174.3526950672895,"GB2-08":1129.052152445537}},"per_game_tracks":{"highest":{"GB2-02":43.84772061297107,"GB2-03":46.59775293801674,"GB2-04":42.432853093100235,"GB2-05":58.31371175686749,"GB2-06":23.513347639552677,"GB2-07":34.26443917732915,"GB2-08":32.76075969582489},"medium":{"GB2-01":35.978837160291505,"GB2-02":42.36808092226087,"GB2-03":35.82836090617413,"GB2-04":38.54585895429939,"GB2-05":15.656946317856486,"GB2-06":26.825718722188785,"GB2-07":21.04197199439183,"GB2-08":27.402944130621222},"none":{"GB2-01":41.02285268035807,"GB2-02":43.108182717729534,"GB2-03":36.35797542911624,"GB2-05":15.848832953040649,"GB2-07":28.682330077154134,"GB2-08":27.402944130621222}},"program_outcomes":{"all":{"counted_attempts":24,"failed":3,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":5,"worked_first_time":16,"working":21},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:01:43Z","reasoning":{"highest":35.21632311420778,"medium":30.456089888510526,"none":24.05288974850248},"reasoning_agg":{"highest":{"max":58.31371175686749,"mean":35.21632311420778,"min":0.0},"medium":{"max":42.36808092226087,"mean":30.456089888510526,"min":15.656946317856486},"none":{"max":43.108182717729534,"mean":24.05288974850248,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"reasoning_variance":11.163433365705302},"working_program_strength":{"all":34.257945323139325,"highest":40.24722641623747,"medium":30.456089888510526,"none":32.07051966466997}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:ec024dcd325d3c19","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":0.5047206500000001},"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":0.3177278},"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":0.3177278},"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":27.072354356647633,"highest":23.71923786071872,"medium":27.649503374548882,"none":29.848321834675282},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed","GB2-07":"failed"},"medium":{"GB2-03":"failed","GB2-04":"failed","GB2-05":"infra_excluded"},"none":{"GB2-02":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":46.01388569184192,"score":41.74468524817588},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.96523676779266,"score":27.310157845195107},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":29.743179600956704,"score":9.914393200318901},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":41.61564461059521,"score":27.74376307373014},"GB2-05":{"attempts":3,"playable":46.05038585084664,"score":46.05038585084664},"GB2-06":{"attempts":3,"playable":35.49155161478094,"score":35.49155161478094},"GB2-07":{"attempts":5,"failed_attempts":3,"playable":7.453073531131658,"score":4.1422550733835495},"GB2-08":{"attempts":4,"playable":30.315270438849115,"score":30.315270438849115}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":25.615202661996257,"score":12.807601330998128},"GB2-02":{"attempts":2,"playable":41.044246615190424,"score":41.044246615190424},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":1,"playable":41.20691855292778,"score":41.20691855292778},"GB2-05":{"attempts":2,"playable":30.373697545633682,"score":30.373697545633682},"GB2-06":{"attempts":1,"playable":34.237718327417056,"score":34.237718327417056},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":2,"playable":30.083720513582705,"score":30.083720513582705}},"medium":{"GB2-01":{"attempts":1,"playable":57.18669310606269,"score":57.18669310606269},"GB2-02":{"attempts":1,"playable":40.886226920394904,"score":40.886226920394904},"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":55.938398527923994,"score":55.938398527923994},"GB2-07":{"attempts":1,"playable":9.947383378037982,"score":9.947383378037982},"GB2-08":{"attempts":1,"playable":29.587821689422583,"score":29.587821689422583}},"none":{"GB2-01":{"attempts":1,"playable":55.239761307466814,"score":55.239761307466814},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":29.743179600956704,"score":29.743179600956704},"GB2-04":{"attempts":1,"playable":42.02437066826265,"score":42.02437066826265},"GB2-05":{"attempts":1,"playable":61.7270741560596,"score":61.7270741560596},"GB2-06":{"attempts":1,"playable":16.298537989001776,"score":16.298537989001776},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":4.958763684225334,"score":2.479381842112667},"GB2-08":{"attempts":1,"playable":31.27426911354207,"score":31.27426911354207}}},"id":"nvidia/nemotron-3-ultra-550b-a55b","is_recent_addition":false,"last_measured_at":"2026-10-31T16:50:36Z","match_totals_all":{"draws":2785,"losses":5846,"wins":2157},"match_totals_tracks":{"highest":{"draws":1476,"losses":2418,"wins":718},"medium":{"draws":585,"losses":1350,"wins":631},"none":{"draws":724,"losses":2078,"wins":808}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","official_rank_by_reasoning":{"highest":61,"none":62},"overall":{"max":61.7270741560596,"mean":27.072354356647633,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","generation_incomplete"],"overall_official_rank":60,"overall_ranking_status":"partial","per_game":{"GB2-01":25.615202661996257,"GB2-02":41.044246615190424,"GB2-04":41.20691855292778,"GB2-05":30.373697545633682,"GB2-06":34.237718327417056,"GB2-08":30.083720513582705},"per_game_all":{"GB2-01":46.01388569184192,"GB2-06":35.49155161478094,"GB2-08":30.315270438849115},"per_game_match_totals_all":{"GB2-01":{"draws":286,"losses":723,"wins":539},"GB2-02":{"draws":1104,"losses":321,"wins":15},"GB2-03":{"draws":179,"losses":274,"wins":43},"GB2-04":{"draws":692,"losses":252,"wins":52},"GB2-05":{"draws":0,"losses":963,"wins":627},"GB2-06":{"draws":21,"losses":1016,"wins":469},"GB2-07":{"draws":0,"losses":994,"wins":66},"GB2-08":{"draws":503,"losses":1303,"wins":346}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":106,"losses":339,"wins":71},"GB2-02":{"draws":729,"losses":217,"wins":14},"GB2-04":{"draws":352,"losses":125,"wins":21},"GB2-05":{"draws":0,"losses":751,"wins":309},"GB2-06":{"draws":13,"losses":345,"wins":144},"GB2-08":{"draws":276,"losses":641,"wins":159}},"medium":{"GB2-01":{"draws":102,"losses":181,"wins":233},"GB2-02":{"draws":375,"losses":104,"wins":1},"GB2-06":{"draws":4,"losses":240,"wins":258},"GB2-07":{"draws":0,"losses":485,"wins":45},"GB2-08":{"draws":104,"losses":340,"wins":94}},"none":{"GB2-01":{"draws":78,"losses":203,"wins":235},"GB2-03":{"draws":179,"losses":274,"wins":43},"GB2-04":{"draws":340,"losses":127,"wins":31},"GB2-05":{"draws":0,"losses":212,"wins":318},"GB2-06":{"draws":4,"losses":431,"wins":67},"GB2-07":{"draws":0,"losses":509,"wins":21},"GB2-08":{"draws":123,"losses":322,"wins":93}}},"per_game_raw_elo_all":{"GB2-01":1426.600034981412,"GB2-06":1193.838314725545,"GB2-08":1162.20223037066},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1222.4964928078195,"GB2-02":1402.6595313518783,"GB2-04":1406.6564558213183,"GB2-05":1170.2323659806984,"GB2-06":1177.2476001100022,"GB2-08":1159.586688276247},"medium":{"GB2-01":1538.1137311842274,"GB2-02":1401.4581776392768,"GB2-06":1511.9343379091952,"GB2-07":831.648760943063,"GB2-08":1154.0284660208497},"none":{"GB2-01":1519.189880952188,"GB2-03":1250.5183754174843,"GB2-04":1413.0399923730834,"GB2-05":1588.3616621838803,"GB2-06":892.3330061574376,"GB2-07":657.4217601928744,"GB2-08":1172.9915368148831}},"per_game_tracks":{"highest":{"GB2-01":25.615202661996257,"GB2-02":41.044246615190424,"GB2-04":41.20691855292778,"GB2-05":30.373697545633682,"GB2-06":34.237718327417056,"GB2-08":30.083720513582705},"medium":{"GB2-01":57.18669310606269,"GB2-02":40.886226920394904,"GB2-06":55.938398527923994,"GB2-07":9.947383378037982,"GB2-08":29.587821689422583},"none":{"GB2-01":55.239761307466814,"GB2-03":29.743179600956704,"GB2-04":42.02437066826265,"GB2-05":61.7270741560596,"GB2-06":16.298537989001776,"GB2-07":4.958763684225334,"GB2-08":31.27426911354207}},"program_outcomes":{"all":{"counted_attempts":30,"failed":9,"infra_excluded":4,"success_rate":0.7,"too_slow":0,"worked_after_repair":14,"worked_first_time":7,"working":21},"highest":{"counted_attempts":14,"failed":5,"infra_excluded":2,"success_rate":0.6428571428571429,"too_slow":0,"worked_after_repair":7,"worked_first_time":2,"working":9},"medium":{"counted_attempts":7,"failed":2,"infra_excluded":2,"success_rate":0.7142857142857143,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"none":{"counted_attempts":9,"failed":2,"infra_excluded":0,"success_rate":0.7777777777777778,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.71923786071872,"medium":27.64950337454888,"none":29.848321834675282},"reasoning_agg":{"highest":{"max":41.20691855292778,"mean":23.71923786071872,"min":0.0},"medium":{"max":57.18669310606269,"mean":27.64950337454888,"min":0.0},"none":{"max":61.7270741560596,"mean":29.848321834675282,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.129083973956561},"working_program_strength":{"all":35.64537354807777,"highest":33.76025070279132,"medium":38.70930472436844,"none":34.46656521707356}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:e074e027ccf8bdfd","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":0.24908164000000005},"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":0.58845395}},"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":0.5884539500000001},"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":26.539413020786913,"highest":32.72029842984122,"medium":19.190260934818877,"none":27.707679697700634},"first_seen_at":null,"game_gaps":{"medium":{"GB2-02":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":25.964090800727746,"score":25.964090800727746},"GB2-02":{"attempts":5,"failed_attempts":2,"playable":42.79060227792722,"score":21.236716974401844},"GB2-03":{"attempts":5,"playable":44.8253642229872,"score":44.8253642229872},"GB2-04":{"attempts":5,"failed_attempts":1,"playable":42.27857423517644,"score":34.98536183816131},"GB2-05":{"attempts":5,"playable":19.277764716046082,"score":19.277764716046082},"GB2-06":{"attempts":5,"failed_attempts":2,"playable":35.3107175137043,"score":21.666834290472682},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":23.484990350865274,"score":19.68168696457081},"GB2-08":{"attempts":5,"failed_attempts":2,"playable":55.23319862682279,"score":24.677484358927625}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":2,"playable":40.09201336891523,"score":40.09201336891523},"GB2-02":{"attempts":2,"playable":41.83909729055662,"score":41.83909729055662},"GB2-03":{"attempts":2,"playable":47.986793701577845,"score":47.986793701577845},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.759274382090815,"score":21.879637191045408},"GB2-05":{"attempts":2,"playable":16.23260796602975,"score":16.23260796602975},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":54.7091671416833,"score":27.35458357084165},"GB2-07":{"attempts":2,"playable":28.779145449843156,"score":28.779145449843156},"GB2-08":{"attempts":2,"playable":37.59850889992015,"score":37.59850889992015}},"medium":{"GB2-01":{"attempts":1,"playable":17.867141687514636,"score":17.867141687514636},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":36.99261086107749,"score":36.99261086107749},"GB2-04":{"attempts":1,"playable":41.61572525276816,"score":41.61572525276816},"GB2-05":{"attempts":1,"playable":14.121751190481621,"score":14.121751190481621},"GB2-06":{"attempts":1,"playable":24.068853201723215,"score":24.068853201723215},"GB2-07":{"attempts":1,"playable":18.856005284985905,"score":18.856005284985905},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"none":{"GB2-01":{"attempts":2,"playable":19.933117345753377,"score":19.933117345753377},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.742107265297825,"score":21.871053632648913},"GB2-03":{"attempts":2,"playable":49.49668810630626,"score":49.49668810630626},"GB2-04":{"attempts":2,"playable":41.46072307067037,"score":41.46072307067037},"GB2-05":{"attempts":2,"playable":27.478934991626875,"score":27.478934991626875},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":27.15413219770637,"score":13.577066098853185},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":22.819820317766755,"score":11.409910158883378},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":72.86788835372543,"score":36.43394417686272}}},"id":"thinkingmachines/inkling","is_recent_addition":false,"last_measured_at":"2026-10-31T17:13:50Z","match_totals_all":{"draws":4083,"losses":9002,"wins":3297},"match_totals_tracks":{"highest":{"draws":1803,"losses":3780,"wins":1597},"medium":{"draws":691,"losses":2013,"wins":368},"none":{"draws":1589,"losses":3209,"wins":1332}},"model_slug":"thinkingmachines-inkling","official_rank_by_reasoning":{"highest":56,"medium":78,"none":70},"overall":{"max":49.49668810630626,"mean":26.539413020786913,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":61,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.09201336891523,"GB2-02":41.83909729055662,"GB2-03":47.986793701577845,"GB2-04":43.759274382090815,"GB2-05":16.23260796602975,"GB2-06":54.7091671416833,"GB2-07":28.779145449843156,"GB2-08":37.59850889992015},"per_game_all":{"GB2-01":25.964090800727746,"GB2-03":44.8253642229872,"GB2-04":42.27857423517644,"GB2-05":19.277764716046082,"GB2-06":35.3107175137043,"GB2-07":23.484990350865274},"per_game_match_totals_all":{"GB2-01":{"draws":628,"losses":1595,"wins":357},"GB2-02":{"draws":1146,"losses":279,"wins":15},"GB2-03":{"draws":773,"losses":1033,"wins":674},"GB2-04":{"draws":1276,"losses":549,"wins":167},"GB2-05":{"draws":0,"losses":2139,"wins":511},"GB2-06":{"draws":21,"losses":1021,"wins":464},"GB2-07":{"draws":0,"losses":1643,"wins":477},"GB2-08":{"draws":239,"losses":743,"wins":632}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":282,"losses":497,"wins":253},"GB2-02":{"draws":752,"losses":198,"wins":10},"GB2-03":{"draws":213,"losses":447,"wins":332},"GB2-04":{"draws":317,"losses":130,"wins":51},"GB2-05":{"draws":0,"losses":898,"wins":162},"GB2-06":{"draws":7,"losses":245,"wins":250},"GB2-07":{"draws":0,"losses":781,"wins":279},"GB2-08":{"draws":232,"losses":584,"wins":260}},"medium":{"GB2-01":{"draws":61,"losses":400,"wins":55},"GB2-03":{"draws":299,"losses":180,"wins":17},"GB2-04":{"draws":328,"losses":135,"wins":35},"GB2-05":{"draws":0,"losses":460,"wins":70},"GB2-06":{"draws":3,"losses":397,"wins":102},"GB2-07":{"draws":0,"losses":441,"wins":89}},"none":{"GB2-01":{"draws":285,"losses":698,"wins":49},"GB2-02":{"draws":394,"losses":81,"wins":5},"GB2-03":{"draws":261,"losses":406,"wins":325},"GB2-04":{"draws":631,"losses":284,"wins":81},"GB2-05":{"draws":0,"losses":781,"wins":279},"GB2-06":{"draws":11,"losses":379,"wins":112},"GB2-07":{"draws":0,"losses":421,"wins":109},"GB2-08":{"draws":7,"losses":159,"wins":372}}},"per_game_raw_elo_all":{"GB2-01":1214.4973376447808,"GB2-03":1386.610294296672,"GB2-04":1414.983185741271,"GB2-05":987.52216991021,"GB2-06":1194.4789610926925,"GB2-07":1095.3427682591494},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1371.5238413727716,"GB2-02":1408.8914630839859,"GB2-03":1413.0130821494313,"GB2-04":1426.521473408679,"GB2-05":937.562740530093,"GB2-06":1492.1184828843188,"GB2-07":1175.6940924279088,"GB2-08":1246.2564053231927},"medium":{"GB2-01":1122.1220691993256,"GB2-03":1317.1133924087865,"GB2-04":1409.8517781055543,"GB2-05":893.2529803376714,"GB2-06":1021.7098567020246,"GB2-07":1022.367285649756},"none":{"GB2-01":1149.8461023622458,"GB2-02":1423.6539460087445,"GB2-03":1429.7044083317987,"GB2-04":1408.5763057095796,"GB2-05":1131.7507888628659,"GB2-06":1069.608543691734,"GB2-07":1087.966926699783,"GB2-08":1750.4559099195649}},"per_game_tracks":{"highest":{"GB2-01":40.09201336891523,"GB2-02":41.83909729055662,"GB2-03":47.986793701577845,"GB2-04":43.759274382090815,"GB2-05":16.23260796602975,"GB2-06":54.7091671416833,"GB2-07":28.779145449843156,"GB2-08":37.59850889992015},"medium":{"GB2-01":17.867141687514636,"GB2-03":36.99261086107749,"GB2-04":41.61572525276816,"GB2-05":14.121751190481621,"GB2-06":24.068853201723215,"GB2-07":18.856005284985905},"none":{"GB2-01":19.933117345753377,"GB2-02":43.742107265297825,"GB2-03":49.49668810630626,"GB2-04":41.46072307067037,"GB2-05":27.478934991626875,"GB2-06":27.15413219770637,"GB2-07":22.819820317766755,"GB2-08":72.86788835372543}},"program_outcomes":{"all":{"counted_attempts":40,"failed":8,"infra_excluded":6,"success_rate":0.8,"too_slow":0,"worked_after_repair":12,"worked_first_time":20,"working":32},"highest":{"counted_attempts":16,"failed":2,"infra_excluded":6,"success_rate":0.875,"too_slow":0,"worked_after_repair":5,"worked_first_time":9,"working":14},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6},"none":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":7,"working":12}},"provider_color":"#31373D","provider_company":"Thinking Machines","provider_key":"thinkingmachines","provider_text_color":"#f8fafc","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:08:25Z","reasoning":{"highest":32.72029842984122,"medium":19.190260934818877,"none":27.707679697700637},"reasoning_agg":{"highest":{"max":47.986793701577845,"mean":32.72029842984122,"min":16.23260796602975},"medium":{"max":41.61572525276816,"mean":19.190260934818877,"min":0.0},"none":{"max":49.49668810630626,"mean":27.707679697700637,"min":11.409910158883378}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"reasoning_variance":13.530037495022345},"working_program_strength":{"all":34.193589020314086,"highest":38.874576025077104,"medium":25.587014579758502,"none":38.11917645610666}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:f2347384b860bae1","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":0.13713908000000002},"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":0.11342239999999999},"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":0.48605809999999994}},"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":24.181097952061254,"highest":15.519235098831379,"medium":26.45434884446013,"none":30.56970991289225},"first_seen_at":null,"game_gaps":{"highest":{"GB2-02":"failed","GB2-03":"failed","GB2-04":"failed"},"medium":{"GB2-02":"failed","GB2-04":"failed"},"none":{"GB2-05":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":17.700288996602637,"score":17.700288996602637},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":43.6364822250689,"score":14.545494075022967},"GB2-03":{"attempts":3,"failed_attempts":1,"playable":36.091449315991525,"score":24.060966210661018},"GB2-04":{"attempts":3,"failed_attempts":2,"playable":40.18420723706202,"score":13.39473574568734},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":45.0069962546106,"score":30.004664169740398},"GB2-06":{"attempts":3,"playable":42.38074457317639,"score":42.38074457317639},"GB2-07":{"attempts":3,"playable":35.15508134253491,"score":35.15508134253491},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":24.310212754596538,"score":16.20680850306436}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":9.74444304963177,"score":9.74444304963177},"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":39.33396578065394,"score":39.33396578065394},"GB2-06":{"attempts":1,"playable":32.652273123909474,"score":32.652273123909474},"GB2-07":{"attempts":1,"playable":25.176189184025738,"score":25.176189184025738},"GB2-08":{"attempts":1,"playable":17.247009652430126,"score":17.247009652430126}},"medium":{"GB2-01":{"attempts":1,"playable":10.355998781952678,"score":10.355998781952678},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":34.8733401530097,"score":34.8733401530097},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":50.68002672856726,"score":50.68002672856726},"GB2-06":{"attempts":1,"playable":45.337575541423426,"score":45.337575541423426},"GB2-07":{"attempts":1,"playable":39.01443369396503,"score":39.01443369396503},"GB2-08":{"attempts":1,"playable":31.37341585676295,"score":31.37341585676295}},"none":{"GB2-01":{"attempts":1,"playable":33.000425158223464,"score":33.000425158223464},"GB2-02":{"attempts":1,"playable":43.6364822250689,"score":43.6364822250689},"GB2-03":{"attempts":1,"playable":37.30955847897335,"score":37.30955847897335},"GB2-04":{"attempts":1,"playable":40.18420723706202,"score":40.18420723706202},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":49.15238505419628,"score":49.15238505419628},"GB2-07":{"attempts":1,"playable":41.27462114961397,"score":41.27462114961397},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"stepfun/step-3.7-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T16:54:48Z","match_totals_all":{"draws":1615,"losses":5178,"wins":1957},"match_totals_tracks":{"highest":{"draws":151,"losses":1946,"wins":519},"medium":{"draws":488,"losses":1850,"wins":774},"none":{"draws":976,"losses":1382,"wins":664}},"model_slug":"stepfun-step-3-7-flash","official_rank_by_reasoning":{"highest":64,"medium":72,"none":59},"overall":{"max":50.68002672856726,"mean":24.181097952061254,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-01":9.74444304963177,"GB2-05":39.33396578065394,"GB2-06":32.652273123909474,"GB2-07":25.176189184025738,"GB2-08":17.247009652430126},"per_game_all":{"GB2-01":17.700288996602637,"GB2-06":42.38074457317639,"GB2-07":35.15508134253491},"per_game_match_totals_all":{"GB2-01":{"draws":192,"losses":1197,"wins":159},"GB2-02":{"draws":383,"losses":87,"wins":10},"GB2-03":{"draws":285,"losses":525,"wins":182},"GB2-04":{"draws":320,"losses":146,"wins":32},"GB2-05":{"draws":0,"losses":599,"wins":461},"GB2-06":{"draws":47,"losses":910,"wins":549},"GB2-07":{"draws":0,"losses":1071,"wins":519},"GB2-08":{"draws":388,"losses":643,"wins":45}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":27,"losses":457,"wins":32},"GB2-05":{"draws":0,"losses":329,"wins":201},"GB2-06":{"draws":6,"losses":356,"wins":140},"GB2-07":{"draws":0,"losses":409,"wins":121},"GB2-08":{"draws":118,"losses":395,"wins":25}},"medium":{"GB2-01":{"draws":69,"losses":433,"wins":14},"GB2-03":{"draws":137,"losses":271,"wins":88},"GB2-05":{"draws":0,"losses":270,"wins":260},"GB2-06":{"draws":12,"losses":291,"wins":199},"GB2-07":{"draws":0,"losses":337,"wins":193},"GB2-08":{"draws":270,"losses":248,"wins":20}},"none":{"GB2-01":{"draws":96,"losses":307,"wins":113},"GB2-02":{"draws":383,"losses":87,"wins":10},"GB2-03":{"draws":148,"losses":254,"wins":94},"GB2-04":{"draws":320,"losses":146,"wins":32},"GB2-06":{"draws":29,"losses":263,"wins":210},"GB2-07":{"draws":0,"losses":325,"wins":205}}},"per_game_raw_elo_all":{"GB2-01":1090.0188333781848,"GB2-06":1301.1523957750198,"GB2-07":1257.6304811105058},"per_game_raw_elo_tracks":{"highest":{"GB2-01":976.512407583661,"GB2-05":1302.7405232470376,"GB2-06":1153.2804073531006,"GB2-07":1123.9114737630157,"GB2-08":999.8374380953201},"medium":{"GB2-01":990.1948324549496,"GB2-03":1298.1476482219546,"GB2-05":1445.6779039413586,"GB2-06":1345.6762406830496,"GB2-07":1310.2950079875257,"GB2-08":1174.0998939723354},"none":{"GB2-01":1303.349260095944,"GB2-02":1422.8368522963538,"GB2-03":1319.9245224373358,"GB2-04":1398.6338753812252,"GB2-06":1404.5005392889097,"GB2-07":1338.6849615809763}},"per_game_tracks":{"highest":{"GB2-01":9.74444304963177,"GB2-05":39.33396578065394,"GB2-06":32.652273123909474,"GB2-07":25.176189184025738,"GB2-08":17.247009652430126},"medium":{"GB2-01":10.355998781952678,"GB2-03":34.8733401530097,"GB2-05":50.68002672856726,"GB2-06":45.337575541423426,"GB2-07":39.01443369396503,"GB2-08":31.37341585676295},"none":{"GB2-01":33.000425158223464,"GB2-02":43.6364822250689,"GB2-03":37.30955847897335,"GB2-04":40.18420723706202,"GB2-06":49.15238505419628,"GB2-07":41.27462114961397}},"program_outcomes":{"all":{"counted_attempts":24,"failed":7,"infra_excluded":0,"success_rate":0.7083333333333334,"too_slow":0,"worked_after_repair":10,"worked_first_time":7,"working":17},"highest":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":-1,"rank_movement_baseline_at":"2026-10-24T23:55:10Z","reasoning":{"highest":15.519235098831379,"medium":26.45434884446013,"none":30.56970991289225},"reasoning_agg":{"highest":{"max":39.33396578065394,"mean":15.519235098831379,"min":0.0},"medium":{"max":50.68002672856726,"mean":26.45434884446013,"min":0.0},"none":{"max":49.15238505419628,"mean":30.56970991289225,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":15.050474814060872},"working_program_strength":{"all":33.620951500422244,"highest":24.830776158130206,"medium":35.272465125946844,"none":40.75961321718967}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:447435701832db27","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":0.010578220000000001},"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":0.010122239999999998},"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":0.010122240000000001},"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":0.007612509999999999},"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":0.028312969999999993},"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":21.83594165731259,"highest":21.49559934706548,"medium":19.841015274937934,"none":24.17121034993435},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed","GB2-05":"failed"},"medium":{"GB2-01":"failed","GB2-03":"failed"},"none":{"GB2-01":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":27.416858473784206,"score":9.138952824594735},"GB2-02":{"attempts":3,"playable":42.61475111618713,"score":42.61475111618713},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":46.39151177343871,"score":15.463837257812903},"GB2-04":{"attempts":3,"playable":41.40931086693529,"score":41.40931086693529},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":28.263938732089002,"score":18.84262582139267},"GB2-06":{"attempts":3,"playable":18.035979374401432,"score":18.035979374401432},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":12.400759399436975,"score":8.267172932957983},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":31.372354596327863,"score":20.914903064218574}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":27.416858473784206,"score":27.416858473784206},"GB2-02":{"attempts":1,"playable":42.36808092226087,"score":42.36808092226087},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.26293567214617,"score":39.26293567214617},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"playable":15.727972653211541,"score":15.727972653211541},"GB2-07":{"attempts":1,"playable":14.032059551887896,"score":14.032059551887896},"GB2-08":{"attempts":1,"playable":33.15688750323314,"score":33.15688750323314}},"medium":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":43.21386575739794,"score":43.21386575739794},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.79795225888314,"score":40.79795225888314},"GB2-05":{"attempts":1,"playable":16.808269614203017,"score":16.808269614203017},"GB2-06":{"attempts":1,"playable":17.550753632610753,"score":17.550753632610753},"GB2-07":{"attempts":1,"playable":10.769459246986056,"score":10.769459246986056},"GB2-08":{"attempts":1,"playable":29.587821689422583,"score":29.587821689422583}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":42.26230666890257,"score":42.26230666890257},"GB2-03":{"attempts":1,"playable":46.39151177343871,"score":46.39151177343871},"GB2-04":{"attempts":1,"playable":44.16704466977656,"score":44.16704466977656},"GB2-05":{"attempts":1,"playable":39.71960784997499,"score":39.71960784997499},"GB2-06":{"attempts":1,"playable":20.829211837382,"score":20.829211837382},"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":"2026-10-31T17:07:40Z","match_totals_all":{"draws":2749,"losses":4804,"wins":1095},"match_totals_tracks":{"highest":{"draws":991,"losses":1757,"wins":316},"medium":{"draws":882,"losses":1889,"wins":307},"none":{"draws":876,"losses":1158,"wins":472}},"model_slug":"inception-mercury-2-5-preview","official_rank_by_reasoning":{"highest":62,"medium":77,"none":76},"overall":{"max":46.39151177343871,"mean":21.83594165731259,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":63,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.416858473784206,"GB2-02":42.36808092226087,"GB2-04":39.26293567214617,"GB2-06":15.727972653211541,"GB2-07":14.032059551887896,"GB2-08":33.15688750323314},"per_game_all":{"GB2-02":42.61475111618713,"GB2-04":41.40931086693529,"GB2-06":18.035979374401432},"per_game_match_totals_all":{"GB2-01":{"draws":118,"losses":324,"wins":74},"GB2-02":{"draws":1174,"losses":263,"wins":3},"GB2-03":{"draws":113,"losses":228,"wins":155},"GB2-04":{"draws":1060,"losses":370,"wins":64},"GB2-05":{"draws":0,"losses":773,"wins":287},"GB2-06":{"draws":6,"losses":1273,"wins":227},"GB2-07":{"draws":0,"losses":946,"wins":114},"GB2-08":{"draws":278,"losses":627,"wins":171}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":118,"losses":324,"wins":74},"GB2-02":{"draws":387,"losses":91,"wins":2},"GB2-04":{"draws":351,"losses":135,"wins":12},"GB2-06":{"draws":3,"losses":434,"wins":65},"GB2-07":{"draws":0,"losses":465,"wins":65},"GB2-08":{"draws":132,"losses":308,"wins":98}},"medium":{"GB2-02":{"draws":397,"losses":82,"wins":1},"GB2-04":{"draws":336,"losses":135,"wins":27},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":3,"losses":426,"wins":73},"GB2-07":{"draws":0,"losses":481,"wins":49},"GB2-08":{"draws":146,"losses":319,"wins":73}},"none":{"GB2-02":{"draws":390,"losses":90,"wins":0},"GB2-03":{"draws":113,"losses":228,"wins":155},"GB2-04":{"draws":373,"losses":100,"wins":25},"GB2-05":{"draws":0,"losses":327,"wins":203},"GB2-06":{"draws":0,"losses":413,"wins":89}}},"per_game_raw_elo_all":{"GB2-02":1414.917695392304,"GB2-04":1408.166700963134,"GB2-06":922.118981359939},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1243.1765687070997,"GB2-02":1413.004832031928,"GB2-04":1391.3665814575538,"GB2-06":881.9333631540053,"GB2-07":929.4993725719916,"GB2-08":1193.946601786256},"medium":{"GB2-02":1419.565240150129,"GB2-04":1403.4535444665357,"GB2-05":949.234055388904,"GB2-06":914.5695875230206,"GB2-07":853.3987218453036,"GB2-08":1154.0284660208497},"none":{"GB2-02":1412.183013994855,"GB2-03":1399.1210603140603,"GB2-04":1429.6799769653126,"GB2-05":1307.762030261386,"GB2-06":969.8539934027909}},"per_game_tracks":{"highest":{"GB2-01":27.416858473784206,"GB2-02":42.36808092226087,"GB2-04":39.26293567214617,"GB2-06":15.727972653211541,"GB2-07":14.032059551887896,"GB2-08":33.15688750323314},"medium":{"GB2-02":43.21386575739794,"GB2-04":40.79795225888314,"GB2-05":16.808269614203017,"GB2-06":17.550753632610753,"GB2-07":10.769459246986056,"GB2-08":29.587821689422583},"none":{"GB2-02":42.26230666890257,"GB2-03":46.39151177343871,"GB2-04":44.16704466977656,"GB2-05":39.71960784997499,"GB2-06":20.829211837382}},"program_outcomes":{"all":{"counted_attempts":24,"failed":7,"infra_excluded":0,"success_rate":0.7083333333333334,"too_slow":0,"worked_after_repair":4,"worked_first_time":13,"working":17},"highest":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":1,"worked_first_time":5,"working":6},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":0,"worked_first_time":6,"working":6},"none":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":3,"worked_first_time":2,"working":5}},"provider_color":"#CBD5E1","provider_company":"Inception","provider_key":"inception","provider_text_color":"#0b1120","rank_movement":-1,"rank_movement_baseline_at":"2026-10-26T02:00:13Z","reasoning":{"highest":21.49559934706548,"medium":19.841015274937934,"none":24.17121034993435},"reasoning_agg":{"highest":{"max":42.36808092226087,"mean":21.49559934706548,"min":0.0},"medium":{"max":43.21386575739794,"mean":19.841015274937934,"min":0.0},"none":{"max":46.39151177343871,"mean":24.17121034993435,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":4.330195074996414},"working_program_strength":{"all":31.263140907522057,"highest":28.66079912942064,"medium":26.45468703325058,"none":38.673936559894955}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:91c933b0f5011fcf","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":0.08108399999999999},"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":0.04706875}},"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":0.081084},"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":0.04706875},"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":0.348093},"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":16.027201445738978,"highest":16.623891909862063,"medium":20.198410014074618,"none":11.259302413280258},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed"},"medium":{"GB2-02":"failed","GB2-03":"failed"},"none":{"GB2-03":"failed","GB2-04":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":23.602008512380873,"score":15.734672341587249},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":42.68533578523171,"score":14.228445261743902},"GB2-03":{"attempts":3,"failed_attempts":3,"score":0.0},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":43.402270865823525,"score":28.93484724388235},"GB2-05":{"attempts":3,"playable":11.236567441758055,"score":11.236567441758055},"GB2-06":{"attempts":3,"playable":21.894673962584225,"score":21.894673962584225},"GB2-07":{"attempts":3,"playable":14.190911503124168,"score":14.190911503124168},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":32.996240716847815,"score":21.997493811231877}},"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":43.759274382090815,"score":43.759274382090815},"GB2-05":{"attempts":1,"playable":10.665360016457495,"score":10.665360016457495},"GB2-06":{"attempts":1,"playable":17.664373152158113,"score":17.664373152158113},"GB2-07":{"attempts":1,"playable":33.499183597568866,"score":33.499183597568866},"GB2-08":{"attempts":1,"playable":27.402944130621222,"score":27.402944130621222}},"medium":{"GB2-01":{"attempts":1,"playable":33.795514956159195,"score":33.795514956159195},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.04526734955624,"score":43.04526734955624},"GB2-05":{"attempts":1,"playable":17.000162007837822,"score":17.000162007837822},"GB2-06":{"attempts":1,"playable":22.733443150388062,"score":22.733443150388062},"GB2-07":{"attempts":1,"playable":6.423355345581195,"score":6.423355345581195},"GB2-08":{"attempts":1,"playable":38.58953730307441,"score":38.58953730307441}},"none":{"GB2-01":{"attempts":1,"playable":13.408502068602552,"score":13.408502068602552},"GB2-02":{"attempts":1,"playable":42.68533578523171,"score":42.68533578523171},"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":6.044180300978851,"score":6.044180300978851},"GB2-06":{"attempts":1,"playable":25.286205585206506,"score":25.286205585206506},"GB2-07":{"attempts":1,"playable":2.650195566222445,"score":2.650195566222445},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"google/gemini-3.1-flash-lite","is_recent_addition":false,"last_measured_at":"2026-10-31T10:33:01Z","match_totals_all":{"draws":1626,"losses":5641,"wins":1003},"match_totals_tracks":{"highest":{"draws":485,"losses":1720,"wins":393},"medium":{"draws":670,"losses":2006,"wins":438},"none":{"draws":471,"losses":1915,"wins":172}},"model_slug":"google-gemini-3-1-flash-lite","official_rank_by_reasoning":{"highest":63,"medium":76,"none":84},"overall":{"max":43.759274382090815,"mean":16.027201445738978,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":64,"overall_ranking_status":"partial","per_game":{"GB2-04":43.759274382090815,"GB2-05":10.665360016457495,"GB2-06":17.664373152158113,"GB2-07":33.499183597568866,"GB2-08":27.402944130621222},"per_game_all":{"GB2-05":11.236567441758055,"GB2-06":21.894673962584225,"GB2-07":14.190911503124168},"per_game_match_totals_all":{"GB2-01":{"draws":331,"losses":638,"wins":63},"GB2-02":{"draws":378,"losses":94,"wins":8},"GB2-04":{"draws":697,"losses":232,"wins":67},"GB2-05":{"draws":0,"losses":1425,"wins":165},"GB2-06":{"draws":7,"losses":1221,"wins":278},"GB2-07":{"draws":0,"losses":1388,"wins":202},"GB2-08":{"draws":213,"losses":643,"wins":220}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":351,"losses":113,"wins":34},"GB2-05":{"draws":0,"losses":478,"wins":52},"GB2-06":{"draws":0,"losses":427,"wins":75},"GB2-07":{"draws":0,"losses":366,"wins":164},"GB2-08":{"draws":134,"losses":336,"wins":68}},"medium":{"GB2-01":{"draws":242,"losses":230,"wins":44},"GB2-04":{"draws":346,"losses":119,"wins":33},"GB2-05":{"draws":0,"losses":445,"wins":85},"GB2-06":{"draws":3,"losses":403,"wins":96},"GB2-07":{"draws":0,"losses":502,"wins":28},"GB2-08":{"draws":79,"losses":307,"wins":152}},"none":{"GB2-01":{"draws":89,"losses":408,"wins":19},"GB2-02":{"draws":378,"losses":94,"wins":8},"GB2-05":{"draws":0,"losses":502,"wins":28},"GB2-06":{"draws":4,"losses":391,"wins":107},"GB2-07":{"draws":0,"losses":520,"wins":10}}},"per_game_raw_elo_all":{"GB2-05":810.1186543766717,"GB2-06":985.9569793311742,"GB2-07":825.7591582182555},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1426.521473408679,"GB2-05":811.1645208087057,"GB2-06":916.5512744760368,"GB2-07":1239.444621620038,"GB2-08":1129.052152445537},"medium":{"GB2-01":1311.5437650298086,"GB2-04":1420.9825192226035,"GB2-05":953.0409294680746,"GB2-06":1000.5810134023784,"GB2-07":719.1736657326039,"GB2-08":1254.0472692792057},"none":{"GB2-01":1050.3580615731605,"GB2-02":1415.4678494651837,"GB2-05":666.1505128532344,"GB2-06":1040.738650115107,"GB2-07":518.6591873021248}},"per_game_tracks":{"highest":{"GB2-04":43.759274382090815,"GB2-05":10.665360016457495,"GB2-06":17.664373152158113,"GB2-07":33.499183597568866,"GB2-08":27.402944130621222},"medium":{"GB2-01":33.795514956159195,"GB2-04":43.04526734955624,"GB2-05":17.000162007837822,"GB2-06":22.733443150388062,"GB2-07":6.423355345581195,"GB2-08":38.58953730307441},"none":{"GB2-01":13.408502068602552,"GB2-02":42.68533578523171,"GB2-05":6.044180300978851,"GB2-06":25.286205585206506,"GB2-07":2.650195566222445}},"program_outcomes":{"all":{"counted_attempts":24,"failed":8,"infra_excluded":0,"success_rate":0.6666666666666666,"too_slow":0,"worked_after_repair":11,"worked_first_time":5,"working":16},"highest":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":4,"worked_first_time":2,"working":6},"none":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":2,"worked_first_time":3,"working":5}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":16.623891909862063,"medium":20.198410014074618,"none":11.259302413280258},"reasoning_agg":{"highest":{"max":43.759274382090815,"mean":16.623891909862063,"min":0.0},"medium":{"max":43.04526734955624,"mean":20.198410014074618,"min":0.0},"none":{"max":42.68533578523171,"mean":11.259302413280258,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":8.93910760079436},"working_program_strength":{"all":23.84810808970907,"highest":26.5982270557793,"medium":26.93121335209949,"none":18.014883861248414}},{"canonical_public_row_identity":"publication-row.v1:overall:upstage-solar-mini4:68d3619b194c4d1e","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":0.13069025},"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":0.13069024999999998}},"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":{"all":8.176962275753155,"highest":13.807063323075162,"medium":5.649647280700354,"none":5.074176223483948},"first_seen_at":null,"game_gaps":{"all":{"GB2-02":"failed","GB2-03":"failed","GB2-08":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-08":"failed"},"medium":{"GB2-02":"infra_excluded","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":19.280991264205923,"score":6.426997088068641},"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":40.593409787871586,"score":13.531136595957195},"GB2-05":{"attempts":3,"failed_attempts":2,"playable":46.07408509214741,"score":15.358028364049138},"GB2-06":{"attempts":3,"failed_attempts":1,"playable":25.766479130479425,"score":17.17765275365295},"GB2-07":{"attempts":3,"failed_attempts":2,"playable":33.1160029321916,"score":11.038667644063866},"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":46.07408509214741,"score":46.07408509214741},"GB2-06":{"attempts":1,"playable":31.2664185602623,"score":31.2664185602623},"GB2-07":{"attempts":1,"playable":33.1160029321916,"score":33.1160029321916},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}},"medium":{"GB2-01":{"attempts":1,"playable":19.280991264205923,"score":19.280991264205923},"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":20.26653970069655,"score":20.26653970069655},"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":40.593409787871586,"score":40.593409787871586},"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":"2026-10-31T16:50:52Z","match_totals_all":{"draws":437,"losses":1952,"wins":689},"match_totals_tracks":{"highest":{"draws":7,"losses":1024,"wins":531},"medium":{"draws":84,"losses":797,"wins":137},"none":{"draws":346,"losses":131,"wins":21}},"model_slug":"upstage-solar-mini4","overall":{"max":46.07408509214741,"mean":8.176962275753155,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":65,"overall_ranking_status":"partial","per_game":{"GB2-05":46.07408509214741,"GB2-06":31.2664185602623,"GB2-07":33.1160029321916},"per_game_match_totals_all":{"GB2-01":{"draws":79,"losses":384,"wins":53},"GB2-04":{"draws":346,"losses":131,"wins":21},"GB2-05":{"draws":0,"losses":294,"wins":236},"GB2-06":{"draws":12,"losses":775,"wins":217},"GB2-07":{"draws":0,"losses":368,"wins":162}},"per_game_match_totals_tracks":{"highest":{"GB2-05":{"draws":0,"losses":294,"wins":236},"GB2-06":{"draws":7,"losses":362,"wins":133},"GB2-07":{"draws":0,"losses":368,"wins":162}},"medium":{"GB2-01":{"draws":79,"losses":384,"wins":53},"GB2-06":{"draws":5,"losses":413,"wins":84}},"none":{"GB2-04":{"draws":346,"losses":131,"wins":21}}},"per_game_raw_elo_tracks":{"highest":{"GB2-05":1388.4048042483132,"GB2-06":1132.2982876997935,"GB2-07":1234.4013115598823},"medium":{"GB2-01":1142.2417168692618,"GB2-06":960.6085475974899},"none":{"GB2-04":1401.8490903366605}},"per_game_tracks":{"highest":{"GB2-05":46.07408509214741,"GB2-06":31.2664185602623,"GB2-07":33.1160029321916},"medium":{"GB2-01":19.280991264205923,"GB2-06":20.26653970069655},"none":{"GB2-04":40.593409787871586}},"program_outcomes":{"all":{"counted_attempts":23,"failed":17,"infra_excluded":1,"success_rate":0.2608695652173913,"too_slow":0,"worked_after_repair":4,"worked_first_time":2,"working":6},"highest":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":3,"worked_first_time":0,"working":3},"medium":{"counted_attempts":7,"failed":5,"infra_excluded":1,"success_rate":0.2857142857142857,"too_slow":0,"worked_after_repair":1,"worked_first_time":1,"working":2},"none":{"counted_attempts":8,"failed":7,"infra_excluded":0,"success_rate":0.125,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1}},"provider_color":"#805CFB","provider_company":"Upstage","provider_key":"upstage","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":13.807063323075162,"medium":5.649647280700354,"none":5.074176223483948},"reasoning_agg":{"highest":{"max":46.07408509214741,"mean":13.807063323075162,"min":0.0},"medium":{"max":20.26653970069655,"mean":5.649647280700354,"min":0.0},"none":{"max":40.593409787871586,"mean":5.074176223483948,"min":0.0}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"reasoning_variance":8.732887099591213},"working_program_strength":{"all":32.39533693284108,"highest":36.81883552820043,"medium":19.77376548245124,"none":40.593409787871586}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:c5eea150f8336c75","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":0.01810518},"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":0.06705538000000001}},"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":{"all":1.618884746319999,"highest":0.0,"medium":4.8566542389599965,"none":0.0},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"highest":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"medium":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":38.85323391167997,"score":12.951077970559991},"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":38.85323391167997,"score":38.85323391167997},"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":"2026-10-30T06:42:25Z","match_totals_all":{"draws":317,"losses":154,"wins":27},"match_totals_tracks":{"medium":{"draws":317,"losses":154,"wins":27}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":38.85323391167997,"mean":1.618884746319999,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","grouped_stability_incomplete"],"overall_official_rank":66,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-04":{"draws":317,"losses":154,"wins":27}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":317,"losses":154,"wins":27}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1388.1207866521295}},"per_game_tracks":{"medium":{"GB2-04":38.85323391167997}},"program_outcomes":{"all":{"counted_attempts":24,"failed":23,"infra_excluded":0,"success_rate":0.041666666666666664,"too_slow":0,"worked_after_repair":1,"worked_first_time":0,"working":1},"highest":{"counted_attempts":8,"failed":8,"infra_excluded":0,"success_rate":0.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":0,"working":0},"medium":{"counted_attempts":8,"failed":7,"infra_excluded":0,"success_rate":0.125,"too_slow":0,"worked_after_repair":1,"worked_first_time":0,"working":1},"none":{"counted_attempts":8,"failed":8,"infra_excluded":0,"success_rate":0.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":0,"working":0}},"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":4.8566542389599965,"none":0.0},"reasoning_agg":{"highest":{"max":0.0,"mean":0.0,"min":0.0},"medium":{"max":38.85323391167997,"mean":4.8566542389599965,"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":4.8566542389599965},"working_program_strength":{"all":38.85323391167997,"medium":38.85323391167997}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10:3f4dae3fc99a9dcb","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128}},"codegen_cost_by_setting":{"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":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0450808,"mean":0.029576600000000005,"median":0.028589200000000002,"min":0.0192776,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":8},"recorded_attempt_count":8,"run_count":8,"total":0.2366128},"codegen_latency_ms":{"attempt_count":8,"max_ms":215199,"mean_ms":151362.125,"min_ms":97625,"run_count":8},"codegen_latency_ms_by_reasoning":{"none":{"attempt_count":8,"max_ms":215199,"mean_ms":151362.125,"min_ms":97625,"run_count":8}},"codegen_output_tokens":{"attempt_count":8,"output_max":11980,"output_mean":7218.375,"output_min":3411,"run_count":8},"codegen_output_tokens_by_reasoning":{"none":{"attempt_count":8,"output_max":11980,"output_mean":7218.375,"output_min":3411,"run_count":8}},"display_name":"Pareto 26.10","economics":{"all":90.60353977700018,"none":90.60353977700018},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":8,"effective_max_output_tokens":[131072],"finish_reason_observations":8,"finish_reasons":["stop"],"indexed_attempts":8,"output_token_observations":8,"provider_post_attempt_observations":8,"provider_post_attempts":8,"reasoning_token_observations":8,"reconciliation_get_attempt_observations":8,"requested_max_output_token_observations":8,"requested_max_output_tokens":[131072],"total_output_tokens":57747,"total_visible_output_tokens":57747,"visible_token_observations":8},"generation_policy":{"generation_policy":"quality_generation_policy","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","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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":91.44532895354745,"score":91.44532895354745},"GB2-02":{"attempts":1,"playable":79.50316732190169,"score":79.50316732190169},"GB2-03":{"attempts":1,"playable":96.42918026777598,"score":96.42918026777598},"GB2-04":{"attempts":1,"playable":85.65568403222447,"score":85.65568403222447},"GB2-05":{"attempts":1,"playable":91.89970430810443,"score":91.89970430810443},"GB2-06":{"attempts":1,"playable":93.57590133320464,"score":93.57590133320464},"GB2-07":{"attempts":1,"playable":95.1478889039897,"score":95.1478889039897},"GB2-08":{"attempts":1,"playable":91.17146309525297,"score":91.17146309525297}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":91.44532895354745,"score":91.44532895354745},"GB2-02":{"attempts":1,"playable":79.50316732190169,"score":79.50316732190169},"GB2-03":{"attempts":1,"playable":96.42918026777598,"score":96.42918026777598},"GB2-04":{"attempts":1,"playable":85.65568403222447,"score":85.65568403222447},"GB2-05":{"attempts":1,"playable":91.89970430810443,"score":91.89970430810443},"GB2-06":{"attempts":1,"playable":93.57590133320464,"score":93.57590133320464},"GB2-07":{"attempts":1,"playable":95.1478889039897,"score":95.1478889039897},"GB2-08":{"attempts":1,"playable":91.17146309525297,"score":91.17146309525297}}},"id":"unbiased/pareto-26.10","is_recent_addition":false,"last_measured_at":"2026-10-24T16:27:19Z","match_totals_all":{"draws":263,"losses":270,"wins":3557},"match_totals_tracks":{"none":{"draws":263,"losses":270,"wins":3557}},"model_slug":"unbiased-pareto-26-10","official_rank_by_reasoning":{"none":1},"overall":{"max":96.42918026777598,"mean":90.60353977700018,"min":79.50316732190169},"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":0,"losses":50,"wins":466},"GB2-02":{"draws":182,"losses":13,"wins":285},"GB2-03":{"draws":2,"losses":17,"wins":477},"GB2-04":{"draws":62,"losses":45,"wins":391},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":17,"losses":27,"wins":458},"GB2-07":{"draws":0,"losses":22,"wins":508},"GB2-08":{"draws":0,"losses":52,"wins":486}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":0,"losses":50,"wins":466},"GB2-02":{"draws":182,"losses":13,"wins":285},"GB2-03":{"draws":2,"losses":17,"wins":477},"GB2-04":{"draws":62,"losses":45,"wins":391},"GB2-05":{"draws":0,"losses":44,"wins":486},"GB2-06":{"draws":17,"losses":27,"wins":458},"GB2-07":{"draws":0,"losses":22,"wins":508},"GB2-08":{"draws":0,"losses":52,"wins":486}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":2022.5322199917155,"GB2-02":1747.4928501532202,"GB2-03":2305.379922195999,"GB2-04":1837.2379801342677,"GB2-05":2335.823263306526,"GB2-06":2301.009357282398,"GB2-07":2445.659111590625,"GB2-08":2215.585368629504}},"per_game_tracks":{"none":{"GB2-01":91.44532895354745,"GB2-02":79.50316732190169,"GB2-03":96.42918026777598,"GB2-04":85.65568403222447,"GB2-05":91.89970430810443,"GB2-06":93.57590133320464,"GB2-07":95.1478889039897,"GB2-08":91.17146309525297}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":90.60353977700018},"reasoning_agg":{"none":{"max":96.42918026777598,"mean":90.60353977700018,"min":79.50316732190169}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":90.60353977700018,"none":90.60353977700018}},{"canonical_public_row_identity":"publication-row.v1:overall:unbiased-pareto-26-10-preview:4e6d98f15d48c5ea","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":0.24543759999999998}},"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":0.2454376}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0380352,"mean":0.030679699999999997,"median":0.0320616,"min":0.0216328,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":9},"recorded_attempt_count":9,"run_count":8,"total":0.24543759999999998},"codegen_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":{"all":89.67565342362519,"none":89.67565342362519},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":73.76239123090475,"score":73.76239123090475},"GB2-02":{"attempts":1,"playable":91.36882694956621,"score":91.36882694956621},"GB2-03":{"attempts":1,"playable":93.7711312759231,"score":93.7711312759231},"GB2-04":{"attempts":1,"playable":86.49906904571996,"score":86.49906904571996},"GB2-05":{"attempts":1,"playable":94.26041271268998,"score":94.26041271268998},"GB2-06":{"attempts":1,"playable":87.59734406733439,"score":87.59734406733439},"GB2-07":{"attempts":1,"playable":95.89860433452299,"score":95.89860433452299},"GB2-08":{"attempts":1,"playable":94.24744777234017,"score":94.24744777234017}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":73.76239123090475,"score":73.76239123090475},"GB2-02":{"attempts":1,"playable":91.36882694956621,"score":91.36882694956621},"GB2-03":{"attempts":1,"playable":93.7711312759231,"score":93.7711312759231},"GB2-04":{"attempts":1,"playable":86.49906904571996,"score":86.49906904571996},"GB2-05":{"attempts":1,"playable":94.26041271268998,"score":94.26041271268998},"GB2-06":{"attempts":1,"playable":87.59734406733439,"score":87.59734406733439},"GB2-07":{"attempts":1,"playable":95.89860433452299,"score":95.89860433452299},"GB2-08":{"attempts":1,"playable":94.24744777234017,"score":94.24744777234017}}},"id":"unbiased/pareto-26.10-preview","is_recent_addition":false,"last_measured_at":"2026-10-31T16:53:03Z","match_totals_all":{"draws":142,"losses":373,"wins":3575},"match_totals_tracks":{"none":{"draws":142,"losses":373,"wins":3575}},"model_slug":"unbiased-pareto-26-10-preview","official_rank_by_reasoning":{"none":2},"overall":{"max":95.89860433452299,"mean":89.67565342362519,"min":73.76239123090475},"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":16,"losses":138,"wins":362},"GB2-02":{"draws":40,"losses":23,"wins":417},"GB2-03":{"draws":5,"losses":31,"wins":460},"GB2-04":{"draws":43,"losses":50,"wins":405},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":38,"losses":50,"wins":414},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":33,"wins":505}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":16,"losses":138,"wins":362},"GB2-02":{"draws":40,"losses":23,"wins":417},"GB2-03":{"draws":5,"losses":31,"wins":460},"GB2-04":{"draws":43,"losses":50,"wins":405},"GB2-05":{"draws":0,"losses":30,"wins":500},"GB2-06":{"draws":38,"losses":50,"wins":414},"GB2-07":{"draws":0,"losses":18,"wins":512},"GB2-08":{"draws":0,"losses":33,"wins":505}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1715.6746015890055,"GB2-02":1965.0057349841527,"GB2-03":2148.7577865989133,"GB2-04":1851.78736208155,"GB2-05":2462.3264882405238,"GB2-06":2118.540764743192,"GB2-07":2496.232053149095,"GB2-08":2340.761715108957}},"per_game_tracks":{"none":{"GB2-01":73.76239123090475,"GB2-02":91.36882694956621,"GB2-03":93.7711312759231,"GB2-04":86.49906904571996,"GB2-05":94.26041271268998,"GB2-06":87.59734406733439,"GB2-07":95.89860433452299,"GB2-08":94.24744777234017}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8}},"provider_color":"#FF563F","provider_company":"Unbiased","provider_key":"unbiased","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":89.67565342362519},"reasoning_agg":{"none":{"max":95.89860433452299,"mean":89.67565342362519,"min":73.76239123090475}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Provider default (reasoning controls unavailable)"},"reasoning_settings":{"baseline":"default"},"working_program_strength":{"all":89.67565342362519,"none":89.67565342362519}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:95e9c36e7c626276","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":0.455327115},"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":0.455327115},"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":0.05751309}},"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":{"all":62.16052504225202,"medium":73.19367509701941,"none":51.127374987484636},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":46.80586413067046,"score":46.80586413067046},"GB2-02":{"attempts":2,"playable":60.514793338414776,"score":60.514793338414776},"GB2-03":{"attempts":2,"playable":65.52006054411564,"score":65.52006054411564},"GB2-04":{"attempts":2,"playable":50.498700298448234,"score":50.498700298448234},"GB2-05":{"attempts":2,"playable":65.3469044314307,"score":65.3469044314307},"GB2-06":{"attempts":2,"playable":56.833246180093845,"score":56.833246180093845},"GB2-07":{"attempts":2,"playable":66.55529214377438,"score":66.55529214377438},"GB2-08":{"attempts":2,"playable":85.20933927106813,"score":85.20933927106813}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":54.069952914790306,"score":54.069952914790306},"GB2-02":{"attempts":1,"playable":80.88509179924897,"score":80.88509179924897},"GB2-03":{"attempts":1,"playable":86.09554444242988,"score":86.09554444242988},"GB2-04":{"attempts":1,"playable":45.38931488396249,"score":45.38931488396249},"GB2-05":{"attempts":1,"playable":85.00424106756313,"score":85.00424106756313},"GB2-06":{"attempts":1,"playable":57.06839769040767,"score":57.06839769040767},"GB2-07":{"attempts":1,"playable":89.77529038922256,"score":89.77529038922256},"GB2-08":{"attempts":1,"playable":87.26156758853024,"score":87.26156758853024}},"none":{"GB2-01":{"attempts":1,"playable":39.54177534655061,"score":39.54177534655061},"GB2-02":{"attempts":1,"playable":40.144494877580584,"score":40.144494877580584},"GB2-03":{"attempts":1,"playable":44.94457664580139,"score":44.94457664580139},"GB2-04":{"attempts":1,"playable":55.60808571293398,"score":55.60808571293398},"GB2-05":{"attempts":1,"playable":45.68956779529827,"score":45.68956779529827},"GB2-06":{"attempts":1,"playable":56.59809466978002,"score":56.59809466978002},"GB2-07":{"attempts":1,"playable":43.3352938983262,"score":43.3352938983262},"GB2-08":{"attempts":1,"playable":83.15711095360602,"score":83.15711095360602}}},"id":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-10-31T17:02:18Z","match_totals_all":{"draws":1399,"losses":2541,"wins":4240},"match_totals_tracks":{"medium":{"draws":385,"losses":960,"wins":2745},"none":{"draws":1014,"losses":1581,"wins":1495}},"model_slug":"xiaomi-mimo-v2-6-pro","official_rank_by_reasoning":{"medium":9,"none":21},"overall":{"max":89.77529038922256,"mean":62.16052504225202,"min":39.54177534655061},"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":304,"losses":418,"wins":310},"GB2-02":{"draws":442,"losses":171,"wins":347},"GB2-03":{"draws":97,"losses":321,"wins":574},"GB2-04":{"draws":507,"losses":257,"wins":232},"GB2-05":{"draws":0,"losses":381,"wins":679},"GB2-06":{"draws":49,"losses":450,"wins":505},"GB2-07":{"draws":0,"losses":366,"wins":694},"GB2-08":{"draws":0,"losses":177,"wins":899}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":80,"losses":208,"wins":228},"GB2-02":{"draws":88,"losses":53,"wins":339},"GB2-03":{"draws":2,"losses":77,"wins":417},"GB2-04":{"draws":185,"losses":188,"wins":125},"GB2-05":{"draws":0,"losses":85,"wins":445},"GB2-06":{"draws":30,"losses":221,"wins":251},"GB2-07":{"draws":0,"losses":52,"wins":478},"GB2-08":{"draws":0,"losses":76,"wins":462}},"none":{"GB2-01":{"draws":224,"losses":210,"wins":82},"GB2-02":{"draws":354,"losses":118,"wins":8},"GB2-03":{"draws":95,"losses":244,"wins":157},"GB2-04":{"draws":322,"losses":69,"wins":107},"GB2-05":{"draws":0,"losses":296,"wins":234},"GB2-06":{"draws":19,"losses":229,"wins":254},"GB2-07":{"draws":0,"losses":314,"wins":216},"GB2-08":{"draws":0,"losses":101,"wins":437}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1507.9089828507726,"GB2-02":1766.0601466346477,"GB2-03":1891.150071495868,"GB2-04":1439.1316755721748,"GB2-05":2059.926331511094,"GB2-06":1530.3207489797242,"GB2-07":2171.216495591708,"GB2-08":2092.078122006486},"none":{"GB2-01":1368.8994954174336,"GB2-02":1395.647438454895,"GB2-03":1386.5596495846637,"GB2-04":1518.708175360683,"GB2-05":1383.604783185163,"GB2-06":1522.647691868356,"GB2-07":1364.3997196256405,"GB2-08":1982.520390343766}},"per_game_tracks":{"medium":{"GB2-01":54.069952914790306,"GB2-02":80.88509179924897,"GB2-03":86.09554444242988,"GB2-04":45.38931488396249,"GB2-05":85.00424106756313,"GB2-06":57.06839769040767,"GB2-07":89.77529038922256,"GB2-08":87.26156758853024},"none":{"GB2-01":39.54177534655061,"GB2-02":40.144494877580584,"GB2-03":44.94457664580139,"GB2-04":55.60808571293398,"GB2-05":45.68956779529827,"GB2-06":56.59809466978002,"GB2-07":43.3352938983262,"GB2-08":83.15711095360602}},"program_outcomes":{"all":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":14,"working":16},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":8,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":73.19367509701941,"none":51.127374987484636},"reasoning_agg":{"medium":{"max":89.77529038922256,"mean":73.19367509701941,"min":45.38931488396249},"none":{"max":83.15711095360602,"mean":51.127374987484636,"min":39.54177534655061}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":22.066300109534772},"working_program_strength":{"all":62.16052504225202,"medium":73.19367509701941,"none":51.127374987484636}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-5-preview:2cae0f4197b494f3","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":{"all":58.71784070007196,"medium":82.99223214287719,"none":34.44344925726674},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":58.71784070007196,"score":58.71784070007196}},"headline_games_tracks":{"medium":{"GB2-08":{"attempts":1,"playable":82.99223214287719,"score":82.99223214287719}},"none":{"GB2-08":{"attempts":1,"playable":34.44344925726674,"score":34.44344925726674}}},"id":"stepfun/step-5-preview","is_recent_addition":false,"last_measured_at":"2026-10-24T17:49:32Z","match_totals_all":{"draws":277,"losses":331,"wins":468},"match_totals_tracks":{"medium":{"draws":2,"losses":101,"wins":435},"none":{"draws":275,"losses":230,"wins":33}},"model_slug":"stepfun-step-5-preview","overall":{"max":82.99223214287719,"mean":58.71784070007196,"min":34.44344925726674},"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":331,"wins":468}},"per_game_match_totals_tracks":{"medium":{"GB2-08":{"draws":2,"losses":101,"wins":435}},"none":{"GB2-08":{"draws":275,"losses":230,"wins":33}}},"per_game_raw_elo_tracks":{"medium":{"GB2-08":1978.3900101901754},"none":{"GB2-08":1208.1888934161886}},"per_game_tracks":{"medium":{"GB2-08":82.99223214287719},"none":{"GB2-08":34.44344925726674}},"program_outcomes":{"all":{"counted_attempts":2,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":2,"working":2},"medium":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1},"none":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":82.99223214287719,"none":34.44344925726674},"reasoning_agg":{"medium":{"max":82.99223214287719,"mean":82.99223214287719,"min":82.99223214287719},"none":{"max":34.44344925726674,"mean":34.44344925726674,"min":34.44344925726674}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low"},"score_diagnostics":{"reasoning_variance":48.54878288561044},"working_program_strength":{"all":58.71784070007196,"medium":82.99223214287719,"none":34.44344925726674}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:34592c5a4472b8d3","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":0.14258062},"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":0.14258062},"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":0.023437400000000004}},"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":0.16601802000000002},"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":{"all":50.85014409438976,"medium":60.64091900382488,"none":41.05936918495465},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":61.04208042215035,"score":61.04208042215035},"GB2-02":{"attempts":2,"playable":54.60282631572224,"score":54.60282631572224},"GB2-03":{"attempts":2,"playable":51.381298901629634,"score":51.381298901629634},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":59.316535047916055,"score":29.658267523958028},"GB2-05":{"attempts":2,"playable":56.40374585135325,"score":56.40374585135325},"GB2-06":{"attempts":2,"playable":58.243963863910835,"score":58.243963863910835},"GB2-07":{"attempts":2,"playable":62.06464138201126,"score":62.06464138201126},"GB2-08":{"attempts":2,"playable":33.404328494382526,"score":33.404328494382526}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":53.679744589817915,"score":53.679744589817915},"GB2-02":{"attempts":1,"playable":66.73180875200472,"score":66.73180875200472},"GB2-03":{"attempts":1,"playable":62.50685252669661,"score":62.50685252669661},"GB2-04":{"attempts":1,"playable":59.316535047916055,"score":59.316535047916055},"GB2-05":{"attempts":1,"playable":60.02229181264216,"score":60.02229181264216},"GB2-06":{"attempts":1,"playable":65.78982558183658,"score":65.78982558183658},"GB2-07":{"attempts":1,"playable":83.23047516946254,"score":83.23047516946254},"GB2-08":{"attempts":1,"playable":33.84981855022246,"score":33.84981855022246}},"none":{"GB2-01":{"attempts":1,"playable":68.40441625448278,"score":68.40441625448278},"GB2-02":{"attempts":1,"playable":42.47384387943976,"score":42.47384387943976},"GB2-03":{"attempts":1,"playable":40.25574527656265,"score":40.25574527656265},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":52.78519989006434,"score":52.78519989006434},"GB2-06":{"attempts":1,"playable":50.69810214598509,"score":50.69810214598509},"GB2-07":{"attempts":1,"playable":40.89880759455998,"score":40.89880759455998},"GB2-08":{"attempts":1,"playable":32.958838438542585,"score":32.958838438542585}}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T16:55:33Z","match_totals_all":{"draws":1213,"losses":3100,"wins":3369},"match_totals_tracks":{"medium":{"draws":434,"losses":1487,"wins":2169},"none":{"draws":779,"losses":1613,"wins":1200}},"model_slug":"xiaomi-mimo-v2-6-flash","official_rank_by_reasoning":{"medium":23,"none":42},"overall":{"max":83.23047516946254,"mean":50.85014409438976,"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":184,"losses":332,"wins":516},"GB2-02":{"draws":563,"losses":170,"wins":227},"GB2-03":{"draws":183,"losses":427,"wins":382},"GB2-04":{"draws":51,"losses":186,"wins":261},"GB2-05":{"draws":0,"losses":480,"wins":580},"GB2-06":{"draws":33,"losses":442,"wins":529},"GB2-07":{"draws":0,"losses":417,"wins":643},"GB2-08":{"draws":199,"losses":646,"wins":231}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":20,"losses":240,"wins":256},"GB2-02":{"draws":205,"losses":65,"wins":210},"GB2-03":{"draws":31,"losses":189,"wins":276},"GB2-04":{"draws":51,"losses":186,"wins":261},"GB2-05":{"draws":0,"losses":221,"wins":309},"GB2-06":{"draws":18,"losses":180,"wins":304},"GB2-07":{"draws":0,"losses":90,"wins":440},"GB2-08":{"draws":109,"losses":316,"wins":113}},"none":{"GB2-01":{"draws":164,"losses":92,"wins":260},"GB2-02":{"draws":358,"losses":105,"wins":17},"GB2-03":{"draws":152,"losses":238,"wins":106},"GB2-05":{"draws":0,"losses":259,"wins":271},"GB2-06":{"draws":15,"losses":262,"wins":225},"GB2-07":{"draws":0,"losses":327,"wins":203},"GB2-08":{"draws":90,"losses":330,"wins":118}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1504.1585074506716,"GB2-02":1610.0866920790015,"GB2-03":1547.1384736505327,"GB2-04":1548.6843359058662,"GB2-05":1565.2210844693427,"GB2-06":1678.8927820314557,"GB2-07":1966.0070492373231,"GB2-08":1201.622636075387},"none":{"GB2-01":1653.6268861196454,"GB2-02":1413.8262385455776,"GB2-03":1345.820421399197,"GB2-05":1471.9549093460673,"GB2-06":1428.5987066897426,"GB2-07":1333.9807039482296,"GB2-08":1191.749792688846}},"per_game_tracks":{"medium":{"GB2-01":53.679744589817915,"GB2-02":66.73180875200472,"GB2-03":62.50685252669661,"GB2-04":59.316535047916055,"GB2-05":60.02229181264216,"GB2-06":65.78982558183658,"GB2-07":83.23047516946254,"GB2-08":33.84981855022246},"none":{"GB2-01":68.40441625448278,"GB2-02":42.47384387943976,"GB2-03":40.25574527656265,"GB2-05":52.78519989006434,"GB2-06":50.69810214598509,"GB2-07":40.89880759455998,"GB2-08":32.958838438542585}},"program_outcomes":{"all":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":6,"worked_first_time":9,"working":15},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":60.64091900382488,"none":41.05936918495464},"reasoning_agg":{"medium":{"max":83.23047516946254,"mean":60.64091900382488,"min":33.84981855022246},"none":{"max":68.40441625448278,"mean":41.05936918495464,"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":19.581549818870236},"working_program_strength":{"all":53.782956179029384,"medium":60.64091900382488,"none":46.924993354233884}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:6c410ee360c44f11","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":0.3015096},"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":0.30150960000000004},"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":{"all":48.07818271906385,"medium":63.16486619666166,"none":32.99149924146603},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":43.158329758797684,"score":43.158329758797684},"GB2-02":{"attempts":2,"playable":51.01436595039087,"score":51.01436595039087},"GB2-03":{"attempts":2,"playable":55.73037765197621,"score":55.73037765197621},"GB2-04":{"attempts":2,"playable":44.158425698914115,"score":44.158425698914115},"GB2-05":{"attempts":2,"playable":44.431404915293214,"score":44.431404915293214},"GB2-06":{"attempts":2,"playable":67.93556755288458,"score":67.93556755288458},"GB2-07":{"attempts":2,"playable":42.5202195388031,"score":42.5202195388031},"GB2-08":{"attempts":2,"playable":35.676770685451004,"score":35.676770685451004}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":51.72667423366556,"score":51.72667423366556},"GB2-02":{"attempts":1,"playable":58.70919464211466,"score":58.70919464211466},"GB2-03":{"attempts":1,"playable":66.30912685890443,"score":66.30912685890443},"GB2-04":{"attempts":1,"playable":48.23496914970478,"score":48.23496914970478},"GB2-05":{"attempts":1,"playable":71.67075233130596,"score":71.67075233130596},"GB2-06":{"attempts":1,"playable":81.25675071077848,"score":81.25675071077848},"GB2-07":{"attempts":1,"playable":75.29899279365294,"score":75.29899279365294},"GB2-08":{"attempts":1,"playable":52.11246885316646,"score":52.11246885316646}},"none":{"GB2-01":{"attempts":1,"playable":34.589985283929806,"score":34.589985283929806},"GB2-02":{"attempts":1,"playable":43.31953725866707,"score":43.31953725866707},"GB2-03":{"attempts":1,"playable":45.151628445048,"score":45.151628445048},"GB2-04":{"attempts":1,"playable":40.08188224812344,"score":40.08188224812344},"GB2-05":{"attempts":1,"playable":17.192057499280473,"score":17.192057499280473},"GB2-06":{"attempts":1,"playable":54.61438439499068,"score":54.61438439499068},"GB2-07":{"attempts":1,"playable":9.741446283953252,"score":9.741446283953252},"GB2-08":{"attempts":1,"playable":19.241072517735542,"score":19.241072517735542}}},"id":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T17:15:04Z","match_totals_all":{"draws":2068,"losses":3407,"wins":2705},"match_totals_tracks":{"medium":{"draws":1010,"losses":1089,"wins":1991},"none":{"draws":1058,"losses":2318,"wins":714}},"model_slug":"qwen-qwen3-8-flash","official_rank_by_reasoning":{"medium":20,"none":54},"overall":{"max":81.25675071077848,"mean":48.07818271906385,"min":9.741446283953252},"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":292,"losses":461,"wins":279},"GB2-02":{"draws":639,"losses":167,"wins":154},"GB2-03":{"draws":253,"losses":349,"wins":390},"GB2-04":{"draws":622,"losses":262,"wins":112},"GB2-05":{"draws":0,"losses":603,"wins":457},"GB2-06":{"draws":36,"losses":335,"wins":633},"GB2-07":{"draws":0,"losses":622,"wins":438},"GB2-08":{"draws":226,"losses":608,"wins":242}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":180,"losses":170,"wins":166},"GB2-02":{"draws":263,"losses":75,"wins":142},"GB2-03":{"draws":126,"losses":122,"wins":248},"GB2-04":{"draws":291,"losses":121,"wins":86},"GB2-05":{"draws":0,"losses":159,"wins":371},"GB2-06":{"draws":32,"losses":88,"wins":382},"GB2-07":{"draws":0,"losses":136,"wins":394},"GB2-08":{"draws":118,"losses":218,"wins":202}},"none":{"GB2-01":{"draws":112,"losses":291,"wins":113},"GB2-02":{"draws":376,"losses":92,"wins":12},"GB2-03":{"draws":127,"losses":227,"wins":142},"GB2-04":{"draws":331,"losses":141,"wins":26},"GB2-05":{"draws":0,"losses":444,"wins":86},"GB2-06":{"draws":4,"losses":247,"wins":251},"GB2-07":{"draws":0,"losses":486,"wins":44},"GB2-08":{"draws":108,"losses":390,"wins":40}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1485.4620848498218,"GB2-02":1540.9126265584355,"GB2-03":1586.8747435027167,"GB2-04":1461.1012472236557,"GB2-05":1741.3990131655412,"GB2-06":1975.216817559478,"GB2-07":1804.1199056610424,"GB2-08":1413.2517964922347},"none":{"GB2-01":1319.6582754405247,"GB2-02":1420.3836444797973,"GB2-03":1388.3558308477325,"GB2-04":1397.828712008195,"GB2-05":956.8253584652471,"GB2-06":1490.5980883177983,"GB2-07":825.9940376473187,"GB2-08":1027.8252726372834}},"per_game_tracks":{"medium":{"GB2-01":51.72667423366556,"GB2-02":58.70919464211466,"GB2-03":66.30912685890443,"GB2-04":48.23496914970478,"GB2-05":71.67075233130596,"GB2-06":81.25675071077848,"GB2-07":75.29899279365294,"GB2-08":52.11246885316646},"none":{"GB2-01":34.589985283929806,"GB2-02":43.31953725866707,"GB2-03":45.151628445048,"GB2-04":40.08188224812344,"GB2-05":17.192057499280473,"GB2-06":54.61438439499068,"GB2-07":9.741446283953252,"GB2-08":19.241072517735542}},"program_outcomes":{"all":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":6,"worked_first_time":10,"working":16},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":63.16486619666166,"none":32.99149924146603},"reasoning_agg":{"medium":{"max":81.25675071077848,"mean":63.16486619666166,"min":48.23496914970478},"none":{"max":54.61438439499068,"mean":32.99149924146603,"min":9.741446283953252}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":30.173366955195632},"working_program_strength":{"all":48.07818271906385,"medium":63.16486619666166,"none":32.99149924146603}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-large-4-0:2e0f5c88da762ffa","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":1.5289414000000001},"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":0.16924832999999997}},"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":0.16924832999999997},"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":{"all":46.80806191603577,"highest":57.929495755993855,"none":35.68662807607769},"first_seen_at":null,"game_gaps":{"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":47.15562756248444,"score":47.15562756248444},"GB2-02":{"attempts":2,"playable":54.40737848833912,"score":54.40737848833912},"GB2-03":{"attempts":2,"playable":37.15450193682904,"score":37.15450193682904},"GB2-04":{"attempts":2,"playable":52.212685569553784,"score":52.212685569553784},"GB2-05":{"attempts":2,"playable":56.66761787205294,"score":56.66761787205294},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":79.62346402908678,"score":39.81173201454339},"GB2-07":{"attempts":2,"playable":44.49122344068183,"score":44.49122344068183},"GB2-08":{"attempts":2,"playable":42.563728443801644,"score":42.563728443801644}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":34.98699018524562,"score":34.98699018524562},"GB2-02":{"attempts":1,"playable":65.8122688064441,"score":65.8122688064441},"GB2-03":{"attempts":1,"playable":43.49199765441698,"score":43.49199765441698},"GB2-04":{"attempts":1,"playable":65.77704452157377,"score":65.77704452157377},"GB2-05":{"attempts":1,"playable":49.53009398538846,"score":49.53009398538846},"GB2-06":{"attempts":1,"playable":79.62346402908678,"score":79.62346402908678},"GB2-07":{"attempts":1,"playable":79.44710646030721,"score":79.44710646030721},"GB2-08":{"attempts":1,"playable":44.76700040548792,"score":44.76700040548792}},"none":{"GB2-01":{"attempts":1,"playable":59.32426493972326,"score":59.32426493972326},"GB2-02":{"attempts":1,"playable":43.00248817023414,"score":43.00248817023414},"GB2-03":{"attempts":1,"playable":30.81700621924111,"score":30.81700621924111},"GB2-04":{"attempts":1,"playable":38.648326617533804,"score":38.648326617533804},"GB2-05":{"attempts":1,"playable":63.80514175871742,"score":63.80514175871742},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":9.535340421056452,"score":9.535340421056452},"GB2-08":{"attempts":1,"playable":40.36045648211537,"score":40.36045648211537}}},"id":"mistralai/mistral-large-4-0","is_recent_addition":false,"last_measured_at":"2026-10-31T17:03:47Z","match_totals_all":{"draws":2205,"losses":2908,"wins":2565},"match_totals_tracks":{"highest":{"draws":993,"losses":1314,"wins":1783},"none":{"draws":1212,"losses":1594,"wins":782}},"model_slug":"mistralai-mistral-large-4-0","official_rank_by_reasoning":{"highest":35,"none":52},"overall":{"max":79.62346402908678,"mean":46.80806191603577,"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":34.98699018524562,"GB2-02":65.8122688064441,"GB2-03":43.49199765441698,"GB2-04":65.77704452157377,"GB2-05":49.53009398538846,"GB2-06":79.62346402908678,"GB2-07":79.44710646030721,"GB2-08":44.76700040548792},"per_game_match_totals_all":{"GB2-01":{"draws":128,"losses":502,"wins":402},"GB2-02":{"draws":653,"losses":127,"wins":180},"GB2-03":{"draws":344,"losses":485,"wins":163},"GB2-04":{"draws":529,"losses":228,"wins":239},"GB2-05":{"draws":0,"losses":477,"wins":583},"GB2-06":{"draws":36,"losses":95,"wins":371},"GB2-07":{"draws":0,"losses":599,"wins":461},"GB2-08":{"draws":515,"losses":395,"wins":166}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":22,"losses":334,"wins":160},"GB2-02":{"draws":266,"losses":39,"wins":175},"GB2-03":{"draws":179,"losses":209,"wins":108},"GB2-04":{"draws":234,"losses":62,"wins":202},"GB2-05":{"draws":0,"losses":276,"wins":254},"GB2-06":{"draws":36,"losses":95,"wins":371},"GB2-07":{"draws":0,"losses":112,"wins":418},"GB2-08":{"draws":256,"losses":187,"wins":95}},"none":{"GB2-01":{"draws":106,"losses":168,"wins":242},"GB2-02":{"draws":387,"losses":88,"wins":5},"GB2-03":{"draws":165,"losses":276,"wins":55},"GB2-04":{"draws":295,"losses":166,"wins":37},"GB2-05":{"draws":0,"losses":201,"wins":329},"GB2-07":{"draws":0,"losses":487,"wins":43},"GB2-08":{"draws":259,"losses":208,"wins":71}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1323.687359169313,"GB2-02":1601.7235643773279,"GB2-03":1373.9619221299329,"GB2-04":1603.9719703701849,"GB2-05":1431.381991022997,"GB2-06":1941.5372305518047,"GB2-07":1881.8497415627442,"GB2-08":1323.907602455501},"none":{"GB2-01":1559.160457483872,"GB2-02":1417.927381542362,"GB2-03":1260.742149550202,"GB2-04":1386.4939744604646,"GB2-05":1617.4847242225287,"GB2-07":820.2452274611999,"GB2-08":1273.7862495816391}},"per_game_tracks":{"highest":{"GB2-01":34.98699018524562,"GB2-02":65.8122688064441,"GB2-03":43.49199765441698,"GB2-04":65.77704452157377,"GB2-05":49.53009398538846,"GB2-06":79.62346402908678,"GB2-07":79.44710646030721,"GB2-08":44.76700040548792},"none":{"GB2-01":59.32426493972326,"GB2-02":43.00248817023414,"GB2-03":30.81700621924111,"GB2-04":38.648326617533804,"GB2-05":63.80514175871742,"GB2-07":9.535340421056452,"GB2-08":40.36045648211537}},"program_outcomes":{"all":{"counted_attempts":16,"failed":1,"infra_excluded":0,"success_rate":0.9375,"too_slow":0,"worked_after_repair":4,"worked_first_time":11,"working":15},"highest":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":57.929495755993855,"none":35.68662807607769},"reasoning_agg":{"highest":{"max":79.62346402908678,"mean":57.929495755993855,"min":34.98699018524562},"none":{"max":63.80514175871742,"mean":35.68662807607769,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":22.242867679916166},"working_program_strength":{"all":49.357106778612746,"highest":57.929495755993855,"none":40.78471780123164}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:c98700024fdd7cc7","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":0.457564}},"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":0.457564},"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":{"all":42.743953233732505,"none":42.743953233732505},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":61.65113437770828,"score":61.65113437770828},"GB2-02":{"attempts":1,"playable":43.31953725866707,"score":43.31953725866707},"GB2-03":{"attempts":1,"playable":39.20603325373902,"score":39.20603325373902},"GB2-04":{"attempts":1,"playable":38.54585895429939,"score":38.54585895429939},"GB2-05":{"attempts":1,"playable":13.929828693479774,"score":13.929828693479774},"GB2-06":{"attempts":1,"playable":49.733262077626506,"score":49.733262077626506},"GB2-07":{"attempts":1,"playable":47.979134052198184,"score":47.979134052198184},"GB2-08":{"attempts":1,"playable":47.58683720214185,"score":47.58683720214185}},"headline_games_tracks":{"none":{"GB2-01":{"attempts":1,"playable":61.65113437770828,"score":61.65113437770828},"GB2-02":{"attempts":1,"playable":43.31953725866707,"score":43.31953725866707},"GB2-03":{"attempts":1,"playable":39.20603325373902,"score":39.20603325373902},"GB2-04":{"attempts":1,"playable":38.54585895429939,"score":38.54585895429939},"GB2-05":{"attempts":1,"playable":13.929828693479774,"score":13.929828693479774},"GB2-06":{"attempts":1,"playable":49.733262077626506,"score":49.733262077626506},"GB2-07":{"attempts":1,"playable":47.979134052198184,"score":47.979134052198184},"GB2-08":{"attempts":1,"playable":47.58683720214185,"score":47.58683720214185}}},"id":"gpt-4.1","is_recent_addition":false,"last_measured_at":"2026-10-31T17:01:22Z","match_totals_all":{"draws":1024,"losses":1935,"wins":1131},"match_totals_tracks":{"none":{"draws":1024,"losses":1935,"wins":1131}},"model_slug":"gpt-4-1","official_rank_by_reasoning":{"none":33},"overall":{"max":61.65113437770828,"mean":42.743953233732505,"min":13.929828693479774},"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":34,"losses":192,"wins":290},"GB2-02":{"draws":388,"losses":86,"wins":6},"GB2-03":{"draws":118,"losses":260,"wins":118},"GB2-04":{"draws":322,"losses":153,"wins":23},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":5,"losses":272,"wins":225},"GB2-07":{"draws":0,"losses":289,"wins":241},"GB2-08":{"draws":157,"losses":222,"wins":159}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":34,"losses":192,"wins":290},"GB2-02":{"draws":388,"losses":86,"wins":6},"GB2-03":{"draws":118,"losses":260,"wins":118},"GB2-04":{"draws":322,"losses":153,"wins":23},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":5,"losses":272,"wins":225},"GB2-07":{"draws":0,"losses":289,"wins":241},"GB2-08":{"draws":157,"losses":222,"wins":159}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1582.4789565744618,"GB2-02":1420.3836444797973,"GB2-03":1336.6359952180958,"GB2-04":1385.6795600510386,"GB2-05":889.0345132950164,"GB2-06":1413.5357146721688,"GB2-07":1422.1895608442098,"GB2-08":1357.1363668428953}},"per_game_tracks":{"none":{"GB2-01":61.65113437770828,"GB2-02":43.31953725866707,"GB2-03":39.20603325373902,"GB2-04":38.54585895429939,"GB2-05":13.929828693479774,"GB2-06":49.733262077626506,"GB2-07":47.979134052198184,"GB2-08":47.58683720214185}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":42.743953233732505},"reasoning_agg":{"none":{"max":61.65113437770828,"mean":42.743953233732505,"min":13.929828693479774}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"working_program_strength":{"all":42.743953233732505,"none":42.743953233732505}},{"canonical_public_row_identity":"publication-row.v1:overall:elorian-glimpse:b4b918abe4735ef0","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1844346}},"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":0.224169,"mean":0.1412031,"median":0.16102650000000002,"min":0.0567792,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":10},"recorded_attempt_count":10,"run_count":8,"total":1.1296248},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0395322,"mean":0.023054325,"median":0.0214521,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":13},"recorded_attempt_count":13,"run_count":8,"total":0.1844346}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.224169,"mean":0.0821287125,"median":0.0481557,"min":0.0107334,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":23,"run_count":16,"total":1.3140593999999999},"codegen_latency_ms":{"attempt_count":23,"max_ms":561371,"mean_ms":157083.3125,"min_ms":8331,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":10,"max_ms":561371,"mean_ms":286804.25,"min_ms":88263,"run_count":8},"none":{"attempt_count":13,"max_ms":43454,"mean_ms":27362.375,"min_ms":8331,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":73204,"output_mean":25017.0625,"output_min":2066,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":10,"output_max":73204,"output_mean":44953.5,"output_min":17269,"run_count":8},"none":{"attempt_count":13,"output_max":8678,"output_mean":5080.625,"output_min":2066,"run_count":8}},"display_name":"Glimpse","economics":{"all":42.678600683305284,"medium":65.8487425754227,"none":19.50845879118786},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-02":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[235929],"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":[235929],"total_output_tokens":400273,"total_reasoning_output_tokens":316594,"total_visible_output_tokens":83679,"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"elorian/glimpse","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":5,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05","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":{"model_code_failures":1},"GB2-06":{"model_code_failures":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":1,"repaired_rate":0.125}},"headline_games_all":{"GB2-01":{"attempts":2,"playable":47.88591912567163,"score":47.88591912567163},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.84772061297107,"score":21.923860306485533},"GB2-03":{"attempts":2,"playable":45.60947901105497,"score":45.60947901105497},"GB2-04":{"attempts":2,"playable":48.25237657071533,"score":48.25237657071533},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.69371174017365,"score":29.346855870086824},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":84.61228190209295,"score":42.30614095104647},"GB2-07":{"attempts":2,"playable":45.78971150511166,"score":45.78971150511166},"GB2-08":{"attempts":2,"playable":60.314462126269824,"score":60.314462126269824}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":83.0747339989928,"score":83.0747339989928},"GB2-02":{"attempts":1,"playable":43.84772061297107,"score":43.84772061297107},"GB2-03":{"attempts":1,"playable":36.569630069103766,"score":36.569630069103766},"GB2-04":{"attempts":1,"playable":55.80906719609976,"score":55.80906719609976},"GB2-05":{"attempts":1,"playable":58.69371174017365,"score":58.69371174017365},"GB2-06":{"attempts":1,"playable":84.61228190209295,"score":84.61228190209295},"GB2-07":{"attempts":1,"playable":75.1255605082591,"score":75.1255605082591},"GB2-08":{"attempts":1,"playable":89.05723457568851,"score":89.05723457568851}},"none":{"GB2-01":{"attempts":1,"playable":12.697104252350455,"score":12.697104252350455},"GB2-02":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-03":{"attempts":1,"playable":54.649327953006186,"score":54.649327953006186},"GB2-04":{"attempts":1,"playable":40.69568594533089,"score":40.69568594533089},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":16.453862501964228,"score":16.453862501964228},"GB2-08":{"attempts":1,"playable":31.57168967685114,"score":31.57168967685114}}},"id":"elorian/glimpse","is_recent_addition":false,"last_measured_at":"2026-10-27T23:46:32Z","match_totals_all":{"draws":1341,"losses":2618,"wins":2709},"match_totals_tracks":{"medium":{"draws":928,"losses":986,"wins":2176},"none":{"draws":413,"losses":1632,"wins":533}},"model_slug":"elorian-glimpse","official_rank_by_reasoning":{"medium":17,"none":81},"overall":{"max":89.05723457568851,"mean":42.678600683305284,"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":53,"losses":526,"wins":453},"GB2-02":{"draws":381,"losses":87,"wins":12},"GB2-03":{"draws":277,"losses":437,"wins":278},"GB2-04":{"draws":611,"losses":227,"wins":158},"GB2-05":{"draws":0,"losses":228,"wins":302},"GB2-06":{"draws":19,"losses":76,"wins":407},"GB2-07":{"draws":0,"losses":590,"wins":470},"GB2-08":{"draws":0,"losses":447,"wins":629}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":21,"losses":86,"wins":409},"GB2-02":{"draws":381,"losses":87,"wins":12},"GB2-03":{"draws":211,"losses":226,"wins":59},"GB2-04":{"draws":296,"losses":81,"wins":121},"GB2-05":{"draws":0,"losses":228,"wins":302},"GB2-06":{"draws":19,"losses":76,"wins":407},"GB2-07":{"draws":0,"losses":137,"wins":393},"GB2-08":{"draws":0,"losses":65,"wins":473}},"none":{"GB2-01":{"draws":32,"losses":440,"wins":44},"GB2-03":{"draws":66,"losses":211,"wins":219},"GB2-04":{"draws":315,"losses":146,"wins":37},"GB2-07":{"draws":0,"losses":453,"wins":77},"GB2-08":{"draws":0,"losses":382,"wins":156}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1846.017671581837,"GB2-02":1424.470731628572,"GB2-03":1313.3524165231274,"GB2-04":1520.3094001049537,"GB2-05":1547.5758027042773,"GB2-06":2047.8299113873663,"GB2-07":1801.1020519165997,"GB2-08":2145.5945517901146},"none":{"GB2-01":1037.3538816324135,"GB2-03":1472.2054845412504,"GB2-04":1402.6515736907934,"GB2-07":978.3678224727971,"GB2-08":1176.3145502836992}},"per_game_tracks":{"medium":{"GB2-01":83.0747339989928,"GB2-02":43.84772061297107,"GB2-03":36.569630069103766,"GB2-04":55.80906719609976,"GB2-05":58.69371174017365,"GB2-06":84.61228190209295,"GB2-07":75.1255605082591,"GB2-08":89.05723457568851},"none":{"GB2-01":12.697104252350455,"GB2-03":54.649327953006186,"GB2-04":40.69568594533089,"GB2-07":16.453862501964228,"GB2-08":31.57168967685114}},"program_outcomes":{"all":{"counted_attempts":16,"failed":3,"infra_excluded":0,"success_rate":0.8125,"too_slow":0,"worked_after_repair":3,"worked_first_time":10,"working":13},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8},"none":{"counted_attempts":8,"failed":3,"infra_excluded":0,"success_rate":0.625,"too_slow":0,"worked_after_repair":1,"worked_first_time":4,"working":5}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":65.8487425754227,"none":19.50845879118786},"reasoning_agg":{"medium":{"max":89.05723457568851,"mean":65.8487425754227,"min":36.569630069103766},"none":{"max":54.649327953006186,"mean":19.50845879118786,"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":46.34028378423484},"working_program_strength":{"all":48.53113832066164,"medium":65.8487425754227,"none":31.213534065900575}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:ce08b7c528aec083","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":1.2830031539999998}},"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":1.2830031540000002}},"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":1.2830031539999998},"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":{"all":40.578239175152625,"medium":40.578239175152625},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"infra_excluded","GB2-06":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"infra_excluded","GB2-06":"failed"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":38.454362787479965,"score":38.454362787479965},"GB2-02":{"attempts":1,"playable":42.79106467362509,"score":42.79106467362509},"GB2-04":{"attempts":1,"playable":38.54585895429939,"score":38.54585895429939},"GB2-05":{"attempts":1,"playable":52.976373447784006,"score":52.976373447784006},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.52209980348025,"score":43.52209980348025},"GB2-08":{"attempts":1,"playable":67.75791455939965,"score":67.75791455939965}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":38.454362787479965,"score":38.454362787479965},"GB2-02":{"attempts":1,"playable":42.79106467362509,"score":42.79106467362509},"GB2-04":{"attempts":1,"playable":38.54585895429939,"score":38.54585895429939},"GB2-05":{"attempts":1,"playable":52.976373447784006,"score":52.976373447784006},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":43.52209980348025,"score":43.52209980348025},"GB2-08":{"attempts":1,"playable":67.75791455939965,"score":67.75791455939965}}},"id":"moonshotai/kimi-k2.7-code","is_recent_addition":false,"last_measured_at":"2026-10-31T11:20:40Z","match_totals_all":{"draws":662,"losses":1356,"wins":1074},"match_totals_tracks":{"medium":{"draws":662,"losses":1356,"wins":1074}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":67.75791455939965,"mean":40.578239175152625,"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":7,"losses":324,"wins":185},"GB2-02":{"draws":361,"losses":102,"wins":17},"GB2-04":{"draws":290,"losses":169,"wins":39},"GB2-05":{"draws":0,"losses":258,"wins":272},"GB2-07":{"draws":0,"losses":313,"wins":217},"GB2-08":{"draws":4,"losses":190,"wins":344}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":324,"wins":185},"GB2-02":{"draws":361,"losses":102,"wins":17},"GB2-04":{"draws":290,"losses":169,"wins":39},"GB2-05":{"draws":0,"losses":258,"wins":272},"GB2-07":{"draws":0,"losses":313,"wins":217},"GB2-08":{"draws":4,"losses":190,"wins":344}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1358.251983653508,"GB2-02":1416.2880700288058,"GB2-04":1385.6795600510386,"GB2-05":1474.3517145967128,"GB2-07":1366.725900241784,"GB2-08":1651.9660196431014}},"per_game_tracks":{"medium":{"GB2-01":38.454362787479965,"GB2-02":42.79106467362509,"GB2-04":38.54585895429939,"GB2-05":52.976373447784006,"GB2-07":43.52209980348025,"GB2-08":67.75791455939965}},"program_outcomes":{"all":{"counted_attempts":7,"failed":1,"infra_excluded":1,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":6,"worked_first_time":0,"working":6},"medium":{"counted_attempts":7,"failed":1,"infra_excluded":1,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":6,"worked_first_time":0,"working":6}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.578239175152625},"reasoning_agg":{"medium":{"max":67.75791455939965,"mean":40.578239175152625,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":47.341279037678056,"medium":47.341279037678056}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:44a91940833966cb","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":0.14705250000000003}},"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":2.01516825},"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":0.14705250000000003},"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":{"all":38.551052324790376,"medium":48.12471621462463,"none":28.977388434956126},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":51.82152560871375,"score":51.82152560871375},"GB2-02":{"attempts":2,"playable":41.521567574621315,"score":41.521567574621315},"GB2-03":{"attempts":2,"playable":45.04798729077221,"score":45.04798729077221},"GB2-04":{"attempts":2,"playable":43.6061560096664,"score":43.6061560096664},"GB2-05":{"attempts":2,"playable":29.714458117145984,"score":29.714458117145984},"GB2-06":{"attempts":2,"playable":39.69370688545042,"score":39.69370688545042},"GB2-07":{"attempts":2,"playable":26.078574291491854,"score":26.078574291491854},"GB2-08":{"attempts":2,"playable":30.92444282046106,"score":30.92444282046106}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":69.74819372845748,"score":69.74819372845748},"GB2-02":{"attempts":1,"playable":41.41570955124123,"score":41.41570955124123},"GB2-03":{"attempts":1,"playable":44.73740966938467,"score":44.73740966938467},"GB2-04":{"attempts":1,"playable":44.16704466977656,"score":44.16704466977656},"GB2-05":{"attempts":1,"playable":48.187142229883186,"score":48.187142229883186},"GB2-06":{"attempts":1,"playable":47.69341686548094,"score":47.69341686548094},"GB2-07":{"attempts":1,"playable":45.942588018997384,"score":45.942588018997384},"GB2-08":{"attempts":1,"playable":43.10622498377552,"score":43.10622498377552}},"none":{"GB2-01":{"attempts":1,"playable":33.89485748897002,"score":33.89485748897002},"GB2-02":{"attempts":1,"playable":41.6274255980014,"score":41.6274255980014},"GB2-03":{"attempts":1,"playable":45.35856491215976,"score":45.35856491215976},"GB2-04":{"attempts":1,"playable":43.04526734955624,"score":43.04526734955624},"GB2-05":{"attempts":1,"playable":11.241774004408784,"score":11.241774004408784},"GB2-06":{"attempts":1,"playable":31.69399690541989,"score":31.69399690541989},"GB2-07":{"attempts":1,"playable":6.214560563986321,"score":6.214560563986321},"GB2-08":{"attempts":1,"playable":18.7426606571466,"score":18.7426606571466}}},"id":"gpt-5.4-mini","is_recent_addition":false,"last_measured_at":"2026-10-31T16:33:55Z","match_totals_all":{"draws":2299,"losses":4085,"wins":1796},"match_totals_tracks":{"medium":{"draws":965,"losses":1744,"wins":1381},"none":{"draws":1334,"losses":2341,"wins":415}},"model_slug":"gpt-5-4-mini","official_rank_by_reasoning":{"medium":42,"none":67},"overall":{"max":69.74819372845748,"mean":38.551052324790376,"min":6.214560563986321},"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":195,"losses":420,"wins":417},"GB2-02":{"draws":746,"losses":204,"wins":10},"GB2-03":{"draws":546,"losses":309,"wins":137},"GB2-04":{"draws":609,"losses":274,"wins":113},"GB2-05":{"draws":0,"losses":758,"wins":302},"GB2-06":{"draws":17,"losses":640,"wins":347},"GB2-07":{"draws":0,"losses":803,"wins":257},"GB2-08":{"draws":186,"losses":677,"wins":213}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":36,"losses":149,"wins":331},"GB2-02":{"draws":364,"losses":107,"wins":9},"GB2-03":{"draws":165,"losses":210,"wins":121},"GB2-04":{"draws":321,"losses":126,"wins":51},"GB2-05":{"draws":0,"losses":283,"wins":247},"GB2-06":{"draws":10,"losses":280,"wins":212},"GB2-07":{"draws":0,"losses":300,"wins":230},"GB2-08":{"draws":69,"losses":289,"wins":180}},"none":{"GB2-01":{"draws":159,"losses":271,"wins":86},"GB2-02":{"draws":382,"losses":97,"wins":1},"GB2-03":{"draws":381,"losses":99,"wins":16},"GB2-04":{"draws":288,"losses":148,"wins":62},"GB2-05":{"draws":0,"losses":475,"wins":55},"GB2-06":{"draws":7,"losses":360,"wins":135},"GB2-07":{"draws":0,"losses":503,"wins":27},"GB2-08":{"draws":117,"losses":388,"wins":33}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1668.6137800710558,"GB2-02":1405.5926698855671,"GB2-03":1384.7627284042778,"GB2-04":1429.6799769653126,"GB2-05":1414.7005801900393,"GB2-06":1381.9064398654732,"GB2-07":1396.837003210234,"GB2-08":1304.8043123031684},"none":{"GB2-01":1312.5623312973464,"GB2-02":1407.2430050206804,"GB2-03":1390.1513382645255,"GB2-04":1420.9825192226035,"GB2-05":825.9000854547314,"GB2-06":1138.7764676006627,"GB2-07":711.1127244008345,"GB2-08":1020.9973799568928}},"per_game_tracks":{"medium":{"GB2-01":69.74819372845748,"GB2-02":41.41570955124123,"GB2-03":44.73740966938467,"GB2-04":44.16704466977656,"GB2-05":48.187142229883186,"GB2-06":47.69341686548094,"GB2-07":45.942588018997384,"GB2-08":43.10622498377552},"none":{"GB2-01":33.89485748897002,"GB2-02":41.6274255980014,"GB2-03":45.35856491215976,"GB2-04":43.04526734955624,"GB2-05":11.241774004408784,"GB2-06":31.69399690541989,"GB2-07":6.214560563986321,"GB2-08":18.7426606571466}},"program_outcomes":{"all":{"counted_attempts":16,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":13,"working":16},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":1,"worked_first_time":7,"working":8},"none":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":2,"worked_first_time":6,"working":8}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":48.12471621462463,"none":28.977388434956126},"reasoning_agg":{"medium":{"max":69.74819372845748,"mean":48.12471621462463,"min":41.41570955124123},"none":{"max":45.35856491215976,"mean":28.977388434956126,"min":6.214560563986321}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":19.1473277796685},"working_program_strength":{"all":38.551052324790376,"medium":48.12471621462463,"none":28.977388434956126}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:dfe6567492f18ae7","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":1.0777302952},"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":1.0777302952},"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":1.3313309784},"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":{"all":38.03043239054561,"medium":46.314589932739075,"none":29.746274848352147},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-02":"infra_excluded","GB2-03":"infra_excluded"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":54.272047501631526,"score":54.272047501631526},"GB2-02":{"attempts":1,"playable":39.083971859687146,"score":39.083971859687146},"GB2-03":{"attempts":1,"playable":34.4481816327219,"score":34.4481816327219},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":47.42285187369465,"score":23.711425936847323},"GB2-05":{"attempts":2,"playable":22.28191613455834,"score":22.28191613455834},"GB2-06":{"attempts":2,"playable":52.42516592375294,"score":52.42516592375294},"GB2-07":{"attempts":2,"playable":45.645654926717796,"score":45.645654926717796},"GB2-08":{"attempts":2,"playable":22.826582021913353,"score":22.826582021913353}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":71.37628247083427,"score":71.37628247083427},"GB2-04":{"attempts":1,"playable":47.42285187369465,"score":47.42285187369465},"GB2-05":{"attempts":1,"playable":25.260560217696167,"score":25.260560217696167},"GB2-06":{"attempts":1,"playable":67.07286625804785,"score":67.07286625804785},"GB2-07":{"attempts":1,"playable":41.83767980020695,"score":41.83767980020695},"GB2-08":{"attempts":1,"playable":24.917298975954544,"score":24.917298975954544}},"none":{"GB2-01":{"attempts":1,"playable":37.16781253242878,"score":37.16781253242878},"GB2-02":{"attempts":1,"playable":39.083971859687146,"score":39.083971859687146},"GB2-03":{"attempts":1,"playable":34.4481816327219,"score":34.4481816327219},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":19.303272051420514,"score":19.303272051420514},"GB2-06":{"attempts":1,"playable":37.77746558945804,"score":37.77746558945804},"GB2-07":{"attempts":1,"playable":49.453630053228636,"score":49.453630053228636},"GB2-08":{"attempts":1,"playable":20.735865067872165,"score":20.735865067872165}}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-31T10:53:55Z","match_totals_all":{"draws":1192,"losses":3615,"wins":1899},"match_totals_tracks":{"medium":{"draws":437,"losses":1532,"wins":1145},"none":{"draws":755,"losses":2083,"wins":754}},"model_slug":"xiaomi-mimo-v2-5-pro","official_rank_by_reasoning":{"none":64},"overall":{"max":71.37628247083427,"mean":38.03043239054561,"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":191,"losses":397,"wins":444},"GB2-02":{"draws":320,"losses":140,"wins":20},"GB2-03":{"draws":183,"losses":250,"wins":63},"GB2-04":{"draws":249,"losses":146,"wins":103},"GB2-05":{"draws":0,"losses":835,"wins":225},"GB2-06":{"draws":15,"losses":509,"wins":480},"GB2-07":{"draws":0,"losses":603,"wins":457},"GB2-08":{"draws":234,"losses":735,"wins":107}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":63,"losses":127,"wins":326},"GB2-04":{"draws":249,"losses":146,"wins":103},"GB2-05":{"draws":0,"losses":402,"wins":128},"GB2-06":{"draws":12,"losses":176,"wins":314},"GB2-07":{"draws":0,"losses":322,"wins":208},"GB2-08":{"draws":113,"losses":359,"wins":66}},"none":{"GB2-01":{"draws":128,"losses":270,"wins":118},"GB2-02":{"draws":320,"losses":140,"wins":20},"GB2-03":{"draws":183,"losses":250,"wins":63},"GB2-05":{"draws":0,"losses":433,"wins":97},"GB2-06":{"draws":3,"losses":333,"wins":166},"GB2-07":{"draws":0,"losses":281,"wins":249},"GB2-08":{"draws":121,"losses":376,"wins":41}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1687.2516568742567,"GB2-04":1454.8307276395326,"GB2-05":1100.080265896353,"GB2-06":1701.8529839725857,"GB2-07":1345.7233989416823,"GB2-08":1099.8334594243147},"none":{"GB2-01":1345.5460344354801,"GB2-02":1387.2954590338918,"GB2-03":1294.30226839641,"GB2-05":997.0999226473639,"GB2-06":1230.739674220028,"GB2-07":1440.598016910797,"GB2-08":1047.7268393939669}},"per_game_tracks":{"medium":{"GB2-01":71.37628247083427,"GB2-04":47.42285187369465,"GB2-05":25.260560217696167,"GB2-06":67.07286625804785,"GB2-07":41.83767980020695,"GB2-08":24.917298975954544},"none":{"GB2-01":37.16781253242878,"GB2-02":39.083971859687146,"GB2-03":34.4481816327219,"GB2-05":19.303272051420514,"GB2-06":37.77746558945804,"GB2-07":49.453630053228636,"GB2-08":20.735865067872165}},"program_outcomes":{"all":{"counted_attempts":14,"failed":1,"infra_excluded":2,"success_rate":0.9285714285714286,"too_slow":0,"worked_after_repair":9,"worked_first_time":4,"working":13},"medium":{"counted_attempts":6,"failed":0,"infra_excluded":2,"success_rate":1.0,"too_slow":0,"worked_after_repair":6,"worked_first_time":0,"working":6},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.314589932739075,"none":29.746274848352147},"reasoning_agg":{"medium":{"max":71.37628247083427,"mean":46.314589932739075,"min":24.917298975954544},"none":{"max":49.453630053228636,"mean":29.746274848352147,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.568315084386928},"working_program_strength":{"all":40.15516630828505,"medium":46.314589932739075,"none":33.995742683831025}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:f83bb28d1f66f75b","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":0.7288237499999999},"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":0.18239874999999997}},"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":0.7288237499999999},"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":0.18239875}},"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":0.9112224999999999},"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":{"all":37.54367297064253,"medium":40.70676369736568,"none":34.380582243919385},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":42.1878536728506,"score":42.1878536728506},"GB2-02":{"attempts":2,"playable":45.219318495328004,"score":45.219318495328004},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":29.097626975428852,"score":14.548813487714426},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.86123300181614,"score":21.93061650090807},"GB2-05":{"attempts":2,"playable":38.08019711157237,"score":38.08019711157237},"GB2-06":{"attempts":2,"playable":38.141841925076626,"score":38.141841925076626},"GB2-07":{"attempts":2,"playable":68.61253663976883,"score":68.61253663976883},"GB2-08":{"attempts":2,"playable":31.628205931921343,"score":31.628205931921343}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.473361657601853,"score":18.473361657601853},"GB2-02":{"attempts":1,"playable":44.48115340783737,"score":44.48115340783737},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.86123300181614,"score":43.86123300181614},"GB2-05":{"attempts":1,"playable":39.526791834903854,"score":39.526791834903854},"GB2-06":{"attempts":1,"playable":60.89843585620225,"score":60.89843585620225},"GB2-07":{"attempts":1,"playable":75.99221530344897,"score":75.99221530344897},"GB2-08":{"attempts":1,"playable":42.42091851711503,"score":42.42091851711503}},"none":{"GB2-01":{"attempts":1,"playable":65.90234568809935,"score":65.90234568809935},"GB2-02":{"attempts":1,"playable":45.95748358281864,"score":45.95748358281864},"GB2-03":{"attempts":1,"playable":29.097626975428852,"score":29.097626975428852},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":36.63360238824088,"score":36.63360238824088},"GB2-06":{"attempts":1,"playable":15.385247993951005,"score":15.385247993951005},"GB2-07":{"attempts":1,"playable":61.232857976088695,"score":61.232857976088695},"GB2-08":{"attempts":1,"playable":20.835493346727663,"score":20.835493346727663}}},"id":"qwen/qwen3.7-max","is_recent_addition":false,"last_measured_at":"2026-10-31T16:53:27Z","match_totals_all":{"draws":1661,"losses":3415,"wins":2110},"match_totals_tracks":{"medium":{"draws":867,"losses":1559,"wins":1168},"none":{"draws":794,"losses":1856,"wins":942}},"model_slug":"qwen-qwen3-7-max","official_rank_by_reasoning":{"medium":55,"none":53},"overall":{"max":75.99221530344897,"mean":37.54367297064253,"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":223,"losses":503,"wins":306},"GB2-02":{"draws":688,"losses":198,"wins":74},"GB2-03":{"draws":191,"losses":271,"wins":34},"GB2-04":{"draws":274,"losses":151,"wins":73},"GB2-05":{"draws":0,"losses":671,"wins":389},"GB2-06":{"draws":33,"losses":636,"wins":335},"GB2-07":{"draws":0,"losses":348,"wins":712},"GB2-08":{"draws":252,"losses":637,"wins":187}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":69,"losses":393,"wins":54},"GB2-02":{"draws":361,"losses":94,"wins":25},"GB2-04":{"draws":274,"losses":151,"wins":73},"GB2-05":{"draws":0,"losses":328,"wins":202},"GB2-06":{"draws":29,"losses":201,"wins":272},"GB2-07":{"draws":0,"losses":132,"wins":398},"GB2-08":{"draws":134,"losses":260,"wins":144}},"none":{"GB2-01":{"draws":154,"losses":110,"wins":252},"GB2-02":{"draws":327,"losses":104,"wins":49},"GB2-03":{"draws":191,"losses":271,"wins":34},"GB2-05":{"draws":0,"losses":343,"wins":187},"GB2-06":{"draws":4,"losses":435,"wins":63},"GB2-07":{"draws":0,"losses":216,"wins":314},"GB2-08":{"draws":118,"losses":377,"wins":43}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1130.8741345578749,"GB2-02":1429.3654092825145,"GB2-04":1427.3115224704388,"GB2-05":1305.2537099440542,"GB2-06":1594.0168584484895,"GB2-07":1816.3435664337833,"GB2-08":1297.0038663018295},"none":{"GB2-01":1626.541870267168,"GB2-02":1440.7535619430269,"GB2-03":1244.2928974683607,"GB2-05":1266.9941539834274,"GB2-06":875.5960151687821,"GB2-07":1592.508418331117,"GB2-08":1049.025204697847}},"per_game_tracks":{"medium":{"GB2-01":18.473361657601853,"GB2-02":44.48115340783737,"GB2-04":43.86123300181614,"GB2-05":39.526791834903854,"GB2-06":60.89843585620225,"GB2-07":75.99221530344897,"GB2-08":42.42091851711503},"none":{"GB2-01":65.90234568809935,"GB2-02":45.95748358281864,"GB2-03":29.097626975428852,"GB2-05":36.63360238824088,"GB2-06":15.385247993951005,"GB2-07":61.232857976088695,"GB2-08":20.835493346727663}},"program_outcomes":{"all":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":6,"worked_first_time":8,"working":14},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":6,"worked_first_time":1,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":0,"worked_first_time":7,"working":7}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":40.70676369736568,"none":34.380582243919385},"reasoning_agg":{"medium":{"max":75.99221530344897,"mean":40.70676369736568,"min":0.0},"none":{"max":65.90234568809935,"mean":34.380582243919385,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.326181453446296},"working_program_strength":{"all":42.907054823591466,"medium":46.522015654132204,"none":39.29209399305073}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:a7cc431cc0a41ac7","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":0.48528459999999995}},"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":0.48528460000000007}},"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":0.48528459999999995},"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":{"all":34.82580958273446,"medium":34.82580958273446},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":37.36584475240178,"score":37.36584475240178},"GB2-02":{"attempts":1,"playable":43.742107265297825,"score":43.742107265297825},"GB2-03":{"attempts":1,"playable":28.98994366750577,"score":28.98994366750577},"GB2-04":{"attempts":1,"playable":40.69568594533089,"score":40.69568594533089},"GB2-05":{"attempts":1,"playable":50.29684037630487,"score":50.29684037630487},"GB2-06":{"attempts":1,"playable":33.18238031445118,"score":33.18238031445118},"GB2-07":{"attempts":1,"playable":15.043638046684018,"score":15.043638046684018},"GB2-08":{"attempts":1,"playable":29.290036293899348,"score":29.290036293899348}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":37.36584475240178,"score":37.36584475240178},"GB2-02":{"attempts":1,"playable":43.742107265297825,"score":43.742107265297825},"GB2-03":{"attempts":1,"playable":28.98994366750577,"score":28.98994366750577},"GB2-04":{"attempts":1,"playable":40.69568594533089,"score":40.69568594533089},"GB2-05":{"attempts":1,"playable":50.29684037630487,"score":50.29684037630487},"GB2-06":{"attempts":1,"playable":33.18238031445118,"score":33.18238031445118},"GB2-07":{"attempts":1,"playable":15.043638046684018,"score":15.043638046684018},"GB2-08":{"attempts":1,"playable":29.290036293899348,"score":29.290036293899348}}},"id":"x-ai/grok-build-0.1","is_recent_addition":false,"last_measured_at":"2026-10-31T15:53:43Z","match_totals_all":{"draws":1087,"losses":2220,"wins":783},"match_totals_tracks":{"medium":{"draws":1087,"losses":2220,"wins":783}},"model_slug":"x-ai-grok-build-0-1","official_rank_by_reasoning":{"medium":62},"overall":{"max":50.29684037630487,"mean":34.82580958273446,"min":15.043638046684018},"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":100,"losses":283,"wins":133},"GB2-02":{"draws":384,"losses":86,"wins":10},"GB2-03":{"draws":130,"losses":302,"wins":64},"GB2-04":{"draws":337,"losses":135,"wins":26},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-06":{"draws":3,"losses":355,"wins":144},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":133,"losses":327,"wins":78}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":100,"losses":283,"wins":133},"GB2-02":{"draws":384,"losses":86,"wins":10},"GB2-03":{"draws":130,"losses":302,"wins":64},"GB2-04":{"draws":337,"losses":135,"wins":26},"GB2-05":{"draws":0,"losses":272,"wins":258},"GB2-06":{"draws":3,"losses":355,"wins":144},"GB2-07":{"draws":0,"losses":460,"wins":70},"GB2-08":{"draws":133,"losses":327,"wins":78}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1347.510146514759,"GB2-02":1423.6539460087445,"GB2-03":1243.2482722525738,"GB2-04":1402.6515736907934,"GB2-05":1440.9114218805828,"GB2-06":1161.2970926678724,"GB2-07":950.5520614879018,"GB2-08":1150.6548883863798}},"per_game_tracks":{"medium":{"GB2-01":37.36584475240178,"GB2-02":43.742107265297825,"GB2-03":28.98994366750577,"GB2-04":40.69568594533089,"GB2-05":50.29684037630487,"GB2-06":33.18238031445118,"GB2-07":15.043638046684018,"GB2-08":29.290036293899348}},"program_outcomes":{"all":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":8,"worked_first_time":0,"working":8},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":8,"worked_first_time":0,"working":8}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.82580958273446},"reasoning_agg":{"medium":{"max":50.29684037630487,"mean":34.82580958273446,"min":15.043638046684018}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":34.82580958273446,"medium":34.82580958273446}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-1-flash:1c5b561ce24b9b78","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":{"all":33.45390440799602,"none":33.45390440799602},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":33.45390440799602,"score":33.45390440799602}},"headline_games_tracks":{"none":{"GB2-08":{"attempts":1,"playable":33.45390440799602,"score":33.45390440799602}}},"id":"inclusionai/ling-3.1-flash","is_recent_addition":false,"last_measured_at":"2026-10-24T14:05:01Z","match_totals_all":{"draws":287,"losses":229,"wins":22},"match_totals_tracks":{"none":{"draws":287,"losses":229,"wins":22}},"model_slug":"inclusionai-ling-3-1-flash","overall":{"max":33.45390440799602,"mean":33.45390440799602,"min":33.45390440799602},"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":229,"wins":22}},"per_game_match_totals_tracks":{"none":{"GB2-08":{"draws":287,"losses":229,"wins":22}}},"per_game_raw_elo_tracks":{"none":{"GB2-08":1197.238631167565}},"per_game_tracks":{"none":{"GB2-08":33.45390440799602}},"program_outcomes":{"all":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1},"none":{"counted_attempts":1,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":33.45390440799602},"reasoning_agg":{"none":{"max":33.45390440799602,"mean":33.45390440799602,"min":33.45390440799602}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning disabled"},"reasoning_settings":{"baseline":"none"},"working_program_strength":{"all":33.45390440799602,"none":33.45390440799602}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:ecc8f58110ed6507","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":0.04917795999999999},"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":0.04176385999999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":16,"cost_basis_counts":{"provider_reported":68},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0068074,"mean":0.0032179299999999995,"median":0.00314426,"min":0.0012446800000000002,"recorded_attempt_count":68,"run_count":28,"total":0.09094181999999999},"codegen_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":{"all":31.62839676127627,"medium":31.472577473908814,"none":31.78421604864373},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-07":"too_slow"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":45.64550005339221,"score":35.414455863916245},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":41.89149308593776,"score":31.669936355839035},"GB2-03":{"attempts":4,"playable":39.42608282625313,"score":39.42608282625313},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.286522511248776,"score":20.143261255624388},"GB2-05":{"attempts":4,"playable":38.23789916222161,"score":38.23789916222161},"GB2-06":{"attempts":2,"playable":20.153512954712276,"score":20.153512954712276},"GB2-07":{"attempts":2,"playable":45.21717009070224,"score":45.21717009070224},"GB2-08":{"attempts":4,"playable":29.637151889337982,"score":29.637151889337982}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":40.924176757903865,"score":20.462088378951933},"GB2-02":{"attempts":2,"playable":42.89675925148062,"score":42.89675925148062},"GB2-03":{"attempts":2,"playable":39.348973195368174,"score":39.348973195368174},"GB2-04":{"attempts":1,"playable":40.286522511248776,"score":40.286522511248776},"GB2-05":{"attempts":2,"playable":28.072963470789123,"score":28.072963470789123},"GB2-06":{"attempts":1,"playable":19.70274607625053,"score":19.70274607625053},"GB2-08":{"attempts":2,"playable":29.537989433272568,"score":29.537989433272568}},"none":{"GB2-01":{"attempts":2,"playable":50.36682334888055,"score":50.36682334888055},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.886226920394904,"score":20.443113460197452},"GB2-03":{"attempts":2,"playable":39.503192457138084,"score":39.503192457138084},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":2,"playable":48.4028348536541,"score":48.4028348536541},"GB2-06":{"attempts":1,"playable":20.60427983317402,"score":20.60427983317402},"GB2-07":{"attempts":2,"playable":45.21717009070224,"score":45.21717009070224},"GB2-08":{"attempts":2,"playable":29.736314345403397,"score":29.736314345403397}}},"id":"poolside/laguna-s-2.1","is_recent_addition":false,"last_measured_at":"2026-10-31T16:44:14Z","match_totals_all":{"draws":2818,"losses":6212,"wins":2776},"match_totals_tracks":{"medium":{"draws":1705,"losses":2946,"wins":953},"none":{"draws":1113,"losses":3266,"wins":1823}},"model_slug":"poolside-laguna-s-2-1","official_rank_by_reasoning":{"medium":66,"none":56},"overall":{"max":50.36682334888055,"mean":31.62839676127627,"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":251,"losses":723,"wins":574},"GB2-02":{"draws":1131,"losses":290,"wins":19},"GB2-03":{"draws":651,"losses":946,"wins":387},"GB2-04":{"draws":297,"losses":157,"wins":44},"GB2-05":{"draws":0,"losses":1335,"wins":785},"GB2-06":{"draws":4,"losses":830,"wins":170},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":484,"losses":1325,"wins":343}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":86,"losses":272,"wins":158},"GB2-02":{"draws":788,"losses":170,"wins":2},"GB2-03":{"draws":303,"losses":485,"wins":204},"GB2-04":{"draws":297,"losses":157,"wins":44},"GB2-05":{"draws":0,"losses":775,"wins":285},"GB2-06":{"draws":2,"losses":417,"wins":83},"GB2-08":{"draws":229,"losses":670,"wins":177}},"none":{"GB2-01":{"draws":165,"losses":451,"wins":416},"GB2-02":{"draws":343,"losses":120,"wins":17},"GB2-03":{"draws":348,"losses":461,"wins":183},"GB2-05":{"draws":0,"losses":560,"wins":500},"GB2-06":{"draws":2,"losses":413,"wins":87},"GB2-07":{"draws":0,"losses":606,"wins":454},"GB2-08":{"draws":255,"losses":655,"wins":166}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1382.3320537436832,"GB2-02":1417.1071689724397,"GB2-03":1337.6621216431572,"GB2-04":1399.4384870146714,"GB2-05":1123.2680199722095,"GB2-06":951.255299413912,"GB2-08":1153.4309766814984},"none":{"GB2-01":1473.1583257328052,"GB2-02":1401.4581776392768,"GB2-03":1338.9708524632456,"GB2-05":1428.752866835215,"GB2-06":966.1682405437386,"GB2-07":1387.574781127361,"GB2-08":1155.6485116907795}},"per_game_tracks":{"medium":{"GB2-01":40.924176757903865,"GB2-02":42.89675925148062,"GB2-03":39.348973195368174,"GB2-04":40.286522511248776,"GB2-05":28.072963470789123,"GB2-06":19.70274607625053,"GB2-08":29.537989433272568},"none":{"GB2-01":50.36682334888055,"GB2-02":40.886226920394904,"GB2-03":39.503192457138084,"GB2-05":48.4028348536541,"GB2-06":20.60427983317402,"GB2-07":45.21717009070224,"GB2-08":29.736314345403397}},"program_outcomes":{"all":{"counted_attempts":26,"failed":3,"infra_excluded":5,"success_rate":0.8846153846153846,"too_slow":1,"worked_after_repair":9,"worked_first_time":14,"working":23},"medium":{"counted_attempts":12,"failed":1,"infra_excluded":3,"success_rate":0.9166666666666666,"too_slow":1,"worked_after_repair":4,"worked_first_time":7,"working":11},"none":{"counted_attempts":14,"failed":2,"infra_excluded":2,"success_rate":0.8571428571428571,"too_slow":0,"worked_after_repair":5,"worked_first_time":7,"working":12}},"provider_color":"#4137FF","provider_company":"Poolside","provider_key":"poolside","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":31.472577473908814,"none":31.78421604864373},"reasoning_agg":{"medium":{"max":42.89675925148062,"mean":31.472577473908814,"min":19.70274607625053},"none":{"max":50.36682334888055,"mean":31.78421604864373,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":0.31163857473491774},"working_program_strength":{"all":36.820498038975785,"medium":34.395732956616236,"none":39.24526312133533}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:e6c2b0dc7e43b018","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":0.010139174}},"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":{"all":31.34251769196765,"highest":32.397843856498376,"none":30.28719152743692},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"failed"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-06":"failed","GB2-07":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":71.81584471657226,"score":71.81584471657226},"GB2-02":{"attempts":2,"playable":38.34073479762753,"score":38.34073479762753},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":32.31593044305844,"score":16.15796522152922},"GB2-04":{"attempts":2,"playable":45.84511907334377,"score":45.84511907334377},"GB2-05":{"attempts":3,"failed_attempts":1,"playable":37.74253642225859,"score":22.68956035925453},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":13.897049766223288,"score":6.948524883111644},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":25.762862075817534,"score":12.881431037908767},"GB2-08":{"attempts":2,"playable":36.060961446393456,"score":36.060961446393456}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":65.22737689866926,"score":65.22737689866926},"GB2-02":{"attempts":1,"playable":39.083971859687146,"score":39.083971859687146},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.86123300181614,"score":43.86123300181614},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":60.21190425201625,"score":30.105952126008123},"GB2-06":{"attempts":1,"playable":13.897049766223288,"score":13.897049766223288},"GB2-07":{"attempts":1,"playable":25.762862075817534,"score":25.762862075817534},"GB2-08":{"attempts":1,"playable":41.24430512376548,"score":41.24430512376548}},"none":{"GB2-01":{"attempts":1,"playable":78.40431253447525,"score":78.40431253447525},"GB2-02":{"attempts":1,"playable":37.59749773556793,"score":37.59749773556793},"GB2-03":{"attempts":1,"playable":32.31593044305844,"score":32.31593044305844},"GB2-04":{"attempts":1,"playable":47.829005144871395,"score":47.829005144871395},"GB2-05":{"attempts":1,"playable":15.27316859250093,"score":15.27316859250093},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":30.87761776902143,"score":30.87761776902143}}},"id":"tencent/hy3-preview","is_recent_addition":false,"last_measured_at":"2026-10-31T16:55:26Z","match_totals_all":{"draws":1936,"losses":3101,"wins":1615},"match_totals_tracks":{"highest":{"draws":872,"losses":1745,"wins":977},"none":{"draws":1064,"losses":1356,"wins":638}},"model_slug":"tencent-hy3-preview","official_rank_by_reasoning":{"highest":58,"none":60},"overall":{"max":78.40431253447525,"mean":31.34251769196765,"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":65.22737689866926,"GB2-02":39.083971859687146,"GB2-04":43.86123300181614,"GB2-05":60.21190425201625,"GB2-06":13.897049766223288,"GB2-07":25.762862075817534,"GB2-08":41.24430512376548},"per_game_match_totals_all":{"GB2-01":{"draws":158,"losses":233,"wins":641},"GB2-02":{"draws":690,"losses":262,"wins":8},"GB2-03":{"draws":119,"losses":292,"wins":85},"GB2-04":{"draws":657,"losses":228,"wins":111},"GB2-05":{"draws":0,"losses":674,"wins":386},"GB2-06":{"draws":5,"losses":441,"wins":56},"GB2-07":{"draws":0,"losses":406,"wins":124},"GB2-08":{"draws":307,"losses":565,"wins":204}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":79,"losses":151,"wins":286},"GB2-02":{"draws":344,"losses":128,"wins":8},"GB2-04":{"draws":360,"losses":108,"wins":30},"GB2-05":{"draws":0,"losses":220,"wins":310},"GB2-06":{"draws":5,"losses":441,"wins":56},"GB2-07":{"draws":0,"losses":406,"wins":124},"GB2-08":{"draws":84,"losses":291,"wins":163}},"none":{"GB2-01":{"draws":79,"losses":82,"wins":355},"GB2-02":{"draws":346,"losses":134,"wins":0},"GB2-03":{"draws":119,"losses":292,"wins":85},"GB2-04":{"draws":297,"losses":120,"wins":81},"GB2-05":{"draws":0,"losses":454,"wins":76},"GB2-08":{"draws":223,"losses":274,"wins":41}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1619.396270498135,"GB2-02":1387.2954590338918,"GB2-04":1427.3115224704388,"GB2-05":1567.7655467449017,"GB2-06":847.1750502560169,"GB2-07":1132.5810896608416,"GB2-08":1283.7065223004918},"none":{"GB2-01":1775.866579497676,"GB2-02":1375.486058677254,"GB2-03":1274.767240872678,"GB2-04":1457.9662275152716,"GB2-05":917.9052744058183,"GB2-08":1168.5508887210021}},"per_game_tracks":{"highest":{"GB2-01":65.22737689866926,"GB2-02":39.083971859687146,"GB2-04":43.86123300181614,"GB2-05":60.21190425201625,"GB2-06":13.897049766223288,"GB2-07":25.762862075817534,"GB2-08":41.24430512376548},"none":{"GB2-01":78.40431253447525,"GB2-02":37.59749773556793,"GB2-03":32.31593044305844,"GB2-04":47.829005144871395,"GB2-05":15.27316859250093,"GB2-08":30.87761776902143}},"program_outcomes":{"all":{"counted_attempts":17,"failed":4,"infra_excluded":0,"success_rate":0.7647058823529411,"too_slow":0,"worked_after_repair":4,"worked_first_time":9,"working":13},"highest":{"counted_attempts":9,"failed":2,"infra_excluded":0,"success_rate":0.7777777777777778,"too_slow":0,"worked_after_repair":2,"worked_first_time":5,"working":7},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.397843856498376,"none":30.28719152743692},"reasoning_agg":{"highest":{"max":65.22737689866926,"mean":32.397843856498376,"min":0.0},"none":{"max":78.40431253447525,"mean":30.28719152743692,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":2.1106523290614554},"working_program_strength":{"all":40.85493980243379,"highest":41.32695756828502,"none":40.38292203658256}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-5-super-vl:d4bad1e12af20a2e","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":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.09347420000000001},"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":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.02850254}},"codegen_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":0.017223799999999997,"mean":0.011684275,"median":0.01118885,"min":0.0072799,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":11},"recorded_attempt_count":11,"run_count":8,"total":0.0934742},"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":0.0053376,"mean":0.0035628175,"median":0.00344317,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":15},"recorded_attempt_count":15,"run_count":8,"total":0.028502539999999996}},"codegen_cost_usd":{"admitted_cell_count":11,"cell_count":16,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.017223799999999997,"mean":0.00762354625,"median":0.00630875,"min":0.0016103,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":26},"recorded_attempt_count":26,"run_count":16,"total":0.12197674000000001},"codegen_latency_ms":{"attempt_count":26,"max_ms":256073,"mean_ms":74799.75,"min_ms":5868,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":256073,"mean_ms":129205.75,"min_ms":48724,"run_count":8},"none":{"attempt_count":15,"max_ms":35513,"mean_ms":20393.75,"min_ms":5868,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":39370,"output_mean":15837.375,"output_min":2130,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":39370,"output_mean":26486.125,"output_min":16576,"run_count":8},"none":{"attempt_count":15,"output_max":9122,"output_mean":5188.625,"output_min":2130,"run_count":8}},"display_name":"Nemotron 3.5 Super Vl","economics":{"all":30.963071124351842,"medium":50.20580124825973,"none":11.720341000443948},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[235929],"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":[235929],"total_output_tokens":253398,"total_reasoning_output_tokens":186412,"total_visible_output_tokens":66986,"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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nvidia","provider_model":"nvidia/nemotron-3.5-super-vl","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":3,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-05","GB2-06"],"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":{"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":2,"repaired_rate":0.25}},"headline_games_all":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":66.19145070045272,"score":33.09572535022636},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":44.797709417002174,"score":22.398854708501087},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":36.35797542911624,"score":18.17898771455812},"GB2-04":{"attempts":2,"playable":42.22801276948496,"score":42.22801276948496},"GB2-05":{"attempts":2,"failed_attempts":1,"playable":58.31371175686749,"score":29.156855878433745},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":46.81318268661005,"score":23.406591343305024},"GB2-07":{"attempts":2,"playable":40.454117371740004,"score":40.454117371740004},"GB2-08":{"attempts":2,"playable":38.78542385856541,"score":38.78542385856541}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":66.19145070045272,"score":66.19145070045272},"GB2-02":{"attempts":1,"playable":44.797709417002174,"score":44.797709417002174},"GB2-03":{"attempts":1,"playable":36.35797542911624,"score":36.35797542911624},"GB2-04":{"attempts":1,"playable":41.10469187570221,"score":41.10469187570221},"GB2-05":{"attempts":1,"playable":58.31371175686749,"score":58.31371175686749},"GB2-06":{"attempts":1,"playable":46.81318268661005,"score":46.81318268661005},"GB2-07":{"attempts":1,"playable":57.10468254686195,"score":57.10468254686195},"GB2-08":{"attempts":1,"playable":50.96300557346501,"score":50.96300557346501}},"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":43.351333663267724,"score":43.351333663267724},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.803552196618057,"score":23.803552196618057},"GB2-08":{"attempts":1,"playable":26.607842143665806,"score":26.607842143665806}}},"id":"nvidia/nemotron-3.5-super-vl","is_recent_addition":false,"last_measured_at":"2026-10-27T23:45:32Z","match_totals_all":{"draws":1317,"losses":2589,"wins":1750},"match_totals_tracks":{"medium":{"draws":968,"losses":1650,"wins":1472},"none":{"draws":349,"losses":939,"wins":278}},"model_slug":"nvidia-nemotron-3-5-super-vl","official_rank_by_reasoning":{"medium":39},"overall":{"max":66.19145070045272,"mean":30.963071124351842,"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":{"GB2-01":{"draws":67,"losses":152,"wins":297},"GB2-02":{"draws":378,"losses":84,"wins":18},"GB2-03":{"draws":183,"losses":241,"wins":72},"GB2-04":{"draws":678,"losses":253,"wins":65},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":11,"losses":284,"wins":207},"GB2-07":{"draws":0,"losses":655,"wins":405},"GB2-08":{"draws":0,"losses":690,"wins":386}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":67,"losses":152,"wins":297},"GB2-02":{"draws":378,"losses":84,"wins":18},"GB2-03":{"draws":183,"losses":241,"wins":72},"GB2-04":{"draws":329,"losses":137,"wins":32},"GB2-05":{"draws":0,"losses":230,"wins":300},"GB2-06":{"draws":11,"losses":284,"wins":207},"GB2-07":{"draws":0,"losses":239,"wins":291},"GB2-08":{"draws":0,"losses":283,"wins":255}},"none":{"GB2-04":{"draws":349,"losses":116,"wins":33},"GB2-07":{"draws":0,"losses":416,"wins":114},"GB2-08":{"draws":0,"losses":407,"wins":131}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1629.6221292550931,"GB2-02":1431.8092136885984,"GB2-03":1311.4662331439877,"GB2-04":1405.856458424986,"GB2-05":1542.5835968148824,"GB2-06":1368.3362032832251,"GB2-07":1537.8801663276763,"GB2-08":1398.615497365626},"none":{"GB2-04":1423.358271631129,"GB2-07":1103.2058978009777,"GB2-08":1119.813265595858}},"per_game_tracks":{"medium":{"GB2-01":66.19145070045272,"GB2-02":44.797709417002174,"GB2-03":36.35797542911624,"GB2-04":41.10469187570221,"GB2-05":58.31371175686749,"GB2-06":46.81318268661005,"GB2-07":57.10468254686195,"GB2-08":50.96300557346501},"none":{"GB2-04":43.351333663267724,"GB2-07":23.803552196618057,"GB2-08":26.607842143665806}},"program_outcomes":{"all":{"counted_attempts":16,"failed":5,"infra_excluded":0,"success_rate":0.6875,"too_slow":0,"worked_after_repair":5,"worked_first_time":6,"working":11},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":2,"worked_first_time":1,"working":3}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":50.20580124825973,"none":11.720341000443947},"reasoning_agg":{"medium":{"max":66.19145070045272,"mean":50.20580124825973,"min":36.35797542911624},"none":{"max":43.351333663267724,"mean":11.720341000443947,"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":38.48546024781579},"working_program_strength":{"all":40.73002195805513,"medium":50.20580124825973,"none":31.25424266785053}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:37c5cd9d362c0a6b","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":0.19736108440000003},"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":0.2720731754},"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":0.1973610844}},"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":30.453661076000913,"highest":34.87153559649795,"medium":30.076610679964038,"none":26.412836951540754},"first_seen_at":null,"game_gaps":{"highest":{"GB2-03":"infra_excluded","GB2-05":"infra_excluded","GB2-07":"infra_excluded"},"medium":{"GB2-03":"infra_excluded"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":32.03324869667217,"score":32.03324869667217},"GB2-02":{"attempts":7,"failed_attempts":2,"playable":42.54345072050256,"score":33.38701752389172},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.7720912253075,"score":15.257363741769167},"GB2-04":{"attempts":6,"playable":40.23989267442467,"score":40.23989267442467},"GB2-05":{"attempts":5,"playable":26.056202202639177,"score":26.056202202639177},"GB2-06":{"attempts":5,"playable":33.936838237733376,"score":33.936838237733376},"GB2-07":{"attempts":5,"failed_attempts":1,"playable":25.986565096796333,"score":22.46403891503921},"GB2-08":{"attempts":7,"failed_attempts":2,"playable":29.363672842864435,"score":21.70260365975744}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"playable":23.508799863240913,"score":23.508799863240913},"GB2-02":{"attempts":1,"playable":44.058912106185545,"score":44.058912106185545},"GB2-04":{"attempts":1,"playable":39.46772973737559,"score":39.46772973737559},"GB2-06":{"attempts":1,"playable":48.180840395057395,"score":48.180840395057395},"GB2-08":{"attempts":1,"playable":19.141395880630316,"score":19.141395880630316}},"medium":{"GB2-01":{"attempts":2,"playable":29.909745930898936,"score":29.909745930898936},"GB2-02":{"attempts":3,"playable":42.36749067057335,"score":42.36749067057335},"GB2-04":{"attempts":3,"playable":39.023321044370306,"score":39.023321044370306},"GB2-05":{"attempts":2,"playable":24.397312428621838,"score":24.397312428621838},"GB2-06":{"attempts":1,"playable":20.829211837382,"score":20.829211837382},"GB2-07":{"attempts":2,"playable":30.837973103049947,"score":30.837973103049947},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.75682961727786,"score":23.171219744851907}},"none":{"GB2-01":{"attempts":3,"playable":42.68120029587667,"score":42.68120029587667},"GB2-02":{"attempts":3,"failed_attempts":2,"playable":41.203949384748796,"score":13.734649794916265},"GB2-03":{"attempts":3,"failed_attempts":2,"playable":45.7720912253075,"score":15.257363741769167},"GB2-04":{"attempts":2,"playable":42.2286272415281,"score":42.2286272415281},"GB2-05":{"attempts":3,"playable":27.71509197665652,"score":27.71509197665652},"GB2-06":{"attempts":3,"playable":32.80046248076072,"score":32.80046248076072},"GB2-07":{"attempts":3,"failed_attempts":1,"playable":21.135157090542716,"score":14.090104727028477},"GB2-08":{"attempts":3,"failed_attempts":1,"playable":34.19279303068514,"score":22.795195353790092}}},"id":"xiaomi/mimo-v2.5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:08:11Z","match_totals_all":{"draws":5128,"losses":10307,"wins":3515},"match_totals_tracks":{"highest":{"draws":1019,"losses":1206,"wins":309},"medium":{"draws":2376,"losses":4057,"wins":1231},"none":{"draws":1733,"losses":5044,"wins":1975}},"model_slug":"xiaomi-mimo-v2-5","official_rank_by_reasoning":{"none":72},"overall":{"max":48.180840395057395,"mean":30.453661076000913,"min":13.734649794916265},"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":23.508799863240913,"GB2-02":44.058912106185545,"GB2-04":39.46772973737559,"GB2-06":48.180840395057395,"GB2-08":19.141395880630316},"per_game_all":{"GB2-01":32.03324869667217,"GB2-02":42.54345072050256,"GB2-04":40.23989267442467,"GB2-06":33.936838237733376,"GB2-08":29.363672842864435},"per_game_match_totals_all":{"GB2-01":{"draws":638,"losses":1742,"wins":716},"GB2-02":{"draws":1862,"losses":489,"wins":49},"GB2-03":{"draws":181,"losses":197,"wins":118},"GB2-04":{"draws":1849,"losses":912,"wins":227},"GB2-05":{"draws":0,"losses":1981,"wins":669},"GB2-06":{"draws":21,"losses":1745,"wins":744},"GB2-07":{"draws":0,"losses":1617,"wins":503},"GB2-08":{"draws":577,"losses":1624,"wins":489}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":215,"losses":295,"wins":6},"GB2-02":{"draws":385,"losses":84,"wins":11},"GB2-04":{"draws":305,"losses":157,"wins":36},"GB2-06":{"draws":5,"losses":280,"wins":217},"GB2-08":{"draws":109,"losses":390,"wins":39}},"medium":{"GB2-01":{"draws":132,"losses":675,"wins":225},"GB2-02":{"draws":1109,"losses":299,"wins":32},"GB2-04":{"draws":934,"losses":468,"wins":92},"GB2-05":{"draws":0,"losses":813,"wins":247},"GB2-06":{"draws":6,"losses":410,"wins":86},"GB2-07":{"draws":0,"losses":759,"wins":301},"GB2-08":{"draws":195,"losses":633,"wins":248}},"none":{"GB2-01":{"draws":291,"losses":772,"wins":485},"GB2-02":{"draws":368,"losses":106,"wins":6},"GB2-03":{"draws":181,"losses":197,"wins":118},"GB2-04":{"draws":610,"losses":287,"wins":99},"GB2-05":{"draws":0,"losses":1168,"wins":422},"GB2-06":{"draws":10,"losses":1055,"wins":441},"GB2-07":{"draws":0,"losses":858,"wins":202},"GB2-08":{"draws":273,"losses":601,"wins":202}}},"per_game_raw_elo_all":{"GB2-01":1288.4763483239992,"GB2-02":1414.3426576291884,"GB2-04":1399.0165051872343,"GB2-06":1171.3648707010618,"GB2-08":1146.8005559094697},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1197.278506188224,"GB2-02":1426.1034096731933,"GB2-04":1392.9856978834107,"GB2-06":1389.4399754801373,"GB2-08":1026.467989309815},"medium":{"GB2-01":1270.0684208201578,"GB2-02":1412.9841727103449,"GB2-04":1389.4324354698583,"GB2-05":1084.0422830408788,"GB2-06":969.8539934027909,"GB2-07":1199.2617058830792,"GB2-08":1208.597766096554},"none":{"GB2-01":1398.082117963616,"GB2-02":1403.9403905040263,"GB2-03":1393.7405943836134,"GB2-04":1414.631382208434,"GB2-05":1106.4805837656502,"GB2-06":1154.8006432202574,"GB2-07":1043.901249176216,"GB2-08":1205.3359123220398}},"per_game_tracks":{"highest":{"GB2-01":23.508799863240913,"GB2-02":44.058912106185545,"GB2-04":39.46772973737559,"GB2-06":48.180840395057395,"GB2-08":19.141395880630316},"medium":{"GB2-01":29.909745930898936,"GB2-02":42.36749067057335,"GB2-04":39.023321044370306,"GB2-05":24.397312428621838,"GB2-06":20.829211837382,"GB2-07":30.837973103049947,"GB2-08":34.75682961727786},"none":{"GB2-01":42.68120029587667,"GB2-02":41.203949384748796,"GB2-03":45.7720912253075,"GB2-04":42.2286272415281,"GB2-05":27.715091976656513,"GB2-06":32.80046248076072,"GB2-07":21.135157090542716,"GB2-08":34.19279303068514}},"program_outcomes":{"all":{"counted_attempts":44,"failed":7,"infra_excluded":12,"success_rate":0.8409090909090909,"too_slow":0,"worked_after_repair":24,"worked_first_time":13,"working":37},"highest":{"counted_attempts":5,"failed":0,"infra_excluded":3,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"medium":{"counted_attempts":16,"failed":1,"infra_excluded":8,"success_rate":0.9375,"too_slow":0,"worked_after_repair":14,"worked_first_time":1,"working":15},"none":{"counted_attempts":23,"failed":6,"infra_excluded":1,"success_rate":0.7391304347826086,"too_slow":0,"worked_after_repair":5,"worked_first_time":12,"working":17}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.87153559649795,"medium":30.076610679964038,"none":26.412836951540754},"reasoning_agg":{"highest":{"max":48.180840395057395,"mean":34.87153559649795,"min":19.141395880630316},"medium":{"max":42.36749067057335,"mean":30.076610679964038,"min":20.829211837382},"none":{"max":42.68120029587667,"mean":26.412836951540754,"min":13.734649794916265}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":8.458698644957195},"working_program_strength":{"all":34.18980166395251,"highest":34.87153559649795,"medium":31.731697804596315,"none":35.96617159076327}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:f2f3aae2a18b47b3","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":0.14744575}},"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":0.14744575},"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":{"all":29.412086144608516,"medium":32.50929579357923,"none":26.314876495637808},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":31.286680806515626,"score":31.286680806515626},"GB2-02":{"attempts":4,"failed_attempts":1,"playable":40.22390724591901,"score":30.187783526523866},"GB2-03":{"attempts":4,"failed_attempts":3,"playable":34.02259098098723,"score":8.505647745246808},"GB2-04":{"attempts":4,"failed_attempts":3,"playable":51.77876932989635,"score":12.944692332474087},"GB2-05":{"attempts":4,"playable":29.54241905933845,"score":29.54241905933845},"GB2-06":{"attempts":4,"playable":50.86042894120123,"score":50.86042894120123},"GB2-07":{"attempts":4,"failed_attempts":1,"playable":28.290518801673976,"score":22.931054094022713},"GB2-08":{"attempts":4,"playable":49.03798265154535,"score":49.03798265154535}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"playable":16.249388935998592,"score":16.249388935998592},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.144494877580584,"score":20.072247438790292},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":51.77876932989635,"score":25.889384664948174},"GB2-05":{"attempts":2,"playable":50.727388601950715,"score":50.727388601950715},"GB2-06":{"attempts":2,"playable":60.233034209943526,"score":60.233034209943526},"GB2-07":{"attempts":2,"playable":35.14317877274289,"score":35.14317877274289},"GB2-08":{"attempts":2,"playable":51.75974372425961,"score":51.75974372425961}},"none":{"GB2-01":{"attempts":2,"playable":46.32397267703266,"score":46.32397267703266},"GB2-02":{"attempts":2,"playable":40.30331961425744,"score":40.30331961425744},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":34.02259098098723,"score":17.011295490493616},"GB2-04":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-05":{"attempts":2,"playable":8.357449516726186,"score":8.357449516726186},"GB2-06":{"attempts":2,"playable":41.48782367245893,"score":41.48782367245893},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":21.43785883060506,"score":10.71892941530253},"GB2-08":{"attempts":2,"playable":46.31622157883108,"score":46.31622157883108}}},"id":"gpt-5.4-nano","is_recent_addition":false,"last_measured_at":"2026-10-31T17:08:02Z","match_totals_all":{"draws":2078,"losses":6743,"wins":3547},"match_totals_tracks":{"medium":{"draws":882,"losses":3203,"wins":2125},"none":{"draws":1196,"losses":3540,"wins":1422}},"model_slug":"gpt-5-4-nano","official_rank_by_reasoning":{"medium":65,"none":73},"overall":{"max":60.233034209943526,"mean":29.412086144608516,"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":385,"losses":1259,"wins":420},"GB2-02":{"draws":1087,"losses":340,"wins":13},"GB2-03":{"draws":141,"losses":273,"wins":82},"GB2-04":{"draws":236,"losses":131,"wins":131},"GB2-05":{"draws":0,"losses":1514,"wins":606},"GB2-06":{"draws":28,"losses":1044,"wins":936},"GB2-07":{"draws":0,"losses":1134,"wins":456},"GB2-08":{"draws":201,"losses":1048,"wins":903}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":161,"losses":796,"wins":75},"GB2-02":{"draws":366,"losses":112,"wins":2},"GB2-04":{"draws":236,"losses":131,"wins":131},"GB2-05":{"draws":0,"losses":534,"wins":526},"GB2-06":{"draws":26,"losses":425,"wins":553},"GB2-07":{"draws":0,"losses":706,"wins":354},"GB2-08":{"draws":93,"losses":499,"wins":484}},"none":{"GB2-01":{"draws":224,"losses":463,"wins":345},"GB2-02":{"draws":721,"losses":228,"wins":11},"GB2-03":{"draws":141,"losses":273,"wins":82},"GB2-05":{"draws":0,"losses":980,"wins":80},"GB2-06":{"draws":2,"losses":619,"wins":383},"GB2-07":{"draws":0,"losses":428,"wins":102},"GB2-08":{"draws":108,"losses":549,"wins":419}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1059.9810262909123,"GB2-02":1395.647438454895,"GB2-04":1488.5737961202894,"GB2-05":1488.886372188246,"GB2-06":1583.5914847493511,"GB2-07":1206.0760353970854,"GB2-08":1478.4637174582415},"none":{"GB2-01":1433.862785852124,"GB2-02":1396.8862041555528,"GB2-03":1290.437545125174,"GB2-05":746.1179262965551,"GB2-06":1293.1847380046804,"GB2-07":1065.9210564463747,"GB2-08":1396.2286645784184}},"per_game_tracks":{"medium":{"GB2-01":16.249388935998592,"GB2-02":40.144494877580584,"GB2-04":51.77876932989635,"GB2-05":50.727388601950715,"GB2-06":60.233034209943526,"GB2-07":35.14317877274289,"GB2-08":51.75974372425961},"none":{"GB2-01":46.32397267703266,"GB2-02":40.30331961425744,"GB2-03":34.02259098098723,"GB2-05":8.357449516726186,"GB2-06":41.48782367245893,"GB2-07":21.43785883060506,"GB2-08":46.31622157883108}},"program_outcomes":{"all":{"counted_attempts":32,"failed":8,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":14,"worked_first_time":10,"working":24},"medium":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":7,"worked_first_time":5,"working":12},"none":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":7,"worked_first_time":5,"working":12}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.50929579357923,"none":26.314876495637808},"reasoning_agg":{"medium":{"max":60.233034209943526,"mean":32.50929579357923,"min":0.0},"none":{"max":46.32397267703266,"mean":26.314876495637808,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":6.194419297941419},"working_program_strength":{"all":38.87751680880506,"medium":43.719428350338895,"none":34.03560526727123}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:dac3a348339f0ac2","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":0.03073979},"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":0.014924670000000001}},"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":0.045664460000000004},"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":{"all":29.22891406766545,"medium":38.11897217594022,"none":20.33885595939068},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-03":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":22.4034773236396,"score":11.2017386618198},"GB2-02":{"attempts":2,"playable":41.73166018606092,"score":41.73166018606092},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":43.80373706716612,"score":21.90186853358306},"GB2-04":{"attempts":2,"playable":44.675729813941686,"score":44.675729813941686},"GB2-05":{"attempts":2,"playable":44.4250978785117,"score":44.4250978785117},"GB2-06":{"attempts":2,"playable":22.281868810613286,"score":22.281868810613286},"GB2-07":{"attempts":2,"playable":14.307990851660772,"score":14.307990851660772},"GB2-08":{"attempts":2,"playable":33.30535780513237,"score":33.30535780513237}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":22.4034773236396,"score":22.4034773236396},"GB2-02":{"attempts":1,"playable":43.530845523290026,"score":43.530845523290026},"GB2-03":{"attempts":1,"playable":43.80373706716612,"score":43.80373706716612},"GB2-04":{"attempts":1,"playable":43.45333472329967,"score":43.45333472329967},"GB2-05":{"attempts":1,"playable":72.04192614282039,"score":72.04192614282039},"GB2-06":{"attempts":1,"playable":27.809351939364863,"score":27.809351939364863},"GB2-07":{"attempts":1,"playable":18.257227516218936,"score":18.257227516218936},"GB2-08":{"attempts":1,"playable":33.65187717172215,"score":33.65187717172215}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":39.93247484883182,"score":39.93247484883182},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":45.898124904583696,"score":45.898124904583696},"GB2-05":{"attempts":1,"playable":16.808269614203013,"score":16.808269614203013},"GB2-06":{"attempts":1,"playable":16.75438568186171,"score":16.75438568186171},"GB2-07":{"attempts":1,"playable":10.358754187102608,"score":10.358754187102608},"GB2-08":{"attempts":1,"playable":32.958838438542585,"score":32.958838438542585}}},"id":"google/gemma-4-31b-it","is_recent_addition":false,"last_measured_at":"2026-10-31T17:12:04Z","match_totals_all":{"draws":2196,"losses":3839,"wins":1133},"match_totals_tracks":{"medium":{"draws":1250,"losses":2003,"wins":837},"none":{"draws":946,"losses":1836,"wins":296}},"model_slug":"google-gemma-4-31b-it","official_rank_by_reasoning":{"medium":58,"none":80},"overall":{"max":72.04192614282039,"mean":29.22891406766545,"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":128,"losses":344,"wins":44},"GB2-02":{"draws":740,"losses":205,"wins":15},"GB2-03":{"draws":114,"losses":240,"wins":142},"GB2-04":{"draws":630,"losses":253,"wins":113},"GB2-05":{"draws":0,"losses":603,"wins":457},"GB2-06":{"draws":35,"losses":795,"wins":174},"GB2-07":{"draws":0,"losses":927,"wins":133},"GB2-08":{"draws":549,"losses":472,"wins":55}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":128,"losses":344,"wins":44},"GB2-02":{"draws":378,"losses":90,"wins":12},"GB2-03":{"draws":114,"losses":240,"wins":142},"GB2-04":{"draws":324,"losses":128,"wins":46},"GB2-05":{"draws":0,"losses":157,"wins":373},"GB2-06":{"draws":33,"losses":365,"wins":104},"GB2-07":{"draws":0,"losses":444,"wins":86},"GB2-08":{"draws":273,"losses":235,"wins":30}},"none":{"GB2-02":{"draws":362,"losses":115,"wins":3},"GB2-04":{"draws":306,"losses":125,"wins":67},"GB2-05":{"draws":0,"losses":446,"wins":84},"GB2-06":{"draws":2,"losses":430,"wins":70},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":276,"losses":237,"wins":25}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1183.5203907319635,"GB2-02":1422.019442691159,"GB2-03":1376.6656389787006,"GB2-04":1424.1495368083795,"GB2-05":1747.9840703533591,"GB2-06":1079.6620055558055,"GB2-07":1011.7504347453604,"GB2-08":1199.4313550709542},"none":{"GB2-02":1393.9820501847682,"GB2-04":1443.0613419164122,"GB2-05":949.2340553889039,"GB2-06":900.5161305081346,"GB2-07":842.6907618887479,"GB2-08":1191.749792688846}},"per_game_tracks":{"medium":{"GB2-01":22.4034773236396,"GB2-02":43.530845523290026,"GB2-03":43.80373706716612,"GB2-04":43.45333472329967,"GB2-05":72.04192614282039,"GB2-06":27.809351939364863,"GB2-07":18.257227516218936,"GB2-08":33.65187717172215},"none":{"GB2-02":39.93247484883182,"GB2-04":45.898124904583696,"GB2-05":16.808269614203013,"GB2-06":16.75438568186171,"GB2-07":10.358754187102608,"GB2-08":32.958838438542585}},"program_outcomes":{"all":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":11,"working":14},"medium":{"counted_attempts":8,"failed":0,"infra_excluded":0,"success_rate":1.0,"too_slow":0,"worked_after_repair":3,"worked_first_time":5,"working":8},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":0,"worked_first_time":6,"working":6}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":38.11897217594022,"none":20.33885595939068},"reasoning_agg":{"medium":{"max":72.04192614282039,"mean":38.11897217594022,"min":18.257227516218936},"none":{"max":45.898124904583696,"mean":20.33885595939068,"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":17.78011621654954},"working_program_strength":{"all":32.618723394230564,"medium":38.11897217594022,"none":27.11847461252091}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:67b72b073a6b634c","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":1.386359256},"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":1.60040646},"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":{"all":28.26341754352226,"medium":27.43069191616448,"none":29.096143170880033},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":42.600393877264615,"score":21.300196938632308},"GB2-02":{"attempts":4,"failed_attempts":2,"playable":41.785447331733614,"score":20.892723665866807},"GB2-03":{"attempts":4,"failed_attempts":1,"playable":37.22562341216647,"score":27.292813958549672},"GB2-04":{"attempts":4,"failed_attempts":1,"playable":42.39682258295531,"score":30.74432623118042},"GB2-05":{"attempts":4,"playable":22.87672100992227,"score":22.87672100992227},"GB2-06":{"attempts":4,"playable":30.3048525936551,"score":30.3048525936551},"GB2-07":{"attempts":4,"playable":36.44743852173522,"score":36.44743852173522},"GB2-08":{"attempts":4,"playable":36.24826742863625,"score":36.24826742863625}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":43.00248817023414,"score":21.50124408511707},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.73123781446718,"score":19.86561890723359},"GB2-04":{"attempts":2,"playable":38.18365975881106,"score":38.18365975881106},"GB2-05":{"attempts":2,"playable":33.64835949928122,"score":33.64835949928122},"GB2-06":{"attempts":2,"playable":24.434851741592013,"score":24.434851741592013},"GB2-07":{"attempts":2,"playable":37.810966628627334,"score":37.810966628627334},"GB2-08":{"attempts":2,"playable":44.000834708653535,"score":44.000834708653535}},"none":{"GB2-01":{"attempts":2,"playable":42.600393877264615,"score":42.600393877264615},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.56840649323309,"score":20.284203246616546},"GB2-03":{"attempts":2,"playable":34.720009009865755,"score":34.720009009865755},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":46.60998540709956,"score":23.30499270354978},"GB2-05":{"attempts":2,"playable":12.105082520563318,"score":12.105082520563318},"GB2-06":{"attempts":2,"playable":36.174853445718185,"score":36.174853445718185},"GB2-07":{"attempts":2,"playable":35.08391041484311,"score":35.08391041484311},"GB2-08":{"attempts":2,"playable":28.495700148618962,"score":28.495700148618962}}},"id":"meituan/longcat-2.0","is_recent_addition":false,"last_measured_at":"2026-10-31T17:13:11Z","match_totals_all":{"draws":2727,"losses":7684,"wins":2963},"match_totals_tracks":{"medium":{"draws":1248,"losses":3430,"wins":1494},"none":{"draws":1479,"losses":4254,"wins":1469}},"model_slug":"meituan-longcat-2-0","official_rank_by_reasoning":{"medium":70,"none":66},"overall":{"max":44.000834708653535,"mean":28.26341754352226,"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":246,"losses":490,"wins":296},"GB2-02":{"draws":767,"losses":191,"wins":2},"GB2-03":{"draws":441,"losses":776,"wins":271},"GB2-04":{"draws":828,"losses":492,"wins":174},"GB2-05":{"draws":0,"losses":1658,"wins":462},"GB2-06":{"draws":39,"losses":1456,"wins":513},"GB2-07":{"draws":0,"losses":1394,"wins":726},"GB2-08":{"draws":406,"losses":1227,"wins":519}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":395,"losses":84,"wins":1},"GB2-03":{"draws":149,"losses":242,"wins":105},"GB2-04":{"draws":543,"losses":360,"wins":93},"GB2-05":{"draws":0,"losses":717,"wins":343},"GB2-06":{"draws":23,"losses":782,"wins":199},"GB2-07":{"draws":0,"losses":679,"wins":381},"GB2-08":{"draws":138,"losses":566,"wins":372}},"none":{"GB2-01":{"draws":246,"losses":490,"wins":296},"GB2-02":{"draws":372,"losses":107,"wins":1},"GB2-03":{"draws":292,"losses":534,"wins":166},"GB2-04":{"draws":285,"losses":132,"wins":81},"GB2-05":{"draws":0,"losses":941,"wins":119},"GB2-06":{"draws":16,"losses":674,"wins":314},"GB2-07":{"draws":0,"losses":715,"wins":345},"GB2-08":{"draws":268,"losses":661,"wins":147}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1417.927381542362,"GB2-03":1341.2361328645734,"GB2-04":1382.5525459990254,"GB2-05":1196.2642445731276,"GB2-06":1026.7480301251542,"GB2-07":1263.4167460161932,"GB2-08":1329.6740387734676},"none":{"GB2-01":1398.4894891121967,"GB2-02":1398.9712066040306,"GB2-03":1295.1039083790795,"GB2-04":1448.5566550224619,"GB2-05":844.0548914885389,"GB2-06":1206.5412000298152,"GB2-07":1258.3643542152531,"GB2-08":1141.6118118953386}},"per_game_tracks":{"medium":{"GB2-02":43.00248817023414,"GB2-03":39.73123781446718,"GB2-04":38.18365975881106,"GB2-05":33.64835949928122,"GB2-06":24.434851741592013,"GB2-07":37.810966628627334,"GB2-08":44.000834708653535},"none":{"GB2-01":42.600393877264615,"GB2-02":40.56840649323309,"GB2-03":34.720009009865755,"GB2-04":46.60998540709956,"GB2-05":12.105082520563318,"GB2-06":36.174853445718185,"GB2-07":35.08391041484311,"GB2-08":28.495700148618962}},"program_outcomes":{"all":{"counted_attempts":32,"failed":6,"infra_excluded":0,"success_rate":0.8125,"too_slow":0,"worked_after_repair":9,"worked_first_time":17,"working":26},"medium":{"counted_attempts":16,"failed":4,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":9,"working":12},"none":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":6,"worked_first_time":8,"working":14}},"provider_color":"#29E154","provider_company":"Meituan","provider_key":"meituan","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":27.43069191616448,"none":29.096143170880033},"reasoning_agg":{"medium":{"max":44.000834708653535,"mean":27.43069191616448,"min":0.0},"none":{"max":42.600393877264615,"mean":29.096143170880033,"min":12.105082520563318}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":1.6654512547155527},"working_program_strength":{"all":35.90185335530158,"medium":37.25891404595235,"none":34.54479266465082}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:25328172d378693d","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":0.8197712500000001},"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":3.4057992500000003},"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":{"all":27.179420851391296,"medium":15.853189830524201,"none":38.50565187225839},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"infra_excluded"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"infra_excluded","GB2-02":"infra_excluded","GB2-04":"failed"},"none":{"GB2-01":"infra_excluded"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":36.428171784028066,"score":36.428171784028066},"GB2-03":{"attempts":2,"playable":32.73937802719653,"score":32.73937802719653},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.922224527830636,"score":20.961112263915318},"GB2-05":{"attempts":2,"playable":21.139534206580972,"score":21.139534206580972},"GB2-06":{"attempts":2,"playable":13.779207638405591,"score":13.779207638405591},"GB2-07":{"attempts":2,"playable":44.10973160015764,"score":44.10973160015764},"GB2-08":{"attempts":2,"playable":31.386301416206894,"score":31.386301416206894}},"headline_games_tracks":{"medium":{"GB2-03":{"attempts":1,"playable":30.924244234220904,"score":30.924244234220904},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":11.818017578348726,"score":11.818017578348726},"GB2-06":{"attempts":1,"playable":15.613762472611755,"score":15.613762472611755},"GB2-07":{"attempts":1,"playable":23.6070271360862,"score":23.6070271360862},"GB2-08":{"attempts":1,"playable":13.156087561877627,"score":13.156087561877627}},"none":{"GB2-02":{"attempts":1,"playable":36.428171784028066,"score":36.428171784028066},"GB2-03":{"attempts":1,"playable":34.55451182017216,"score":34.55451182017216},"GB2-04":{"attempts":1,"playable":41.922224527830636,"score":41.922224527830636},"GB2-05":{"attempts":1,"playable":30.461050834813218,"score":30.461050834813218},"GB2-06":{"attempts":1,"playable":11.944652804199427,"score":11.944652804199427},"GB2-07":{"attempts":1,"playable":64.61243606422907,"score":64.61243606422907},"GB2-08":{"attempts":1,"playable":49.61651527053616,"score":49.61651527053616}}},"id":"nex-agi/nex-n2-pro","is_recent_addition":false,"last_measured_at":"2026-10-31T16:06:29Z","match_totals_all":{"draws":1149,"losses":3848,"wins":1173},"match_totals_tracks":{"medium":{"draws":193,"losses":2061,"wins":342},"none":{"draws":956,"losses":1787,"wins":831}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":64.61243606422907,"mean":27.179420851391296,"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":325,"losses":150,"wins":5},"GB2-03":{"draws":396,"losses":501,"wins":95},"GB2-04":{"draws":357,"losses":119,"wins":22},"GB2-05":{"draws":0,"losses":847,"wins":213},"GB2-06":{"draws":18,"losses":879,"wins":107},"GB2-07":{"draws":0,"losses":614,"wins":446},"GB2-08":{"draws":53,"losses":738,"wins":285}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":160,"losses":278,"wins":58},"GB2-05":{"draws":0,"losses":472,"wins":58},"GB2-06":{"draws":14,"losses":429,"wins":59},"GB2-07":{"draws":0,"losses":417,"wins":113},"GB2-08":{"draws":19,"losses":465,"wins":54}},"none":{"GB2-02":{"draws":325,"losses":150,"wins":5},"GB2-03":{"draws":236,"losses":223,"wins":37},"GB2-04":{"draws":357,"losses":119,"wins":22},"GB2-05":{"draws":0,"losses":375,"wins":155},"GB2-06":{"draws":4,"losses":450,"wins":48},"GB2-07":{"draws":0,"losses":197,"wins":333},"GB2-08":{"draws":34,"losses":273,"wins":231}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1261.7546689591024,"GB2-05":840.1558318978928,"GB2-06":879.8293299625265,"GB2-07":1100.1895999705946,"GB2-08":935.0966361227563},"none":{"GB2-02":1366.0961611377302,"GB2-03":1295.2653930884178,"GB2-04":1412.2435791687822,"GB2-05":1180.317267284268,"GB2-06":807.1058392096875,"GB2-07":1638.9868972186441,"GB2-08":1381.8195654963652}},"per_game_tracks":{"medium":{"GB2-03":30.924244234220904,"GB2-05":11.818017578348726,"GB2-06":15.613762472611755,"GB2-07":23.6070271360862,"GB2-08":13.156087561877627},"none":{"GB2-02":36.428171784028066,"GB2-03":34.55451182017216,"GB2-04":41.922224527830636,"GB2-05":30.461050834813218,"GB2-06":11.944652804199427,"GB2-07":64.61243606422907,"GB2-08":49.61651527053616}},"program_outcomes":{"all":{"counted_attempts":13,"failed":1,"infra_excluded":11,"success_rate":0.9230769230769231,"too_slow":0,"worked_after_repair":12,"worked_first_time":0,"working":12},"medium":{"counted_attempts":6,"failed":1,"infra_excluded":2,"success_rate":0.8333333333333334,"too_slow":0,"worked_after_repair":5,"worked_first_time":0,"working":5},"none":{"counted_attempts":7,"failed":0,"infra_excluded":9,"success_rate":1.0,"too_slow":0,"worked_after_repair":7,"worked_first_time":0,"working":7}},"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":15.853189830524201,"none":38.50565187225839},"reasoning_agg":{"medium":{"max":30.924244234220904,"mean":15.853189830524201,"min":0.0},"none":{"max":64.61243606422907,"mean":38.50565187225839,"min":11.944652804199427}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":22.65246204173419},"working_program_strength":{"all":28.764739834443716,"medium":19.023827796629043,"none":38.50565187225839}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:77ef69bca80e8838","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":0.58451034},"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":0.20304798000000002}},"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":{"all":26.72371894985375,"medium":23.164855222907114,"none":30.282582676800388},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-04":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":38.65803810810782,"score":38.65803810810782},"GB2-02":{"attempts":2,"playable":39.773430593248534,"score":39.773430593248534},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":39.83619514464155,"score":19.918097572320775},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":40.18420723706202,"score":20.09210361853101},"GB2-05":{"attempts":2,"playable":15.445351886892665,"score":15.445351886892665},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":17.550753632610753,"score":8.775376816305377},"GB2-07":{"attempts":2,"playable":32.90516861461784,"score":32.90516861461784},"GB2-08":{"attempts":2,"playable":38.222184388806,"score":38.222184388806}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":18.57435678582085,"score":18.57435678582085},"GB2-02":{"attempts":1,"playable":39.826448878377086,"score":39.826448878377086},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":40.18420723706202,"score":40.18420723706202},"GB2-05":{"attempts":1,"playable":2.164288139743077,"score":2.164288139743077},"GB2-06":{"attempts":1,"playable":17.550753632610753,"score":17.550753632610753},"GB2-07":{"attempts":1,"playable":42.39994525540825,"score":42.39994525540825},"GB2-08":{"attempts":1,"playable":24.618841854234887,"score":24.618841854234887}},"none":{"GB2-01":{"attempts":1,"playable":58.74171943039478,"score":58.74171943039478},"GB2-02":{"attempts":1,"playable":39.720412308119975,"score":39.720412308119975},"GB2-03":{"attempts":1,"playable":39.83619514464155,"score":39.83619514464155},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":28.72641563404225,"score":28.72641563404225},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":23.410391973827434,"score":23.410391973827434},"GB2-08":{"attempts":1,"playable":51.825526923377105,"score":51.825526923377105}}},"id":"minimax/minimax-m3","is_recent_addition":false,"last_measured_at":"2026-10-31T16:30:44Z","match_totals_all":{"draws":1365,"losses":3950,"wins":1369},"match_totals_tracks":{"medium":{"draws":810,"losses":2310,"wins":474},"none":{"draws":555,"losses":1640,"wins":895}},"model_slug":"minimax-minimax-m3","official_rank_by_reasoning":{"medium":75,"none":61},"overall":{"max":58.74171943039478,"mean":26.72371894985375,"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":104,"losses":599,"wins":329},"GB2-02":{"draws":725,"losses":231,"wins":4},"GB2-03":{"draws":104,"losses":264,"wins":128},"GB2-04":{"draws":320,"losses":146,"wins":32},"GB2-05":{"draws":0,"losses":906,"wins":154},"GB2-06":{"draws":3,"losses":426,"wins":73},"GB2-07":{"draws":0,"losses":737,"wins":323},"GB2-08":{"draws":109,"losses":641,"wins":326}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":22,"losses":416,"wins":78},"GB2-02":{"draws":365,"losses":114,"wins":1},"GB2-04":{"draws":320,"losses":146,"wins":32},"GB2-05":{"draws":0,"losses":522,"wins":8},"GB2-06":{"draws":3,"losses":426,"wins":73},"GB2-07":{"draws":0,"losses":319,"wins":211},"GB2-08":{"draws":100,"losses":367,"wins":71}},"none":{"GB2-01":{"draws":82,"losses":183,"wins":251},"GB2-02":{"draws":360,"losses":117,"wins":3},"GB2-03":{"draws":104,"losses":264,"wins":128},"GB2-05":{"draws":0,"losses":384,"wins":146},"GB2-07":{"draws":0,"losses":418,"wins":112},"GB2-08":{"draws":9,"losses":274,"wins":255}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1132.313443099124,"GB2-02":1393.148448829668,"GB2-04":1398.6338753812252,"GB2-05":441.5488725083401,"GB2-06":914.5695875230206,"GB2-07":1352.7418847204226,"GB2-08":1096.2520339165608},"none":{"GB2-01":1553.3926496646798,"GB2-02":1392.314230671829,"GB2-03":1342.1542188662136,"GB2-05":1154.3940472202178,"GB2-07":1097.157858760854,"GB2-08":1409.5710179774376}},"per_game_tracks":{"medium":{"GB2-01":18.57435678582085,"GB2-02":39.826448878377086,"GB2-04":40.18420723706202,"GB2-05":2.164288139743077,"GB2-06":17.550753632610753,"GB2-07":42.39994525540825,"GB2-08":24.618841854234887},"none":{"GB2-01":58.74171943039478,"GB2-02":39.720412308119975,"GB2-03":39.83619514464155,"GB2-05":28.72641563404225,"GB2-07":23.410391973827434,"GB2-08":51.825526923377105}},"program_outcomes":{"all":{"counted_attempts":16,"failed":3,"infra_excluded":0,"success_rate":0.8125,"too_slow":0,"worked_after_repair":9,"worked_first_time":4,"working":13},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":0,"working":7},"none":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.164855222907114,"none":30.282582676800388},"reasoning_agg":{"medium":{"max":42.39994525540825,"mean":23.164855222907114,"min":0.0},"none":{"max":58.74171943039478,"mean":30.282582676800388,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":7.1177274538932735},"working_program_strength":{"all":33.425448578575754,"medium":26.47412025475099,"none":40.376776902400515}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:db598f876bca3856","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":1.397542663983281},"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":{"all":25.624652129492915,"highest":28.293075614157832,"none":22.956228644827995},"first_seen_at":null,"game_gaps":{"highest":{"GB2-01":"failed"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-07":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":11.985169375627612,"score":5.992584687813806},"GB2-02":{"attempts":2,"playable":43.001018840333856,"score":43.001018840333856},"GB2-03":{"attempts":2,"playable":36.03832478862042,"score":36.03832478862042},"GB2-04":{"attempts":2,"playable":36.850197377929035,"score":36.850197377929035},"GB2-05":{"attempts":2,"playable":25.18720144884458,"score":25.18720144884458},"GB2-06":{"attempts":2,"playable":22.032922347061294,"score":22.032922347061294},"GB2-07":{"attempts":2,"failed_attempts":1,"playable":12.813261718497019,"score":6.4066308592485095},"GB2-08":{"attempts":2,"playable":29.488336686091806,"score":29.488336686091806}},"headline_games_tracks":{"highest":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":44.692202712312394,"score":44.692202712312394},"GB2-03":{"attempts":1,"playable":37.30955847897335,"score":37.30955847897335},"GB2-04":{"attempts":1,"playable":39.77484924906058,"score":39.77484924906058},"GB2-05":{"attempts":1,"playable":37.21234678344789,"score":37.21234678344789},"GB2-06":{"attempts":1,"playable":25.94737504918606,"score":25.94737504918606},"GB2-07":{"attempts":1,"playable":12.813261718497019,"score":12.813261718497019},"GB2-08":{"attempts":1,"playable":28.595010921785363,"score":28.595010921785363}},"none":{"GB2-01":{"attempts":1,"playable":11.985169375627612,"score":11.985169375627612},"GB2-02":{"attempts":1,"playable":41.30983496835532,"score":41.30983496835532},"GB2-03":{"attempts":1,"playable":34.76709109826749,"score":34.76709109826749},"GB2-04":{"attempts":1,"playable":33.9255455067975,"score":33.9255455067975},"GB2-05":{"attempts":1,"playable":13.162056114241267,"score":13.162056114241267},"GB2-06":{"attempts":1,"playable":18.11846964493653,"score":18.11846964493653},"GB2-07":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-08":{"attempts":1,"playable":30.38166245039825,"score":30.38166245039825}}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-10-31T17:06:33Z","match_totals_all":{"draws":1848,"losses":4287,"wins":999},"match_totals_tracks":{"highest":{"draws":961,"losses":2027,"wins":586},"none":{"draws":887,"losses":2260,"wins":413}},"model_slug":"mistralai-mistral-medium-3-5","official_rank_by_reasoning":{"highest":60,"none":79},"overall":{"max":44.692202712312394,"mean":25.624652129492915,"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":44.692202712312394,"GB2-03":37.30955847897335,"GB2-04":39.77484924906058,"GB2-05":37.21234678344789,"GB2-06":25.94737504918606,"GB2-07":12.813261718497019,"GB2-08":28.595010921785363},"per_game_match_totals_all":{"GB2-01":{"draws":47,"losses":436,"wins":33},"GB2-02":{"draws":750,"losses":188,"wins":22},"GB2-03":{"draws":238,"losses":549,"wins":205},"GB2-04":{"draws":557,"losses":366,"wins":73},"GB2-05":{"draws":0,"losses":805,"wins":255},"GB2-06":{"draws":2,"losses":814,"wins":188},"GB2-07":{"draws":0,"losses":471,"wins":59},"GB2-08":{"draws":254,"losses":658,"wins":164}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":371,"losses":88,"wins":21},"GB2-03":{"draws":130,"losses":263,"wins":103},"GB2-04":{"draws":328,"losses":144,"wins":26},"GB2-05":{"draws":0,"losses":340,"wins":190},"GB2-06":{"draws":2,"losses":389,"wins":111},"GB2-07":{"draws":0,"losses":471,"wins":59},"GB2-08":{"draws":130,"losses":332,"wins":76}},"none":{"GB2-01":{"draws":47,"losses":436,"wins":33},"GB2-02":{"draws":379,"losses":100,"wins":1},"GB2-03":{"draws":108,"losses":286,"wins":102},"GB2-04":{"draws":229,"losses":222,"wins":47},"GB2-05":{"draws":0,"losses":465,"wins":65},"GB2-06":{"draws":0,"losses":425,"wins":77},"GB2-08":{"draws":124,"losses":326,"wins":88}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1430.9948536583947,"GB2-03":1319.9245224373358,"GB2-04":1395.4098318529295,"GB2-05":1274.7483355795428,"GB2-06":1050.997477592587,"GB2-07":902.6985721507657,"GB2-08":1142.746134660557},"none":{"GB2-01":1023.7770062017337,"GB2-02":1404.766777445727,"GB2-03":1297.1880696905162,"GB2-04":1348.184052552599,"GB2-05":871.812562366546,"GB2-06":924.417274086525,"GB2-08":1162.9826577374083}},"per_game_tracks":{"highest":{"GB2-02":44.692202712312394,"GB2-03":37.30955847897335,"GB2-04":39.77484924906058,"GB2-05":37.21234678344789,"GB2-06":25.94737504918606,"GB2-07":12.813261718497019,"GB2-08":28.595010921785363},"none":{"GB2-01":11.985169375627612,"GB2-02":41.30983496835532,"GB2-03":34.76709109826749,"GB2-04":33.9255455067975,"GB2-05":13.162056114241267,"GB2-06":18.11846964493653,"GB2-08":30.38166245039825}},"program_outcomes":{"all":{"counted_attempts":16,"failed":2,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":7,"worked_first_time":7,"working":14},"highest":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":4,"worked_first_time":3,"working":7},"none":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.293075614157832,"none":22.956228644827995},"reasoning_agg":{"highest":{"max":44.692202712312394,"mean":28.293075614157832,"min":0.0},"none":{"max":41.30983496835532,"mean":22.956228644827995,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":5.336846969329837},"working_program_strength":{"all":29.28531671942047,"highest":32.33494355903752,"none":26.235689879803424}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:48cad3280fe927da","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":0.43500895999999994},"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":0.43500896000000006},"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":{"all":25.48860212638092,"medium":32.66835523618563,"none":18.308849016576204},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed","GB2-04":"failed"},"none":{"GB2-03":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":34.96136067645908,"score":30.21680596162017},"GB2-02":{"attempts":2,"playable":40.88382624158531,"score":40.88382624158531},"GB2-03":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":43.45333472329967,"score":21.726667361649834},"GB2-05":{"attempts":2,"playable":38.077340909830035,"score":38.077340909830035},"GB2-06":{"attempts":2,"playable":42.51744841206229,"score":42.51744841206229},"GB2-07":{"attempts":2,"playable":16.338196663531505,"score":16.338196663531505},"GB2-08":{"attempts":2,"failed_attempts":1,"playable":28.297062921536437,"score":14.148531460768218}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":50.944502493562524,"score":50.944502493562524},"GB2-02":{"attempts":1,"playable":43.108182717729534,"score":43.108182717729534},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"playable":43.95813459945167,"score":43.95813459945167},"GB2-06":{"attempts":1,"playable":70.45039702810364,"score":70.45039702810364},"GB2-07":{"attempts":1,"playable":24.588562129101295,"score":24.588562129101295},"GB2-08":{"attempts":1,"playable":28.297062921536437,"score":28.297062921536437}},"none":{"GB2-01":{"attempts":2,"failed_attempts":1,"playable":18.978218859355632,"score":9.489109429677816},"GB2-02":{"attempts":1,"playable":38.65946976544109,"score":38.65946976544109},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":43.45333472329967,"score":43.45333472329967},"GB2-05":{"attempts":1,"playable":32.1965472202084,"score":32.1965472202084},"GB2-06":{"attempts":1,"playable":14.584499796020948,"score":14.584499796020948},"GB2-07":{"attempts":1,"playable":8.08783119796172,"score":8.08783119796172},"GB2-08":{"attempts":1,"failed_attempts":1,"score":0.0}}},"id":"qwen/qwen3.7-plus","is_recent_addition":false,"last_measured_at":"2026-10-31T16:43:42Z","match_totals_all":{"draws":1425,"losses":3429,"wins":1298},"match_totals_tracks":{"medium":{"draws":630,"losses":1509,"wins":957},"none":{"draws":795,"losses":1920,"wins":341}},"model_slug":"qwen-qwen3-7-plus","official_rank_by_reasoning":{"medium":64,"none":83},"overall":{"max":70.45039702810364,"mean":25.48860212638092,"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":196,"losses":591,"wins":245},"GB2-02":{"draws":742,"losses":212,"wins":6},"GB2-04":{"draws":332,"losses":124,"wins":42},"GB2-05":{"draws":0,"losses":671,"wins":389},"GB2-06":{"draws":28,"losses":590,"wins":386},"GB2-07":{"draws":0,"losses":906,"wins":154},"GB2-08":{"draws":127,"losses":335,"wins":76}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":88,"losses":220,"wins":208},"GB2-02":{"draws":392,"losses":85,"wins":3},"GB2-05":{"draws":0,"losses":305,"wins":225},"GB2-06":{"draws":23,"losses":152,"wins":327},"GB2-07":{"draws":0,"losses":412,"wins":118},"GB2-08":{"draws":127,"losses":335,"wins":76}},"none":{"GB2-01":{"draws":108,"losses":371,"wins":37},"GB2-02":{"draws":350,"losses":127,"wins":3},"GB2-04":{"draws":332,"losses":124,"wins":42},"GB2-05":{"draws":0,"losses":366,"wins":164},"GB2-06":{"draws":5,"losses":438,"wins":59},"GB2-07":{"draws":0,"losses":494,"wins":36}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1478.0023461061749,"GB2-02":1418.7464884796957,"GB2-05":1361.898583084348,"GB2-06":1763.6579777335264,"GB2-07":1115.1224425437117,"GB2-08":1139.3396063604114},"none":{"GB2-01":1138.0176270299473,"GB2-02":1383.9361117360347,"GB2-04":1424.1495368083795,"GB2-05":1205.5073729508085,"GB2-06":860.4979727998624,"GB2-07":776.9960427084548}},"per_game_tracks":{"medium":{"GB2-01":50.944502493562524,"GB2-02":43.108182717729534,"GB2-05":43.95813459945167,"GB2-06":70.45039702810364,"GB2-07":24.588562129101295,"GB2-08":28.297062921536437},"none":{"GB2-01":18.978218859355632,"GB2-02":38.65946976544109,"GB2-04":43.45333472329967,"GB2-05":32.1965472202084,"GB2-06":14.584499796020948,"GB2-07":8.08783119796172}},"program_outcomes":{"all":{"counted_attempts":17,"failed":5,"infra_excluded":0,"success_rate":0.7058823529411765,"too_slow":0,"worked_after_repair":7,"worked_first_time":5,"working":12},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6},"none":{"counted_attempts":9,"failed":3,"infra_excluded":0,"success_rate":0.6666666666666666,"too_slow":0,"worked_after_repair":2,"worked_first_time":4,"working":6}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.66835523618563,"none":18.308849016576204},"reasoning_agg":{"medium":{"max":70.45039702810364,"mean":32.66835523618563,"min":0.0},"none":{"max":43.45333472329967,"mean":18.308849016576204,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":14.359506219609429},"working_program_strength":{"all":34.77556195431438,"medium":43.557806981580846,"none":25.99331692704791}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:432d200d01d8da23","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":{"all":24.739772586913418,"medium":30.67649396518031,"none":18.803051208646526},"first_seen_at":null,"game_gaps":{"all":{"GB2-05":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"infra_excluded","GB2-05":"infra_excluded","GB2-08":"infra_excluded"},"none":{"GB2-05":"failed","GB2-07":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":27.575440023772206,"score":27.575440023772206},"GB2-02":{"attempts":3,"failed_attempts":1,"playable":39.242165331482596,"score":29.07357596339526},"GB2-03":{"attempts":2,"playable":29.134127945808064,"score":29.134127945808064},"GB2-04":{"attempts":3,"failed_attempts":1,"playable":42.48080715774395,"score":31.235290471394023},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":3,"playable":14.659053039878351,"score":14.659053039878351},"GB2-07":{"attempts":4,"failed_attempts":2,"playable":36.069013697178576,"score":18.034506848589288},"GB2-08":{"attempts":3,"playable":33.51701885520744,"score":33.51701885520744}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":19.482780540796433,"score":19.482780540796433},"GB2-02":{"attempts":1,"playable":37.80997319061584,"score":37.80997319061584},"GB2-04":{"attempts":1,"playable":39.9795475700882,"score":39.9795475700882},"GB2-06":{"attempts":1,"playable":20.041154827222503,"score":20.041154827222503},"GB2-07":{"attempts":2,"playable":36.069013697178576,"score":36.069013697178576}},"none":{"GB2-01":{"attempts":2,"playable":35.66809950674798,"score":35.66809950674798},"GB2-02":{"attempts":2,"failed_attempts":1,"playable":40.67435747234936,"score":20.33717873617468},"GB2-03":{"attempts":2,"playable":29.134127945808064,"score":29.134127945808064},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":44.9820667453997,"score":22.49103337269985},"GB2-05":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-06":{"attempts":2,"playable":9.2769512525342,"score":9.2769512525342},"GB2-07":{"attempts":2,"failed_attempts":2,"score":0.0},"GB2-08":{"attempts":3,"playable":33.51701885520744,"score":33.51701885520744}}},"id":"inclusionai/ling-3.0-flash","is_recent_addition":false,"last_measured_at":"2026-10-31T16:48:34Z","match_totals_all":{"draws":2541,"losses":4921,"wins":1214},"match_totals_tracks":{"medium":{"draws":806,"losses":1754,"wins":496},"none":{"draws":1735,"losses":3167,"wins":718}},"model_slug":"inclusionai-ling-3-0-flash","official_rank_by_reasoning":{"none":82},"overall":{"max":39.9795475700882,"mean":24.739772586913418,"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":323,"losses":944,"wins":281},"GB2-02":{"draws":705,"losses":246,"wins":9},"GB2-03":{"draws":311,"losses":577,"wins":104},"GB2-04":{"draws":699,"losses":240,"wins":57},"GB2-06":{"draws":6,"losses":1341,"wins":159},"GB2-07":{"draws":0,"losses":705,"wins":355},"GB2-08":{"draws":497,"losses":868,"wins":249}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":129,"losses":358,"wins":29},"GB2-02":{"draws":334,"losses":139,"wins":7},"GB2-04":{"draws":340,"losses":137,"wins":21},"GB2-06":{"draws":3,"losses":415,"wins":84},"GB2-07":{"draws":0,"losses":705,"wins":355}},"none":{"GB2-01":{"draws":194,"losses":586,"wins":252},"GB2-02":{"draws":371,"losses":107,"wins":2},"GB2-03":{"draws":311,"losses":577,"wins":104},"GB2-04":{"draws":359,"losses":103,"wins":36},"GB2-06":{"draws":3,"losses":926,"wins":75},"GB2-08":{"draws":497,"losses":868,"wins":249}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1145.0328924187002,"GB2-02":1377.1822879360532,"GB2-04":1397.0229889545221,"GB2-06":956.8806419470943,"GB2-07":1272.5429912627797},"none":{"GB2-01":1329.2098270561721,"GB2-02":1399.8007400236527,"GB2-03":1243.4417790455132,"GB2-04":1435.9846452169086,"GB2-06":627.6418523890947,"GB2-08":1197.8359349757272}},"per_game_tracks":{"medium":{"GB2-01":19.482780540796433,"GB2-02":37.80997319061584,"GB2-04":39.9795475700882,"GB2-06":20.041154827222503,"GB2-07":36.069013697178576},"none":{"GB2-01":35.66809950674798,"GB2-02":40.67435747234936,"GB2-03":29.134127945808064,"GB2-04":44.9820667453997,"GB2-06":9.2769512525342,"GB2-08":33.51701885520744}},"program_outcomes":{"all":{"counted_attempts":23,"failed":6,"infra_excluded":10,"success_rate":0.7391304347826086,"too_slow":0,"worked_after_repair":9,"worked_first_time":8,"working":17},"medium":{"counted_attempts":6,"failed":0,"infra_excluded":10,"success_rate":1.0,"too_slow":0,"worked_after_repair":5,"worked_first_time":1,"working":6},"none":{"counted_attempts":17,"failed":6,"infra_excluded":0,"success_rate":0.6470588235294118,"too_slow":0,"worked_after_repair":4,"worked_first_time":7,"working":11}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#000000","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.67649396518031,"none":18.803051208646526},"reasoning_agg":{"medium":{"max":39.9795475700882,"mean":30.67649396518031,"min":19.482780540796433},"none":{"max":35.66809950674798,"mean":18.803051208646526,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"reasoning_variance":11.873442756533784},"working_program_strength":{"all":31.442632130760714,"medium":30.67649396518031,"none":32.20877029634112}},{"canonical_public_row_identity":"publication-row.v1:overall:recursive-flint-v1-0:d9c69a116ed62ccb","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0}},"codegen_cost_usd":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0,"mean":0.0,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":12},"recorded_attempt_count":12,"run_count":8,"total":0.0},"codegen_latency_ms":{"attempt_count":12,"max_ms":304042,"mean_ms":184222.375,"min_ms":109335,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":12,"max_ms":304042,"mean_ms":184222.375,"min_ms":109335,"run_count":8}},"codegen_output_tokens":{"attempt_count":12,"output_max":45150,"output_mean":24220.375,"output_min":14107,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":12,"output_max":45150,"output_mean":24220.375,"output_min":14107,"run_count":8}},"display_name":"Flint V1.0","economics":{"all":23.631752147251508,"medium":23.631752147251508},"first_seen_at":null,"game_gaps":{"all":{"GB2-03":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-03":"failed"},"none":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":12,"effective_max_output_tokens":[235929],"finish_reason_observations":12,"finish_reasons":["stop"],"indexed_attempts":12,"output_token_observations":12,"provider_post_attempt_observations":12,"provider_post_attempts":12,"reasoning_token_observations":12,"reconciliation_get_attempt_observations":12,"requested_max_output_token_observations":12,"requested_max_output_tokens":[235929],"total_output_tokens":193763,"total_reasoning_output_tokens":181158,"total_visible_output_tokens":12944,"visible_token_observations":12},"generation_policy":{"generation_policy":"quality_generation_policy","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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"other","provider_model":"recursive/flint-v1.0","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"unknown_legacy","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":4,"first_pass_rate":0.5,"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":3,"repaired_rate":0.375}},"headline_games_all":{"GB2-01":{"attempts":1,"playable":44.76602273365789,"score":44.76602273365789},"GB2-02":{"attempts":1,"playable":35.04472559887727,"score":35.04472559887727},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.77484924906058,"score":39.77484924906058},"GB2-05":{"attempts":1,"playable":13.929828693479774,"score":13.929828693479774},"GB2-06":{"attempts":1,"playable":16.982100171333382,"score":16.982100171333382},"GB2-07":{"attempts":1,"playable":10.358754187102608,"score":10.358754187102608},"GB2-08":{"attempts":1,"playable":28.197736544500568,"score":28.197736544500568}},"headline_games_tracks":{"medium":{"GB2-01":{"attempts":1,"playable":44.76602273365789,"score":44.76602273365789},"GB2-02":{"attempts":1,"playable":35.04472559887727,"score":35.04472559887727},"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-04":{"attempts":1,"playable":39.77484924906058,"score":39.77484924906058},"GB2-05":{"attempts":1,"playable":13.929828693479774,"score":13.929828693479774},"GB2-06":{"attempts":1,"playable":16.982100171333382,"score":16.982100171333382},"GB2-07":{"attempts":1,"playable":10.358754187102608,"score":10.358754187102608},"GB2-08":{"attempts":1,"playable":28.197736544500568,"score":28.197736544500568}}},"id":"recursive/flint-v1.0","is_recent_addition":false,"last_measured_at":"2026-10-24T18:07:56Z","match_totals_all":{"draws":733,"losses":2329,"wins":532},"match_totals_tracks":{"medium":{"draws":733,"losses":2329,"wins":532}},"model_slug":"recursive-flint-v1-0","official_rank_by_reasoning":{"medium":73},"overall":{"max":44.76602273365789,"mean":23.631752147251508,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game_match_totals_all":{"GB2-01":{"draws":75,"losses":258,"wins":183},"GB2-02":{"draws":322,"losses":158,"wins":0},"GB2-04":{"draws":334,"losses":141,"wins":23},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":2,"losses":429,"wins":71},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":0,"losses":399,"wins":139}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":75,"losses":258,"wins":183},"GB2-02":{"draws":322,"losses":158,"wins":0},"GB2-04":{"draws":334,"losses":141,"wins":23},"GB2-05":{"draws":0,"losses":461,"wins":69},"GB2-06":{"draws":2,"losses":429,"wins":71},"GB2-07":{"draws":0,"losses":483,"wins":47},"GB2-08":{"draws":0,"losses":399,"wins":139}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1419.2189031245157,"GB2-02":1354.852310036019,"GB2-04":1395.4098318529295,"GB2-05":889.0345132950164,"GB2-06":904.5649260997757,"GB2-07":842.690761888748,"GB2-08":1138.2016859250384}},"per_game_tracks":{"medium":{"GB2-01":44.76602273365789,"GB2-02":35.04472559887727,"GB2-04":39.77484924906058,"GB2-05":13.929828693479774,"GB2-06":16.982100171333382,"GB2-07":10.358754187102608,"GB2-08":28.197736544500568}},"program_outcomes":{"all":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7},"medium":{"counted_attempts":8,"failed":1,"infra_excluded":0,"success_rate":0.875,"too_slow":0,"worked_after_repair":3,"worked_first_time":4,"working":7}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.631752147251508},"reasoning_agg":{"medium":{"max":44.76602273365789,"mean":23.631752147251508,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"Setting not tested"},"reasoning_settings":{},"working_program_strength":{"all":27.00771673971601,"medium":27.00771673971601}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-5-pro:9145cdfa46fd7b2f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":11,"run_count":9,"total":0.04440505},"medium":{"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.020746485000000002,"mean":0.0054863575000000005,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":5},"recorded_attempt_count":12,"run_count":9,"total":0.043890860000000004},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0040270015625,"median":0.0034028549999999998,"min":0.0009412025,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":15,"run_count":9,"total":0.033157215}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.020746485000000002,"mean":0.0054863575000000005,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":5},"recorded_attempt_count":11,"run_count":8,"total":0.043890860000000004},"historical-provider-setting-balanced-variant-2":{"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-variant-1":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007327775,"mean":0.0041446518750000005,"median":0.0034028549999999998,"min":0.001882405,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":14},"recorded_attempt_count":14,"run_count":8,"total":0.033157215000000004},"historical-provider-setting-baseline-variant-2":{"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-intensive-variant-1":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02555855,"mean":0.00555063125,"median":0.0,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":4},"recorded_attempt_count":10,"run_count":8,"total":0.04440505},"historical-provider-setting-intensive-variant-2":{"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}},"codegen_cost_usd":{"admitted_cell_count":5,"cell_count":24,"cost_basis_counts":{"provider_reported":38},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.02555855,"mean":0.0050213301041666675,"median":0.00152996375,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-10-09":23},"recorded_attempt_count":38,"run_count":27,"total":0.12145312500000002},"codegen_latency_ms":{"attempt_count":23,"max_ms":2441104,"mean_ms":798480.3076923077,"min_ms":99802,"run_count":13},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":4,"max_ms":2441104,"mean_ms":2103669.0,"min_ms":1766234,"run_count":2},"medium":{"attempt_count":5,"max_ms":1803928,"mean_ms":1240602.3333333333,"min_ms":254972,"run_count":3},"none":{"attempt_count":14,"max_ms":535646,"mean_ms":306387.375,"min_ms":99802,"run_count":8}},"codegen_output_tokens":{"attempt_count":38,"output_max":170673,"output_mean":49682.0,"output_min":3766,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":91928,"output_mean":64861.0,"output_min":10319,"run_count":9},"medium":{"attempt_count":12,"output_max":170673,"output_mean":72901.44444444444,"output_min":9244,"run_count":9},"none":{"attempt_count":15,"output_max":20225,"output_mean":11283.555555555555,"output_min":3766,"run_count":9}},"display_name":"Nex N2.5 Pro","economics":{"all":19.648913703150146,"highest":20.637310574806985,"none":18.660516831493307},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed"},"highest":{"GB2-01":"infra_excluded","GB2-02":"infra_excluded","GB2-03":"failed","GB2-04":"infra_excluded","GB2-05":"infra_excluded","GB2-06":"infra_excluded","GB2-08":"infra_excluded"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-06":"failed"}},"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":38,"effective_max_output_tokens":[235929],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":38,"output_token_observations":38,"provider_post_attempt_observations":38,"provider_post_attempts":40,"reasoning_token_observations":38,"reconciliation_get_attempt_observations":38,"requested_max_output_token_observations":38,"requested_max_output_tokens":[235929],"total_output_tokens":1341414,"total_reasoning_output_tokens":1137994,"total_visible_output_tokens":203420,"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":"unknown_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":235929,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"nex-agi","provider_model":"nex-agi/nex-n2.5-pro","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openrouter","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"baseline":{"admitted_plugins":4,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-04","GB2-05","GB2-06"],"first_pass_admitted":4,"first_pass_rate":0.5,"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":{"model_code_failures":1},"GB2-07":{"admitted":1},"GB2-08":{"admitted":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}},"intensive":{"admitted_plugins":1,"evaluated_cells":2,"failed_game_aliases":["GB2-03"],"first_pass_admitted":1,"first_pass_rate":0.5,"game_attempts":{"GB2-01":{"infra_failures_excluded":1},"GB2-02":{"infra_failures_excluded":1},"GB2-03":{"model_code_failures":1},"GB2-04":{"infra_failures_excluded":1},"GB2-05":{"infra_failures_excluded":1},"GB2-06":{"infra_failures_excluded":1},"GB2-07":{"admitted":1},"GB2-08":{"infra_failures_excluded":1}},"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":6,"model_code_failure_rate":0.5,"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}}},"headline_games_all":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":37.49124495968166,"score":37.49124495968166},"GB2-03":{"attempts":2,"failed_attempts":1,"playable":45.9786807565218,"score":22.9893403782609},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":2,"playable":38.056019962226245,"score":38.056019962226245},"GB2-08":{"attempts":1,"playable":30.97679016090451,"score":30.97679016090451}},"headline_games_tracks":{"highest":{"GB2-03":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":41.27462114961397,"score":41.27462114961397}},"none":{"GB2-01":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-02":{"attempts":1,"playable":37.49124495968166,"score":37.49124495968166},"GB2-03":{"attempts":1,"playable":45.9786807565218,"score":45.9786807565218},"GB2-04":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-05":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":34.83741877483851,"score":34.83741877483851},"GB2-08":{"attempts":1,"playable":30.97679016090451,"score":30.97679016090451}}},"id":"nex-agi/nex-n2.5-pro","is_recent_addition":false,"last_measured_at":"2026-10-24T14:00:28Z","match_totals_all":{"draws":498,"losses":1414,"wins":662},"match_totals_tracks":{"highest":{"draws":0,"losses":325,"wins":205},"none":{"draws":498,"losses":1089,"wins":457}},"model_slug":"nex-agi-nex-n2-5-pro","overall":{"max":45.9786807565218,"mean":19.648913703150146,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold","generation_incomplete"],"overall_official_rank":null,"overall_ranking_status":"provisional","per_game":{"GB2-07":41.27462114961397},"per_game_match_totals_all":{"GB2-02":{"draws":341,"losses":137,"wins":2},"GB2-03":{"draws":157,"losses":208,"wins":131},"GB2-07":{"draws":0,"losses":684,"wins":376},"GB2-08":{"draws":0,"losses":385,"wins":153}},"per_game_match_totals_tracks":{"highest":{"GB2-07":{"draws":0,"losses":325,"wins":205}},"none":{"GB2-02":{"draws":341,"losses":137,"wins":2},"GB2-03":{"draws":157,"losses":208,"wins":131},"GB2-07":{"draws":0,"losses":359,"wins":171},"GB2-08":{"draws":0,"losses":385,"wins":153}}},"per_game_raw_elo_tracks":{"highest":{"GB2-07":1338.6849615809763},"none":{"GB2-02":1374.6367233029687,"GB2-03":1395.5344738119816,"GB2-07":1256.9132241625532,"GB2-08":1169.662164758129}},"per_game_tracks":{"highest":{"GB2-07":41.27462114961397},"none":{"GB2-02":37.49124495968166,"GB2-03":45.9786807565218,"GB2-07":34.83741877483851,"GB2-08":30.97679016090451}},"program_outcomes":{"all":{"counted_attempts":10,"failed":5,"infra_excluded":6,"success_rate":0.5,"too_slow":0,"worked_after_repair":0,"worked_first_time":5,"working":5},"highest":{"counted_attempts":2,"failed":1,"infra_excluded":6,"success_rate":0.5,"too_slow":0,"worked_after_repair":0,"worked_first_time":1,"working":1},"none":{"counted_attempts":8,"failed":4,"infra_excluded":0,"success_rate":0.5,"too_slow":0,"worked_after_repair":0,"worked_first_time":4,"working":4}},"provider_color":"#111827","provider_company":"Nex AGI","provider_key":"nex-agi","provider_text_color":"#f8fafc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.637310574806985,"none":18.660516831493307},"reasoning_agg":{"highest":{"max":41.27462114961397,"mean":20.637310574806985,"min":0.0},"none":{"max":45.9786807565218,"mean":18.660516831493307,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"reasoning_variance":1.976793743313678},"working_program_strength":{"all":39.29782740630029,"highest":41.27462114961397,"none":37.321033662986615}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:1234cb5692bc501c","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":{"all":15.057838585478697,"medium":23.394180709807728,"none":6.721496461149666},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-02":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"failed","GB2-02":"failed"},"none":{"GB2-01":"failed","GB2-02":"failed","GB2-03":"failed","GB2-04":"failed","GB2-06":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":21.6078160167764,"score":10.8039080083882},"GB2-04":{"attempts":2,"failed_attempts":1,"playable":41.820068227319894,"score":20.910034113659947},"GB2-05":{"attempts":2,"playable":33.16886710996443,"score":33.16886710996443},"GB2-06":{"attempts":2,"failed_attempts":1,"playable":16.754385681861702,"score":8.377192840930851},"GB2-07":{"attempts":2,"playable":16.12695485493272,"score":16.12695485493272},"GB2-08":{"attempts":2,"playable":31.075751755953426,"score":31.075751755953426}},"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":21.6078160167764,"score":21.6078160167764},"GB2-04":{"attempts":1,"playable":41.820068227319894,"score":41.820068227319894},"GB2-05":{"attempts":1,"playable":46.458506638358834,"score":46.458506638358834},"GB2-06":{"attempts":1,"playable":16.754385681861702,"score":16.754385681861702},"GB2-07":{"attempts":1,"playable":30.23021606524361,"score":30.23021606524361},"GB2-08":{"attempts":1,"playable":30.282453048901388,"score":30.282453048901388}},"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":19.87922758157003,"score":19.87922758157003},"GB2-06":{"attempts":1,"failed_attempts":1,"score":0.0},"GB2-07":{"attempts":1,"playable":2.0236936446218325,"score":2.0236936446218325},"GB2-08":{"attempts":1,"playable":31.869050463005465,"score":31.869050463005465}}},"id":"cohere/north-mini-code","is_recent_addition":false,"last_measured_at":"2026-08-05T05:19:01Z","match_totals_all":{"draws":816,"losses":3119,"wins":757},"match_totals_tracks":{"medium":{"draws":533,"losses":1927,"wins":634},"none":{"draws":283,"losses":1192,"wins":123}},"model_slug":"cohere-north-mini-code","official_rank_by_reasoning":{"medium":74},"overall":{"max":46.458506638358834,"mean":15.057838585478697,"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":112,"losses":345,"wins":39},"GB2-04":{"draws":308,"losses":144,"wins":46},"GB2-05":{"draws":0,"losses":722,"wins":338},"GB2-06":{"draws":2,"losses":430,"wins":70},"GB2-07":{"draws":0,"losses":906,"wins":154},"GB2-08":{"draws":394,"losses":572,"wins":110}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":112,"losses":345,"wins":39},"GB2-04":{"draws":308,"losses":144,"wins":46},"GB2-05":{"draws":0,"losses":292,"wins":238},"GB2-06":{"draws":2,"losses":430,"wins":70},"GB2-07":{"draws":0,"losses":383,"wins":147},"GB2-08":{"draws":111,"losses":333,"wins":94}},"none":{"GB2-05":{"draws":0,"losses":430,"wins":100},"GB2-07":{"draws":0,"losses":523,"wins":7},"GB2-08":{"draws":283,"losses":239,"wins":16}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1166.0071134402888,"GB2-04":1411.4467439815573,"GB2-05":1393.1978632249861,"GB2-06":900.5161305081344,"GB2-07":1195.713548278675,"GB2-08":1161.8665290564563},"none":{"GB2-05":1007.6930766151784,"GB2-07":462.5500537778771,"GB2-08":1179.6316173666253}},"per_game_tracks":{"medium":{"GB2-03":21.6078160167764,"GB2-04":41.820068227319894,"GB2-05":46.458506638358834,"GB2-06":16.754385681861702,"GB2-07":30.23021606524361,"GB2-08":30.282453048901388},"none":{"GB2-05":19.87922758157003,"GB2-07":2.0236936446218325,"GB2-08":31.869050463005465}},"program_outcomes":{"all":{"counted_attempts":16,"failed":7,"infra_excluded":0,"success_rate":0.5625,"too_slow":0,"worked_after_repair":4,"worked_first_time":5,"working":9},"medium":{"counted_attempts":8,"failed":2,"infra_excluded":0,"success_rate":0.75,"too_slow":0,"worked_after_repair":3,"worked_first_time":3,"working":6},"none":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":1,"worked_first_time":2,"working":3}},"provider_color":"#FF7759","provider_company":"Cohere","provider_key":"cohere","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":23.394180709807728,"none":6.721496461149666},"reasoning_agg":{"medium":{"max":46.458506638358834,"mean":23.394180709807728,"min":0.0},"none":{"max":31.869050463005465,"mean":6.721496461149666,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"reasoning_variance":16.67268424865806},"working_program_strength":{"all":24.55811575473804,"medium":31.192240946410305,"none":17.923990563065775}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:e3821806f8f4f3d0","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":{"all":11.8124248410361,"none":11.8124248410361},"first_seen_at":null,"game_gaps":{"all":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"},"highest":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"medium":{"GB2-01":"untested","GB2-02":"untested","GB2-03":"untested","GB2-04":"untested","GB2-05":"untested","GB2-06":"untested","GB2-07":"untested","GB2-08":"untested"},"none":{"GB2-01":"failed","GB2-04":"failed","GB2-05":"failed","GB2-07":"failed","GB2-08":"failed"}},"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":"1932e5bf7d911021b914de7f78743853e59ab0a0710896f1a32d8ce4907166cf","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":41.30983496835532,"score":41.30983496835532},"GB2-03":{"attempts":1,"playable":35.298065392804716,"score":35.298065392804716},"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":17.89149836712876,"score":17.89149836712876},"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":41.30983496835532,"score":41.30983496835532},"GB2-03":{"attempts":1,"playable":35.298065392804716,"score":35.298065392804716},"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":17.89149836712876,"score":17.89149836712876},"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":"2026-10-31T16:26:25Z","match_totals_all":{"draws":680,"losses":713,"wins":85},"match_totals_tracks":{"none":{"draws":680,"losses":713,"wins":85}},"model_slug":"gpt-4-1-nano","overall":{"max":41.30983496835532,"mean":11.8124248410361,"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":375,"losses":102,"wins":3},"GB2-03":{"draws":299,"losses":188,"wins":9},"GB2-06":{"draws":6,"losses":423,"wins":73}},"per_game_match_totals_tracks":{"none":{"GB2-02":{"draws":375,"losses":102,"wins":3},"GB2-03":{"draws":299,"losses":188,"wins":9},"GB2-06":{"draws":6,"losses":423,"wins":73}}},"per_game_raw_elo_tracks":{"none":{"GB2-02":1404.766777445727,"GB2-03":1301.9745366423936,"GB2-06":920.4962278676068}},"per_game_tracks":{"none":{"GB2-02":41.30983496835532,"GB2-03":35.298065392804716,"GB2-06":17.89149836712876}},"program_outcomes":{"all":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":0,"worked_first_time":3,"working":3},"none":{"counted_attempts":8,"failed":5,"infra_excluded":0,"success_rate":0.375,"too_slow":0,"worked_after_repair":0,"worked_first_time":3,"working":3}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#111418","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":11.8124248410361},"reasoning_agg":{"none":{"max":41.30983496835532,"mean":11.8124248410361,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"working_program_strength":{"all":31.499799576096265,"none":31.499799576096265}}],"public_release_id":"gb2-20261101-00b883bd2c89","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":"gb2-20261101-00b883bd2c89","schema_version":2,"snapshot_id":"20261101_080050","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-11-01 08:00 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":27},"claude-fable-5":{"draws":17,"losses":96,"wins":19},"claude-fable-5-1":{"draws":7,"losses":135,"wins":6},"claude-haiku-5-5":{"draws":28,"losses":73,"wins":25},"claude-opus-4-5":{"draws":67,"losses":93,"wins":54},"claude-opus-4-8":{"draws":30,"losses":69,"wins":21},"claude-opus-5":{"draws":27,"losses":177,"wins":22},"claude-opus-5-5":{"draws":6,"losses":131,"wins":7},"claude-sonnet-5":{"draws":36,"losses":71,"wins":25},"claude-sonnet-5-5":{"draws":28,"losses":80,"wins":24},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":23},"deepseek/deepseek-v4-flash":{"draws":55,"losses":68,"wins":73},"deepseek/deepseek-v4-pro":{"draws":30,"losses":61,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":53,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":67,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":89,"wins":20},"elorian/glimpse":{"draws":16,"losses":34,"wins":22},"fireworks/ember-1":{"draws":36,"losses":70,"wins":26},"gemini-3.1-pro-preview":{"draws":31,"losses":63,"wins":38},"gemini-4-argon":{"draws":3,"losses":123,"wins":6},"google/gemini-3.1-flash-lite":{"draws":22,"losses":19,"wins":47},"google/gemini-3.5-flash":{"draws":34,"losses":82,"wins":50},"google/gemini-3.5-flash-lite":{"draws":70,"losses":77,"wins":87},"google/gemini-3.6-flash":{"draws":56,"losses":139,"wins":59},"google/gemini-3.8-flash":{"draws":26,"losses":83,"wins":23},"google/gemma-4-31b-it":{"draws":27,"losses":24,"wins":25},"gpt-4.1":{"draws":14,"losses":19,"wins":11},"gpt-4.1-nano":{"draws":8,"losses":4,"wins":4},"gpt-5":{"draws":32,"losses":43,"wins":41},"gpt-5.4":{"draws":29,"losses":70,"wins":29},"gpt-5.4-mini":{"draws":29,"losses":26,"wins":33},"gpt-5.4-nano":{"draws":26,"losses":48,"wins":58},"gpt-5.5":{"draws":41,"losses":57,"wins":24},"gpt-5.6-luna":{"draws":39,"losses":46,"wins":47},"gpt-5.6-sol":{"draws":22,"losses":98,"wins":12},"gpt-5.6-terra":{"draws":31,"losses":69,"wins":26},"gpt-6-astra":{"draws":6,"losses":120,"wins":6},"gpt-6-luna":{"draws":40,"losses":53,"wins":39},"gpt-6-sol":{"draws":15,"losses":103,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":113,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":25,"wins":35},"inception/mercury-3":{"draws":25,"losses":34,"wins":27},"inclusionai/ling-3.0-flash":{"draws":36,"losses":16,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":34,"losses":45,"wins":65},"meta/muse-glimmer-30b":{"draws":35,"losses":37,"wins":44},"meta/muse-spark-1.2":{"draws":31,"losses":64,"wins":31},"meta/muse-spark-1.3":{"draws":27,"losses":83,"wins":22},"meta/muse-spark-open":{"draws":26,"losses":75,"wins":27},"meta/muse-wonder":{"draws":30,"losses":86,"wins":16},"minimax/minimax-m3":{"draws":18,"losses":13,"wins":39},"minimax/minimax-m3.1-flash":{"draws":26,"losses":47,"wins":43},"mistralai/mistral-large-4-0":{"draws":25,"losses":33,"wins":24},"mistralai/mistral-medium-3-5":{"draws":30,"losses":19,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":15,"wins":8},"moonshotai/kimi-k3":{"draws":34,"losses":60,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":105,"wins":8},"nex-agi/nex-n2-pro":{"draws":14,"losses":16,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":37,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":22,"wins":16},"o3":{"draws":38,"losses":90,"wins":56},"openai/gpt-oss-120b":{"draws":34,"losses":33,"wins":47},"poolside/laguna-s-2.1":{"draws":40,"losses":41,"wins":47},"qwen/qwen3.7-max":{"draws":21,"losses":29,"wins":26},"qwen/qwen3.7-plus":{"draws":18,"losses":21,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":63,"wins":30},"qwen/qwen3.8-27b":{"draws":22,"losses":48,"wins":24},"qwen/qwen3.8-flash":{"draws":26,"losses":40,"wins":22},"qwen/qwen3.8-max":{"draws":41,"losses":53,"wins":38},"qwen/qwen3.8-max-0902":{"draws":31,"losses":77,"wins":24},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":32,"losses":57,"wins":31},"stealth/ox-alpha":{"draws":92,"losses":259,"wins":89},"stealth/space-bunny-alpha":{"draws":34,"losses":40,"wins":30},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":38},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":24,"wins":26},"tencent/hy4-preview":{"draws":35,"losses":75,"wins":18},"thinkingmachines/inkling":{"draws":57,"losses":48,"wins":73},"thinkingmachines/inkling-small":{"draws":42,"losses":30,"wins":60},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":0},"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":30,"losses":85,"wins":17},"x-ai/grok-4.6":{"draws":30,"losses":85,"wins":17},"x-ai/grok-4.7":{"draws":6,"losses":93,"wins":15},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":21},"xiaomi/mimo-v2.5":{"draws":66,"losses":55,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":25,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":51,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":57,"wins":18},"z-ai/glm-5.2":{"draws":88,"losses":100,"wins":76},"z-ai/glm-5.3":{"draws":22,"losses":88,"wins":16},"z-ai/glm-5.3-flash":{"draws":28,"losses":74,"wins":30},"z-ai/glm-5.3-flashx":{"draws":20,"losses":86,"wins":26}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":19,"wins":96},"claude-fable-5":{"draws":14,"losses":41,"wins":41},"claude-fable-5-1":{"draws":10,"losses":134,"wins":18},"claude-haiku-5-5":{"draws":25,"losses":39,"wins":74},"claude-opus-4-5":{"draws":36,"losses":40,"wins":158},"claude-opus-4-8":{"draws":22,"losses":37,"wins":73},"claude-opus-5":{"draws":33,"losses":142,"wins":71},"claude-opus-5-5":{"draws":12,"losses":122,"wins":22},"claude-sonnet-5":{"draws":23,"losses":27,"wins":94},"claude-sonnet-5-5":{"draws":26,"losses":59,"wins":59},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":35,"losses":14,"wins":167},"deepseek/deepseek-v4-pro":{"draws":24,"losses":27,"wins":81},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":26,"wins":88},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":37,"wins":74},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":53,"wins":65},"elorian/glimpse":{"draws":11,"losses":28,"wins":39},"fireworks/ember-1":{"draws":31,"losses":22,"wins":91},"gemini-3.1-pro-preview":{"draws":29,"losses":29,"wins":86},"gemini-4-argon":{"draws":13,"losses":101,"wins":30},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":83},"google/gemini-3.5-flash":{"draws":28,"losses":33,"wins":119},"google/gemini-3.5-flash-lite":{"draws":38,"losses":28,"wins":186},"google/gemini-3.6-flash":{"draws":39,"losses":80,"wins":157},"google/gemini-3.8-flash":{"draws":19,"losses":57,"wins":68},"google/gemma-4-31b-it":{"draws":18,"losses":8,"wins":58},"gpt-4.1":{"draws":8,"losses":12,"wins":28},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":20,"losses":21,"wins":85},"gpt-5.4":{"draws":31,"losses":40,"wins":67},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":66},"gpt-5.4-nano":{"draws":16,"losses":15,"wins":113},"gpt-5.5":{"draws":30,"losses":39,"wins":63},"gpt-5.6-luna":{"draws":27,"losses":18,"wins":99},"gpt-5.6-sol":{"draws":16,"losses":64,"wins":64},"gpt-5.6-terra":{"draws":31,"losses":20,"wins":87},"gpt-6-astra":{"draws":11,"losses":112,"wins":21},"gpt-6-luna":{"draws":29,"losses":27,"wins":88},"gpt-6-sol":{"draws":18,"losses":83,"wins":43},"gpt-6.1-sol":{"draws":10,"losses":100,"wins":34},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":5,"wins":71},"inception/mercury-3":{"draws":24,"losses":13,"wins":59},"inclusionai/ling-3.0-flash":{"draws":18,"losses":4,"wins":80},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":14,"losses":20,"wins":122},"meta/muse-glimmer-30b":{"draws":22,"losses":7,"wins":97},"meta/muse-spark-1.2":{"draws":19,"losses":31,"wins":88},"meta/muse-spark-1.3":{"draws":22,"losses":43,"wins":79},"meta/muse-spark-open":{"draws":21,"losses":31,"wins":86},"meta/muse-wonder":{"draws":25,"losses":57,"wins":62},"minimax/minimax-m3":{"draws":18,"losses":6,"wins":54},"minimax/minimax-m3.1-flash":{"draws":23,"losses":20,"wins":83},"mistralai/mistral-large-4-0":{"draws":21,"losses":20,"wins":49},"mistralai/mistral-medium-3-5":{"draws":17,"losses":6,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":27},"moonshotai/kimi-k3":{"draws":24,"losses":28,"wins":86},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":98,"wins":35},"nex-agi/nex-n2-pro":{"draws":12,"losses":2,"wins":58},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":13,"wins":93},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":4,"wins":49},"o3":{"draws":16,"losses":30,"wins":152},"openai/gpt-oss-120b":{"draws":26,"losses":11,"wins":89},"poolside/laguna-s-2.1":{"draws":20,"losses":20,"wins":98},"qwen/qwen3.7-max":{"draws":11,"losses":13,"wins":60},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":36,"wins":76},"qwen/qwen3.8-27b":{"draws":20,"losses":16,"wins":66},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":56},"qwen/qwen3.8-max":{"draws":24,"losses":36,"wins":84},"qwen/qwen3.8-max-0902":{"draws":28,"losses":35,"wins":81},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":26,"wins":81},"stealth/ox-alpha":{"draws":75,"losses":122,"wins":277},"stealth/space-bunny-alpha":{"draws":29,"losses":15,"wins":70},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":82},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":45},"tencent/hy4-preview":{"draws":18,"losses":30,"wins":90},"thinkingmachines/inkling":{"draws":36,"losses":12,"wins":144},"thinkingmachines/inkling-small":{"draws":23,"losses":14,"wins":107},"unbiased/pareto-26.10":{"draws":1,"losses":43,"wins":4},"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":24,"losses":47,"wins":73},"x-ai/grok-4.6":{"draws":31,"losses":49,"wins":64},"x-ai/grok-4.7":{"draws":7,"losses":77,"wins":42},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":34},"xiaomi/mimo-v2.5":{"draws":38,"losses":6,"wins":178},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":66},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":21,"wins":53},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":40,"wins":48},"z-ai/glm-5.2":{"draws":58,"losses":42,"wins":188},"z-ai/glm-5.3":{"draws":21,"losses":63,"wins":54},"z-ai/glm-5.3-flash":{"draws":22,"losses":46,"wins":76},"z-ai/glm-5.3-flashx":{"draws":22,"losses":43,"wins":79}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":135},"claude-fable-5":{"draws":10,"losses":18,"wins":134},"claude-fable-5-1":{"draws":8,"losses":62,"wins":62},"claude-haiku-5-5":{"draws":8,"losses":10,"wins":136},"claude-opus-4-5":{"draws":12,"losses":11,"wins":239},"claude-opus-4-8":{"draws":10,"losses":11,"wins":125},"claude-opus-5":{"draws":23,"losses":76,"wins":179},"claude-opus-5-5":{"draws":15,"losses":88,"wins":71},"claude-sonnet-5":{"draws":7,"losses":6,"wins":149},"claude-sonnet-5-5":{"draws":8,"losses":37,"wins":117},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":60},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":233},"deepseek/deepseek-v4-pro":{"draws":10,"losses":5,"wins":135},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":144},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":136},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":133},"elorian/glimpse":{"draws":7,"losses":9,"wins":74},"fireworks/ember-1":{"draws":5,"losses":10,"wins":147},"gemini-3.1-pro-preview":{"draws":8,"losses":5,"wins":149},"gemini-4-argon":{"draws":14,"losses":53,"wins":95},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":99},"google/gemini-3.5-flash":{"draws":13,"losses":7,"wins":182},"google/gemini-3.5-flash-lite":{"draws":14,"losses":3,"wins":267},"google/gemini-3.6-flash":{"draws":15,"losses":19,"wins":278},"google/gemini-3.8-flash":{"draws":11,"losses":14,"wins":137},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":89},"gpt-4.1":{"draws":5,"losses":2,"wins":47},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":20},"gpt-5":{"draws":4,"losses":1,"wins":137},"gpt-5.4":{"draws":9,"losses":15,"wins":132},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":102},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":152},"gpt-5.5":{"draws":6,"losses":17,"wins":127},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":146},"gpt-5.6-sol":{"draws":13,"losses":19,"wins":130},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":143},"gpt-6-astra":{"draws":15,"losses":83,"wins":64},"gpt-6-luna":{"draws":12,"losses":6,"wins":144},"gpt-6-sol":{"draws":12,"losses":40,"wins":110},"gpt-6.1-sol":{"draws":10,"losses":78,"wins":74},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":107},"inception/mercury-3":{"draws":4,"losses":1,"wins":101},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":106},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":7,"wins":165},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":136},"meta/muse-spark-1.2":{"draws":8,"losses":9,"wins":139},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":135},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":137},"meta/muse-wonder":{"draws":13,"losses":31,"wins":118},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"minimax/minimax-m3.1-flash":{"draws":8,"losses":5,"wins":131},"mistralai/mistral-large-4-0":{"draws":5,"losses":8,"wins":89},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":87},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":37},"moonshotai/kimi-k3":{"draws":7,"losses":11,"wins":138},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":43,"wins":104},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":77},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":127},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":71},"o3":{"draws":3,"losses":9,"wins":206},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":137},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":145},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":89},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":74},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":7,"wins":147},"qwen/qwen3.8-27b":{"draws":6,"losses":1,"wins":107},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":96},"qwen/qwen3.8-max":{"draws":9,"losses":4,"wins":149},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":137},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":44},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":2,"wins":141},"stealth/ox-alpha":{"draws":26,"losses":26,"wins":498},"stealth/space-bunny-alpha":{"draws":3,"losses":2,"wins":125},"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":7,"losses":4,"wins":75},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":134},"thinkingmachines/inkling":{"draws":8,"losses":1,"wins":209},"thinkingmachines/inkling-small":{"draws":12,"losses":0,"wins":150},"unbiased/pareto-26.10":{"draws":7,"losses":26,"wins":21},"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":12,"losses":11,"wins":139},"x-ai/grok-4.6":{"draws":9,"losses":24,"wins":129},"x-ai/grok-4.7":{"draws":6,"losses":34,"wins":100},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":51},"xiaomi/mimo-v2.5":{"draws":12,"losses":6,"wins":226},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":84},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":8,"wins":87},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":10,"wins":84},"z-ai/glm-5.2":{"draws":16,"losses":5,"wins":303},"z-ai/glm-5.3":{"draws":13,"losses":20,"wins":123},"z-ai/glm-5.3-flash":{"draws":9,"losses":12,"wins":141},"z-ai/glm-5.3-flashx":{"draws":10,"losses":14,"wins":138}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":73},"claude-fable-5":{"draws":25,"losses":74,"wins":39},"claude-fable-5-1":{"draws":8,"losses":136,"wins":10},"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":27,"losses":57,"wins":46},"claude-opus-5":{"draws":38,"losses":159,"wins":37},"claude-opus-5-5":{"draws":16,"losses":127,"wins":7},"claude-sonnet-5":{"draws":35,"losses":40,"wins":63},"claude-sonnet-5-5":{"draws":24,"losses":71,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":58,"losses":29,"wins":121},"deepseek/deepseek-v4-pro":{"draws":33,"losses":41,"wins":52},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":29,"wins":63},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":39,"wins":57},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":61,"wins":52},"elorian/glimpse":{"draws":11,"losses":29,"wins":34},"fireworks/ember-1":{"draws":37,"losses":38,"wins":63},"gemini-3.1-pro-preview":{"draws":34,"losses":46,"wins":58},"gemini-4-argon":{"draws":14,"losses":98,"wins":26},"google/gemini-3.1-flash-lite":{"draws":20,"losses":8,"wins":68},"google/gemini-3.5-flash":{"draws":37,"losses":60,"wins":77},"google/gemini-3.5-flash-lite":{"draws":52,"losses":40,"wins":150},"google/gemini-3.6-flash":{"draws":62,"losses":99,"wins":103},"google/gemini-3.8-flash":{"draws":34,"losses":61,"wins":43},"google/gemma-4-31b-it":{"draws":22,"losses":9,"wins":51},"gpt-4.1":{"draws":14,"losses":8,"wins":24},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":9},"gpt-5":{"draws":31,"losses":26,"wins":63},"gpt-5.4":{"draws":31,"losses":51,"wins":50},"gpt-5.4-mini":{"draws":27,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":29,"losses":39,"wins":74},"gpt-5.5":{"draws":46,"losses":35,"wins":45},"gpt-5.6-luna":{"draws":40,"losses":24,"wins":74},"gpt-5.6-sol":{"draws":20,"losses":77,"wins":41},"gpt-5.6-terra":{"draws":39,"losses":37,"wins":56},"gpt-6-astra":{"draws":8,"losses":123,"wins":7},"gpt-6-luna":{"draws":35,"losses":39,"wins":64},"gpt-6-sol":{"draws":25,"losses":85,"wins":28},"gpt-6.1-sol":{"draws":13,"losses":114,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":66},"inception/mercury-3":{"draws":23,"losses":29,"wins":40},"inclusionai/ling-3.0-flash":{"draws":29,"losses":5,"wins":64},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":32,"losses":21,"wins":97},"meta/muse-glimmer-30b":{"draws":36,"losses":15,"wins":69},"meta/muse-spark-1.2":{"draws":28,"losses":40,"wins":64},"meta/muse-spark-1.3":{"draws":27,"losses":51,"wins":60},"meta/muse-spark-open":{"draws":19,"losses":55,"wins":58},"meta/muse-wonder":{"draws":30,"losses":79,"wins":29},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":53},"minimax/minimax-m3.1-flash":{"draws":24,"losses":28,"wins":68},"mistralai/mistral-large-4-0":{"draws":29,"losses":28,"wins":29},"mistralai/mistral-medium-3-5":{"draws":21,"losses":4,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":15},"moonshotai/kimi-k3":{"draws":34,"losses":39,"wins":59},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":99,"wins":23},"nex-agi/nex-n2-pro":{"draws":14,"losses":10,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":26,"wins":66},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":20,"wins":33},"o3":{"draws":32,"losses":61,"wins":101},"openai/gpt-oss-120b":{"draws":29,"losses":12,"wins":79},"poolside/laguna-s-2.1":{"draws":34,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":28,"losses":20,"wins":34},"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":30,"wins":46},"qwen/qwen3.8-flash":{"draws":27,"losses":18,"wins":47},"qwen/qwen3.8-max":{"draws":34,"losses":37,"wins":67},"qwen/qwen3.8-max-0902":{"draws":40,"losses":47,"wins":51},"recursive/flint-v1.0":{"draws":9,"losses":8,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":35,"wins":66},"stealth/ox-alpha":{"draws":95,"losses":165,"wins":174},"stealth/space-bunny-alpha":{"draws":30,"losses":23,"wins":57},"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":50,"losses":23,"wins":109},"thinkingmachines/inkling-small":{"draws":33,"losses":13,"wins":92},"unbiased/pareto-26.10":{"draws":4,"losses":38,"wins":4},"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":92,"wins":18},"x-ai/grok-build-0.1":{"draws":12,"losses":4,"wins":30},"xiaomi/mimo-v2.5":{"draws":57,"losses":31,"wins":132},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":18,"wins":41},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":27,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":43,"wins":32},"z-ai/glm-5.2":{"draws":64,"losses":65,"wins":147},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":32},"z-ai/glm-5.3-flash":{"draws":27,"losses":56,"wins":55},"z-ai/glm-5.3-flashx":{"draws":29,"losses":52,"wins":57}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":34,"wins":63},"claude-fable-5":{"draws":23,"losses":92,"wins":29},"claude-fable-5-1":{"draws":11,"losses":143,"wins":8},"claude-haiku-5-5":{"draws":40,"losses":55,"wins":43},"claude-opus-4-5":{"draws":61,"losses":53,"wins":72},"claude-opus-4-8":{"draws":37,"losses":57,"wins":38},"claude-opus-5":{"draws":37,"losses":186,"wins":23},"claude-opus-5-5":{"draws":12,"losses":135,"wins":9},"claude-sonnet-5":{"draws":49,"losses":44,"wins":51},"claude-sonnet-5-5":{"draws":29,"losses":72,"wins":43},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":43},"deepseek/deepseek-v4-flash":{"draws":56,"losses":44,"wins":116},"deepseek/deepseek-v4-pro":{"draws":36,"losses":47,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":49,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":61,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":84,"wins":33},"elorian/glimpse":{"draws":19,"losses":35,"wins":24},"fireworks/ember-1":{"draws":48,"losses":56,"wins":40},"gemini-3.1-pro-preview":{"draws":32,"losses":46,"wins":66},"gemini-4-argon":{"draws":6,"losses":129,"wins":9},"google/gemini-3.1-flash-lite":{"draws":20,"losses":2,"wins":74},"google/gemini-3.5-flash":{"draws":42,"losses":72,"wins":66},"google/gemini-3.5-flash-lite":{"draws":79,"losses":50,"wins":123},"google/gemini-3.6-flash":{"draws":72,"losses":124,"wins":80},"google/gemini-3.8-flash":{"draws":39,"losses":73,"wins":32},"google/gemma-4-31b-it":{"draws":28,"losses":10,"wins":46},"gpt-4.1":{"draws":18,"losses":12,"wins":18},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":6},"gpt-5":{"draws":36,"losses":41,"wins":49},"gpt-5.4":{"draws":37,"losses":68,"wins":33},"gpt-5.4-mini":{"draws":36,"losses":18,"wins":42},"gpt-5.4-nano":{"draws":38,"losses":32,"wins":74},"gpt-5.5":{"draws":54,"losses":53,"wins":25},"gpt-5.6-luna":{"draws":51,"losses":30,"wins":63},"gpt-5.6-sol":{"draws":22,"losses":97,"wins":25},"gpt-5.6-terra":{"draws":49,"losses":41,"wins":48},"gpt-6-astra":{"draws":9,"losses":126,"wins":9},"gpt-6-luna":{"draws":43,"losses":49,"wins":52},"gpt-6-sol":{"draws":23,"losses":106,"wins":15},"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":42,"losses":6,"wins":54},"inception/mercury-3":{"draws":27,"losses":33,"wins":36},"inclusionai/ling-3.0-flash":{"draws":37,"losses":10,"wins":55},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":38,"losses":22,"wins":96},"meta/muse-glimmer-30b":{"draws":39,"losses":18,"wins":69},"meta/muse-spark-1.2":{"draws":34,"losses":66,"wins":38},"meta/muse-spark-1.3":{"draws":28,"losses":80,"wins":36},"meta/muse-spark-open":{"draws":37,"losses":59,"wins":42},"meta/muse-wonder":{"draws":27,"losses":87,"wins":30},"minimax/minimax-m3":{"draws":20,"losses":9,"wins":49},"minimax/minimax-m3.1-flash":{"draws":31,"losses":37,"wins":58},"mistralai/mistral-large-4-0":{"draws":30,"losses":27,"wins":33},"mistralai/mistral-medium-3-5":{"draws":23,"losses":8,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":19},"moonshotai/kimi-k3":{"draws":47,"losses":48,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":114,"wins":13},"nex-agi/nex-n2-pro":{"draws":17,"losses":9,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":16,"wins":71},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":21,"wins":22},"o3":{"draws":25,"losses":55,"wins":118},"openai/gpt-oss-120b":{"draws":38,"losses":22,"wins":66},"poolside/laguna-s-2.1":{"draws":41,"losses":20,"wins":77},"qwen/qwen3.7-max":{"draws":20,"losses":21,"wins":43},"qwen/qwen3.7-plus":{"draws":20,"losses":14,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":46,"losses":60,"wins":38},"qwen/qwen3.8-27b":{"draws":29,"losses":37,"wins":36},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":33},"qwen/qwen3.8-max":{"draws":37,"losses":64,"wins":43},"qwen/qwen3.8-max-0902":{"draws":36,"losses":58,"wins":50},"recursive/flint-v1.0":{"draws":12,"losses":1,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":44,"losses":42,"wins":46},"stealth/ox-alpha":{"draws":122,"losses":200,"wins":152},"stealth/space-bunny-alpha":{"draws":33,"losses":27,"wins":54},"stepfun/step-3.7-flash":{"draws":15,"losses":21,"wins":66},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":27,"losses":17,"wins":34},"tencent/hy4-preview":{"draws":32,"losses":62,"wins":44},"thinkingmachines/inkling":{"draws":58,"losses":30,"wins":104},"thinkingmachines/inkling-small":{"draws":42,"losses":18,"wins":84},"unbiased/pareto-26.10":{"draws":5,"losses":43,"wins":0},"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":40,"losses":62,"wins":42},"x-ai/grok-4.6":{"draws":34,"losses":76,"wins":34},"x-ai/grok-4.7":{"draws":11,"losses":89,"wins":26},"x-ai/grok-build-0.1":{"draws":15,"losses":7,"wins":26},"xiaomi/mimo-v2.5":{"draws":70,"losses":31,"wins":121},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":26,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":43,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":52,"wins":20},"z-ai/glm-5.2":{"draws":83,"losses":79,"wins":126},"z-ai/glm-5.3":{"draws":32,"losses":83,"wins":23},"z-ai/glm-5.3-flash":{"draws":31,"losses":75,"wins":38},"z-ai/glm-5.3-flashx":{"draws":36,"losses":75,"wins":33}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":21,"wins":69},"claude-fable-5":{"draws":22,"losses":73,"wins":37},"claude-fable-5-1":{"draws":10,"losses":125,"wins":11},"claude-haiku-5-5":{"draws":27,"losses":46,"wins":57},"claude-opus-4-5":{"draws":61,"losses":54,"wins":103},"claude-opus-4-8":{"draws":16,"losses":34,"wins":34},"claude-opus-5":{"draws":32,"losses":157,"wins":33},"claude-opus-5-5":{"draws":12,"losses":115,"wins":17},"claude-sonnet-5":{"draws":33,"losses":40,"wins":59},"claude-sonnet-5-5":{"draws":26,"losses":63,"wins":43},"cohere/north-mini-code":{"draws":10,"losses":3,"wins":37},"deepseek/deepseek-v4-flash":{"draws":45,"losses":30,"wins":125},"deepseek/deepseek-v4-pro":{"draws":27,"losses":37,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":39,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":58,"wins":49},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":66,"wins":42},"elorian/glimpse":{"draws":14,"losses":29,"wins":27},"fireworks/ember-1":{"draws":42,"losses":38,"wins":52},"gemini-3.1-pro-preview":{"draws":29,"losses":38,"wins":65},"gemini-4-argon":{"draws":9,"losses":98,"wins":25},"google/gemini-3.1-flash-lite":{"draws":19,"losses":7,"wins":70},"google/gemini-3.5-flash":{"draws":37,"losses":49,"wins":82},"google/gemini-3.5-flash-lite":{"draws":57,"losses":25,"wins":150},"google/gemini-3.6-flash":{"draws":53,"losses":105,"wins":94},"google/gemini-3.8-flash":{"draws":27,"losses":61,"wins":44},"google/gemma-4-31b-it":{"draws":23,"losses":10,"wins":47},"gpt-4.1":{"draws":10,"losses":7,"wins":27},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":7},"gpt-5":{"draws":27,"losses":31,"wins":56},"gpt-5.4":{"draws":30,"losses":56,"wins":40},"gpt-5.4-mini":{"draws":20,"losses":24,"wins":44},"gpt-5.4-nano":{"draws":25,"losses":31,"wins":84},"gpt-5.5":{"draws":34,"losses":50,"wins":36},"gpt-5.6-luna":{"draws":34,"losses":33,"wins":65},"gpt-5.6-sol":{"draws":21,"losses":74,"wins":37},"gpt-5.6-terra":{"draws":28,"losses":40,"wins":58},"gpt-6-astra":{"draws":8,"losses":114,"wins":10},"gpt-6-luna":{"draws":29,"losses":39,"wins":64},"gpt-6-sol":{"draws":17,"losses":80,"wins":35},"gpt-6.1-sol":{"draws":6,"losses":110,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":29,"losses":11,"wins":58},"inception/mercury-3":{"draws":24,"losses":20,"wins":44},"inclusionai/ling-3.0-flash":{"draws":31,"losses":0,"wins":63},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":28,"losses":24,"wins":92},"meta/muse-glimmer-30b":{"draws":24,"losses":19,"wins":71},"meta/muse-spark-1.2":{"draws":27,"losses":47,"wins":52},"meta/muse-spark-1.3":{"draws":23,"losses":56,"wins":53},"meta/muse-spark-open":{"draws":27,"losses":47,"wins":52},"meta/muse-wonder":{"draws":26,"losses":62,"wins":44},"minimax/minimax-m3":{"draws":17,"losses":10,"wins":47},"minimax/minimax-m3.1-flash":{"draws":26,"losses":28,"wins":60},"mistralai/mistral-large-4-0":{"draws":18,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":21,"losses":6,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":21},"moonshotai/kimi-k3":{"draws":34,"losses":43,"wins":49},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":106,"wins":13},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":20,"wins":80},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":12,"wins":35},"o3":{"draws":25,"losses":55,"wins":110},"openai/gpt-oss-120b":{"draws":33,"losses":13,"wins":68},"poolside/laguna-s-2.1":{"draws":33,"losses":18,"wins":71},"qwen/qwen3.7-max":{"draws":21,"losses":22,"wins":37},"qwen/qwen3.7-plus":{"draws":18,"losses":11,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":50,"wins":42},"qwen/qwen3.8-27b":{"draws":20,"losses":31,"wins":43},"qwen/qwen3.8-flash":{"draws":28,"losses":18,"wins":42},"qwen/qwen3.8-max":{"draws":25,"losses":47,"wins":60},"qwen/qwen3.8-max-0902":{"draws":29,"losses":52,"wins":51},"recursive/flint-v1.0":{"draws":11,"losses":2,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":32,"wins":62},"stealth/ox-alpha":{"draws":76,"losses":162,"wins":156},"stealth/space-bunny-alpha":{"draws":25,"losses":27,"wins":54},"stepfun/step-3.7-flash":{"draws":16,"losses":18,"wins":60},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":6},"tencent/hy3-preview":{"draws":17,"losses":17,"wins":40},"tencent/hy4-preview":{"draws":29,"losses":49,"wins":48},"thinkingmachines/inkling":{"draws":42,"losses":22,"wins":108},"thinkingmachines/inkling-small":{"draws":35,"losses":13,"wins":84},"unbiased/pareto-26.10":{"draws":4,"losses":36,"wins":4},"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":36,"losses":52,"wins":44},"x-ai/grok-4.6":{"draws":31,"losses":57,"wins":44},"x-ai/grok-4.7":{"draws":15,"losses":72,"wins":31},"x-ai/grok-build-0.1":{"draws":9,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":59,"losses":30,"wins":129},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":16,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":42,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":42,"wins":37},"z-ai/glm-5.2":{"draws":69,"losses":62,"wins":133},"z-ai/glm-5.3":{"draws":19,"losses":77,"wins":30},"z-ai/glm-5.3-flash":{"draws":19,"losses":62,"wins":51},"z-ai/glm-5.3-flashx":{"draws":21,"losses":53,"wins":58}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":177},"claude-fable-5":{"draws":33,"losses":71,"wins":142},"claude-fable-5-1":{"draws":23,"losses":179,"wins":76},"claude-haiku-5-5":{"draws":38,"losses":37,"wins":159},"claude-opus-4-5":{"draws":69,"losses":35,"wins":294},"claude-opus-4-8":{"draws":32,"losses":33,"wins":157},"claude-opus-5":{"draws":52,"losses":166,"wins":166},"claude-opus-5-5":{"draws":24,"losses":168,"wins":78},"claude-sonnet-5":{"draws":35,"losses":33,"wins":178},"claude-sonnet-5-5":{"draws":26,"losses":81,"wins":139},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":80},"deepseek/deepseek-v4-flash":{"draws":44,"losses":21,"wins":297},"deepseek/deepseek-v4-pro":{"draws":25,"losses":33,"wins":174},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":26,"wins":176},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":37,"wins":169},"deepseek/deepseek-v4.1-flash-1017":{"draws":35,"losses":53,"wins":158},"elorian/glimpse":{"draws":19,"losses":28,"wins":91},"fireworks/ember-1":{"draws":27,"losses":41,"wins":178},"gemini-3.1-pro-preview":{"draws":26,"losses":31,"wins":189},"gemini-4-argon":{"draws":30,"losses":114,"wins":102},"google/gemini-3.1-flash-lite":{"draws":18,"losses":5,"wins":127},"google/gemini-3.5-flash":{"draws":35,"losses":32,"wins":237},"google/gemini-3.5-flash-lite":{"draws":51,"losses":35,"wins":338},"google/gemini-3.6-flash":{"draws":58,"losses":89,"wins":321},"google/gemini-3.8-flash":{"draws":26,"losses":53,"wins":167},"google/gemma-4-31b-it":{"draws":21,"losses":10,"wins":109},"gpt-4.1":{"draws":11,"losses":4,"wins":67},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":18},"gpt-5":{"draws":26,"losses":18,"wins":176},"gpt-5.4":{"draws":29,"losses":35,"wins":170},"gpt-5.4-mini":{"draws":30,"losses":13,"wins":121},"gpt-5.4-nano":{"draws":22,"losses":15,"wins":199},"gpt-5.5":{"draws":30,"losses":47,"wins":155},"gpt-5.6-luna":{"draws":28,"losses":24,"wins":194},"gpt-5.6-sol":{"draws":30,"losses":65,"wins":151},"gpt-5.6-terra":{"draws":25,"losses":23,"wins":186},"gpt-6-astra":{"draws":22,"losses":167,"wins":57},"gpt-6-luna":{"draws":44,"losses":25,"wins":177},"gpt-6-sol":{"draws":38,"losses":89,"wins":119},"gpt-6.1-sol":{"draws":32,"losses":140,"wins":74},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":6},"inception/mercury-2.5-preview":{"draws":31,"losses":7,"wins":128},"inception/mercury-3":{"draws":18,"losses":18,"wins":128},"inclusionai/ling-3.0-flash":{"draws":26,"losses":7,"wins":133},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":22,"losses":21,"wins":213},"meta/muse-glimmer-30b":{"draws":15,"losses":22,"wins":193},"meta/muse-spark-1.2":{"draws":34,"losses":36,"wins":174},"meta/muse-spark-1.3":{"draws":32,"losses":50,"wins":164},"meta/muse-spark-open":{"draws":24,"losses":42,"wins":168},"meta/muse-wonder":{"draws":28,"losses":77,"wins":141},"minimax/minimax-m3":{"draws":17,"losses":6,"wins":115},"minimax/minimax-m3.1-flash":{"draws":29,"losses":21,"wins":160},"mistralai/mistral-large-4-0":{"draws":24,"losses":21,"wins":117},"mistralai/mistral-medium-3-5":{"draws":23,"losses":12,"wins":109},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":3,"wins":57},"moonshotai/kimi-k3":{"draws":36,"losses":40,"wins":168},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":111,"wins":109},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":109},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":46},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":5,"wins":183},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":81},"o3":{"draws":24,"losses":23,"wins":265},"openai/gpt-oss-120b":{"draws":26,"losses":11,"wins":183},"poolside/laguna-s-2.1":{"draws":24,"losses":13,"wins":211},"qwen/qwen3.7-max":{"draws":17,"losses":12,"wins":111},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":93},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":42,"wins":173},"qwen/qwen3.8-27b":{"draws":30,"losses":13,"wins":123},"qwen/qwen3.8-flash":{"draws":24,"losses":14,"wins":126},"qwen/qwen3.8-max":{"draws":36,"losses":31,"wins":179},"qwen/qwen3.8-max-0902":{"draws":34,"losses":41,"wins":171},"recursive/flint-v1.0":{"draws":7,"losses":1,"wins":62},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":23,"wins":180},"stealth/ox-alpha":{"draws":133,"losses":122,"wins":577},"stealth/space-bunny-alpha":{"draws":30,"losses":15,"wins":151},"stepfun/step-3.7-flash":{"draws":15,"losses":7,"wins":140},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":24,"losses":12,"wins":106},"tencent/hy4-preview":{"draws":21,"losses":36,"wins":177},"thinkingmachines/inkling":{"draws":48,"losses":30,"wins":260},"thinkingmachines/inkling-small":{"draws":40,"losses":11,"wins":195},"unbiased/pareto-26.10":{"draws":7,"losses":51,"wins":24},"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":38,"losses":52,"wins":156},"x-ai/grok-4.6":{"draws":37,"losses":48,"wins":161},"x-ai/grok-4.7":{"draws":21,"losses":97,"wins":102},"x-ai/grok-build-0.1":{"draws":15,"losses":3,"wins":64},"xiaomi/mimo-v2.5":{"draws":56,"losses":23,"wins":299},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":5,"wins":110},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":17,"wins":120},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":41,"wins":97},"z-ai/glm-5.2":{"draws":74,"losses":34,"wins":384},"z-ai/glm-5.3":{"draws":29,"losses":64,"wins":141},"z-ai/glm-5.3-flash":{"draws":35,"losses":46,"wins":165},"z-ai/glm-5.3-flashx":{"draws":38,"losses":42,"wins":166}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":7,"wins":131},"claude-fable-5":{"draws":12,"losses":22,"wins":122},"claude-fable-5-1":{"draws":15,"losses":71,"wins":88},"claude-haiku-5-5":{"draws":16,"losses":7,"wins":127},"claude-opus-4-5":{"draws":19,"losses":15,"wins":220},"claude-opus-4-8":{"draws":12,"losses":17,"wins":115},"claude-opus-5":{"draws":24,"losses":78,"wins":168},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":10,"losses":9,"wins":137},"claude-sonnet-5-5":{"draws":14,"losses":31,"wins":111},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":60},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":218},"deepseek/deepseek-v4-pro":{"draws":11,"losses":5,"wins":128},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":4,"wins":133},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":14,"wins":132},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":18,"wins":128},"elorian/glimpse":{"draws":7,"losses":7,"wins":72},"fireworks/ember-1":{"draws":8,"losses":12,"wins":136},"gemini-3.1-pro-preview":{"draws":9,"losses":9,"wins":138},"gemini-4-argon":{"draws":9,"losses":47,"wins":100},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":96},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":176},"google/gemini-3.5-flash-lite":{"draws":17,"losses":1,"wins":254},"google/gemini-3.6-flash":{"draws":20,"losses":25,"wins":251},"google/gemini-3.8-flash":{"draws":13,"losses":20,"wins":123},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":87},"gpt-4.1":{"draws":3,"losses":1,"wins":48},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":8,"losses":2,"wins":128},"gpt-5.4":{"draws":9,"losses":12,"wins":129},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":96},"gpt-5.4-nano":{"draws":7,"losses":1,"wins":152},"gpt-5.5":{"draws":13,"losses":15,"wins":116},"gpt-5.6-luna":{"draws":16,"losses":4,"wins":136},"gpt-5.6-sol":{"draws":11,"losses":20,"wins":125},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":139},"gpt-6-astra":{"draws":16,"losses":71,"wins":69},"gpt-6-luna":{"draws":12,"losses":3,"wins":141},"gpt-6-sol":{"draws":14,"losses":39,"wins":103},"gpt-6.1-sol":{"draws":17,"losses":64,"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},"inception/mercury-3":{"draws":5,"losses":1,"wins":102},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":106},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":155},"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":10,"losses":14,"wins":132},"meta/muse-spark-open":{"draws":10,"losses":15,"wins":125},"meta/muse-wonder":{"draws":9,"losses":31,"wins":116},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":83},"minimax/minimax-m3.1-flash":{"draws":7,"losses":2,"wins":121},"mistralai/mistral-large-4-0":{"draws":14,"losses":4,"wins":80},"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":4,"losses":10,"wins":136},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":50,"wins":94},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":74},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":31},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":136},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":66},"o3":{"draws":11,"losses":3,"wins":204},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":129},"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":10,"losses":17,"wins":129},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":98},"qwen/qwen3.8-flash":{"draws":10,"losses":3,"wins":91},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":130},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":131},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":43},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":4,"wins":126},"stealth/ox-alpha":{"draws":45,"losses":28,"wins":433},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":114},"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":10,"losses":15,"wins":125},"thinkingmachines/inkling":{"draws":19,"losses":0,"wins":185},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":146},"unbiased/pareto-26.10":{"draws":4,"losses":21,"wins":27},"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":18,"wins":120},"x-ai/grok-4.6":{"draws":16,"losses":14,"wins":126},"x-ai/grok-4.7":{"draws":10,"losses":30,"wins":98},"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":7,"losses":2,"wins":89},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":81},"z-ai/glm-5.2":{"draws":17,"losses":12,"wins":283},"z-ai/glm-5.3":{"draws":12,"losses":25,"wins":113},"z-ai/glm-5.3-flash":{"draws":11,"losses":11,"wins":134},"z-ai/glm-5.3-flashx":{"draws":15,"losses":9,"wins":132}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":25,"wins":71},"claude-fable-5":{"draws":23,"losses":94,"wins":27},"claude-fable-5-1":{"draws":7,"losses":149,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":63,"wins":40},"claude-opus-4-5":{"draws":74,"losses":78,"wins":82},"claude-opus-4-8":{"draws":33,"losses":59,"wins":40},"claude-opus-5":{"draws":35,"losses":178,"wins":33},"claude-opus-5-5":{"draws":10,"losses":137,"wins":9},"claude-sonnet-5":{"draws":24,"losses":36,"wins":36},"claude-sonnet-5-5":{"draws":24,"losses":83,"wins":37},"cohere/north-mini-code":{"draws":8,"losses":8,"wins":38},"deepseek/deepseek-v4-flash":{"draws":57,"losses":45,"wins":114},"deepseek/deepseek-v4-pro":{"draws":40,"losses":47,"wins":45},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":49,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":58,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":31,"losses":81,"wins":32},"elorian/glimpse":{"draws":18,"losses":31,"wins":29},"fireworks/ember-1":{"draws":37,"losses":62,"wins":45},"gemini-3.1-pro-preview":{"draws":36,"losses":50,"wins":58},"gemini-4-argon":{"draws":12,"losses":124,"wins":8},"google/gemini-3.1-flash-lite":{"draws":26,"losses":5,"wins":65},"google/gemini-3.5-flash":{"draws":46,"losses":77,"wins":57},"google/gemini-3.5-flash-lite":{"draws":64,"losses":56,"wins":132},"google/gemini-3.6-flash":{"draws":66,"losses":121,"wins":89},"google/gemini-3.8-flash":{"draws":32,"losses":77,"wins":35},"google/gemma-4-31b-it":{"draws":27,"losses":12,"wins":45},"gpt-4.1":{"draws":14,"losses":15,"wins":19},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":35,"losses":38,"wins":53},"gpt-5.4":{"draws":35,"losses":73,"wins":30},"gpt-5.4-mini":{"draws":38,"losses":28,"wins":30},"gpt-5.4-nano":{"draws":33,"losses":41,"wins":70},"gpt-5.5":{"draws":46,"losses":57,"wins":29},"gpt-5.6-luna":{"draws":36,"losses":43,"wins":65},"gpt-5.6-sol":{"draws":20,"losses":106,"wins":18},"gpt-5.6-terra":{"draws":47,"losses":47,"wins":44},"gpt-6-astra":{"draws":6,"losses":132,"wins":6},"gpt-6-luna":{"draws":36,"losses":54,"wins":54},"gpt-6-sol":{"draws":23,"losses":103,"wins":18},"gpt-6.1-sol":{"draws":6,"losses":130,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":35,"losses":11,"wins":56},"inception/mercury-3":{"draws":31,"losses":33,"wins":32},"inclusionai/ling-3.0-flash":{"draws":34,"losses":8,"wins":60},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":38,"losses":33,"wins":85},"meta/muse-glimmer-30b":{"draws":39,"losses":19,"wins":68},"meta/muse-spark-1.2":{"draws":37,"losses":64,"wins":37},"meta/muse-spark-1.3":{"draws":35,"losses":75,"wins":34},"meta/muse-spark-open":{"draws":32,"losses":74,"wins":32},"meta/muse-wonder":{"draws":31,"losses":85,"wins":28},"minimax/minimax-m3":{"draws":21,"losses":15,"wins":42},"minimax/minimax-m3.1-flash":{"draws":32,"losses":37,"wins":57},"mistralai/mistral-large-4-0":{"draws":27,"losses":24,"wins":39},"mistralai/mistral-medium-3-5":{"draws":26,"losses":11,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":16,"wins":9},"moonshotai/kimi-k3":{"draws":38,"losses":58,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":118,"wins":11},"nex-agi/nex-n2-pro":{"draws":20,"losses":10,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":29,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":17,"wins":31},"o3":{"draws":27,"losses":83,"wins":88},"openai/gpt-oss-120b":{"draws":35,"losses":17,"wins":74},"poolside/laguna-s-2.1":{"draws":40,"losses":27,"wins":71},"qwen/qwen3.7-max":{"draws":23,"losses":21,"wins":40},"qwen/qwen3.7-plus":{"draws":20,"losses":16,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":62,"wins":37},"qwen/qwen3.8-27b":{"draws":24,"losses":40,"wins":38},"qwen/qwen3.8-flash":{"draws":30,"losses":33,"wins":33},"qwen/qwen3.8-max":{"draws":44,"losses":59,"wins":41},"qwen/qwen3.8-max-0902":{"draws":35,"losses":70,"wins":39},"recursive/flint-v1.0":{"draws":12,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":39,"losses":46,"wins":47},"stealth/ox-alpha":{"draws":102,"losses":241,"wins":131},"stealth/space-bunny-alpha":{"draws":24,"losses":40,"wins":50},"stepfun/step-3.7-flash":{"draws":21,"losses":27,"wins":54},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":25,"losses":21,"wins":32},"tencent/hy4-preview":{"draws":35,"losses":64,"wins":39},"thinkingmachines/inkling":{"draws":61,"losses":28,"wins":103},"thinkingmachines/inkling-small":{"draws":44,"losses":24,"wins":76},"unbiased/pareto-26.10":{"draws":4,"losses":43,"wins":1},"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":38,"losses":73,"wins":33},"x-ai/grok-4.6":{"draws":38,"losses":73,"wins":33},"x-ai/grok-4.7":{"draws":12,"losses":88,"wins":26},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":27},"xiaomi/mimo-v2.5":{"draws":71,"losses":44,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":21,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":50,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":25},"z-ai/glm-5.2":{"draws":75,"losses":94,"wins":119},"z-ai/glm-5.3":{"draws":25,"losses":94,"wins":19},"z-ai/glm-5.3-flash":{"draws":23,"losses":80,"wins":41},"z-ai/glm-5.3-flashx":{"draws":31,"losses":78,"wins":35}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":24,"wins":80},"claude-fable-5":{"draws":26,"losses":59,"wins":59},"claude-fable-5-1":{"draws":8,"losses":117,"wins":37},"claude-haiku-5-5":{"draws":24,"losses":43,"wins":71},"claude-opus-4-5":{"draws":47,"losses":61,"wins":126},"claude-opus-4-8":{"draws":26,"losses":43,"wins":63},"claude-opus-5":{"draws":26,"losses":139,"wins":81},"claude-opus-5-5":{"draws":14,"losses":111,"wins":31},"claude-sonnet-5":{"draws":24,"losses":37,"wins":83},"claude-sonnet-5-5":{"draws":8,"losses":44,"wins":44},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":40},"deepseek/deepseek-v4-flash":{"draws":43,"losses":31,"wins":142},"deepseek/deepseek-v4-pro":{"draws":30,"losses":34,"wins":68},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":33,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":40,"wins":75},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":60,"wins":60},"elorian/glimpse":{"draws":16,"losses":19,"wins":43},"fireworks/ember-1":{"draws":28,"losses":44,"wins":72},"gemini-3.1-pro-preview":{"draws":21,"losses":42,"wins":81},"gemini-4-argon":{"draws":12,"losses":88,"wins":44},"google/gemini-3.1-flash-lite":{"draws":15,"losses":12,"wins":69},"google/gemini-3.5-flash":{"draws":31,"losses":47,"wins":102},"google/gemini-3.5-flash-lite":{"draws":47,"losses":39,"wins":166},"google/gemini-3.6-flash":{"draws":50,"losses":95,"wins":131},"google/gemini-3.8-flash":{"draws":19,"losses":55,"wins":70},"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":26,"losses":26,"wins":74},"gpt-5.4":{"draws":34,"losses":42,"wins":62},"gpt-5.4-mini":{"draws":17,"losses":17,"wins":62},"gpt-5.4-nano":{"draws":20,"losses":19,"wins":105},"gpt-5.5":{"draws":29,"losses":42,"wins":61},"gpt-5.6-luna":{"draws":33,"losses":27,"wins":84},"gpt-5.6-sol":{"draws":14,"losses":74,"wins":56},"gpt-5.6-terra":{"draws":31,"losses":31,"wins":76},"gpt-6-astra":{"draws":11,"losses":101,"wins":32},"gpt-6-luna":{"draws":32,"losses":44,"wins":68},"gpt-6-sol":{"draws":11,"losses":82,"wins":51},"gpt-6.1-sol":{"draws":3,"losses":106,"wins":35},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":65},"inception/mercury-3":{"draws":21,"losses":22,"wins":53},"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":19,"losses":31,"wins":106},"meta/muse-glimmer-30b":{"draws":21,"losses":21,"wins":84},"meta/muse-spark-1.2":{"draws":29,"losses":43,"wins":66},"meta/muse-spark-1.3":{"draws":21,"losses":54,"wins":69},"meta/muse-spark-open":{"draws":24,"losses":52,"wins":62},"meta/muse-wonder":{"draws":21,"losses":54,"wins":69},"minimax/minimax-m3":{"draws":13,"losses":13,"wins":52},"minimax/minimax-m3.1-flash":{"draws":25,"losses":22,"wins":79},"mistralai/mistral-large-4-0":{"draws":23,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":18,"losses":8,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":7,"wins":20},"moonshotai/kimi-k3":{"draws":28,"losses":46,"wins":64},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":90,"wins":40},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":22,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":11,"wins":39},"o3":{"draws":17,"losses":46,"wins":135},"openai/gpt-oss-120b":{"draws":25,"losses":18,"wins":83},"poolside/laguna-s-2.1":{"draws":26,"losses":26,"wins":86},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":44},"qwen/qwen3.7-plus":{"draws":15,"losses":13,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":50,"wins":63},"qwen/qwen3.8-27b":{"draws":17,"losses":26,"wins":59},"qwen/qwen3.8-flash":{"draws":17,"losses":30,"wins":49},"qwen/qwen3.8-max":{"draws":20,"losses":42,"wins":82},"qwen/qwen3.8-max-0902":{"draws":26,"losses":53,"wins":65},"recursive/flint-v1.0":{"draws":7,"losses":4,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":34,"wins":67},"stealth/ox-alpha":{"draws":78,"losses":163,"wins":233},"stealth/space-bunny-alpha":{"draws":21,"losses":24,"wins":69},"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":22,"losses":48,"wins":68},"thinkingmachines/inkling":{"draws":41,"losses":40,"wins":111},"thinkingmachines/inkling-small":{"draws":31,"losses":21,"wins":92},"unbiased/pareto-26.10":{"draws":4,"losses":36,"wins":8},"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":31,"losses":50,"wins":63},"x-ai/grok-4.6":{"draws":22,"losses":61,"wins":61},"x-ai/grok-4.7":{"draws":15,"losses":63,"wins":48},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":33},"xiaomi/mimo-v2.5":{"draws":47,"losses":29,"wins":146},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":13,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":33,"wins":47},"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":21,"losses":63,"wins":54},"z-ai/glm-5.3-flash":{"draws":19,"losses":55,"wins":70},"z-ai/glm-5.3-flashx":{"draws":24,"losses":54,"wins":66}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":23,"wins":14},"claude-fable-5":{"draws":8,"losses":44,"wins":2},"claude-fable-5-1":{"draws":1,"losses":60,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":9},"claude-opus-4-5":{"draws":9,"losses":71,"wins":8},"claude-opus-4-8":{"draws":10,"losses":37,"wins":3},"claude-opus-5":{"draws":6,"losses":80,"wins":4},"claude-opus-5-5":{"draws":2,"losses":60,"wins":0},"claude-sonnet-5":{"draws":8,"losses":38,"wins":8},"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":21,"losses":34,"wins":25},"deepseek/deepseek-v4-pro":{"draws":10,"losses":28,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":33,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":35,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":47,"wins":1},"elorian/glimpse":{"draws":3,"losses":21,"wins":6},"fireworks/ember-1":{"draws":10,"losses":35,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":26,"wins":16},"gemini-4-argon":{"draws":0,"losses":52,"wins":2},"google/gemini-3.1-flash-lite":{"draws":10,"losses":14,"wins":18},"google/gemini-3.5-flash":{"draws":14,"losses":44,"wins":12},"google/gemini-3.5-flash-lite":{"draws":32,"losses":35,"wins":31},"google/gemini-3.6-flash":{"draws":20,"losses":76,"wins":8},"google/gemini-3.8-flash":{"draws":8,"losses":40,"wins":6},"google/gemma-4-31b-it":{"draws":10,"losses":18,"wins":6},"gpt-4.1":{"draws":6,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":34,"wins":6},"gpt-5.4":{"draws":9,"losses":35,"wins":10},"gpt-5.4-mini":{"draws":9,"losses":17,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":36,"wins":13},"gpt-5.5":{"draws":12,"losses":36,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":28,"wins":10},"gpt-5.6-sol":{"draws":2,"losses":47,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":33,"wins":6},"gpt-6-astra":{"draws":2,"losses":52,"wins":0},"gpt-6-luna":{"draws":12,"losses":33,"wins":9},"gpt-6-sol":{"draws":4,"losses":49,"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":10,"losses":15,"wins":13},"inception/mercury-3":{"draws":2,"losses":26,"wins":6},"inclusionai/ling-3.0-flash":{"draws":12,"losses":13,"wins":9},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":39,"wins":15},"meta/muse-glimmer-30b":{"draws":18,"losses":17,"wins":15},"meta/muse-spark-1.2":{"draws":4,"losses":39,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":47,"wins":2},"meta/muse-spark-open":{"draws":6,"losses":41,"wins":7},"meta/muse-wonder":{"draws":3,"losses":47,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":17,"wins":10},"minimax/minimax-m3.1-flash":{"draws":8,"losses":27,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":20,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":11,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":35,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":53,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":17,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":20,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":22,"wins":3},"o3":{"draws":13,"losses":61,"wins":14},"openai/gpt-oss-120b":{"draws":15,"losses":20,"wins":15},"poolside/laguna-s-2.1":{"draws":13,"losses":19,"wins":22},"qwen/qwen3.7-max":{"draws":11,"losses":17,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":45,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":25,"wins":6},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":42,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":41,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":7,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":39,"wins":9},"stealth/ox-alpha":{"draws":24,"losses":132,"wins":22},"stealth/space-bunny-alpha":{"draws":11,"losses":28,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":25,"wins":7},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":14,"losses":36,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":33,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"losses":22,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":18,"wins":0},"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":7,"losses":44,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":41,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":45,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":9,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":31,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":23,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":60,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":44,"wins":2},"z-ai/glm-5.3-flash":{"draws":6,"losses":36,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":40,"wins":5}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":55,"losses":73,"wins":68},"claude-fable-5":{"draws":35,"losses":167,"wins":14},"claude-fable-5-1":{"draws":6,"losses":233,"wins":1},"claude-haiku-5-5":{"draws":58,"losses":121,"wins":29},"claude-opus-4-5":{"draws":97,"losses":185,"wins":70},"claude-opus-4-8":{"draws":45,"losses":125,"wins":30},"claude-opus-5":{"draws":44,"losses":297,"wins":21},"claude-opus-5-5":{"draws":12,"losses":218,"wins":6},"claude-sonnet-5":{"draws":57,"losses":114,"wins":45},"claude-sonnet-5-5":{"draws":43,"losses":142,"wins":31},"cohere/north-mini-code":{"draws":21,"losses":25,"wins":34},"deepseek/deepseek-v4-flash":{"draws":80,"losses":90,"wins":90},"deepseek/deepseek-v4-pro":{"draws":53,"losses":100,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":56,"losses":91,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":56,"losses":124,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":150,"wins":26},"elorian/glimpse":{"draws":25,"losses":61,"wins":30},"fireworks/ember-1":{"draws":63,"losses":108,"wins":45},"gemini-3.1-pro-preview":{"draws":56,"losses":97,"wins":63},"gemini-4-argon":{"draws":13,"losses":199,"wins":4},"google/gemini-3.1-flash-lite":{"draws":35,"losses":27,"wins":84},"google/gemini-3.5-flash":{"draws":59,"losses":144,"wins":67},"google/gemini-3.5-flash-lite":{"draws":97,"losses":133,"wins":144},"google/gemini-3.6-flash":{"draws":89,"losses":256,"wins":67},"google/gemini-3.8-flash":{"draws":40,"losses":155,"wins":21},"google/gemma-4-31b-it":{"draws":58,"losses":22,"wins":46},"gpt-4.1":{"draws":18,"losses":37,"wins":17},"gpt-4.1-nano":{"draws":17,"losses":3,"wins":8},"gpt-5":{"draws":51,"losses":95,"wins":44},"gpt-5.4":{"draws":53,"losses":123,"wins":30},"gpt-5.4-mini":{"draws":51,"losses":51,"wins":42},"gpt-5.4-nano":{"draws":48,"losses":96,"wins":82},"gpt-5.5":{"draws":58,"losses":112,"wins":26},"gpt-5.6-luna":{"draws":72,"losses":82,"wins":62},"gpt-5.6-sol":{"draws":29,"losses":169,"wins":18},"gpt-5.6-terra":{"draws":55,"losses":115,"wins":38},"gpt-6-astra":{"draws":10,"losses":201,"wins":5},"gpt-6-luna":{"draws":59,"losses":106,"wins":51},"gpt-6-sol":{"draws":32,"losses":169,"wins":15},"gpt-6.1-sol":{"draws":14,"losses":196,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":55,"losses":28,"wins":69},"inception/mercury-3":{"draws":43,"losses":70,"wins":37},"inclusionai/ling-3.0-flash":{"draws":59,"losses":43,"wins":56},"inclusionai/ling-3.1-flash":{"draws":8,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":57,"losses":78,"wins":99},"meta/muse-glimmer-30b":{"draws":65,"losses":47,"wins":74},"meta/muse-spark-1.2":{"draws":53,"losses":120,"wins":33},"meta/muse-spark-1.3":{"draws":38,"losses":150,"wins":28},"meta/muse-spark-open":{"draws":39,"losses":136,"wins":31},"meta/muse-wonder":{"draws":37,"losses":148,"wins":31},"minimax/minimax-m3":{"draws":32,"losses":46,"wins":42},"minimax/minimax-m3.1-flash":{"draws":39,"losses":86,"wins":61},"mistralai/mistral-large-4-0":{"draws":43,"losses":71,"wins":20},"mistralai/mistral-medium-3-5":{"draws":46,"losses":30,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":29,"wins":12},"moonshotai/kimi-k3":{"draws":59,"losses":106,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":188,"wins":9},"nex-agi/nex-n2-pro":{"draws":21,"losses":33,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":23,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":59,"wins":80},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":44,"wins":32},"o3":{"draws":43,"losses":183,"wins":80},"openai/gpt-oss-120b":{"draws":61,"losses":64,"wins":65},"poolside/laguna-s-2.1":{"draws":64,"losses":72,"wins":74},"qwen/qwen3.7-max":{"draws":39,"losses":52,"wins":39},"qwen/qwen3.7-plus":{"draws":31,"losses":38,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":65,"losses":120,"wins":31},"qwen/qwen3.8-27b":{"draws":38,"losses":81,"wins":35},"qwen/qwen3.8-flash":{"draws":42,"losses":70,"wins":32},"qwen/qwen3.8-max":{"draws":59,"losses":119,"wins":38},"qwen/qwen3.8-max-0902":{"draws":57,"losses":123,"wins":36},"recursive/flint-v1.0":{"draws":12,"losses":16,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":42,"losses":112,"wins":42},"stealth/ox-alpha":{"draws":158,"losses":404,"wins":134},"stealth/space-bunny-alpha":{"draws":48,"losses":71,"wins":49},"stepfun/step-3.7-flash":{"draws":34,"losses":58,"wins":66},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":34,"losses":42,"wins":40},"tencent/hy4-preview":{"draws":48,"losses":117,"wins":41},"thinkingmachines/inkling":{"draws":85,"losses":99,"wins":100},"thinkingmachines/inkling-small":{"draws":82,"losses":48,"wins":86},"unbiased/pareto-26.10":{"draws":4,"losses":68,"wins":0},"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":39,"losses":145,"wins":32},"x-ai/grok-4.6":{"draws":50,"losses":141,"wins":25},"x-ai/grok-4.7":{"draws":18,"losses":159,"wins":15},"x-ai/grok-build-0.1":{"draws":22,"losses":19,"wins":31},"xiaomi/mimo-v2.5":{"draws":105,"losses":110,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":45,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":86,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":95,"wins":24},"z-ai/glm-5.2":{"draws":134,"losses":185,"wins":113},"z-ai/glm-5.3":{"draws":39,"losses":150,"wins":17},"z-ai/glm-5.3-flash":{"draws":51,"losses":120,"wins":45},"z-ai/glm-5.3-flashx":{"draws":45,"losses":128,"wins":43}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":31,"wins":61},"claude-fable-5":{"draws":24,"losses":81,"wins":27},"claude-fable-5-1":{"draws":10,"losses":135,"wins":5},"claude-haiku-5-5":{"draws":33,"losses":52,"wins":41},"claude-opus-4-5":{"draws":62,"losses":76,"wins":76},"claude-opus-4-8":{"draws":27,"losses":56,"wins":37},"claude-opus-5":{"draws":25,"losses":174,"wins":33},"claude-opus-5-5":{"draws":11,"losses":128,"wins":5},"claude-sonnet-5":{"draws":40,"losses":45,"wins":47},"claude-sonnet-5-5":{"draws":30,"losses":68,"wins":34},"cohere/north-mini-code":{"draws":10,"losses":14,"wins":28},"deepseek/deepseek-v4-flash":{"draws":53,"losses":43,"wins":100},"deepseek/deepseek-v4-pro":{"draws":20,"losses":30,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":46,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":53,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":79,"wins":25},"elorian/glimpse":{"draws":20,"losses":37,"wins":17},"fireworks/ember-1":{"draws":37,"losses":56,"wins":39},"gemini-3.1-pro-preview":{"draws":30,"losses":54,"wins":48},"gemini-4-argon":{"draws":14,"losses":104,"wins":14},"google/gemini-3.1-flash-lite":{"draws":23,"losses":6,"wins":59},"google/gemini-3.5-flash":{"draws":37,"losses":72,"wins":57},"google/gemini-3.5-flash-lite":{"draws":61,"losses":67,"wins":104},"google/gemini-3.6-flash":{"draws":63,"losses":109,"wins":82},"google/gemini-3.8-flash":{"draws":25,"losses":74,"wins":33},"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":28,"losses":38,"wins":52},"gpt-5.4":{"draws":27,"losses":63,"wins":38},"gpt-5.4-mini":{"draws":28,"losses":26,"wins":34},"gpt-5.4-nano":{"draws":15,"losses":48,"wins":67},"gpt-5.5":{"draws":36,"losses":61,"wins":27},"gpt-5.6-luna":{"draws":43,"losses":36,"wins":53},"gpt-5.6-sol":{"draws":16,"losses":87,"wins":29},"gpt-5.6-terra":{"draws":38,"losses":46,"wins":42},"gpt-6-astra":{"draws":11,"losses":114,"wins":7},"gpt-6-luna":{"draws":34,"losses":56,"wins":42},"gpt-6-sol":{"draws":12,"losses":98,"wins":22},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":35,"losses":9,"wins":46},"inception/mercury-3":{"draws":24,"losses":31,"wins":31},"inclusionai/ling-3.0-flash":{"draws":32,"losses":18,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":27,"losses":31,"wins":86},"meta/muse-glimmer-30b":{"draws":35,"losses":29,"wins":56},"meta/muse-spark-1.2":{"draws":21,"losses":61,"wins":46},"meta/muse-spark-1.3":{"draws":21,"losses":76,"wins":35},"meta/muse-spark-open":{"draws":27,"losses":71,"wins":30},"meta/muse-wonder":{"draws":23,"losses":79,"wins":30},"minimax/minimax-m3":{"draws":11,"losses":13,"wins":48},"minimax/minimax-m3.1-flash":{"draws":32,"losses":29,"wins":55},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":26},"mistralai/mistral-medium-3-5":{"draws":19,"losses":11,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":12,"wins":15},"moonshotai/kimi-k3":{"draws":28,"losses":60,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":16},"nex-agi/nex-n2-pro":{"draws":15,"losses":14,"wins":37},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":24,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":20,"wins":25},"o3":{"draws":20,"losses":72,"wins":92},"openai/gpt-oss-120b":{"draws":34,"losses":27,"wins":55},"poolside/laguna-s-2.1":{"draws":30,"losses":47,"wins":51},"qwen/qwen3.7-max":{"draws":22,"losses":17,"wins":37},"qwen/qwen3.7-plus":{"draws":14,"losses":15,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":62,"wins":37},"qwen/qwen3.8-27b":{"draws":26,"losses":35,"wins":31},"qwen/qwen3.8-flash":{"draws":18,"losses":40,"wins":30},"qwen/qwen3.8-max":{"draws":37,"losses":59,"wins":36},"qwen/qwen3.8-max-0902":{"draws":34,"losses":63,"wins":35},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":47,"wins":45},"stealth/ox-alpha":{"draws":103,"losses":207,"wins":132},"stealth/space-bunny-alpha":{"draws":30,"losses":29,"wins":47},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":55},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":29},"tencent/hy4-preview":{"draws":26,"losses":63,"wins":39},"thinkingmachines/inkling":{"draws":58,"losses":30,"wins":92},"thinkingmachines/inkling-small":{"draws":44,"losses":19,"wins":69},"unbiased/pareto-26.10":{"draws":1,"losses":42,"wins":1},"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":33,"losses":62,"wins":37},"x-ai/grok-4.6":{"draws":32,"losses":73,"wins":27},"x-ai/grok-4.7":{"draws":10,"losses":86,"wins":20},"x-ai/grok-build-0.1":{"draws":17,"losses":9,"wins":18},"xiaomi/mimo-v2.5":{"draws":71,"losses":32,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":38,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":47,"wins":25},"z-ai/glm-5.2":{"draws":79,"losses":84,"wins":101},"z-ai/glm-5.3":{"draws":22,"losses":77,"wins":27},"z-ai/glm-5.3-flash":{"draws":20,"losses":73,"wins":39},"z-ai/glm-5.3-flashx":{"draws":31,"losses":60,"wins":41}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":36,"wins":53},"claude-fable-5":{"draws":18,"losses":88,"wins":26},"claude-fable-5-1":{"draws":3,"losses":144,"wins":3},"claude-haiku-5-5":{"draws":34,"losses":63,"wins":29},"claude-opus-4-5":{"draws":57,"losses":79,"wins":78},"claude-opus-4-8":{"draws":29,"losses":52,"wins":39},"claude-opus-5":{"draws":20,"losses":176,"wins":26},"claude-opus-5-5":{"draws":7,"losses":133,"wins":4},"claude-sonnet-5":{"draws":41,"losses":42,"wins":49},"claude-sonnet-5-5":{"draws":21,"losses":78,"wins":33},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":56,"losses":51,"wins":91},"deepseek/deepseek-v4-pro":{"draws":34,"losses":42,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":34,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":67,"wins":33},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":76,"wins":32},"elorian/glimpse":{"draws":15,"losses":31,"wins":28},"fireworks/ember-1":{"draws":32,"losses":59,"wins":41},"gemini-3.1-pro-preview":{"draws":33,"losses":46,"wins":53},"gemini-4-argon":{"draws":13,"losses":111,"wins":8},"google/gemini-3.1-flash-lite":{"draws":24,"losses":10,"wins":54},"google/gemini-3.5-flash":{"draws":38,"losses":75,"wins":53},"google/gemini-3.5-flash-lite":{"draws":69,"losses":48,"wins":115},"google/gemini-3.6-flash":{"draws":52,"losses":123,"wins":79},"google/gemini-3.8-flash":{"draws":28,"losses":70,"wins":34},"google/gemma-4-31b-it":{"draws":31,"losses":7,"wins":38},"gpt-4.1":{"draws":11,"losses":13,"wins":20},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":24,"losses":46,"wins":46},"gpt-5.4":{"draws":23,"losses":68,"wins":37},"gpt-5.4-mini":{"draws":30,"losses":18,"wins":40},"gpt-5.4-nano":{"draws":23,"losses":42,"wins":65},"gpt-5.5":{"draws":29,"losses":55,"wins":38},"gpt-5.6-luna":{"draws":42,"losses":38,"wins":52},"gpt-5.6-sol":{"draws":16,"losses":89,"wins":27},"gpt-5.6-terra":{"draws":33,"losses":54,"wins":41},"gpt-6-astra":{"draws":8,"losses":123,"wins":1},"gpt-6-luna":{"draws":33,"losses":50,"wins":49},"gpt-6-sol":{"draws":13,"losses":99,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":123,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":32,"losses":14,"wins":46},"inception/mercury-3":{"draws":22,"losses":38,"wins":28},"inclusionai/ling-3.0-flash":{"draws":34,"losses":20,"wins":44},"inclusionai/ling-3.1-flash":{"draws":4,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":38,"losses":34,"wins":72},"meta/muse-glimmer-30b":{"draws":33,"losses":21,"wins":62},"meta/muse-spark-1.2":{"draws":22,"losses":66,"wins":38},"meta/muse-spark-1.3":{"draws":26,"losses":67,"wins":39},"meta/muse-spark-open":{"draws":20,"losses":73,"wins":35},"meta/muse-wonder":{"draws":25,"losses":78,"wins":29},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":41},"minimax/minimax-m3.1-flash":{"draws":20,"losses":41,"wins":55},"mistralai/mistral-large-4-0":{"draws":30,"losses":24,"wins":28},"mistralai/mistral-medium-3-5":{"draws":21,"losses":12,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":11,"wins":15},"moonshotai/kimi-k3":{"draws":33,"losses":42,"wins":51},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":105,"wins":15},"nex-agi/nex-n2-pro":{"draws":11,"losses":15,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":20,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":23,"wins":23},"o3":{"draws":26,"losses":57,"wins":101},"openai/gpt-oss-120b":{"draws":37,"losses":27,"wins":50},"poolside/laguna-s-2.1":{"draws":27,"losses":35,"wins":62},"qwen/qwen3.7-max":{"draws":25,"losses":18,"wins":33},"qwen/qwen3.7-plus":{"draws":13,"losses":22,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":58,"wins":43},"qwen/qwen3.8-27b":{"draws":23,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":20,"losses":37,"wins":31},"qwen/qwen3.8-max":{"draws":37,"losses":56,"wins":39},"qwen/qwen3.8-max-0902":{"draws":37,"losses":57,"wins":38},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":51,"wins":39},"stealth/ox-alpha":{"draws":101,"losses":187,"wins":152},"stealth/space-bunny-alpha":{"draws":28,"losses":28,"wins":48},"stepfun/step-3.7-flash":{"draws":20,"losses":20,"wins":56},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":25,"losses":21,"wins":24},"tencent/hy4-preview":{"draws":24,"losses":58,"wins":46},"thinkingmachines/inkling":{"draws":57,"losses":43,"wins":76},"thinkingmachines/inkling-small":{"draws":39,"losses":25,"wins":68},"unbiased/pareto-26.10":{"draws":3,"losses":40,"wins":1},"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":29,"losses":59,"wins":44},"x-ai/grok-4.6":{"draws":35,"losses":68,"wins":29},"x-ai/grok-4.7":{"draws":8,"losses":82,"wins":24},"x-ai/grok-build-0.1":{"draws":16,"losses":5,"wins":23},"xiaomi/mimo-v2.5":{"draws":62,"losses":41,"wins":99},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":20,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":35,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":49,"wins":27},"z-ai/glm-5.2":{"draws":82,"losses":79,"wins":103},"z-ai/glm-5.3":{"draws":23,"losses":77,"wins":26},"z-ai/glm-5.3-flash":{"draws":18,"losses":78,"wins":36},"z-ai/glm-5.3-flashx":{"draws":26,"losses":66,"wins":40}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":34,"wins":67},"claude-fable-5":{"draws":33,"losses":74,"wins":37},"claude-fable-5-1":{"draws":13,"losses":136,"wins":13},"claude-haiku-5-5":{"draws":42,"losses":57,"wins":39},"claude-opus-4-5":{"draws":59,"losses":71,"wins":104},"claude-opus-4-8":{"draws":25,"losses":49,"wins":58},"claude-opus-5":{"draws":40,"losses":169,"wins":37},"claude-opus-5-5":{"draws":10,"losses":132,"wins":14},"claude-sonnet-5":{"draws":36,"losses":50,"wins":58},"claude-sonnet-5-5":{"draws":29,"losses":75,"wins":40},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":35},"deepseek/deepseek-v4-flash":{"draws":56,"losses":36,"wins":124},"deepseek/deepseek-v4-pro":{"draws":37,"losses":42,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":33,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":42,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":70,"wins":41},"elorian/glimpse":{"draws":17,"losses":31,"wins":30},"fireworks/ember-1":{"draws":38,"losses":54,"wins":52},"gemini-3.1-pro-preview":{"draws":28,"losses":50,"wins":66},"gemini-4-argon":{"draws":12,"losses":114,"wins":18},"google/gemini-3.1-flash-lite":{"draws":27,"losses":11,"wins":58},"google/gemini-3.5-flash":{"draws":40,"losses":60,"wins":80},"google/gemini-3.5-flash-lite":{"draws":70,"losses":54,"wins":128},"google/gemini-3.6-flash":{"draws":76,"losses":110,"wins":90},"google/gemini-3.8-flash":{"draws":36,"losses":63,"wins":45},"google/gemma-4-31b-it":{"draws":34,"losses":12,"wins":38},"gpt-4.1":{"draws":9,"losses":14,"wins":25},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":9},"gpt-5":{"draws":36,"losses":30,"wins":60},"gpt-5.4":{"draws":39,"losses":53,"wins":46},"gpt-5.4-mini":{"draws":36,"losses":20,"wins":40},"gpt-5.4-nano":{"draws":35,"losses":37,"wins":72},"gpt-5.5":{"draws":40,"losses":44,"wins":48},"gpt-5.6-luna":{"draws":41,"losses":35,"wins":68},"gpt-5.6-sol":{"draws":25,"losses":76,"wins":43},"gpt-5.6-terra":{"draws":46,"losses":36,"wins":56},"gpt-6-astra":{"draws":13,"losses":124,"wins":7},"gpt-6-luna":{"draws":40,"losses":41,"wins":63},"gpt-6-sol":{"draws":24,"losses":91,"wins":29},"gpt-6.1-sol":{"draws":13,"losses":116,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":37,"losses":12,"wins":53},"inception/mercury-3":{"draws":27,"losses":29,"wins":40},"inclusionai/ling-3.0-flash":{"draws":42,"losses":10,"wins":50},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":37,"wins":91},"meta/muse-glimmer-30b":{"draws":43,"losses":18,"wins":65},"meta/muse-spark-1.2":{"draws":35,"losses":52,"wins":51},"meta/muse-spark-1.3":{"draws":27,"losses":63,"wins":54},"meta/muse-spark-open":{"draws":27,"losses":55,"wins":56},"meta/muse-wonder":{"draws":37,"losses":71,"wins":36},"minimax/minimax-m3":{"draws":15,"losses":18,"wins":45},"minimax/minimax-m3.1-flash":{"draws":34,"losses":25,"wins":67},"mistralai/mistral-large-4-0":{"draws":33,"losses":26,"wins":31},"mistralai/mistral-medium-3-5":{"draws":24,"losses":9,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":12,"wins":15},"moonshotai/kimi-k3":{"draws":35,"losses":45,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":23,"losses":96,"wins":25},"nex-agi/nex-n2-pro":{"draws":9,"losses":12,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":23,"wins":61},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":17,"wins":34},"o3":{"draws":38,"losses":65,"wins":95},"openai/gpt-oss-120b":{"draws":31,"losses":25,"wins":70},"poolside/laguna-s-2.1":{"draws":54,"losses":25,"wins":59},"qwen/qwen3.7-max":{"draws":31,"losses":18,"wins":35},"qwen/qwen3.7-plus":{"draws":25,"losses":7,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":49,"wins":60},"qwen/qwen3.8-27b":{"draws":23,"losses":29,"wins":50},"qwen/qwen3.8-flash":{"draws":32,"losses":24,"wins":40},"qwen/qwen3.8-max":{"draws":35,"losses":56,"wins":53},"qwen/qwen3.8-max-0902":{"draws":42,"losses":53,"wins":49},"recursive/flint-v1.0":{"draws":12,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":34,"losses":38,"wins":60},"stealth/ox-alpha":{"draws":103,"losses":187,"wins":184},"stealth/space-bunny-alpha":{"draws":24,"losses":28,"wins":62},"stepfun/step-3.7-flash":{"draws":24,"losses":15,"wins":63},"stepfun/step-5-preview":{"draws":4,"losses":7,"wins":1},"tencent/hy3-preview":{"draws":22,"losses":17,"wins":39},"tencent/hy4-preview":{"draws":39,"losses":58,"wins":41},"thinkingmachines/inkling":{"draws":61,"losses":31,"wins":100},"thinkingmachines/inkling-small":{"draws":37,"losses":25,"wins":82},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"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":67,"wins":46},"x-ai/grok-4.6":{"draws":36,"losses":60,"wins":48},"x-ai/grok-4.7":{"draws":12,"losses":82,"wins":32},"x-ai/grok-build-0.1":{"draws":17,"losses":5,"wins":26},"xiaomi/mimo-v2.5":{"draws":66,"losses":34,"wins":122},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":21,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":34,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":43,"wins":31},"z-ai/glm-5.2":{"draws":95,"losses":67,"wins":126},"z-ai/glm-5.3":{"draws":21,"losses":88,"wins":29},"z-ai/glm-5.3-flash":{"draws":25,"losses":61,"wins":58},"z-ai/glm-5.3-flashx":{"draws":24,"losses":68,"wins":52}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":20,"wins":89},"claude-fable-5":{"draws":26,"losses":65,"wins":53},"claude-fable-5-1":{"draws":9,"losses":133,"wins":20},"claude-haiku-5-5":{"draws":25,"losses":52,"wins":61},"claude-opus-4-5":{"draws":44,"losses":52,"wins":138},"claude-opus-4-8":{"draws":24,"losses":42,"wins":66},"claude-opus-5":{"draws":35,"losses":158,"wins":53},"claude-opus-5-5":{"draws":10,"losses":128,"wins":18},"claude-sonnet-5":{"draws":31,"losses":32,"wins":81},"claude-sonnet-5-5":{"draws":24,"losses":60,"wins":60},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":47},"deepseek/deepseek-v4-flash":{"draws":40,"losses":26,"wins":150},"deepseek/deepseek-v4-pro":{"draws":28,"losses":25,"wins":79},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":32,"wins":76},"deepseek/deepseek-v4.1-flash":{"draws":33,"losses":41,"wins":70},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":41,"wins":41},"elorian/glimpse":{"draws":17,"losses":26,"wins":35},"fireworks/ember-1":{"draws":34,"losses":32,"wins":78},"gemini-3.1-pro-preview":{"draws":26,"losses":37,"wins":81},"gemini-4-argon":{"draws":18,"losses":107,"wins":19},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":78},"google/gemini-3.5-flash":{"draws":29,"losses":50,"wins":101},"google/gemini-3.5-flash-lite":{"draws":38,"losses":31,"wins":183},"google/gemini-3.6-flash":{"draws":42,"losses":101,"wins":133},"google/gemini-3.8-flash":{"draws":26,"losses":47,"wins":71},"google/gemma-4-31b-it":{"draws":16,"losses":7,"wins":61},"gpt-4.1":{"draws":11,"losses":7,"wins":30},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":10},"gpt-5":{"draws":25,"losses":28,"wins":73},"gpt-5.4":{"draws":26,"losses":49,"wins":63},"gpt-5.4-mini":{"draws":23,"losses":9,"wins":64},"gpt-5.4-nano":{"draws":21,"losses":27,"wins":96},"gpt-5.5":{"draws":39,"losses":43,"wins":50},"gpt-5.6-luna":{"draws":29,"losses":25,"wins":90},"gpt-5.6-sol":{"draws":26,"losses":67,"wins":51},"gpt-5.6-terra":{"draws":33,"losses":25,"wins":80},"gpt-6-astra":{"draws":11,"losses":123,"wins":10},"gpt-6-luna":{"draws":34,"losses":34,"wins":76},"gpt-6-sol":{"draws":15,"losses":89,"wins":40},"gpt-6.1-sol":{"draws":10,"losses":107,"wins":27},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":6,"wins":66},"inception/mercury-3":{"draws":26,"losses":15,"wins":55},"inclusionai/ling-3.0-flash":{"draws":20,"losses":3,"wins":79},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":26,"losses":22,"wins":108},"meta/muse-glimmer-30b":{"draws":30,"losses":12,"wins":84},"meta/muse-spark-1.2":{"draws":26,"losses":44,"wins":68},"meta/muse-spark-1.3":{"draws":16,"losses":62,"wins":66},"meta/muse-spark-open":{"draws":27,"losses":38,"wins":73},"meta/muse-wonder":{"draws":32,"losses":57,"wins":55},"minimax/minimax-m3":{"draws":11,"losses":5,"wins":62},"minimax/minimax-m3.1-flash":{"draws":29,"losses":24,"wins":73},"mistralai/mistral-large-4-0":{"draws":16,"losses":23,"wins":51},"mistralai/mistral-medium-3-5":{"draws":16,"losses":5,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":26},"moonshotai/kimi-k3":{"draws":18,"losses":39,"wins":81},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":102,"wins":29},"nex-agi/nex-n2-pro":{"draws":12,"losses":7,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":2,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":10,"wins":94},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":11,"wins":41},"o3":{"draws":18,"losses":56,"wins":124},"openai/gpt-oss-120b":{"draws":25,"losses":17,"wins":84},"poolside/laguna-s-2.1":{"draws":27,"losses":18,"wins":93},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":58},"qwen/qwen3.7-plus":{"draws":13,"losses":9,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":43,"wins":73},"qwen/qwen3.8-27b":{"draws":15,"losses":26,"wins":61},"qwen/qwen3.8-flash":{"draws":21,"losses":24,"wins":51},"qwen/qwen3.8-max":{"draws":29,"losses":33,"wins":82},"qwen/qwen3.8-max-0902":{"draws":32,"losses":40,"wins":72},"recursive/flint-v1.0":{"draws":6,"losses":1,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":27,"wins":76},"stealth/ox-alpha":{"draws":79,"losses":163,"wins":232},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":76},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":74},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":20,"losses":10,"wins":48},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":71},"thinkingmachines/inkling":{"draws":46,"losses":25,"wins":121},"thinkingmachines/inkling-small":{"draws":25,"losses":14,"wins":105},"unbiased/pareto-26.10":{"draws":6,"losses":40,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":37,"wins":10},"upstage/solar-mini4":{"draws":4,"losses":1,"wins":31},"x-ai/grok-4.5":{"draws":27,"losses":56,"wins":61},"x-ai/grok-4.6":{"draws":40,"losses":47,"wins":57},"x-ai/grok-4.7":{"draws":20,"losses":68,"wins":38},"x-ai/grok-build-0.1":{"draws":6,"losses":7,"wins":35},"xiaomi/mimo-v2.5":{"draws":47,"losses":16,"wins":159},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":22,"wins":53},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":44,"wins":42},"z-ai/glm-5.2":{"draws":62,"losses":53,"wins":173},"z-ai/glm-5.3":{"draws":24,"losses":73,"wins":41},"z-ai/glm-5.3-flash":{"draws":25,"losses":45,"wins":74},"z-ai/glm-5.3-flashx":{"draws":24,"losses":48,"wins":72}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":22,"wins":34},"claude-fable-5":{"draws":11,"losses":39,"wins":28},"claude-fable-5-1":{"draws":7,"losses":74,"wins":9},"claude-haiku-5-5":{"draws":11,"losses":34,"wins":29},"claude-opus-4-5":{"draws":29,"losses":41,"wins":56},"claude-opus-4-8":{"draws":14,"losses":27,"wins":29},"claude-opus-5":{"draws":19,"losses":91,"wins":28},"claude-opus-5-5":{"draws":7,"losses":72,"wins":7},"claude-sonnet-5":{"draws":18,"losses":29,"wins":31},"claude-sonnet-5-5":{"draws":16,"losses":43,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":21},"deepseek/deepseek-v4-flash":{"draws":25,"losses":30,"wins":61},"deepseek/deepseek-v4-pro":{"draws":20,"losses":17,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":28,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":30,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":17,"losses":35,"wins":26},"elorian/glimpse":{"draws":2,"losses":9,"wins":9},"fireworks/ember-1":{"draws":18,"losses":31,"wins":29},"gemini-3.1-pro-preview":{"draws":15,"losses":31,"wins":32},"gemini-4-argon":{"draws":8,"losses":59,"wins":11},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":30},"google/gemini-3.5-flash":{"draws":19,"losses":34,"wins":45},"google/gemini-3.5-flash-lite":{"draws":38,"losses":27,"wins":71},"google/gemini-3.6-flash":{"draws":30,"losses":62,"wins":58},"google/gemini-3.8-flash":{"draws":13,"losses":35,"wins":30},"google/gemma-4-31b-it":{"draws":12,"losses":9,"wins":23},"gpt-4.1":{"draws":6,"losses":8,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":22,"wins":34},"gpt-5.4":{"draws":18,"losses":32,"wins":26},"gpt-5.4-mini":{"draws":15,"losses":13,"wins":24},"gpt-5.4-nano":{"draws":13,"losses":22,"wins":39},"gpt-5.5":{"draws":17,"losses":33,"wins":24},"gpt-5.6-luna":{"draws":22,"losses":20,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":46,"wins":22},"gpt-5.6-terra":{"draws":19,"losses":25,"wins":32},"gpt-6-astra":{"draws":6,"losses":65,"wins":7},"gpt-6-luna":{"draws":14,"losses":27,"wins":37},"gpt-6-sol":{"draws":10,"losses":53,"wins":15},"gpt-6.1-sol":{"draws":4,"losses":64,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":5,"wins":32},"inception/mercury-3":{"draws":8,"losses":21,"wins":23},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":17,"losses":20,"wins":47},"meta/muse-glimmer-30b":{"draws":19,"losses":17,"wins":36},"meta/muse-spark-1.2":{"draws":16,"losses":35,"wins":25},"meta/muse-spark-1.3":{"draws":16,"losses":37,"wins":25},"meta/muse-spark-open":{"draws":13,"losses":28,"wins":35},"meta/muse-wonder":{"draws":15,"losses":42,"wins":21},"minimax/minimax-m3":{"draws":9,"losses":10,"wins":23},"minimax/minimax-m3.1-flash":{"draws":18,"losses":15,"wins":35},"mistralai/mistral-large-4-0":{"draws":12,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":9},"moonshotai/kimi-k3":{"draws":19,"losses":26,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":56,"wins":15},"nex-agi/nex-n2-pro":{"draws":8,"losses":10,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":44},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":10,"wins":17},"o3":{"draws":14,"losses":36,"wins":56},"openai/gpt-oss-120b":{"draws":14,"losses":18,"wins":36},"poolside/laguna-s-2.1":{"draws":18,"losses":16,"wins":40},"qwen/qwen3.7-max":{"draws":8,"losses":14,"wins":22},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":29,"wins":29},"qwen/qwen3.8-27b":{"draws":11,"losses":21,"wins":22},"qwen/qwen3.8-flash":{"draws":13,"losses":17,"wins":22},"qwen/qwen3.8-max":{"draws":17,"losses":31,"wins":30},"qwen/qwen3.8-max-0902":{"draws":20,"losses":30,"wins":28},"recursive/flint-v1.0":{"draws":5,"losses":4,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":21,"wins":33},"stealth/ox-alpha":{"draws":65,"losses":107,"wins":94},"stealth/space-bunny-alpha":{"draws":13,"losses":18,"wins":31},"stepfun/step-3.7-flash":{"draws":5,"losses":13,"wins":38},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":12,"losses":11,"wins":19},"tencent/hy4-preview":{"draws":13,"losses":30,"wins":33},"thinkingmachines/inkling":{"draws":27,"losses":26,"wins":53},"thinkingmachines/inkling-small":{"draws":18,"losses":12,"wins":48},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":24,"wins":2},"upstage/solar-mini4":{"draws":4,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":14,"losses":36,"wins":28},"x-ai/grok-4.6":{"draws":20,"losses":33,"wins":25},"x-ai/grok-4.7":{"draws":7,"losses":44,"wins":17},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":34,"losses":20,"wins":64},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":14,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":26,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":22,"wins":22},"z-ai/glm-5.2":{"draws":35,"losses":49,"wins":72},"z-ai/glm-5.3":{"draws":13,"losses":46,"wins":15},"z-ai/glm-5.3-flash":{"draws":12,"losses":35,"wins":31},"z-ai/glm-5.3-flashx":{"draws":17,"losses":32,"wins":29}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":26,"wins":70},"claude-fable-5":{"draws":31,"losses":91,"wins":22},"claude-fable-5-1":{"draws":5,"losses":147,"wins":10},"claude-haiku-5-5":{"draws":37,"losses":63,"wins":38},"claude-opus-4-5":{"draws":78,"losses":66,"wins":90},"claude-opus-4-8":{"draws":42,"losses":52,"wins":38},"claude-opus-5":{"draws":27,"losses":178,"wins":41},"claude-opus-5-5":{"draws":8,"losses":136,"wins":12},"claude-sonnet-5":{"draws":37,"losses":45,"wins":62},"claude-sonnet-5-5":{"draws":28,"losses":72,"wins":44},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":35},"deepseek/deepseek-v4-flash":{"draws":63,"losses":45,"wins":108},"deepseek/deepseek-v4-pro":{"draws":37,"losses":39,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":41,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":52,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":34,"losses":78,"wins":32},"elorian/glimpse":{"draws":18,"losses":29,"wins":31},"fireworks/ember-1":{"draws":24,"losses":36,"wins":36},"gemini-3.1-pro-preview":{"draws":31,"losses":44,"wins":69},"gemini-4-argon":{"draws":10,"losses":118,"wins":16},"google/gemini-3.1-flash-lite":{"draws":19,"losses":7,"wins":70},"google/gemini-3.5-flash":{"draws":46,"losses":64,"wins":70},"google/gemini-3.5-flash-lite":{"draws":82,"losses":50,"wins":120},"google/gemini-3.6-flash":{"draws":76,"losses":98,"wins":102},"google/gemini-3.8-flash":{"draws":32,"losses":64,"wins":48},"google/gemma-4-31b-it":{"draws":31,"losses":12,"wins":41},"gpt-4.1":{"draws":13,"losses":14,"wins":21},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":8},"gpt-5":{"draws":30,"losses":35,"wins":61},"gpt-5.4":{"draws":36,"losses":63,"wins":39},"gpt-5.4-mini":{"draws":36,"losses":14,"wins":46},"gpt-5.4-nano":{"draws":32,"losses":33,"wins":79},"gpt-5.5":{"draws":38,"losses":50,"wins":44},"gpt-5.6-luna":{"draws":44,"losses":44,"wins":56},"gpt-5.6-sol":{"draws":22,"losses":86,"wins":36},"gpt-5.6-terra":{"draws":40,"losses":37,"wins":61},"gpt-6-astra":{"draws":10,"losses":129,"wins":5},"gpt-6-luna":{"draws":37,"losses":43,"wins":64},"gpt-6-sol":{"draws":20,"losses":101,"wins":23},"gpt-6.1-sol":{"draws":10,"losses":116,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":54},"inception/mercury-3":{"draws":33,"losses":32,"wins":31},"inclusionai/ling-3.0-flash":{"draws":42,"losses":5,"wins":55},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":36,"losses":32,"wins":88},"meta/muse-glimmer-30b":{"draws":38,"losses":19,"wins":69},"meta/muse-spark-1.2":{"draws":36,"losses":48,"wins":54},"meta/muse-spark-1.3":{"draws":33,"losses":67,"wins":44},"meta/muse-spark-open":{"draws":29,"losses":59,"wins":50},"meta/muse-wonder":{"draws":38,"losses":76,"wins":30},"minimax/minimax-m3":{"draws":16,"losses":7,"wins":55},"minimax/minimax-m3.1-flash":{"draws":31,"losses":38,"wins":57},"mistralai/mistral-large-4-0":{"draws":26,"losses":33,"wins":31},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":11,"wins":14},"moonshotai/kimi-k3":{"draws":42,"losses":39,"wins":57},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":115,"wins":14},"nex-agi/nex-n2-pro":{"draws":19,"losses":9,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":5,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":23,"wins":62},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":19,"wins":29},"o3":{"draws":37,"losses":50,"wins":111},"openai/gpt-oss-120b":{"draws":43,"losses":18,"wins":65},"poolside/laguna-s-2.1":{"draws":46,"losses":26,"wins":66},"qwen/qwen3.7-max":{"draws":21,"losses":21,"wins":42},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":47,"wins":50},"qwen/qwen3.8-27b":{"draws":28,"losses":39,"wins":35},"qwen/qwen3.8-flash":{"draws":30,"losses":32,"wins":34},"qwen/qwen3.8-max":{"draws":38,"losses":46,"wins":60},"qwen/qwen3.8-max-0902":{"draws":37,"losses":63,"wins":44},"recursive/flint-v1.0":{"draws":10,"losses":5,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":51,"wins":45},"stealth/ox-alpha":{"draws":112,"losses":185,"wins":177},"stealth/space-bunny-alpha":{"draws":30,"losses":29,"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":29,"losses":14,"wins":35},"tencent/hy4-preview":{"draws":36,"losses":55,"wins":47},"thinkingmachines/inkling":{"draws":57,"losses":28,"wins":107},"thinkingmachines/inkling-small":{"draws":43,"losses":20,"wins":81},"unbiased/pareto-26.10":{"draws":2,"losses":45,"wins":1},"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":32,"losses":72,"wins":40},"x-ai/grok-4.6":{"draws":36,"losses":65,"wins":43},"x-ai/grok-4.7":{"draws":10,"losses":88,"wins":28},"x-ai/grok-build-0.1":{"draws":16,"losses":8,"wins":24},"xiaomi/mimo-v2.5":{"draws":70,"losses":38,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":20,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":42,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":46,"wins":29},"z-ai/glm-5.2":{"draws":82,"losses":75,"wins":131},"z-ai/glm-5.3":{"draws":23,"losses":89,"wins":26},"z-ai/glm-5.3-flash":{"draws":24,"losses":73,"wins":47},"z-ai/glm-5.3-flashx":{"draws":28,"losses":67,"wins":49}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":38,"wins":63},"claude-fable-5":{"draws":29,"losses":86,"wins":29},"claude-fable-5-1":{"draws":8,"losses":149,"wins":5},"claude-haiku-5-5":{"draws":34,"losses":58,"wins":46},"claude-opus-4-5":{"draws":57,"losses":103,"wins":74},"claude-opus-4-8":{"draws":29,"losses":65,"wins":38},"claude-opus-5":{"draws":26,"losses":189,"wins":31},"claude-opus-5-5":{"draws":9,"losses":138,"wins":9},"claude-sonnet-5":{"draws":36,"losses":58,"wins":50},"claude-sonnet-5-5":{"draws":21,"losses":81,"wins":42},"cohere/north-mini-code":{"draws":12,"losses":16,"wins":26},"deepseek/deepseek-v4-flash":{"draws":56,"losses":63,"wins":97},"deepseek/deepseek-v4-pro":{"draws":30,"losses":48,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":53,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":66,"wins":50},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":81,"wins":37},"elorian/glimpse":{"draws":15,"losses":32,"wins":31},"fireworks/ember-1":{"draws":31,"losses":69,"wins":44},"gemini-3.1-pro-preview":{"draws":20,"losses":38,"wins":38},"gemini-4-argon":{"draws":11,"losses":118,"wins":15},"google/gemini-3.1-flash-lite":{"draws":20,"losses":20,"wins":56},"google/gemini-3.5-flash":{"draws":34,"losses":83,"wins":63},"google/gemini-3.5-flash-lite":{"draws":79,"losses":64,"wins":109},"google/gemini-3.6-flash":{"draws":65,"losses":124,"wins":87},"google/gemini-3.8-flash":{"draws":27,"losses":82,"wins":35},"google/gemma-4-31b-it":{"draws":30,"losses":15,"wins":39},"gpt-4.1":{"draws":11,"losses":19,"wins":18},"gpt-4.1-nano":{"draws":11,"losses":3,"wins":4},"gpt-5":{"draws":36,"losses":36,"wins":54},"gpt-5.4":{"draws":31,"losses":68,"wins":39},"gpt-5.4-mini":{"draws":31,"losses":25,"wins":40},"gpt-5.4-nano":{"draws":31,"losses":40,"wins":73},"gpt-5.5":{"draws":31,"losses":65,"wins":36},"gpt-5.6-luna":{"draws":36,"losses":52,"wins":56},"gpt-5.6-sol":{"draws":17,"losses":94,"wins":33},"gpt-5.6-terra":{"draws":44,"losses":48,"wins":46},"gpt-6-astra":{"draws":7,"losses":135,"wins":2},"gpt-6-luna":{"draws":33,"losses":49,"wins":62},"gpt-6-sol":{"draws":14,"losses":102,"wins":28},"gpt-6.1-sol":{"draws":3,"losses":128,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":36,"losses":24,"wins":42},"inception/mercury-3":{"draws":32,"losses":39,"wins":25},"inclusionai/ling-3.0-flash":{"draws":34,"losses":18,"wins":50},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":36,"losses":49,"wins":71},"meta/muse-glimmer-30b":{"draws":44,"losses":21,"wins":61},"meta/muse-spark-1.2":{"draws":31,"losses":57,"wins":50},"meta/muse-spark-1.3":{"draws":22,"losses":83,"wins":39},"meta/muse-spark-open":{"draws":29,"losses":69,"wins":40},"meta/muse-wonder":{"draws":25,"losses":94,"wins":25},"minimax/minimax-m3":{"draws":17,"losses":22,"wins":39},"minimax/minimax-m3.1-flash":{"draws":34,"losses":43,"wins":49},"mistralai/mistral-large-4-0":{"draws":22,"losses":33,"wins":35},"mistralai/mistral-medium-3-5":{"draws":25,"losses":13,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":18},"moonshotai/kimi-k3":{"draws":34,"losses":65,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":105,"wins":24},"nex-agi/nex-n2-pro":{"draws":19,"losses":11,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":31,"wins":53},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":25,"wins":26},"o3":{"draws":30,"losses":91,"wins":77},"openai/gpt-oss-120b":{"draws":34,"losses":33,"wins":59},"poolside/laguna-s-2.1":{"draws":42,"losses":35,"wins":61},"qwen/qwen3.7-max":{"draws":21,"losses":29,"wins":34},"qwen/qwen3.7-plus":{"draws":24,"losses":14,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":67,"wins":43},"qwen/qwen3.8-27b":{"draws":23,"losses":48,"wins":31},"qwen/qwen3.8-flash":{"draws":34,"losses":31,"wins":31},"qwen/qwen3.8-max":{"draws":36,"losses":61,"wins":47},"qwen/qwen3.8-max-0902":{"draws":31,"losses":72,"wins":41},"recursive/flint-v1.0":{"draws":11,"losses":4,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":53,"wins":48},"stealth/ox-alpha":{"draws":94,"losses":232,"wins":148},"stealth/space-bunny-alpha":{"draws":25,"losses":41,"wins":48},"stepfun/step-3.7-flash":{"draws":21,"losses":32,"wins":49},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":21,"losses":24,"wins":33},"tencent/hy4-preview":{"draws":30,"losses":64,"wins":44},"thinkingmachines/inkling":{"draws":59,"losses":48,"wins":85},"thinkingmachines/inkling-small":{"draws":39,"losses":28,"wins":77},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":3},"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":30,"losses":70,"wins":44},"x-ai/grok-4.6":{"draws":34,"losses":80,"wins":30},"x-ai/grok-4.7":{"draws":12,"losses":89,"wins":25},"x-ai/grok-build-0.1":{"draws":12,"losses":14,"wins":22},"xiaomi/mimo-v2.5":{"draws":66,"losses":59,"wins":97},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":29,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":49,"wins":29},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":57,"wins":24},"z-ai/glm-5.2":{"draws":75,"losses":97,"wins":116},"z-ai/glm-5.3":{"draws":24,"losses":87,"wins":27},"z-ai/glm-5.3-flash":{"draws":31,"losses":73,"wins":40},"z-ai/glm-5.3-flashx":{"draws":28,"losses":75,"wins":41}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":6,"wins":123},"claude-fable-5":{"draws":13,"losses":30,"wins":101},"claude-fable-5-1":{"draws":14,"losses":95,"wins":53},"claude-haiku-5-5":{"draws":14,"losses":26,"wins":98},"claude-opus-4-5":{"draws":9,"losses":18,"wins":207},"claude-opus-4-8":{"draws":9,"losses":25,"wins":98},"claude-opus-5":{"draws":30,"losses":102,"wins":114},"claude-opus-5-5":{"draws":9,"losses":100,"wins":47},"claude-sonnet-5":{"draws":12,"losses":8,"wins":124},"claude-sonnet-5-5":{"draws":12,"losses":44,"wins":88},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":52},"deepseek/deepseek-v4-flash":{"draws":13,"losses":4,"wins":199},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":104},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":111},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":114},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":19,"wins":107},"elorian/glimpse":{"draws":8,"losses":11,"wins":59},"fireworks/ember-1":{"draws":10,"losses":16,"wins":118},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":118},"gemini-4-argon":{"draws":14,"losses":41,"wins":41},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":160},"google/gemini-3.5-flash-lite":{"draws":14,"losses":11,"wins":227},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":226},"google/gemini-3.8-flash":{"draws":15,"losses":21,"wins":108},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":80},"gpt-4.1":{"draws":5,"losses":0,"wins":43},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":18},"gpt-5":{"draws":4,"losses":9,"wins":113},"gpt-5.4":{"draws":13,"losses":22,"wins":103},"gpt-5.4-mini":{"draws":13,"losses":0,"wins":83},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":134},"gpt-5.5":{"draws":9,"losses":23,"wins":100},"gpt-5.6-luna":{"draws":13,"losses":8,"wins":123},"gpt-5.6-sol":{"draws":11,"losses":33,"wins":100},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":116},"gpt-6-astra":{"draws":17,"losses":87,"wins":40},"gpt-6-luna":{"draws":10,"losses":8,"wins":126},"gpt-6-sol":{"draws":14,"losses":58,"wins":72},"gpt-6.1-sol":{"draws":19,"losses":79,"wins":46},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":94},"inception/mercury-3":{"draws":11,"losses":8,"wins":77},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":91},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":138},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":109},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":114},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":113},"meta/muse-spark-open":{"draws":11,"losses":21,"wins":106},"meta/muse-wonder":{"draws":17,"losses":32,"wins":95},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":75},"minimax/minimax-m3.1-flash":{"draws":15,"losses":10,"wins":101},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":73},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":79},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":29},"moonshotai/kimi-k3":{"draws":6,"losses":15,"wins":117},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":57,"wins":72},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":59},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":114},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":55},"o3":{"draws":2,"losses":9,"wins":187},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":121},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":127},"qwen/qwen3.7-max":{"draws":4,"losses":7,"wins":73},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":68},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":23,"wins":112},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":88},"qwen/qwen3.8-flash":{"draws":12,"losses":11,"wins":73},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":123},"qwen/qwen3.8-max-0902":{"draws":12,"losses":14,"wins":118},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":13,"wins":112},"stealth/ox-alpha":{"draws":45,"losses":49,"wins":380},"stealth/space-bunny-alpha":{"draws":7,"losses":4,"wins":103},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":98},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":71},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":105},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":164},"thinkingmachines/inkling-small":{"draws":16,"losses":4,"wins":124},"unbiased/pareto-26.10":{"draws":4,"losses":31,"wins":13},"unbiased/pareto-26.10-preview":{"draws":3,"losses":27,"wins":18},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":33},"x-ai/grok-4.5":{"draws":10,"losses":26,"wins":108},"x-ai/grok-4.6":{"draws":19,"losses":20,"wins":105},"x-ai/grok-4.7":{"draws":16,"losses":40,"wins":70},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":44},"xiaomi/mimo-v2.5":{"draws":16,"losses":1,"wins":205},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":72},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":79},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":23,"wins":64},"z-ai/glm-5.2":{"draws":27,"losses":14,"wins":247},"z-ai/glm-5.3":{"draws":15,"losses":40,"wins":83},"z-ai/glm-5.3-flash":{"draws":15,"losses":19,"wins":110},"z-ai/glm-5.3-flashx":{"draws":12,"losses":22,"wins":110}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":47,"wins":19},"claude-fable-5":{"draws":9,"losses":83,"wins":4},"claude-fable-5-1":{"draws":7,"losses":99,"wins":0},"claude-haiku-5-5":{"draws":20,"losses":68,"wins":8},"claude-opus-4-5":{"draws":35,"losses":118,"wins":7},"claude-opus-4-8":{"draws":19,"losses":70,"wins":7},"claude-opus-5":{"draws":18,"losses":127,"wins":5},"claude-opus-5-5":{"draws":8,"losses":96,"wins":0},"claude-sonnet-5":{"draws":26,"losses":65,"wins":5},"claude-sonnet-5-5":{"draws":15,"losses":69,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":18,"wins":14},"deepseek/deepseek-v4-flash":{"draws":35,"losses":84,"wins":27},"deepseek/deepseek-v4-pro":{"draws":23,"losses":59,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":54,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":58,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":78,"wins":4},"elorian/glimpse":{"draws":13,"losses":30,"wins":7},"fireworks/ember-1":{"draws":19,"losses":70,"wins":7},"gemini-3.1-pro-preview":{"draws":20,"losses":56,"wins":20},"gemini-4-argon":{"draws":4,"losses":92,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":22,"wins":22},"google/gemini-3.5-flash":{"draws":29,"losses":82,"wins":15},"google/gemini-3.5-flash-lite":{"draws":43,"losses":91,"wins":40},"google/gemini-3.6-flash":{"draws":35,"losses":132,"wins":19},"google/gemini-3.8-flash":{"draws":20,"losses":74,"wins":2},"google/gemma-4-31b-it":{"draws":19,"losses":26,"wins":15},"gpt-4.1":{"draws":9,"losses":19,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":5},"gpt-5":{"draws":19,"losses":57,"wins":8},"gpt-5.4":{"draws":18,"losses":68,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":40,"wins":8},"gpt-5.4-nano":{"draws":21,"losses":65,"wins":22},"gpt-5.5":{"draws":20,"losses":64,"wins":4},"gpt-5.6-luna":{"draws":18,"losses":57,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":82,"wins":5},"gpt-5.6-terra":{"draws":22,"losses":63,"wins":5},"gpt-6-astra":{"draws":2,"losses":94,"wins":0},"gpt-6-luna":{"draws":24,"losses":59,"wins":13},"gpt-6-sol":{"draws":14,"losses":80,"wins":2},"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":22,"losses":29,"wins":21},"inception/mercury-3":{"draws":13,"losses":40,"wins":7},"inclusionai/ling-3.0-flash":{"draws":20,"losses":24,"wins":22},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":65,"wins":30},"meta/muse-glimmer-30b":{"draws":26,"losses":35,"wins":21},"meta/muse-spark-1.2":{"draws":22,"losses":60,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":79,"wins":5},"meta/muse-spark-open":{"draws":15,"losses":73,"wins":6},"meta/muse-wonder":{"draws":9,"losses":83,"wins":4},"minimax/minimax-m3":{"draws":13,"losses":25,"wins":16},"minimax/minimax-m3.1-flash":{"draws":17,"losses":59,"wins":10},"mistralai/mistral-large-4-0":{"draws":17,"losses":39,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":25,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":21,"wins":1},"moonshotai/kimi-k3":{"draws":25,"losses":56,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":91,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":30,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":14,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":45,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":31,"wins":6},"o3":{"draws":24,"losses":123,"wins":11},"openai/gpt-oss-120b":{"draws":21,"losses":38,"wins":23},"poolside/laguna-s-2.1":{"draws":24,"losses":40,"wins":22},"qwen/qwen3.7-max":{"draws":14,"losses":37,"wins":9},"qwen/qwen3.7-plus":{"draws":11,"losses":32,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":66,"wins":7},"qwen/qwen3.8-27b":{"draws":15,"losses":46,"wins":9},"qwen/qwen3.8-flash":{"draws":19,"losses":35,"wins":10},"qwen/qwen3.8-max":{"draws":23,"losses":72,"wins":1},"qwen/qwen3.8-max-0902":{"draws":24,"losses":69,"wins":3},"recursive/flint-v1.0":{"draws":8,"losses":12,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":65,"wins":7},"stealth/ox-alpha":{"draws":47,"losses":196,"wins":29},"stealth/space-bunny-alpha":{"draws":17,"losses":50,"wins":13},"stepfun/step-3.7-flash":{"draws":16,"losses":48,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":17,"losses":22,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":69,"wins":6},"thinkingmachines/inkling":{"draws":33,"losses":58,"wins":35},"thinkingmachines/inkling-small":{"draws":29,"losses":36,"wins":31},"unbiased/pareto-26.10":{"draws":1,"losses":31,"wins":0},"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":17,"losses":77,"wins":2},"x-ai/grok-4.6":{"draws":17,"losses":75,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":78,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":19,"wins":5},"xiaomi/mimo-v2.5":{"draws":47,"losses":76,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":44,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":49,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":50,"wins":4},"z-ai/glm-5.2":{"draws":39,"losses":127,"wins":26},"z-ai/glm-5.3":{"draws":9,"losses":83,"wins":0},"z-ai/glm-5.3-flash":{"draws":19,"losses":64,"wins":13},"z-ai/glm-5.3-flashx":{"draws":21,"losses":66,"wins":9}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":50,"wins":82},"claude-fable-5":{"draws":28,"losses":119,"wins":33},"claude-fable-5-1":{"draws":13,"losses":182,"wins":7},"claude-haiku-5-5":{"draws":37,"losses":77,"wins":60},"claude-opus-4-5":{"draws":75,"losses":105,"wins":114},"claude-opus-4-8":{"draws":37,"losses":82,"wins":49},"claude-opus-5":{"draws":35,"losses":237,"wins":32},"claude-opus-5-5":{"draws":11,"losses":176,"wins":9},"claude-sonnet-5":{"draws":46,"losses":57,"wins":77},"claude-sonnet-5-5":{"draws":31,"losses":102,"wins":47},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":44},"deepseek/deepseek-v4-flash":{"draws":59,"losses":67,"wins":144},"deepseek/deepseek-v4-pro":{"draws":37,"losses":57,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":53,"wins":75},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":80,"wins":60},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":101,"wins":50},"elorian/glimpse":{"draws":19,"losses":45,"wins":34},"fireworks/ember-1":{"draws":46,"losses":70,"wins":64},"gemini-3.1-pro-preview":{"draws":34,"losses":63,"wins":83},"gemini-4-argon":{"draws":12,"losses":160,"wins":8},"google/gemini-3.1-flash-lite":{"draws":29,"losses":15,"wins":82},"google/gemini-3.5-flash":{"draws":30,"losses":69,"wins":69},"google/gemini-3.5-flash-lite":{"draws":72,"losses":83,"wins":163},"google/gemini-3.6-flash":{"draws":70,"losses":149,"wins":127},"google/gemini-3.8-flash":{"draws":31,"losses":105,"wins":44},"google/gemma-4-31b-it":{"draws":32,"losses":22,"wins":52},"gpt-4.1":{"draws":12,"losses":17,"wins":31},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":11},"gpt-5":{"draws":34,"losses":53,"wins":71},"gpt-5.4":{"draws":22,"losses":99,"wins":53},"gpt-5.4-mini":{"draws":32,"losses":32,"wins":56},"gpt-5.4-nano":{"draws":23,"losses":50,"wins":111},"gpt-5.5":{"draws":41,"losses":76,"wins":49},"gpt-5.6-luna":{"draws":48,"losses":53,"wins":79},"gpt-5.6-sol":{"draws":20,"losses":123,"wins":37},"gpt-5.6-terra":{"draws":43,"losses":71,"wins":58},"gpt-6-astra":{"draws":7,"losses":167,"wins":6},"gpt-6-luna":{"draws":49,"losses":64,"wins":67},"gpt-6-sol":{"draws":23,"losses":127,"wins":30},"gpt-6.1-sol":{"draws":7,"losses":154,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":42,"losses":19,"wins":67},"inception/mercury-3":{"draws":27,"losses":48,"wins":43},"inclusionai/ling-3.0-flash":{"draws":35,"losses":16,"wins":77},"inclusionai/ling-3.1-flash":{"draws":5,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":36,"losses":43,"wins":119},"meta/muse-glimmer-30b":{"draws":40,"losses":29,"wins":89},"meta/muse-spark-1.2":{"draws":32,"losses":83,"wins":57},"meta/muse-spark-1.3":{"draws":31,"losses":102,"wins":47},"meta/muse-spark-open":{"draws":28,"losses":93,"wins":53},"meta/muse-wonder":{"draws":27,"losses":123,"wins":30},"minimax/minimax-m3":{"draws":19,"losses":25,"wins":54},"minimax/minimax-m3.1-flash":{"draws":32,"losses":53,"wins":73},"mistralai/mistral-large-4-0":{"draws":37,"losses":39,"wins":36},"mistralai/mistral-medium-3-5":{"draws":25,"losses":16,"wins":63},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":16,"wins":18},"moonshotai/kimi-k3":{"draws":47,"losses":67,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":148,"wins":20},"nex-agi/nex-n2-pro":{"draws":17,"losses":20,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":38,"wins":86},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":35},"o3":{"draws":31,"losses":90,"wins":137},"openai/gpt-oss-120b":{"draws":36,"losses":38,"wins":82},"poolside/laguna-s-2.1":{"draws":30,"losses":34,"wins":106},"qwen/qwen3.7-max":{"draws":25,"losses":39,"wins":42},"qwen/qwen3.7-plus":{"draws":17,"losses":20,"wins":55},"qwen/qwen3.8-2.4t-a95b":{"draws":47,"losses":81,"wins":52},"qwen/qwen3.8-27b":{"draws":20,"losses":51,"wins":57},"qwen/qwen3.8-flash":{"draws":26,"losses":41,"wins":53},"qwen/qwen3.8-max":{"draws":49,"losses":68,"wins":63},"qwen/qwen3.8-max-0902":{"draws":44,"losses":90,"wins":46},"recursive/flint-v1.0":{"draws":10,"losses":8,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":41,"losses":68,"wins":55},"stealth/ox-alpha":{"draws":94,"losses":279,"wins":203},"stealth/space-bunny-alpha":{"draws":40,"losses":38,"wins":66},"stepfun/step-3.7-flash":{"draws":22,"losses":27,"wins":81},"stepfun/step-5-preview":{"draws":6,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":26,"losses":29,"wins":43},"tencent/hy4-preview":{"draws":34,"losses":84,"wins":56},"thinkingmachines/inkling":{"draws":50,"losses":48,"wins":142},"thinkingmachines/inkling-small":{"draws":43,"losses":35,"wins":102},"unbiased/pareto-26.10":{"draws":7,"losses":50,"wins":3},"unbiased/pareto-26.10-preview":{"draws":2,"losses":53,"wins":5},"upstage/solar-mini4":{"draws":7,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":33,"losses":85,"wins":62},"x-ai/grok-4.6":{"draws":41,"losses":100,"wins":39},"x-ai/grok-4.7":{"draws":17,"losses":118,"wins":23},"x-ai/grok-build-0.1":{"draws":14,"losses":9,"wins":37},"xiaomi/mimo-v2.5":{"draws":76,"losses":54,"wins":154},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":30,"wins":53},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":55,"wins":41},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":63,"wins":37},"z-ai/glm-5.2":{"draws":82,"losses":119,"wins":159},"z-ai/glm-5.3":{"draws":28,"losses":109,"wins":35},"z-ai/glm-5.3-flash":{"draws":21,"losses":102,"wins":57},"z-ai/glm-5.3-flashx":{"draws":35,"losses":94,"wins":51}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":70,"losses":87,"wins":77},"claude-fable-5":{"draws":38,"losses":186,"wins":28},"claude-fable-5-1":{"draws":14,"losses":267,"wins":3},"claude-haiku-5-5":{"draws":52,"losses":150,"wins":40},"claude-opus-4-5":{"draws":125,"losses":194,"wins":91},"claude-opus-4-8":{"draws":57,"losses":150,"wins":25},"claude-opus-5":{"draws":51,"losses":338,"wins":35},"claude-opus-5-5":{"draws":17,"losses":254,"wins":1},"claude-sonnet-5":{"draws":64,"losses":132,"wins":56},"claude-sonnet-5-5":{"draws":47,"losses":166,"wins":39},"cohere/north-mini-code":{"draws":32,"losses":31,"wins":35},"deepseek/deepseek-v4-flash":{"draws":97,"losses":144,"wins":133},"deepseek/deepseek-v4-pro":{"draws":61,"losses":104,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":69,"losses":115,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":70,"losses":128,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":38,"losses":183,"wins":31},"elorian/glimpse":{"draws":38,"losses":71,"wins":27},"fireworks/ember-1":{"draws":82,"losses":120,"wins":50},"gemini-3.1-pro-preview":{"draws":79,"losses":109,"wins":64},"gemini-4-argon":{"draws":14,"losses":227,"wins":11},"google/gemini-3.1-flash-lite":{"draws":43,"losses":40,"wins":91},"google/gemini-3.5-flash":{"draws":72,"losses":163,"wins":83},"google/gemini-3.5-flash-lite":{"draws":96,"losses":134,"wins":134},"google/gemini-3.6-flash":{"draws":119,"losses":267,"wins":100},"google/gemini-3.8-flash":{"draws":44,"losses":187,"wins":21},"google/gemma-4-31b-it":{"draws":55,"losses":35,"wins":58},"gpt-4.1":{"draws":25,"losses":31,"wins":28},"gpt-4.1-nano":{"draws":18,"losses":3,"wins":9},"gpt-5":{"draws":54,"losses":104,"wins":62},"gpt-5.4":{"draws":55,"losses":145,"wins":44},"gpt-5.4-mini":{"draws":51,"losses":63,"wins":54},"gpt-5.4-nano":{"draws":46,"losses":98,"wins":108},"gpt-5.5":{"draws":80,"losses":114,"wins":38},"gpt-5.6-luna":{"draws":68,"losses":108,"wins":76},"gpt-5.6-sol":{"draws":34,"losses":196,"wins":22},"gpt-5.6-terra":{"draws":61,"losses":131,"wins":48},"gpt-6-astra":{"draws":14,"losses":238,"wins":0},"gpt-6-luna":{"draws":73,"losses":117,"wins":62},"gpt-6-sol":{"draws":36,"losses":193,"wins":23},"gpt-6.1-sol":{"draws":15,"losses":235,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":68,"losses":43,"wins":69},"inception/mercury-3":{"draws":47,"losses":84,"wins":31},"inclusionai/ling-3.0-flash":{"draws":56,"losses":42,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":73,"losses":93,"wins":112},"meta/muse-glimmer-30b":{"draws":74,"losses":62,"wins":84},"meta/muse-spark-1.2":{"draws":63,"losses":129,"wins":48},"meta/muse-spark-1.3":{"draws":44,"losses":170,"wins":38},"meta/muse-spark-open":{"draws":42,"losses":162,"wins":40},"meta/muse-wonder":{"draws":43,"losses":182,"wins":27},"minimax/minimax-m3":{"draws":35,"losses":46,"wins":53},"minimax/minimax-m3.1-flash":{"draws":54,"losses":101,"wins":69},"mistralai/mistral-large-4-0":{"draws":50,"losses":77,"wins":29},"mistralai/mistral-medium-3-5":{"draws":42,"losses":39,"wins":67},"moonshotai/kimi-k2.7-code":{"draws":16,"losses":32,"wins":14},"moonshotai/kimi-k3":{"draws":75,"losses":118,"wins":47},"moonshotai/kimi-k3.1-pro":{"draws":31,"losses":209,"wins":12},"nex-agi/nex-n2-pro":{"draws":24,"losses":47,"wins":57},"nex-agi/nex-n2.5-pro":{"draws":13,"losses":17,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":67,"losses":76,"wins":77},"nvidia/nemotron-3.5-super-vl":{"draws":36,"losses":55,"wins":25},"o3":{"draws":57,"losses":202,"wins":97},"openai/gpt-oss-120b":{"draws":62,"losses":79,"wins":77},"poolside/laguna-s-2.1":{"draws":61,"losses":106,"wins":71},"qwen/qwen3.7-max":{"draws":34,"losses":69,"wins":43},"qwen/qwen3.7-plus":{"draws":32,"losses":40,"wins":54},"qwen/qwen3.8-2.4t-a95b":{"draws":77,"losses":135,"wins":40},"qwen/qwen3.8-27b":{"draws":36,"losses":103,"wins":41},"qwen/qwen3.8-flash":{"draws":53,"losses":79,"wins":36},"qwen/qwen3.8-max":{"draws":69,"losses":131,"wins":52},"qwen/qwen3.8-max-0902":{"draws":69,"losses":146,"wins":37},"recursive/flint-v1.0":{"draws":20,"losses":12,"wins":42},"reflection/beam-1.0-501b-a23b":{"draws":63,"losses":120,"wins":47},"stealth/ox-alpha":{"draws":172,"losses":486,"wins":168},"stealth/space-bunny-alpha":{"draws":52,"losses":89,"wins":61},"stepfun/step-3.7-flash":{"draws":49,"losses":60,"wins":71},"stepfun/step-5-preview":{"draws":10,"losses":10,"wins":0},"tencent/hy3-preview":{"draws":49,"losses":60,"wins":27},"tencent/hy4-preview":{"draws":57,"losses":132,"wins":55},"thinkingmachines/inkling":{"draws":88,"losses":114,"wins":136},"thinkingmachines/inkling-small":{"draws":71,"losses":76,"wins":105},"unbiased/pareto-26.10":{"draws":5,"losses":79,"wins":0},"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":60,"losses":145,"wins":47},"x-ai/grok-4.6":{"draws":56,"losses":162,"wins":34},"x-ai/grok-4.7":{"draws":20,"losses":170,"wins":28},"x-ai/grok-build-0.1":{"draws":30,"losses":27,"wins":27},"xiaomi/mimo-v2.5":{"draws":112,"losses":141,"wins":139},"xiaomi/mimo-v2.5-pro":{"draws":33,"losses":52,"wins":53},"xiaomi/mimo-v2.6-flash":{"draws":27,"losses":109,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":117,"wins":30},"z-ai/glm-5.2":{"draws":145,"losses":210,"wins":149},"z-ai/glm-5.3":{"draws":38,"losses":190,"wins":14},"z-ai/glm-5.3-flash":{"draws":46,"losses":158,"wins":48},"z-ai/glm-5.3-flashx":{"draws":58,"losses":147,"wins":47}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":56,"losses":59,"wins":139},"claude-fable-5":{"draws":39,"losses":157,"wins":80},"claude-fable-5-1":{"draws":15,"losses":278,"wins":19},"claude-haiku-5-5":{"draws":62,"losses":103,"wins":99},"claude-opus-4-5":{"draws":121,"losses":124,"wins":203},"claude-opus-4-8":{"draws":53,"losses":94,"wins":105},"claude-opus-5":{"draws":58,"losses":321,"wins":89},"claude-opus-5-5":{"draws":20,"losses":251,"wins":25},"claude-sonnet-5":{"draws":66,"losses":89,"wins":121},"claude-sonnet-5-5":{"draws":50,"losses":131,"wins":95},"cohere/north-mini-code":{"draws":20,"losses":8,"wins":76},"deepseek/deepseek-v4-flash":{"draws":89,"losses":67,"wins":256},"deepseek/deepseek-v4-pro":{"draws":63,"losses":82,"wins":109},"deepseek/deepseek-v4-pro-0813":{"draws":52,"losses":79,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":76,"losses":90,"wins":110},"deepseek/deepseek-v4.1-flash-1017":{"draws":42,"losses":133,"wins":101},"elorian/glimpse":{"draws":30,"losses":58,"wins":62},"fireworks/ember-1":{"draws":76,"losses":102,"wins":98},"gemini-3.1-pro-preview":{"draws":65,"losses":87,"wins":124},"gemini-4-argon":{"draws":18,"losses":226,"wins":32},"google/gemini-3.1-flash-lite":{"draws":35,"losses":19,"wins":132},"google/gemini-3.5-flash":{"draws":70,"losses":127,"wins":149},"google/gemini-3.5-flash-lite":{"draws":119,"losses":100,"wins":267},"google/gemini-3.6-flash":{"draws":96,"losses":172,"wins":172},"google/gemini-3.8-flash":{"draws":54,"losses":136,"wins":86},"google/gemma-4-31b-it":{"draws":51,"losses":20,"wins":89},"gpt-4.1":{"draws":25,"losses":19,"wins":48},"gpt-4.1-nano":{"draws":14,"losses":2,"wins":18},"gpt-5":{"draws":49,"losses":78,"wins":115},"gpt-5.4":{"draws":55,"losses":110,"wins":101},"gpt-5.4-mini":{"draws":50,"losses":33,"wins":101},"gpt-5.4-nano":{"draws":44,"losses":63,"wins":167},"gpt-5.5":{"draws":67,"losses":100,"wins":87},"gpt-5.6-luna":{"draws":72,"losses":61,"wins":143},"gpt-5.6-sol":{"draws":34,"losses":169,"wins":73},"gpt-5.6-terra":{"draws":67,"losses":67,"wins":130},"gpt-6-astra":{"draws":19,"losses":238,"wins":19},"gpt-6-luna":{"draws":73,"losses":78,"wins":125},"gpt-6-sol":{"draws":34,"losses":180,"wins":62},"gpt-6.1-sol":{"draws":18,"losses":238,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":11,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":60,"losses":16,"wins":118},"inception/mercury-3":{"draws":45,"losses":48,"wins":87},"inclusionai/ling-3.0-flash":{"draws":61,"losses":21,"wins":112},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":60,"losses":48,"wins":192},"meta/muse-glimmer-30b":{"draws":71,"losses":39,"wins":132},"meta/muse-spark-1.2":{"draws":56,"losses":105,"wins":103},"meta/muse-spark-1.3":{"draws":49,"losses":131,"wins":96},"meta/muse-spark-open":{"draws":50,"losses":110,"wins":106},"meta/muse-wonder":{"draws":51,"losses":154,"wins":71},"minimax/minimax-m3":{"draws":28,"losses":29,"wins":91},"minimax/minimax-m3.1-flash":{"draws":59,"losses":61,"wins":126},"mistralai/mistral-large-4-0":{"draws":41,"losses":59,"wins":72},"mistralai/mistral-medium-3-5":{"draws":45,"losses":20,"wins":95},"moonshotai/kimi-k2.7-code":{"draws":19,"losses":17,"wins":32},"moonshotai/kimi-k3":{"draws":70,"losses":89,"wins":105},"moonshotai/kimi-k3.1-pro":{"draws":29,"losses":203,"wins":44},"nex-agi/nex-n2-pro":{"draws":21,"losses":23,"wins":94},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":14,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":63,"losses":41,"wins":134},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":31,"wins":62},"o3":{"draws":50,"losses":127,"wins":207},"openai/gpt-oss-120b":{"draws":64,"losses":39,"wins":137},"poolside/laguna-s-2.1":{"draws":61,"losses":56,"wins":145},"qwen/qwen3.7-max":{"draws":37,"losses":42,"wins":81},"qwen/qwen3.7-plus":{"draws":33,"losses":23,"wins":82},"qwen/qwen3.8-2.4t-a95b":{"draws":63,"losses":95,"wins":118},"qwen/qwen3.8-27b":{"draws":41,"losses":66,"wins":91},"qwen/qwen3.8-flash":{"draws":50,"losses":48,"wins":86},"qwen/qwen3.8-max":{"draws":59,"losses":98,"wins":119},"qwen/qwen3.8-max-0902":{"draws":69,"losses":108,"wins":99},"recursive/flint-v1.0":{"draws":26,"losses":9,"wins":45},"reflection/beam-1.0-501b-a23b":{"draws":59,"losses":79,"wins":114},"stealth/ox-alpha":{"draws":178,"losses":373,"wins":365},"stealth/space-bunny-alpha":{"draws":54,"losses":49,"wins":117},"stepfun/step-3.7-flash":{"draws":34,"losses":32,"wins":132},"stepfun/step-5-preview":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":44,"losses":30,"wins":74},"tencent/hy4-preview":{"draws":51,"losses":99,"wins":116},"thinkingmachines/inkling":{"draws":103,"losses":52,"wins":217},"thinkingmachines/inkling-small":{"draws":76,"losses":46,"wins":154},"unbiased/pareto-26.10":{"draws":8,"losses":81,"wins":3},"unbiased/pareto-26.10-preview":{"draws":3,"losses":80,"wins":9},"upstage/solar-mini4":{"draws":14,"losses":9,"wins":49},"x-ai/grok-4.5":{"draws":58,"losses":114,"wins":104},"x-ai/grok-4.6":{"draws":66,"losses":128,"wins":82},"x-ai/grok-4.7":{"draws":14,"losses":168,"wins":58},"x-ai/grok-build-0.1":{"draws":27,"losses":7,"wins":58},"xiaomi/mimo-v2.5":{"draws":119,"losses":59,"wins":246},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":34,"wins":89},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":79,"wins":72},"xiaomi/mimo-v2.6-pro":{"draws":39,"losses":86,"wins":59},"z-ai/glm-5.2":{"draws":135,"losses":160,"wins":257},"z-ai/glm-5.3":{"draws":50,"losses":155,"wins":59},"z-ai/glm-5.3-flash":{"draws":41,"losses":142,"wins":93},"z-ai/glm-5.3-flashx":{"draws":62,"losses":114,"wins":100}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":23,"wins":83},"claude-fable-5":{"draws":19,"losses":68,"wins":57},"claude-fable-5-1":{"draws":11,"losses":137,"wins":14},"claude-haiku-5-5":{"draws":34,"losses":43,"wins":61},"claude-opus-4-5":{"draws":68,"losses":47,"wins":119},"claude-opus-4-8":{"draws":27,"losses":44,"wins":61},"claude-opus-5":{"draws":26,"losses":167,"wins":53},"claude-opus-5-5":{"draws":13,"losses":123,"wins":20},"claude-sonnet-5":{"draws":32,"losses":35,"wins":77},"claude-sonnet-5-5":{"draws":19,"losses":70,"wins":55},"cohere/north-mini-code":{"draws":8,"losses":6,"wins":40},"deepseek/deepseek-v4-flash":{"draws":40,"losses":21,"wins":155},"deepseek/deepseek-v4-pro":{"draws":25,"losses":33,"wins":74},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":34,"wins":70},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":45,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":71,"wins":47},"elorian/glimpse":{"draws":13,"losses":30,"wins":35},"fireworks/ember-1":{"draws":32,"losses":48,"wins":64},"gemini-3.1-pro-preview":{"draws":27,"losses":35,"wins":82},"gemini-4-argon":{"draws":15,"losses":108,"wins":21},"google/gemini-3.1-flash-lite":{"draws":20,"losses":2,"wins":74},"google/gemini-3.5-flash":{"draws":31,"losses":44,"wins":105},"google/gemini-3.5-flash-lite":{"draws":44,"losses":21,"wins":187},"google/gemini-3.6-flash":{"draws":54,"losses":86,"wins":136},"google/gemini-3.8-flash":{"draws":20,"losses":38,"wins":38},"google/gemma-4-31b-it":{"draws":23,"losses":9,"wins":52},"gpt-4.1":{"draws":14,"losses":8,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":23,"losses":31,"wins":72},"gpt-5.4":{"draws":24,"losses":52,"wins":62},"gpt-5.4-mini":{"draws":21,"losses":12,"wins":63},"gpt-5.4-nano":{"draws":24,"losses":23,"wins":97},"gpt-5.5":{"draws":41,"losses":45,"wins":46},"gpt-5.6-luna":{"draws":31,"losses":26,"wins":87},"gpt-5.6-sol":{"draws":19,"losses":74,"wins":51},"gpt-5.6-terra":{"draws":35,"losses":39,"wins":64},"gpt-6-astra":{"draws":13,"losses":121,"wins":10},"gpt-6-luna":{"draws":40,"losses":34,"wins":70},"gpt-6-sol":{"draws":21,"losses":90,"wins":33},"gpt-6.1-sol":{"draws":16,"losses":110,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":31,"losses":4,"wins":67},"inception/mercury-3":{"draws":24,"losses":23,"wins":49},"inclusionai/ling-3.0-flash":{"draws":25,"losses":2,"wins":75},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":25,"losses":19,"wins":112},"meta/muse-glimmer-30b":{"draws":29,"losses":15,"wins":82},"meta/muse-spark-1.2":{"draws":24,"losses":57,"wins":57},"meta/muse-spark-1.3":{"draws":33,"losses":52,"wins":59},"meta/muse-spark-open":{"draws":23,"losses":54,"wins":61},"meta/muse-wonder":{"draws":36,"losses":67,"wins":41},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":57},"minimax/minimax-m3.1-flash":{"draws":26,"losses":25,"wins":75},"mistralai/mistral-large-4-0":{"draws":29,"losses":25,"wins":36},"mistralai/mistral-medium-3-5":{"draws":17,"losses":6,"wins":61},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":17,"wins":15},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":28},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":9,"wins":84},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":38},"o3":{"draws":20,"losses":46,"wins":132},"openai/gpt-oss-120b":{"draws":26,"losses":8,"wins":92},"poolside/laguna-s-2.1":{"draws":22,"losses":17,"wins":99},"qwen/qwen3.7-max":{"draws":24,"losses":20,"wins":40},"qwen/qwen3.7-plus":{"draws":15,"losses":7,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":46,"wins":68},"qwen/qwen3.8-27b":{"draws":16,"losses":25,"wins":61},"qwen/qwen3.8-flash":{"draws":17,"losses":29,"wins":50},"qwen/qwen3.8-max":{"draws":32,"losses":51,"wins":61},"qwen/qwen3.8-max-0902":{"draws":37,"losses":48,"wins":59},"recursive/flint-v1.0":{"draws":7,"losses":2,"wins":33},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":35,"wins":71},"stealth/ox-alpha":{"draws":93,"losses":153,"wins":228},"stealth/space-bunny-alpha":{"draws":23,"losses":19,"wins":72},"stepfun/step-3.7-flash":{"draws":16,"losses":9,"wins":77},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy3-preview":{"draws":31,"losses":8,"wins":39},"tencent/hy4-preview":{"draws":29,"losses":53,"wins":56},"thinkingmachines/inkling":{"draws":48,"losses":20,"wins":124},"thinkingmachines/inkling-small":{"draws":35,"losses":19,"wins":90},"unbiased/pareto-26.10":{"draws":4,"losses":39,"wins":5},"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":24,"losses":67,"wins":53},"x-ai/grok-4.6":{"draws":40,"losses":51,"wins":53},"x-ai/grok-4.7":{"draws":11,"losses":90,"wins":25},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":32},"xiaomi/mimo-v2.5":{"draws":57,"losses":20,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":13,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":29,"wins":42},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":47,"wins":29},"z-ai/glm-5.2":{"draws":68,"losses":59,"wins":161},"z-ai/glm-5.3":{"draws":28,"losses":72,"wins":38},"z-ai/glm-5.3-flash":{"draws":18,"losses":54,"wins":72},"z-ai/glm-5.3-flashx":{"draws":27,"losses":51,"wins":66}},"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":22,"losses":51,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":61,"wins":7},"elorian/glimpse":{"draws":12,"losses":23,"wins":9},"fireworks/ember-1":{"draws":31,"losses":41,"wins":12},"gemini-3.1-pro-preview":{"draws":30,"losses":39,"wins":15},"gemini-4-argon":{"draws":3,"losses":80,"wins":1},"google/gemini-3.1-flash-lite":{"draws":19,"losses":15,"wins":26},"google/gemini-3.5-flash":{"draws":32,"losses":52,"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},"inception/mercury-3":{"draws":19,"losses":29,"wins":8},"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":24,"losses":39,"wins":17},"meta/muse-spark-1.3":{"draws":23,"losses":53,"wins":8},"meta/muse-spark-open":{"draws":20,"losses":54,"wins":6},"meta/muse-wonder":{"draws":17,"losses":60,"wins":7},"minimax/minimax-m3":{"draws":19,"losses":16,"wins":11},"minimax/minimax-m3.1-flash":{"draws":20,"losses":35,"wins":17},"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},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":73,"wins":2},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":11,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":18,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":6},"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},"recursive/flint-v1.0":{"draws":7,"losses":7,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":47,"wins":12},"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":{"draws":2,"losses":26,"wins":0},"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":18,"losses":56,"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":60,"losses":41,"wins":33},"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":14,"losses":11,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":24,"wins":8},"claude-opus-4-5":{"draws":26,"losses":35,"wins":17},"claude-opus-4-8":{"draws":10,"losses":27,"wins":7},"claude-opus-5":{"draws":11,"losses":67,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":19,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":37},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":12,"losses":31,"wins":17},"google/gemini-3.5-flash-lite":{"draws":25,"losses":28,"wins":31},"google/gemini-3.6-flash":{"draws":25,"losses":48,"wins":19},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":15,"wins":16},"gpt-5.4":{"draws":11,"losses":24,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":18,"wins":21},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":13,"losses":14,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":14,"wins":14},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":9,"losses":20,"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":13,"losses":8,"wins":13},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":28},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":22,"wins":8},"meta/muse-spark-1.3":{"draws":16,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":7,"losses":28,"wins":11},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":8,"losses":17,"wins":17},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":43,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":7},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":39,"losses":81,"wins":38},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":11,"losses":28,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":16,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":17,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":40,"wins":23},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"z-ai/glm-5.3-flashx":{"draws":8,"losses":30,"wins":10}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"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},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"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-spark-open":{"draws":9,"losses":6,"wins":1},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"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},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":0},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":0},"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":{"draws":0,"losses":6,"wins":0},"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":32,"losses":41,"wins":43},"claude-fable-5":{"draws":20,"losses":85,"wins":21},"claude-fable-5-1":{"draws":4,"losses":137,"wins":1},"claude-haiku-5-5":{"draws":31,"losses":63,"wins":26},"claude-opus-4-5":{"draws":62,"losses":75,"wins":67},"claude-opus-4-8":{"draws":27,"losses":56,"wins":31},"claude-opus-5":{"draws":26,"losses":176,"wins":18},"claude-opus-5-5":{"draws":8,"losses":128,"wins":2},"claude-sonnet-5":{"draws":35,"losses":53,"wins":38},"claude-sonnet-5-5":{"draws":26,"losses":74,"wins":26},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":34},"deepseek/deepseek-v4-flash":{"draws":51,"losses":44,"wins":95},"deepseek/deepseek-v4-pro":{"draws":28,"losses":52,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":46,"wins":46},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":60,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":73,"wins":28},"elorian/glimpse":{"draws":14,"losses":34,"wins":22},"fireworks/ember-1":{"draws":30,"losses":61,"wins":35},"gemini-3.1-pro-preview":{"draws":36,"losses":54,"wins":36},"gemini-4-argon":{"draws":4,"losses":113,"wins":9},"google/gemini-3.1-flash-lite":{"draws":19,"losses":8,"wins":57},"google/gemini-3.5-flash":{"draws":34,"losses":71,"wins":53},"google/gemini-3.5-flash-lite":{"draws":54,"losses":62,"wins":104},"google/gemini-3.6-flash":{"draws":49,"losses":115,"wins":78},"google/gemini-3.8-flash":{"draws":23,"losses":72,"wins":31},"google/gemma-4-31b-it":{"draws":31,"losses":9,"wins":32},"gpt-4.1":{"draws":11,"losses":16,"wins":15},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":4},"gpt-5":{"draws":16,"losses":28,"wins":28},"gpt-5.4":{"draws":17,"losses":68,"wins":37},"gpt-5.4-mini":{"draws":23,"losses":28,"wins":33},"gpt-5.4-nano":{"draws":16,"losses":44,"wins":68},"gpt-5.5":{"draws":39,"losses":52,"wins":27},"gpt-5.6-luna":{"draws":36,"losses":36,"wins":54},"gpt-5.6-sol":{"draws":17,"losses":92,"wins":17},"gpt-5.6-terra":{"draws":27,"losses":54,"wins":39},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":38,"losses":47,"wins":41},"gpt-6-sol":{"draws":13,"losses":97,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":116,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":32,"losses":9,"wins":43},"inception/mercury-3":{"draws":17,"losses":40,"wins":27},"inclusionai/ling-3.0-flash":{"draws":29,"losses":20,"wins":39},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":32,"wins":74},"meta/muse-glimmer-30b":{"draws":34,"losses":26,"wins":54},"meta/muse-spark-1.2":{"draws":26,"losses":65,"wins":31},"meta/muse-spark-1.3":{"draws":25,"losses":73,"wins":28},"meta/muse-spark-open":{"draws":27,"losses":71,"wins":24},"meta/muse-wonder":{"draws":23,"losses":80,"wins":23},"minimax/minimax-m3":{"draws":15,"losses":16,"wins":39},"minimax/minimax-m3.1-flash":{"draws":25,"losses":34,"wins":51},"mistralai/mistral-large-4-0":{"draws":30,"losses":34,"wins":16},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":28,"losses":50,"wins":44},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":103,"wins":14},"nex-agi/nex-n2-pro":{"draws":10,"losses":22,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":19,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":22,"wins":23},"o3":{"draws":23,"losses":68,"wins":89},"openai/gpt-oss-120b":{"draws":33,"losses":22,"wins":57},"poolside/laguna-s-2.1":{"draws":32,"losses":39,"wins":55},"qwen/qwen3.7-max":{"draws":25,"losses":20,"wins":29},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":55,"wins":35},"qwen/qwen3.8-27b":{"draws":17,"losses":41,"wins":30},"qwen/qwen3.8-flash":{"draws":16,"losses":36,"wins":32},"qwen/qwen3.8-max":{"draws":34,"losses":64,"wins":28},"qwen/qwen3.8-max-0902":{"draws":32,"losses":62,"wins":32},"recursive/flint-v1.0":{"draws":5,"losses":10,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":54,"wins":39},"stealth/ox-alpha":{"draws":89,"losses":202,"wins":133},"stealth/space-bunny-alpha":{"draws":20,"losses":39,"wins":41},"stepfun/step-3.7-flash":{"draws":21,"losses":18,"wins":53},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":27,"wins":21},"tencent/hy4-preview":{"draws":32,"losses":53,"wins":37},"thinkingmachines/inkling":{"draws":38,"losses":39,"wins":95},"thinkingmachines/inkling-small":{"draws":40,"losses":23,"wins":63},"unbiased/pareto-26.10":{"draws":1,"losses":41,"wins":0},"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":25,"losses":67,"wins":34},"x-ai/grok-4.6":{"draws":34,"losses":72,"wins":20},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":18},"x-ai/grok-build-0.1":{"draws":13,"losses":8,"wins":21},"xiaomi/mimo-v2.5":{"draws":53,"losses":42,"wins":95},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":23,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":44,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":51,"wins":23},"z-ai/glm-5.2":{"draws":73,"losses":77,"wins":102},"z-ai/glm-5.3":{"draws":16,"losses":84,"wins":20},"z-ai/glm-5.3-flash":{"draws":18,"losses":73,"wins":35},"z-ai/glm-5.3-flashx":{"draws":27,"losses":64,"wins":35}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":29,"wins":70},"claude-fable-5":{"draws":31,"losses":67,"wins":40},"claude-fable-5-1":{"draws":9,"losses":132,"wins":15},"claude-haiku-5-5":{"draws":31,"losses":50,"wins":51},"claude-opus-4-5":{"draws":63,"losses":50,"wins":111},"claude-opus-4-8":{"draws":30,"losses":40,"wins":56},"claude-opus-5":{"draws":29,"losses":170,"wins":35},"claude-opus-5-5":{"draws":9,"losses":129,"wins":12},"claude-sonnet-5":{"draws":35,"losses":30,"wins":73},"claude-sonnet-5-5":{"draws":34,"losses":62,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":35},"deepseek/deepseek-v4-flash":{"draws":53,"losses":30,"wins":123},"deepseek/deepseek-v4-pro":{"draws":27,"losses":38,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":37,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":46,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":63,"wins":49},"elorian/glimpse":{"draws":18,"losses":26,"wins":32},"fireworks/ember-1":{"draws":36,"losses":39,"wins":63},"gemini-3.1-pro-preview":{"draws":31,"losses":39,"wins":68},"gemini-4-argon":{"draws":13,"losses":103,"wins":22},"google/gemini-3.1-flash-lite":{"draws":18,"losses":8,"wins":68},"google/gemini-3.5-flash":{"draws":22,"losses":53,"wins":99},"google/gemini-3.5-flash-lite":{"draws":55,"losses":44,"wins":145},"google/gemini-3.6-flash":{"draws":55,"losses":101,"wins":110},"google/gemini-3.8-flash":{"draws":24,"losses":62,"wins":52},"google/gemma-4-31b-it":{"draws":28,"losses":9,"wins":43},"gpt-4.1":{"draws":11,"losses":11,"wins":24},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":6},"gpt-5":{"draws":17,"losses":37,"wins":68},"gpt-5.4":{"draws":20,"losses":34,"wins":34},"gpt-5.4-mini":{"draws":28,"losses":6,"wins":58},"gpt-5.4-nano":{"draws":16,"losses":32,"wins":90},"gpt-5.5":{"draws":33,"losses":46,"wins":49},"gpt-5.6-luna":{"draws":45,"losses":22,"wins":71},"gpt-5.6-sol":{"draws":22,"losses":69,"wins":47},"gpt-5.6-terra":{"draws":32,"losses":37,"wins":63},"gpt-6-astra":{"draws":6,"losses":114,"wins":18},"gpt-6-luna":{"draws":41,"losses":37,"wins":60},"gpt-6-sol":{"draws":13,"losses":103,"wins":22},"gpt-6.1-sol":{"draws":9,"losses":110,"wins":19},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":39,"losses":6,"wins":51},"inception/mercury-3":{"draws":16,"losses":30,"wins":44},"inclusionai/ling-3.0-flash":{"draws":24,"losses":17,"wins":57},"inclusionai/ling-3.1-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":32,"losses":25,"wins":95},"meta/muse-glimmer-30b":{"draws":30,"losses":18,"wins":74},"meta/muse-spark-1.2":{"draws":22,"losses":50,"wins":60},"meta/muse-spark-1.3":{"draws":30,"losses":54,"wins":54},"meta/muse-spark-open":{"draws":27,"losses":55,"wins":52},"meta/muse-wonder":{"draws":29,"losses":66,"wins":43},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":45},"minimax/minimax-m3.1-flash":{"draws":24,"losses":25,"wins":73},"mistralai/mistral-large-4-0":{"draws":30,"losses":16,"wins":40},"mistralai/mistral-medium-3-5":{"draws":22,"losses":13,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":8,"wins":21},"moonshotai/kimi-k3":{"draws":25,"losses":38,"wins":69},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":99,"wins":27},"nex-agi/nex-n2-pro":{"draws":16,"losses":16,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":12,"wins":72},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":14,"wins":34},"o3":{"draws":19,"losses":49,"wins":128},"openai/gpt-oss-120b":{"draws":31,"losses":20,"wins":69},"poolside/laguna-s-2.1":{"draws":31,"losses":21,"wins":80},"qwen/qwen3.7-max":{"draws":16,"losses":19,"wins":45},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":50},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":52,"wins":58},"qwen/qwen3.8-27b":{"draws":20,"losses":20,"wins":58},"qwen/qwen3.8-flash":{"draws":18,"losses":29,"wins":45},"qwen/qwen3.8-max":{"draws":32,"losses":52,"wins":54},"qwen/qwen3.8-max-0902":{"draws":29,"losses":47,"wins":62},"recursive/flint-v1.0":{"draws":6,"losses":4,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":37,"wins":58},"stealth/ox-alpha":{"draws":113,"losses":161,"wins":184},"stealth/space-bunny-alpha":{"draws":30,"losses":19,"wins":61},"stepfun/step-3.7-flash":{"draws":18,"losses":16,"wins":66},"stepfun/step-5-preview":{"draws":5,"losses":6,"wins":1},"tencent/hy3-preview":{"draws":26,"losses":14,"wins":34},"tencent/hy4-preview":{"draws":27,"losses":47,"wins":60},"thinkingmachines/inkling":{"draws":49,"losses":29,"wins":108},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":84},"unbiased/pareto-26.10":{"draws":4,"losses":38,"wins":4},"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":33,"losses":46,"wins":59},"x-ai/grok-4.6":{"draws":37,"losses":55,"wins":46},"x-ai/grok-4.7":{"draws":12,"losses":81,"wins":27},"x-ai/grok-build-0.1":{"draws":11,"losses":7,"wins":28},"xiaomi/mimo-v2.5":{"draws":54,"losses":22,"wins":136},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":25,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":38},"z-ai/glm-5.2":{"draws":76,"losses":60,"wins":140},"z-ai/glm-5.3":{"draws":25,"losses":69,"wins":38},"z-ai/glm-5.3-flash":{"draws":16,"losses":59,"wins":63},"z-ai/glm-5.3-flashx":{"draws":29,"losses":55,"wins":54}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":33,"wins":26},"claude-fable-5":{"draws":19,"losses":66,"wins":11},"claude-fable-5-1":{"draws":6,"losses":102,"wins":0},"claude-haiku-5-5":{"draws":27,"losses":53,"wins":12},"claude-opus-4-5":{"draws":54,"losses":70,"wins":32},"claude-opus-4-8":{"draws":20,"losses":44,"wins":24},"claude-opus-5":{"draws":30,"losses":121,"wins":13},"claude-opus-5-5":{"draws":5,"losses":96,"wins":3},"claude-sonnet-5":{"draws":38,"losses":30,"wins":28},"claude-sonnet-5-5":{"draws":17,"losses":62,"wins":17},"cohere/north-mini-code":{"draws":9,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":51,"losses":42,"wins":51},"deepseek/deepseek-v4-pro":{"draws":28,"losses":34,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":40,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":40,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":23,"losses":64,"wins":9},"elorian/glimpse":{"draws":15,"losses":24,"wins":13},"fireworks/ember-1":{"draws":36,"losses":46,"wins":14},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":25},"gemini-4-argon":{"draws":13,"losses":83,"wins":0},"google/gemini-3.1-flash-lite":{"draws":16,"losses":8,"wins":40},"google/gemini-3.5-flash":{"draws":32,"losses":56,"wins":32},"google/gemini-3.5-flash-lite":{"draws":51,"losses":54,"wins":63},"google/gemini-3.6-flash":{"draws":50,"losses":101,"wins":33},"google/gemini-3.8-flash":{"draws":21,"losses":63,"wins":12},"google/gemma-4-31b-it":{"draws":22,"losses":10,"wins":24},"gpt-4.1":{"draws":12,"losses":6,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":3},"gpt-5":{"draws":23,"losses":33,"wins":28},"gpt-5.4":{"draws":28,"losses":58,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":21,"losses":46,"wins":29},"gpt-5.5":{"draws":36,"losses":35,"wins":17},"gpt-5.6-luna":{"draws":36,"losses":35,"wins":25},"gpt-5.6-sol":{"draws":19,"losses":65,"wins":12},"gpt-5.6-terra":{"draws":37,"losses":36,"wins":19},"gpt-6-astra":{"draws":6,"losses":90,"wins":0},"gpt-6-luna":{"draws":42,"losses":39,"wins":15},"gpt-6-sol":{"draws":13,"losses":73,"wins":10},"gpt-6.1-sol":{"draws":3,"losses":88,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":16,"wins":24},"inception/mercury-3":{"draws":21,"losses":34,"wins":9},"inclusionai/ling-3.0-flash":{"draws":26,"losses":16,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":31,"wins":40},"meta/muse-glimmer-30b":{"draws":37,"losses":15,"wins":32},"meta/muse-spark-1.2":{"draws":26,"losses":48,"wins":18},"meta/muse-spark-1.3":{"draws":19,"losses":66,"wins":11},"meta/muse-spark-open":{"draws":23,"losses":55,"wins":14},"meta/muse-wonder":{"draws":24,"losses":62,"wins":10},"minimax/minimax-m3":{"draws":15,"losses":19,"wins":18},"minimax/minimax-m3.1-flash":{"draws":32,"losses":34,"wins":18},"mistralai/mistral-large-4-0":{"draws":29,"losses":21,"wins":10},"mistralai/mistral-medium-3-5":{"draws":21,"losses":10,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":29,"losses":42,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":81,"wins":6},"nex-agi/nex-n2-pro":{"draws":15,"losses":17,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":29,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":24,"wins":6},"o3":{"draws":23,"losses":74,"wins":35},"openai/gpt-oss-120b":{"draws":31,"losses":21,"wins":32},"poolside/laguna-s-2.1":{"draws":28,"losses":30,"wins":34},"qwen/qwen3.7-max":{"draws":11,"losses":29,"wins":16},"qwen/qwen3.7-plus":{"draws":12,"losses":21,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":52,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":36,"wins":17},"qwen/qwen3.8-flash":{"draws":18,"losses":30,"wins":16},"qwen/qwen3.8-max":{"draws":35,"losses":41,"wins":20},"qwen/qwen3.8-max-0902":{"draws":38,"losses":43,"wins":15},"recursive/flint-v1.0":{"draws":8,"losses":8,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":42,"wins":18},"stealth/ox-alpha":{"draws":84,"losses":171,"wins":61},"stealth/space-bunny-alpha":{"draws":23,"losses":36,"wins":17},"stepfun/step-3.7-flash":{"draws":21,"losses":23,"wins":24},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":21,"losses":17,"wins":14},"tencent/hy4-preview":{"draws":27,"losses":49,"wins":16},"thinkingmachines/inkling":{"draws":45,"losses":36,"wins":47},"thinkingmachines/inkling-small":{"draws":37,"losses":27,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":30,"wins":0},"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":29,"losses":52,"wins":15},"x-ai/grok-4.6":{"draws":31,"losses":53,"wins":12},"x-ai/grok-4.7":{"draws":13,"losses":66,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":9,"wins":14},"xiaomi/mimo-v2.5":{"draws":50,"losses":41,"wins":57},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":22,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":36,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":40,"wins":9},"z-ai/glm-5.2":{"draws":71,"losses":82,"wins":39},"z-ai/glm-5.3":{"draws":20,"losses":64,"wins":8},"z-ai/glm-5.3-flash":{"draws":21,"losses":54,"wins":21},"z-ai/glm-5.3-flashx":{"draws":24,"losses":59,"wins":13}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":58,"wins":48},"claude-fable-5":{"draws":16,"losses":113,"wins":15},"claude-fable-5-1":{"draws":2,"losses":152,"wins":0},"claude-haiku-5-5":{"draws":29,"losses":74,"wins":39},"claude-opus-4-5":{"draws":61,"losses":114,"wins":63},"claude-opus-4-8":{"draws":25,"losses":84,"wins":31},"claude-opus-5":{"draws":22,"losses":199,"wins":15},"claude-opus-5-5":{"draws":7,"losses":152,"wins":1},"claude-sonnet-5":{"draws":33,"losses":70,"wins":41},"claude-sonnet-5-5":{"draws":20,"losses":105,"wins":19},"cohere/north-mini-code":{"draws":7,"losses":13,"wins":36},"deepseek/deepseek-v4-flash":{"draws":48,"losses":82,"wins":96},"deepseek/deepseek-v4-pro":{"draws":15,"losses":67,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":65,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":72,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":96,"wins":27},"elorian/glimpse":{"draws":13,"losses":39,"wins":22},"fireworks/ember-1":{"draws":32,"losses":79,"wins":33},"gemini-3.1-pro-preview":{"draws":31,"losses":73,"wins":40},"gemini-4-argon":{"draws":2,"losses":134,"wins":8},"google/gemini-3.1-flash-lite":{"draws":21,"losses":22,"wins":65},"google/gemini-3.5-flash":{"draws":23,"losses":111,"wins":50},"google/gemini-3.5-flash-lite":{"draws":46,"losses":108,"wins":98},"google/gemini-3.6-flash":{"draws":44,"losses":167,"wins":63},"google/gemini-3.8-flash":{"draws":24,"losses":97,"wins":23},"google/gemma-4-31b-it":{"draws":26,"losses":17,"wins":43},"gpt-4.1":{"draws":9,"losses":21,"wins":18},"gpt-4.1-nano":{"draws":8,"losses":1,"wins":7},"gpt-5":{"draws":16,"losses":68,"wins":44},"gpt-5.4":{"draws":16,"losses":90,"wins":32},"gpt-5.4-mini":{"draws":21,"losses":29,"wins":46},"gpt-5.4-nano":{"draws":16,"losses":52,"wins":52},"gpt-5.5":{"draws":27,"losses":71,"wins":32},"gpt-5.6-luna":{"draws":32,"losses":61,"wins":51},"gpt-5.6-sol":{"draws":12,"losses":114,"wins":18},"gpt-5.6-terra":{"draws":23,"losses":75,"wins":38},"gpt-6-astra":{"draws":3,"losses":139,"wins":2},"gpt-6-luna":{"draws":29,"losses":72,"wins":43},"gpt-6-sol":{"draws":20,"losses":112,"wins":12},"gpt-6.1-sol":{"draws":5,"losses":134,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":30,"losses":15,"wins":57},"inception/mercury-3":{"draws":26,"losses":46,"wins":28},"inclusionai/ling-3.0-flash":{"draws":24,"losses":30,"wins":50},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":24,"losses":51,"wins":85},"meta/muse-glimmer-30b":{"draws":25,"losses":44,"wins":53},"meta/muse-spark-1.2":{"draws":23,"losses":69,"wins":44},"meta/muse-spark-1.3":{"draws":22,"losses":93,"wins":29},"meta/muse-spark-open":{"draws":20,"losses":94,"wins":24},"meta/muse-wonder":{"draws":14,"losses":108,"wins":22},"minimax/minimax-m3":{"draws":15,"losses":29,"wins":40},"minimax/minimax-m3.1-flash":{"draws":16,"losses":57,"wins":49},"mistralai/mistral-large-4-0":{"draws":17,"losses":47,"wins":24},"mistralai/mistral-medium-3-5":{"draws":15,"losses":19,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":18,"wins":14},"moonshotai/kimi-k3":{"draws":32,"losses":70,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":128,"wins":5},"nex-agi/nex-n2-pro":{"draws":10,"losses":27,"wins":35},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":14,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":50,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":29,"wins":24},"o3":{"draws":16,"losses":107,"wins":103},"openai/gpt-oss-120b":{"draws":35,"losses":47,"wins":44},"poolside/laguna-s-2.1":{"draws":26,"losses":59,"wins":59},"qwen/qwen3.7-max":{"draws":20,"losses":39,"wins":33},"qwen/qwen3.7-plus":{"draws":15,"losses":34,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":84,"wins":26},"qwen/qwen3.8-27b":{"draws":19,"losses":51,"wins":34},"qwen/qwen3.8-flash":{"draws":17,"losses":50,"wins":29},"qwen/qwen3.8-max":{"draws":32,"losses":74,"wins":38},"qwen/qwen3.8-max-0902":{"draws":35,"losses":74,"wins":35},"recursive/flint-v1.0":{"draws":10,"losses":17,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":69,"wins":34},"stealth/ox-alpha":{"draws":69,"losses":232,"wins":123},"stealth/space-bunny-alpha":{"draws":23,"losses":50,"wins":39},"stepfun/step-3.7-flash":{"draws":16,"losses":34,"wins":60},"stepfun/step-5-preview":{"draws":3,"losses":9,"wins":4},"tencent/hy3-preview":{"draws":20,"losses":37,"wins":23},"tencent/hy4-preview":{"draws":17,"losses":92,"wins":29},"thinkingmachines/inkling":{"draws":39,"losses":70,"wins":79},"thinkingmachines/inkling-small":{"draws":40,"losses":41,"wins":63},"unbiased/pareto-26.10":{"draws":3,"losses":43,"wins":2},"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":31,"losses":84,"wins":29},"x-ai/grok-4.6":{"draws":21,"losses":97,"wins":26},"x-ai/grok-4.7":{"draws":14,"losses":110,"wins":8},"x-ai/grok-build-0.1":{"draws":7,"losses":15,"wins":26},"xiaomi/mimo-v2.5":{"draws":51,"losses":75,"wins":110},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":38,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":21,"losses":52,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":66,"wins":17},"z-ai/glm-5.2":{"draws":59,"losses":130,"wins":99},"z-ai/glm-5.3":{"draws":19,"losses":96,"wins":21},"z-ai/glm-5.3-flash":{"draws":20,"losses":84,"wins":40},"z-ai/glm-5.3-flashx":{"draws":28,"losses":80,"wins":36}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":24,"wins":57},"claude-fable-5":{"draws":30,"losses":63,"wins":39},"claude-fable-5-1":{"draws":6,"losses":127,"wins":17},"claude-haiku-5-5":{"draws":46,"losses":45,"wins":35},"claude-opus-4-5":{"draws":84,"losses":49,"wins":81},"claude-opus-4-8":{"draws":34,"losses":36,"wins":50},"claude-opus-5":{"draws":30,"losses":155,"wins":47},"claude-opus-5-5":{"draws":13,"losses":116,"wins":15},"claude-sonnet-5":{"draws":46,"losses":29,"wins":57},"claude-sonnet-5-5":{"draws":29,"losses":61,"wins":42},"cohere/north-mini-code":{"draws":12,"losses":4,"wins":36},"deepseek/deepseek-v4-flash":{"draws":58,"losses":26,"wins":112},"deepseek/deepseek-v4-pro":{"draws":36,"losses":27,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":38,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":48,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":39,"losses":50,"wins":43},"elorian/glimpse":{"draws":17,"losses":24,"wins":33},"fireworks/ember-1":{"draws":38,"losses":44,"wins":50},"gemini-3.1-pro-preview":{"draws":31,"losses":36,"wins":65},"gemini-4-argon":{"draws":9,"losses":100,"wins":23},"google/gemini-3.1-flash-lite":{"draws":20,"losses":4,"wins":64},"google/gemini-3.5-flash":{"draws":41,"losses":49,"wins":76},"google/gemini-3.5-flash-lite":{"draws":80,"losses":38,"wins":114},"google/gemini-3.6-flash":{"draws":67,"losses":87,"wins":100},"google/gemini-3.8-flash":{"draws":41,"losses":46,"wins":45},"google/gemma-4-31b-it":{"draws":30,"losses":6,"wins":40},"gpt-4.1":{"draws":10,"losses":9,"wins":25},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":4},"gpt-5":{"draws":39,"losses":27,"wins":52},"gpt-5.4":{"draws":33,"losses":49,"wins":46},"gpt-5.4-mini":{"draws":36,"losses":17,"wins":35},"gpt-5.4-nano":{"draws":27,"losses":32,"wins":71},"gpt-5.5":{"draws":32,"losses":24,"wins":24},"gpt-5.6-luna":{"draws":44,"losses":25,"wins":63},"gpt-5.6-sol":{"draws":24,"losses":64,"wins":44},"gpt-5.6-terra":{"draws":42,"losses":32,"wins":52},"gpt-6-astra":{"draws":5,"losses":119,"wins":8},"gpt-6-luna":{"draws":45,"losses":30,"wins":57},"gpt-6-sol":{"draws":19,"losses":83,"wins":30},"gpt-6.1-sol":{"draws":7,"losses":103,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":36,"losses":9,"wins":45},"inception/mercury-3":{"draws":26,"losses":21,"wins":39},"inclusionai/ling-3.0-flash":{"draws":38,"losses":9,"wins":45},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":40,"losses":27,"wins":77},"meta/muse-glimmer-30b":{"draws":42,"losses":18,"wins":60},"meta/muse-spark-1.2":{"draws":25,"losses":44,"wins":59},"meta/muse-spark-1.3":{"draws":32,"losses":52,"wins":48},"meta/muse-spark-open":{"draws":24,"losses":55,"wins":49},"meta/muse-wonder":{"draws":37,"losses":59,"wins":36},"minimax/minimax-m3":{"draws":22,"losses":10,"wins":40},"minimax/minimax-m3.1-flash":{"draws":38,"losses":28,"wins":50},"mistralai/mistral-large-4-0":{"draws":29,"losses":22,"wins":33},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":44},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":13,"wins":12},"moonshotai/kimi-k3":{"draws":34,"losses":46,"wins":48},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":94,"wins":28},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":12,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":23,"losses":10,"wins":29},"o3":{"draws":35,"losses":44,"wins":105},"openai/gpt-oss-120b":{"draws":42,"losses":16,"wins":58},"poolside/laguna-s-2.1":{"draws":43,"losses":26,"wins":59},"qwen/qwen3.7-max":{"draws":24,"losses":14,"wins":38},"qwen/qwen3.7-plus":{"draws":22,"losses":6,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":46,"wins":47},"qwen/qwen3.8-27b":{"draws":26,"losses":28,"wins":38},"qwen/qwen3.8-flash":{"draws":29,"losses":20,"wins":39},"qwen/qwen3.8-max":{"draws":40,"losses":43,"wins":49},"qwen/qwen3.8-max-0902":{"draws":43,"losses":44,"wins":45},"recursive/flint-v1.0":{"draws":11,"losses":2,"wins":25},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":32,"wins":60},"stealth/ox-alpha":{"draws":110,"losses":172,"wins":160},"stealth/space-bunny-alpha":{"draws":38,"losses":21,"wins":47},"stepfun/step-3.7-flash":{"draws":26,"losses":14,"wins":54},"stepfun/step-5-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":33,"losses":9,"wins":30},"tencent/hy4-preview":{"draws":38,"losses":48,"wins":42},"thinkingmachines/inkling":{"draws":55,"losses":27,"wins":98},"thinkingmachines/inkling-small":{"draws":42,"losses":21,"wins":69},"unbiased/pareto-26.10":{"draws":2,"losses":37,"wins":5},"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":35,"losses":55,"wins":42},"x-ai/grok-4.6":{"draws":37,"losses":56,"wins":39},"x-ai/grok-4.7":{"draws":10,"losses":69,"wins":37},"x-ai/grok-build-0.1":{"draws":19,"losses":8,"wins":17},"xiaomi/mimo-v2.5":{"draws":79,"losses":23,"wins":100},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":15,"wins":39},"xiaomi/mimo-v2.6-flash":{"draws":20,"losses":25,"wins":37},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":37,"wins":30},"z-ai/glm-5.2":{"draws":91,"losses":50,"wins":123},"z-ai/glm-5.3":{"draws":27,"losses":76,"wins":23},"z-ai/glm-5.3-flash":{"draws":25,"losses":57,"wins":50},"z-ai/glm-5.3-flashx":{"draws":34,"losses":51,"wins":47}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":39,"losses":47,"wins":46},"claude-fable-5":{"draws":27,"losses":99,"wins":18},"claude-fable-5-1":{"draws":10,"losses":146,"wins":6},"claude-haiku-5-5":{"draws":40,"losses":74,"wins":24},"claude-opus-4-5":{"draws":80,"losses":95,"wins":59},"claude-opus-4-8":{"draws":34,"losses":65,"wins":33},"claude-opus-5":{"draws":28,"losses":194,"wins":24},"claude-opus-5-5":{"draws":16,"losses":136,"wins":4},"claude-sonnet-5":{"draws":36,"losses":65,"wins":43},"claude-sonnet-5-5":{"draws":33,"losses":84,"wins":27},"cohere/north-mini-code":{"draws":16,"losses":10,"wins":28},"deepseek/deepseek-v4-flash":{"draws":72,"losses":62,"wins":82},"deepseek/deepseek-v4-pro":{"draws":43,"losses":53,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":52,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":41,"losses":68,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":90,"wins":25},"elorian/glimpse":{"draws":22,"losses":36,"wins":20},"fireworks/ember-1":{"draws":44,"losses":56,"wins":44},"gemini-3.1-pro-preview":{"draws":36,"losses":56,"wins":52},"gemini-4-argon":{"draws":13,"losses":123,"wins":8},"google/gemini-3.1-flash-lite":{"draws":18,"losses":21,"wins":57},"google/gemini-3.5-flash":{"draws":48,"losses":79,"wins":53},"google/gemini-3.5-flash-lite":{"draws":68,"losses":76,"wins":108},"google/gemini-3.6-flash":{"draws":72,"losses":143,"wins":61},"google/gemini-3.8-flash":{"draws":31,"losses":87,"wins":26},"google/gemma-4-31b-it":{"draws":34,"losses":20,"wins":30},"gpt-4.1":{"draws":13,"losses":21,"wins":14},"gpt-4.1-nano":{"draws":11,"losses":1,"wins":6},"gpt-5":{"draws":36,"losses":54,"wins":36},"gpt-5.4":{"draws":45,"losses":71,"wins":22},"gpt-5.4-mini":{"draws":36,"losses":25,"wins":35},"gpt-5.4-nano":{"draws":32,"losses":51,"wins":61},"gpt-5.5":{"draws":44,"losses":63,"wins":25},"gpt-5.6-luna":{"draws":30,"losses":33,"wins":33},"gpt-5.6-sol":{"draws":21,"losses":98,"wins":25},"gpt-5.6-terra":{"draws":37,"losses":56,"wins":45},"gpt-6-astra":{"draws":12,"losses":128,"wins":4},"gpt-6-luna":{"draws":44,"losses":60,"wins":40},"gpt-6-sol":{"draws":23,"losses":107,"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":41,"losses":21,"wins":40},"inception/mercury-3":{"draws":32,"losses":40,"wins":24},"inclusionai/ling-3.0-flash":{"draws":48,"losses":19,"wins":35},"inclusionai/ling-3.1-flash":{"draws":3,"losses":3,"wins":0},"meituan/longcat-2.0":{"draws":38,"losses":50,"wins":68},"meta/muse-glimmer-30b":{"draws":40,"losses":32,"wins":54},"meta/muse-spark-1.2":{"draws":39,"losses":65,"wins":34},"meta/muse-spark-1.3":{"draws":34,"losses":80,"wins":30},"meta/muse-spark-open":{"draws":34,"losses":71,"wins":33},"meta/muse-wonder":{"draws":28,"losses":91,"wins":25},"minimax/minimax-m3":{"draws":26,"losses":20,"wins":32},"minimax/minimax-m3.1-flash":{"draws":30,"losses":50,"wins":46},"mistralai/mistral-large-4-0":{"draws":32,"losses":43,"wins":15},"mistralai/mistral-medium-3-5":{"draws":30,"losses":12,"wins":42},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":18,"wins":8},"moonshotai/kimi-k3":{"draws":46,"losses":62,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":122,"wins":13},"nex-agi/nex-n2-pro":{"draws":15,"losses":17,"wins":40},"nex-agi/nex-n2.5-pro":{"draws":11,"losses":13,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":33,"wins":55},"nvidia/nemotron-3.5-super-vl":{"draws":21,"losses":28,"wins":17},"o3":{"draws":40,"losses":90,"wins":68},"openai/gpt-oss-120b":{"draws":49,"losses":29,"wins":48},"poolside/laguna-s-2.1":{"draws":47,"losses":41,"wins":50},"qwen/qwen3.7-max":{"draws":23,"losses":34,"wins":27},"qwen/qwen3.7-plus":{"draws":27,"losses":18,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":66,"wins":27},"qwen/qwen3.8-27b":{"draws":32,"losses":45,"wins":25},"qwen/qwen3.8-flash":{"draws":31,"losses":37,"wins":28},"qwen/qwen3.8-max":{"draws":43,"losses":72,"wins":29},"qwen/qwen3.8-max-0902":{"draws":43,"losses":65,"wins":36},"recursive/flint-v1.0":{"draws":9,"losses":10,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":43,"losses":55,"wins":34},"stealth/ox-alpha":{"draws":139,"losses":231,"wins":104},"stealth/space-bunny-alpha":{"draws":33,"losses":45,"wins":36},"stepfun/step-3.7-flash":{"draws":27,"losses":31,"wins":44},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":25,"losses":30,"wins":23},"tencent/hy4-preview":{"draws":40,"losses":69,"wins":29},"thinkingmachines/inkling":{"draws":58,"losses":46,"wins":88},"thinkingmachines/inkling-small":{"draws":54,"losses":37,"wins":53},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"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":36,"losses":72,"wins":36},"x-ai/grok-4.6":{"draws":32,"losses":90,"wins":22},"x-ai/grok-4.7":{"draws":13,"losses":96,"wins":17},"x-ai/grok-build-0.1":{"draws":15,"losses":11,"wins":22},"xiaomi/mimo-v2.5":{"draws":76,"losses":54,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":29,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":47,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":62,"wins":17},"z-ai/glm-5.2":{"draws":95,"losses":115,"wins":78},"z-ai/glm-5.3":{"draws":23,"losses":97,"wins":18},"z-ai/glm-5.3-flash":{"draws":37,"losses":79,"wins":28},"z-ai/glm-5.3-flashx":{"draws":31,"losses":77,"wins":36}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":12,"wins":98},"claude-fable-5":{"draws":16,"losses":64,"wins":64},"claude-fable-5-1":{"draws":13,"losses":130,"wins":19},"claude-haiku-5-5":{"draws":20,"losses":41,"wins":77},"claude-opus-4-5":{"draws":44,"losses":37,"wins":153},"claude-opus-4-8":{"draws":21,"losses":37,"wins":74},"claude-opus-5":{"draws":30,"losses":151,"wins":65},"claude-opus-5-5":{"draws":11,"losses":125,"wins":20},"claude-sonnet-5":{"draws":20,"losses":18,"wins":106},"claude-sonnet-5-5":{"draws":14,"losses":56,"wins":74},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":47},"deepseek/deepseek-v4-flash":{"draws":29,"losses":18,"wins":169},"deepseek/deepseek-v4-pro":{"draws":16,"losses":29,"wins":87},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":27,"wins":89},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":43,"wins":76},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":51,"wins":67},"elorian/glimpse":{"draws":10,"losses":22,"wins":46},"fireworks/ember-1":{"draws":22,"losses":36,"wins":86},"gemini-3.1-pro-preview":{"draws":17,"losses":33,"wins":94},"gemini-4-argon":{"draws":11,"losses":100,"wins":33},"google/gemini-3.1-flash-lite":{"draws":9,"losses":5,"wins":82},"google/gemini-3.5-flash":{"draws":20,"losses":37,"wins":123},"google/gemini-3.5-flash-lite":{"draws":34,"losses":22,"wins":196},"google/gemini-3.6-flash":{"draws":34,"losses":73,"wins":169},"google/gemini-3.8-flash":{"draws":19,"losses":51,"wins":74},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":67},"gpt-4.1":{"draws":8,"losses":5,"wins":35},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":14},"gpt-5":{"draws":17,"losses":17,"wins":92},"gpt-5.4":{"draws":22,"losses":47,"wins":69},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":65},"gpt-5.4-nano":{"draws":12,"losses":18,"wins":114},"gpt-5.5":{"draws":24,"losses":44,"wins":64},"gpt-5.6-luna":{"draws":21,"losses":25,"wins":98},"gpt-5.6-sol":{"draws":8,"losses":44,"wins":44},"gpt-5.6-terra":{"draws":25,"losses":24,"wins":89},"gpt-6-astra":{"draws":14,"losses":114,"wins":16},"gpt-6-luna":{"draws":27,"losses":24,"wins":93},"gpt-6-sol":{"draws":13,"losses":85,"wins":46},"gpt-6.1-sol":{"draws":12,"losses":106,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":0,"wins":83},"inception/mercury-3":{"draws":14,"losses":17,"wins":65},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":85},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":20,"losses":14,"wins":122},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":99},"meta/muse-spark-1.2":{"draws":18,"losses":33,"wins":87},"meta/muse-spark-1.3":{"draws":21,"losses":48,"wins":75},"meta/muse-spark-open":{"draws":22,"losses":43,"wins":73},"meta/muse-wonder":{"draws":22,"losses":65,"wins":57},"minimax/minimax-m3":{"draws":13,"losses":4,"wins":61},"minimax/minimax-m3.1-flash":{"draws":15,"losses":25,"wins":86},"mistralai/mistral-large-4-0":{"draws":19,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":25},"moonshotai/kimi-k3":{"draws":23,"losses":30,"wins":85},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":97,"wins":35},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":59},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":100},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":44},"o3":{"draws":11,"losses":31,"wins":156},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":104},"poolside/laguna-s-2.1":{"draws":19,"losses":8,"wins":111},"qwen/qwen3.7-max":{"draws":11,"losses":14,"wins":59},"qwen/qwen3.7-plus":{"draws":13,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":37,"wins":87},"qwen/qwen3.8-27b":{"draws":15,"losses":16,"wins":71},"qwen/qwen3.8-flash":{"draws":17,"losses":18,"wins":61},"qwen/qwen3.8-max":{"draws":25,"losses":31,"wins":88},"qwen/qwen3.8-max-0902":{"draws":21,"losses":33,"wins":90},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":38},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":24,"wins":87},"stealth/ox-alpha":{"draws":68,"losses":114,"wins":292},"stealth/space-bunny-alpha":{"draws":19,"losses":14,"wins":81},"stepfun/step-3.7-flash":{"draws":11,"losses":6,"wins":85},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":8,"wins":56},"tencent/hy4-preview":{"draws":19,"losses":47,"wins":72},"thinkingmachines/inkling":{"draws":28,"losses":17,"wins":147},"thinkingmachines/inkling-small":{"draws":22,"losses":13,"wins":109},"unbiased/pareto-26.10":{"draws":4,"losses":41,"wins":3},"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":18,"losses":44,"wins":82},"x-ai/grok-4.6":{"draws":28,"losses":59,"wins":57},"x-ai/grok-4.7":{"draws":16,"losses":68,"wins":42},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":34},"xiaomi/mimo-v2.5":{"draws":36,"losses":12,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":14,"wins":54},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":20,"wins":61},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":35,"wins":44},"z-ai/glm-5.2":{"draws":37,"losses":45,"wins":206},"z-ai/glm-5.3":{"draws":22,"losses":55,"wins":61},"z-ai/glm-5.3-flash":{"draws":24,"losses":47,"wins":73},"z-ai/glm-5.3-flashx":{"draws":24,"losses":41,"wins":79}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":26,"wins":69},"claude-fable-5":{"draws":31,"losses":87,"wins":20},"claude-fable-5-1":{"draws":7,"losses":143,"wins":6},"claude-haiku-5-5":{"draws":39,"losses":56,"wins":37},"claude-opus-4-5":{"draws":72,"losses":83,"wins":69},"claude-opus-4-8":{"draws":28,"losses":58,"wins":40},"claude-opus-5":{"draws":25,"losses":186,"wins":23},"claude-opus-5-5":{"draws":8,"losses":139,"wins":3},"claude-sonnet-5":{"draws":47,"losses":44,"wins":47},"claude-sonnet-5-5":{"draws":31,"losses":76,"wins":31},"cohere/north-mini-code":{"draws":11,"losses":6,"wins":33},"deepseek/deepseek-v4-flash":{"draws":55,"losses":38,"wins":115},"deepseek/deepseek-v4-pro":{"draws":38,"losses":42,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":41,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":46,"losses":56,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":33,"losses":80,"wins":25},"elorian/glimpse":{"draws":19,"losses":32,"wins":25},"fireworks/ember-1":{"draws":40,"losses":61,"wins":37},"gemini-3.1-pro-preview":{"draws":44,"losses":46,"wins":48},"gemini-4-argon":{"draws":14,"losses":116,"wins":8},"google/gemini-3.1-flash-lite":{"draws":22,"losses":5,"wins":63},"google/gemini-3.5-flash":{"draws":43,"losses":58,"wins":71},"google/gemini-3.5-flash-lite":{"draws":61,"losses":48,"wins":131},"google/gemini-3.6-flash":{"draws":67,"losses":130,"wins":67},"google/gemini-3.8-flash":{"draws":35,"losses":64,"wins":39},"google/gemma-4-31b-it":{"draws":32,"losses":9,"wins":39},"gpt-4.1":{"draws":18,"losses":14,"wins":14},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":27,"losses":39,"wins":54},"gpt-5.4":{"draws":32,"losses":63,"wins":37},"gpt-5.4-mini":{"draws":37,"losses":19,"wins":36},"gpt-5.4-nano":{"draws":23,"losses":38,"wins":75},"gpt-5.5":{"draws":42,"losses":52,"wins":32},"gpt-5.6-luna":{"draws":37,"losses":45,"wins":56},"gpt-5.6-sol":{"draws":25,"losses":89,"wins":24},"gpt-5.6-terra":{"draws":32,"losses":28,"wins":28},"gpt-6-astra":{"draws":12,"losses":123,"wins":3},"gpt-6-luna":{"draws":38,"losses":59,"wins":41},"gpt-6-sol":{"draws":23,"losses":98,"wins":17},"gpt-6.1-sol":{"draws":9,"losses":121,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":9,"wins":54},"inception/mercury-3":{"draws":29,"losses":33,"wins":32},"inclusionai/ling-3.0-flash":{"draws":32,"losses":7,"wins":63},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":39,"losses":36,"wins":73},"meta/muse-glimmer-30b":{"draws":39,"losses":18,"wins":63},"meta/muse-spark-1.2":{"draws":38,"losses":57,"wins":37},"meta/muse-spark-1.3":{"draws":32,"losses":68,"wins":38},"meta/muse-spark-open":{"draws":36,"losses":63,"wins":33},"meta/muse-wonder":{"draws":31,"losses":77,"wins":30},"minimax/minimax-m3":{"draws":16,"losses":13,"wins":45},"minimax/minimax-m3.1-flash":{"draws":32,"losses":37,"wins":51},"mistralai/mistral-large-4-0":{"draws":41,"losses":26,"wins":19},"mistralai/mistral-medium-3-5":{"draws":20,"losses":11,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":12,"wins":13},"moonshotai/kimi-k3":{"draws":37,"losses":50,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":112,"wins":17},"nex-agi/nex-n2-pro":{"draws":13,"losses":14,"wins":41},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":11,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":23,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":24,"losses":18,"wins":22},"o3":{"draws":33,"losses":67,"wins":86},"openai/gpt-oss-120b":{"draws":37,"losses":13,"wins":70},"poolside/laguna-s-2.1":{"draws":40,"losses":17,"wins":73},"qwen/qwen3.7-max":{"draws":20,"losses":17,"wins":43},"qwen/qwen3.7-plus":{"draws":26,"losses":10,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":61,"wins":33},"qwen/qwen3.8-27b":{"draws":33,"losses":31,"wins":34},"qwen/qwen3.8-flash":{"draws":27,"losses":30,"wins":35},"qwen/qwen3.8-max":{"draws":46,"losses":51,"wins":41},"qwen/qwen3.8-max-0902":{"draws":43,"losses":58,"wins":37},"recursive/flint-v1.0":{"draws":10,"losses":2,"wins":28},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":48,"wins":43},"stealth/ox-alpha":{"draws":118,"losses":208,"wins":130},"stealth/space-bunny-alpha":{"draws":35,"losses":32,"wins":41},"stepfun/step-3.7-flash":{"draws":24,"losses":21,"wins":53},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":29,"losses":16,"wins":29},"tencent/hy4-preview":{"draws":33,"losses":56,"wins":43},"thinkingmachines/inkling":{"draws":53,"losses":38,"wins":91},"thinkingmachines/inkling-small":{"draws":38,"losses":23,"wins":77},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":1},"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":39,"losses":66,"wins":33},"x-ai/grok-4.6":{"draws":43,"losses":75,"wins":20},"x-ai/grok-4.7":{"draws":11,"losses":87,"wins":22},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":26},"xiaomi/mimo-v2.5":{"draws":69,"losses":18,"wins":125},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":14,"wins":47},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":36,"wins":33},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":45,"wins":23},"z-ai/glm-5.2":{"draws":99,"losses":73,"wins":104},"z-ai/glm-5.3":{"draws":29,"losses":82,"wins":21},"z-ai/glm-5.3-flash":{"draws":30,"losses":66,"wins":42},"z-ai/glm-5.3-flashx":{"draws":32,"losses":64,"wins":42}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":120},"claude-fable-5":{"draws":11,"losses":21,"wins":112},"claude-fable-5-1":{"draws":15,"losses":64,"wins":83},"claude-haiku-5-5":{"draws":8,"losses":7,"wins":123},"claude-opus-4-5":{"draws":15,"losses":10,"wins":209},"claude-opus-4-8":{"draws":8,"losses":10,"wins":114},"claude-opus-5":{"draws":22,"losses":57,"wins":167},"claude-opus-5-5":{"draws":16,"losses":69,"wins":71},"claude-sonnet-5":{"draws":6,"losses":6,"wins":132},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":101},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":10,"losses":5,"wins":201},"deepseek/deepseek-v4-pro":{"draws":11,"losses":7,"wins":114},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":1,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":7,"wins":124},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":10,"wins":123},"elorian/glimpse":{"draws":6,"losses":7,"wins":65},"fireworks/ember-1":{"draws":10,"losses":5,"wins":129},"gemini-3.1-pro-preview":{"draws":7,"losses":2,"wins":135},"gemini-4-argon":{"draws":17,"losses":40,"wins":87},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":94},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":167},"google/gemini-3.5-flash-lite":{"draws":14,"losses":0,"wins":238},"google/gemini-3.6-flash":{"draws":19,"losses":19,"wins":238},"google/gemini-3.8-flash":{"draws":13,"losses":10,"wins":121},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":80},"gpt-4.1":{"draws":3,"losses":0,"wins":45},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":16},"gpt-5":{"draws":9,"losses":1,"wins":116},"gpt-5.4":{"draws":6,"losses":18,"wins":114},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":90},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":139},"gpt-5.5":{"draws":5,"losses":8,"wins":119},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":128},"gpt-5.6-sol":{"draws":14,"losses":16,"wins":114},"gpt-5.6-terra":{"draws":12,"losses":3,"wins":123},"gpt-6-astra":{"draws":12,"losses":42,"wins":42},"gpt-6-luna":{"draws":13,"losses":10,"wins":121},"gpt-6-sol":{"draws":17,"losses":28,"wins":99},"gpt-6.1-sol":{"draws":19,"losses":53,"wins":72},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":95},"inception/mercury-3":{"draws":11,"losses":2,"wins":83},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":96},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":3,"wins":146},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":120},"meta/muse-spark-1.2":{"draws":8,"losses":4,"wins":126},"meta/muse-spark-1.3":{"draws":14,"losses":13,"wins":117},"meta/muse-spark-open":{"draws":7,"losses":3,"wins":128},"meta/muse-wonder":{"draws":14,"losses":16,"wins":114},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":76},"minimax/minimax-m3.1-flash":{"draws":9,"losses":0,"wins":117},"mistralai/mistral-large-4-0":{"draws":9,"losses":5,"wins":76},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":33},"moonshotai/kimi-k3":{"draws":11,"losses":9,"wins":118},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":38,"wins":95},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":68},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":116},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":64},"o3":{"draws":7,"losses":1,"wins":190},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":114},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":131},"qwen/qwen3.7-max":{"draws":5,"losses":0,"wins":79},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":69},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":133},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":97},"qwen/qwen3.8-flash":{"draws":12,"losses":3,"wins":81},"qwen/qwen3.8-max":{"draws":13,"losses":4,"wins":127},"qwen/qwen3.8-max-0902":{"draws":9,"losses":6,"wins":129},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":39},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":4,"wins":117},"stealth/ox-alpha":{"draws":35,"losses":22,"wins":417},"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":10,"losses":0,"wins":68},"tencent/hy4-preview":{"draws":10,"losses":5,"wins":123},"thinkingmachines/inkling":{"draws":11,"losses":1,"wins":180},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":135},"unbiased/pareto-26.10":{"draws":8,"losses":18,"wins":22},"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":9,"losses":15,"wins":120},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":121},"x-ai/grok-4.7":{"draws":10,"losses":22,"wins":94},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.5":{"draws":14,"losses":2,"wins":206},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":74},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":82},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":80},"z-ai/glm-5.2":{"draws":21,"losses":8,"wins":259},"z-ai/glm-5.3":{"draws":17,"losses":11,"wins":110},"z-ai/glm-5.3-flash":{"draws":12,"losses":8,"wins":124},"z-ai/glm-5.3-flashx":{"draws":15,"losses":8,"wins":121}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":39,"wins":53},"claude-fable-5":{"draws":29,"losses":88,"wins":27},"claude-fable-5-1":{"draws":12,"losses":144,"wins":6},"claude-haiku-5-5":{"draws":35,"losses":64,"wins":39},"claude-opus-4-5":{"draws":72,"losses":85,"wins":77},"claude-opus-4-8":{"draws":29,"losses":64,"wins":39},"claude-opus-5":{"draws":44,"losses":177,"wins":25},"claude-opus-5-5":{"draws":12,"losses":141,"wins":3},"claude-sonnet-5":{"draws":36,"losses":54,"wins":54},"claude-sonnet-5-5":{"draws":32,"losses":68,"wins":44},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":59,"losses":51,"wins":106},"deepseek/deepseek-v4-pro":{"draws":34,"losses":42,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":49,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":40,"losses":63,"wins":41},"deepseek/deepseek-v4.1-flash-1017":{"draws":34,"losses":76,"wins":34},"elorian/glimpse":{"draws":14,"losses":37,"wins":27},"fireworks/ember-1":{"draws":37,"losses":64,"wins":43},"gemini-3.1-pro-preview":{"draws":33,"losses":62,"wins":49},"gemini-4-argon":{"draws":10,"losses":126,"wins":8},"google/gemini-3.1-flash-lite":{"draws":24,"losses":13,"wins":59},"google/gemini-3.5-flash":{"draws":49,"losses":67,"wins":64},"google/gemini-3.5-flash-lite":{"draws":73,"losses":62,"wins":117},"google/gemini-3.6-flash":{"draws":73,"losses":125,"wins":78},"google/gemini-3.8-flash":{"draws":40,"losses":70,"wins":34},"google/gemma-4-31b-it":{"draws":28,"losses":18,"wins":38},"gpt-4.1":{"draws":9,"losses":19,"wins":20},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":7},"gpt-5":{"draws":38,"losses":41,"wins":47},"gpt-5.4":{"draws":41,"losses":60,"wins":37},"gpt-5.4-mini":{"draws":42,"losses":15,"wins":39},"gpt-5.4-nano":{"draws":29,"losses":43,"wins":72},"gpt-5.5":{"draws":45,"losses":57,"wins":30},"gpt-5.6-luna":{"draws":44,"losses":40,"wins":60},"gpt-5.6-sol":{"draws":27,"losses":93,"wins":24},"gpt-5.6-terra":{"draws":38,"losses":41,"wins":59},"gpt-6-astra":{"draws":13,"losses":121,"wins":10},"gpt-6-luna":{"draws":24,"losses":36,"wins":36},"gpt-6-sol":{"draws":21,"losses":105,"wins":18},"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":38,"losses":10,"wins":54},"inception/mercury-3":{"draws":26,"losses":31,"wins":39},"inclusionai/ling-3.0-flash":{"draws":32,"losses":15,"wins":55},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":35,"losses":35,"wins":86},"meta/muse-glimmer-30b":{"draws":39,"losses":23,"wins":64},"meta/muse-spark-1.2":{"draws":37,"losses":62,"wins":39},"meta/muse-spark-1.3":{"draws":25,"losses":83,"wins":36},"meta/muse-spark-open":{"draws":31,"losses":64,"wins":43},"meta/muse-wonder":{"draws":34,"losses":77,"wins":33},"minimax/minimax-m3":{"draws":22,"losses":15,"wins":41},"minimax/minimax-m3.1-flash":{"draws":26,"losses":44,"wins":56},"mistralai/mistral-large-4-0":{"draws":27,"losses":31,"wins":32},"mistralai/mistral-medium-3-5":{"draws":27,"losses":7,"wins":50},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":12,"wins":13},"moonshotai/kimi-k3":{"draws":43,"losses":52,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":119,"wins":11},"nex-agi/nex-n2-pro":{"draws":13,"losses":14,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":8,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":25,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":33,"losses":65,"wins":100},"openai/gpt-oss-120b":{"draws":38,"losses":29,"wins":59},"poolside/laguna-s-2.1":{"draws":42,"losses":38,"wins":58},"qwen/qwen3.7-max":{"draws":21,"losses":27,"wins":36},"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":24,"losses":37,"wins":41},"qwen/qwen3.8-flash":{"draws":28,"losses":33,"wins":35},"qwen/qwen3.8-max":{"draws":35,"losses":61,"wins":48},"qwen/qwen3.8-max-0902":{"draws":38,"losses":58,"wins":48},"recursive/flint-v1.0":{"draws":11,"losses":5,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":47,"wins":57},"stealth/ox-alpha":{"draws":105,"losses":211,"wins":158},"stealth/space-bunny-alpha":{"draws":37,"losses":25,"wins":52},"stepfun/step-3.7-flash":{"draws":21,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":25,"losses":21,"wins":32},"tencent/hy4-preview":{"draws":40,"losses":61,"wins":37},"thinkingmachines/inkling":{"draws":56,"losses":41,"wins":95},"thinkingmachines/inkling-small":{"draws":40,"losses":32,"wins":72},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"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":33,"losses":66,"wins":45},"x-ai/grok-4.6":{"draws":36,"losses":83,"wins":25},"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":73,"losses":32,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":19,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":40,"wins":32},"xiaomi/mimo-v2.6-pro":{"draws":20,"losses":50,"wins":26},"z-ai/glm-5.2":{"draws":100,"losses":73,"wins":115},"z-ai/glm-5.3":{"draws":23,"losses":86,"wins":29},"z-ai/glm-5.3-flash":{"draws":39,"losses":71,"wins":34},"z-ai/glm-5.3-flashx":{"draws":27,"losses":71,"wins":46}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":14,"wins":103},"claude-fable-5":{"draws":18,"losses":43,"wins":83},"claude-fable-5-1":{"draws":12,"losses":110,"wins":40},"claude-haiku-5-5":{"draws":25,"losses":28,"wins":85},"claude-opus-4-5":{"draws":35,"losses":25,"wins":174},"claude-opus-4-8":{"draws":17,"losses":35,"wins":80},"claude-opus-5":{"draws":38,"losses":119,"wins":89},"claude-opus-5-5":{"draws":14,"losses":103,"wins":39},"claude-sonnet-5":{"draws":23,"losses":18,"wins":103},"claude-sonnet-5-5":{"draws":11,"losses":51,"wins":82},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":49},"deepseek/deepseek-v4-flash":{"draws":32,"losses":15,"wins":169},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":98},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":99},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":29,"wins":91},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":40,"wins":89},"elorian/glimpse":{"draws":10,"losses":15,"wins":53},"fireworks/ember-1":{"draws":20,"losses":23,"wins":101},"gemini-3.1-pro-preview":{"draws":14,"losses":28,"wins":102},"gemini-4-argon":{"draws":14,"losses":72,"wins":58},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":80},"google/gemini-3.5-flash":{"draws":23,"losses":30,"wins":127},"google/gemini-3.5-flash-lite":{"draws":36,"losses":23,"wins":193},"google/gemini-3.6-flash":{"draws":34,"losses":62,"wins":180},"google/gemini-3.8-flash":{"draws":21,"losses":33,"wins":90},"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":13,"losses":16,"wins":97},"gpt-5.4":{"draws":13,"losses":22,"wins":103},"gpt-5.4-mini":{"draws":13,"losses":10,"wins":73},"gpt-5.4-nano":{"draws":20,"losses":12,"wins":112},"gpt-5.5":{"draws":19,"losses":30,"wins":83},"gpt-5.6-luna":{"draws":23,"losses":14,"wins":107},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":85},"gpt-5.6-terra":{"draws":23,"losses":17,"wins":98},"gpt-6-astra":{"draws":17,"losses":99,"wins":28},"gpt-6-luna":{"draws":21,"losses":18,"wins":105},"gpt-6-sol":{"draws":12,"losses":42,"wins":42},"gpt-6.1-sol":{"draws":14,"losses":90,"wins":40},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":16,"losses":4,"wins":82},"inception/mercury-3":{"draws":16,"losses":14,"wins":66},"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":17,"losses":24,"wins":97},"meta/muse-spark-1.3":{"draws":22,"losses":23,"wins":99},"meta/muse-spark-open":{"draws":12,"losses":22,"wins":104},"meta/muse-wonder":{"draws":18,"losses":45,"wins":81},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":62},"minimax/minimax-m3.1-flash":{"draws":15,"losses":9,"wins":102},"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":5,"losses":3,"wins":28},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":98},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":82,"wins":45},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":62},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":106},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":52},"o3":{"draws":10,"losses":17,"wins":171},"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":16,"losses":14,"wins":72},"qwen/qwen3.8-flash":{"draws":9,"losses":19,"wins":68},"qwen/qwen3.8-max":{"draws":16,"losses":26,"wins":102},"qwen/qwen3.8-max-0902":{"draws":18,"losses":28,"wins":98},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":16,"wins":98},"stealth/ox-alpha":{"draws":61,"losses":72,"wins":341},"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":18,"losses":25,"wins":95},"thinkingmachines/inkling":{"draws":25,"losses":13,"wins":154},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":118},"unbiased/pareto-26.10":{"draws":3,"losses":38,"wins":7},"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":19,"losses":32,"wins":93},"x-ai/grok-4.6":{"draws":21,"losses":28,"wins":95},"x-ai/grok-4.7":{"draws":13,"losses":60,"wins":53},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":38},"xiaomi/mimo-v2.5":{"draws":36,"losses":17,"wins":169},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":64},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":19,"wins":62},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":26,"wins":52},"z-ai/glm-5.2":{"draws":42,"losses":34,"wins":212},"z-ai/glm-5.3":{"draws":20,"losses":45,"wins":73},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":90},"z-ai/glm-5.3-flashx":{"draws":16,"losses":42,"wins":86}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":113},"claude-fable-5":{"draws":10,"losses":34,"wins":100},"claude-fable-5-1":{"draws":10,"losses":74,"wins":78},"claude-haiku-5-5":{"draws":13,"losses":11,"wins":114},"claude-opus-4-5":{"draws":20,"losses":15,"wins":199},"claude-opus-4-8":{"draws":6,"losses":16,"wins":110},"claude-opus-5":{"draws":32,"losses":74,"wins":140},"claude-opus-5-5":{"draws":17,"losses":75,"wins":64},"claude-sonnet-5":{"draws":6,"losses":8,"wins":130},"claude-sonnet-5-5":{"draws":3,"losses":35,"wins":106},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":52},"deepseek/deepseek-v4-flash":{"draws":14,"losses":6,"wins":196},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":116},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":2,"wins":123},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":15,"wins":116},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":107},"elorian/glimpse":{"draws":4,"losses":10,"wins":64},"fireworks/ember-1":{"draws":10,"losses":18,"wins":116},"gemini-3.1-pro-preview":{"draws":3,"losses":13,"wins":128},"gemini-4-argon":{"draws":19,"losses":46,"wins":79},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":92},"google/gemini-3.5-flash":{"draws":7,"losses":19,"wins":154},"google/gemini-3.5-flash-lite":{"draws":15,"losses":2,"wins":235},"google/gemini-3.6-flash":{"draws":18,"losses":20,"wins":238},"google/gemini-3.8-flash":{"draws":16,"losses":18,"wins":110},"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":4,"wins":116},"gpt-5.4":{"draws":9,"losses":19,"wins":110},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":88},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":134},"gpt-5.5":{"draws":7,"losses":22,"wins":103},"gpt-5.6-luna":{"draws":10,"losses":9,"wins":125},"gpt-5.6-sol":{"draws":12,"losses":26,"wins":106},"gpt-5.6-terra":{"draws":9,"losses":8,"wins":121},"gpt-6-astra":{"draws":19,"losses":72,"wins":53},"gpt-6-luna":{"draws":13,"losses":6,"wins":125},"gpt-6-sol":{"draws":14,"losses":40,"wins":90},"gpt-6.1-sol":{"draws":2,"losses":47,"wins":47},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":93},"inception/mercury-3":{"draws":7,"losses":7,"wins":82},"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":11,"wins":139},"meta/muse-glimmer-30b":{"draws":8,"losses":1,"wins":117},"meta/muse-spark-1.2":{"draws":13,"losses":17,"wins":108},"meta/muse-spark-1.3":{"draws":12,"losses":14,"wins":118},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":118},"meta/muse-wonder":{"draws":19,"losses":29,"wins":96},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":70},"minimax/minimax-m3.1-flash":{"draws":12,"losses":2,"wins":112},"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":3,"losses":3,"wins":30},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":116},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":47,"wins":83},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":68},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":112},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":58},"o3":{"draws":3,"losses":8,"wins":187},"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":6,"losses":2,"wins":76},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":66},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":20,"wins":116},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":91},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":81},"qwen/qwen3.8-max":{"draws":10,"losses":6,"wins":128},"qwen/qwen3.8-max-0902":{"draws":11,"losses":12,"wins":121},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":41},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":6,"wins":120},"stealth/ox-alpha":{"draws":40,"losses":33,"wins":401},"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":6,"losses":13,"wins":119},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":175},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":138},"unbiased/pareto-26.10":{"draws":6,"losses":25,"wins":17},"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":18,"wins":116},"x-ai/grok-4.6":{"draws":17,"losses":12,"wins":115},"x-ai/grok-4.7":{"draws":6,"losses":38,"wins":82},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":48},"xiaomi/mimo-v2.5":{"draws":18,"losses":8,"wins":196},"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":10,"wins":248},"z-ai/glm-5.3":{"draws":21,"losses":24,"wins":93},"z-ai/glm-5.3-flash":{"draws":12,"losses":16,"wins":116},"z-ai/glm-5.3-flashx":{"draws":15,"losses":18,"wins":111}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":1,"wins":0},"elorian/glimpse":{"draws":3,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":1,"losses":5,"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},"inception/mercury-3":{"draws":2,"losses":0,"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-spark-open":{"draws":4,"losses":2,"wins":0},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":1},"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},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":5,"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},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":0},"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":{"draws":1,"losses":1,"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":32,"losses":35,"wins":25},"claude-fable-5":{"draws":26,"losses":71,"wins":5},"claude-fable-5-1":{"draws":7,"losses":107,"wins":0},"claude-haiku-5-5":{"draws":30,"losses":66,"wins":4},"claude-opus-4-5":{"draws":70,"losses":90,"wins":8},"claude-opus-4-8":{"draws":29,"losses":58,"wins":11},"claude-opus-5":{"draws":31,"losses":128,"wins":7},"claude-opus-5-5":{"draws":8,"losses":102,"wins":0},"claude-sonnet-5":{"draws":35,"losses":56,"wins":11},"claude-sonnet-5-5":{"draws":25,"losses":65,"wins":12},"cohere/north-mini-code":{"draws":10,"losses":13,"wins":15},"deepseek/deepseek-v4-flash":{"draws":55,"losses":69,"wins":28},"deepseek/deepseek-v4-pro":{"draws":35,"losses":46,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":46,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":53,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":30,"losses":66,"wins":6},"elorian/glimpse":{"draws":15,"losses":32,"wins":5},"fireworks/ember-1":{"draws":40,"losses":54,"wins":8},"gemini-3.1-pro-preview":{"draws":36,"losses":42,"wins":24},"gemini-4-argon":{"draws":8,"losses":94,"wins":0},"google/gemini-3.1-flash-lite":{"draws":22,"losses":21,"wins":29},"google/gemini-3.5-flash":{"draws":42,"losses":67,"wins":19},"google/gemini-3.5-flash-lite":{"draws":68,"losses":69,"wins":43},"google/gemini-3.6-flash":{"draws":60,"losses":118,"wins":16},"google/gemini-3.8-flash":{"draws":31,"losses":67,"wins":4},"google/gemma-4-31b-it":{"draws":30,"losses":18,"wins":16},"gpt-4.1":{"draws":13,"losses":13,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":5,"wins":3},"gpt-5":{"draws":32,"losses":43,"wins":9},"gpt-5.4":{"draws":39,"losses":51,"wins":6},"gpt-5.4-mini":{"draws":28,"losses":24,"wins":16},"gpt-5.4-nano":{"draws":30,"losses":57,"wins":15},"gpt-5.5":{"draws":36,"losses":45,"wins":9},"gpt-5.6-luna":{"draws":41,"losses":40,"wins":21},"gpt-5.6-sol":{"draws":19,"losses":83,"wins":0},"gpt-5.6-terra":{"draws":35,"losses":54,"wins":9},"gpt-6-astra":{"draws":7,"losses":95,"wins":0},"gpt-6-luna":{"draws":38,"losses":54,"wins":10},"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":24,"losses":12,"wins":12},"inception/mercury-3":{"draws":30,"losses":30,"wins":8},"inclusionai/ling-3.0-flash":{"draws":35,"losses":20,"wins":17},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":44,"wins":31},"meta/muse-glimmer-30b":{"draws":36,"losses":26,"wins":22},"meta/muse-spark-1.2":{"draws":33,"losses":51,"wins":12},"meta/muse-spark-1.3":{"draws":27,"losses":66,"wins":9},"meta/muse-spark-open":{"draws":27,"losses":63,"wins":6},"meta/muse-wonder":{"draws":28,"losses":70,"wins":4},"minimax/minimax-m3":{"draws":24,"losses":19,"wins":11},"minimax/minimax-m3.1-flash":{"draws":30,"losses":47,"wins":11},"mistralai/mistral-large-4-0":{"draws":26,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":26,"losses":18,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":44,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":81,"wins":3},"nex-agi/nex-n2-pro":{"draws":16,"losses":19,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":28,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":25,"wins":6},"o3":{"draws":30,"losses":89,"wins":17},"openai/gpt-oss-120b":{"draws":32,"losses":31,"wins":25},"poolside/laguna-s-2.1":{"draws":36,"losses":30,"wins":24},"qwen/qwen3.7-max":{"draws":21,"losses":23,"wins":16},"qwen/qwen3.7-plus":{"draws":22,"losses":23,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":56,"wins":6},"qwen/qwen3.8-27b":{"draws":22,"losses":43,"wins":7},"qwen/qwen3.8-flash":{"draws":29,"losses":33,"wins":6},"qwen/qwen3.8-max":{"draws":37,"losses":57,"wins":8},"qwen/qwen3.8-max-0902":{"draws":39,"losses":53,"wins":10},"recursive/flint-v1.0":{"draws":12,"losses":12,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":52,"wins":6},"stealth/ox-alpha":{"draws":93,"losses":184,"wins":33},"stealth/space-bunny-alpha":{"draws":31,"losses":38,"wins":13},"stepfun/step-3.7-flash":{"draws":20,"losses":38,"wins":10},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":15,"wins":14},"tencent/hy4-preview":{"draws":35,"losses":50,"wins":11},"thinkingmachines/inkling":{"draws":48,"losses":46,"wins":34},"thinkingmachines/inkling-small":{"draws":42,"losses":31,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":33,"wins":0},"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":34,"losses":64,"wins":4},"x-ai/grok-4.6":{"draws":28,"losses":67,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":72,"wins":3},"x-ai/grok-build-0.1":{"draws":16,"losses":10,"wins":8},"xiaomi/mimo-v2.5":{"draws":70,"losses":71,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":25,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":45,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":49,"wins":1},"z-ai/glm-5.2":{"draws":79,"losses":103,"wins":22},"z-ai/glm-5.3":{"draws":24,"losses":69,"wins":7},"z-ai/glm-5.3-flash":{"draws":24,"losses":66,"wins":12},"z-ai/glm-5.3-flashx":{"draws":21,"losses":72,"wins":9}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":27,"wins":34},"claude-fable-5":{"draws":24,"losses":59,"wins":13},"claude-fable-5-1":{"draws":4,"losses":101,"wins":1},"claude-haiku-5-5":{"draws":23,"losses":40,"wins":29},"claude-opus-4-5":{"draws":49,"losses":55,"wins":52},"claude-opus-4-8":{"draws":24,"losses":44,"wins":20},"claude-opus-5":{"draws":18,"losses":128,"wins":18},"claude-opus-5-5":{"draws":5,"losses":102,"wins":1},"claude-sonnet-5":{"draws":31,"losses":32,"wins":33},"claude-sonnet-5-5":{"draws":21,"losses":53,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":26},"deepseek/deepseek-v4-flash":{"draws":43,"losses":37,"wins":70},"deepseek/deepseek-v4-pro":{"draws":24,"losses":31,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":28,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":40,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":55,"wins":15},"elorian/glimpse":{"draws":8,"losses":23,"wins":21},"fireworks/ember-1":{"draws":33,"losses":31,"wins":32},"gemini-3.1-pro-preview":{"draws":32,"losses":25,"wins":39},"gemini-4-argon":{"draws":11,"losses":77,"wins":8},"google/gemini-3.1-flash-lite":{"draws":13,"losses":7,"wins":40},"google/gemini-3.5-flash":{"draws":27,"losses":43,"wins":48},"google/gemini-3.5-flash-lite":{"draws":47,"losses":31,"wins":84},"google/gemini-3.6-flash":{"draws":45,"losses":87,"wins":48},"google/gemini-3.8-flash":{"draws":24,"losses":49,"wins":23},"google/gemma-4-31b-it":{"draws":19,"losses":8,"wins":29},"gpt-4.1":{"draws":8,"losses":9,"wins":15},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":6},"gpt-5":{"draws":17,"losses":27,"wins":40},"gpt-5.4":{"draws":16,"losses":44,"wins":30},"gpt-5.4-mini":{"draws":21,"losses":9,"wins":34},"gpt-5.4-nano":{"draws":26,"losses":28,"wins":46},"gpt-5.5":{"draws":26,"losses":39,"wins":21},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":40},"gpt-5.6-sol":{"draws":14,"losses":65,"wins":17},"gpt-5.6-terra":{"draws":29,"losses":32,"wins":33},"gpt-6-astra":{"draws":11,"losses":83,"wins":2},"gpt-6-luna":{"draws":26,"losses":39,"wins":31},"gpt-6-sol":{"draws":16,"losses":66,"wins":14},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":8,"wins":30},"inception/mercury-3":{"draws":14,"losses":13,"wins":13},"inclusionai/ling-3.0-flash":{"draws":20,"losses":16,"wins":38},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":25,"losses":27,"wins":50},"meta/muse-glimmer-30b":{"draws":24,"losses":17,"wins":41},"meta/muse-spark-1.2":{"draws":26,"losses":42,"wins":24},"meta/muse-spark-1.3":{"draws":19,"losses":55,"wins":22},"meta/muse-spark-open":{"draws":18,"losses":50,"wins":22},"meta/muse-wonder":{"draws":24,"losses":50,"wins":22},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":29},"minimax/minimax-m3.1-flash":{"draws":18,"losses":21,"wins":39},"mistralai/mistral-large-4-0":{"draws":17,"losses":18,"wins":25},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":10},"moonshotai/kimi-k3":{"draws":26,"losses":30,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":71,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":8,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":18,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":10,"wins":21},"o3":{"draws":17,"losses":36,"wins":75},"openai/gpt-oss-120b":{"draws":26,"losses":21,"wins":39},"poolside/laguna-s-2.1":{"draws":30,"losses":17,"wins":49},"qwen/qwen3.7-max":{"draws":15,"losses":18,"wins":25},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":34,"wins":30},"qwen/qwen3.8-27b":{"draws":20,"losses":25,"wins":21},"qwen/qwen3.8-flash":{"draws":19,"losses":24,"wins":21},"qwen/qwen3.8-max":{"draws":30,"losses":40,"wins":26},"qwen/qwen3.8-max-0902":{"draws":27,"losses":39,"wins":30},"recursive/flint-v1.0":{"draws":8,"losses":6,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":31,"wins":29},"stealth/ox-alpha":{"draws":79,"losses":130,"wins":103},"stealth/space-bunny-alpha":{"draws":19,"losses":20,"wins":33},"stepfun/step-3.7-flash":{"draws":15,"losses":14,"wins":39},"stepfun/step-5-preview":{"draws":0,"losses":7,"wins":5},"tencent/hy3-preview":{"draws":17,"losses":13,"wins":22},"tencent/hy4-preview":{"draws":22,"losses":40,"wins":28},"thinkingmachines/inkling":{"draws":43,"losses":26,"wins":53},"thinkingmachines/inkling-small":{"draws":29,"losses":15,"wins":52},"unbiased/pareto-26.10":{"draws":2,"losses":29,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":30,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":3,"wins":15},"x-ai/grok-4.5":{"draws":31,"losses":42,"wins":23},"x-ai/grok-4.6":{"draws":29,"losses":48,"wins":19},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":10},"x-ai/grok-build-0.1":{"draws":11,"losses":4,"wins":17},"xiaomi/mimo-v2.5":{"draws":52,"losses":24,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":14,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":22,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":32,"wins":18},"z-ai/glm-5.2":{"draws":64,"losses":48,"wins":80},"z-ai/glm-5.3":{"draws":22,"losses":49,"wins":21},"z-ai/glm-5.3-flash":{"draws":22,"losses":38,"wins":36},"z-ai/glm-5.3-flashx":{"draws":21,"losses":42,"wins":33}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":42,"wins":16},"claude-fable-5":{"draws":18,"losses":80,"wins":4},"claude-fable-5-1":{"draws":8,"losses":106,"wins":0},"claude-haiku-5-5":{"draws":29,"losses":64,"wins":5},"claude-opus-4-5":{"draws":59,"losses":89,"wins":18},"claude-opus-4-8":{"draws":31,"losses":63,"wins":0},"claude-opus-5":{"draws":26,"losses":133,"wins":7},"claude-opus-5-5":{"draws":8,"losses":106,"wins":0},"claude-sonnet-5":{"draws":34,"losses":60,"wins":8},"claude-sonnet-5-5":{"draws":26,"losses":69,"wins":7},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":13},"deepseek/deepseek-v4-flash":{"draws":59,"losses":56,"wins":43},"deepseek/deepseek-v4-pro":{"draws":32,"losses":42,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":34,"losses":44,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":50,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":79,"wins":3},"elorian/glimpse":{"draws":16,"losses":32,"wins":10},"fireworks/ember-1":{"draws":42,"losses":55,"wins":5},"gemini-3.1-pro-preview":{"draws":34,"losses":50,"wins":18},"gemini-4-argon":{"draws":7,"losses":91,"wins":4},"google/gemini-3.1-flash-lite":{"draws":20,"losses":22,"wins":24},"google/gemini-3.5-flash":{"draws":35,"losses":77,"wins":16},"google/gemini-3.5-flash-lite":{"draws":56,"losses":78,"wins":42},"google/gemini-3.6-flash":{"draws":61,"losses":112,"wins":21},"google/gemini-3.8-flash":{"draws":25,"losses":75,"wins":2},"google/gemma-4-31b-it":{"draws":32,"losses":13,"wins":13},"gpt-4.1":{"draws":13,"losses":20,"wins":1},"gpt-4.1-nano":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":29,"losses":39,"wins":20},"gpt-5.4":{"draws":24,"losses":57,"wins":17},"gpt-5.4-mini":{"draws":26,"losses":26,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":50,"wins":30},"gpt-5.5":{"draws":38,"losses":45,"wins":9},"gpt-5.6-luna":{"draws":48,"losses":35,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":85,"wins":5},"gpt-5.6-terra":{"draws":32,"losses":63,"wins":7},"gpt-6-astra":{"draws":5,"losses":96,"wins":1},"gpt-6-luna":{"draws":32,"losses":55,"wins":15},"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":35,"losses":17,"wins":20},"inception/mercury-3":{"draws":20,"losses":38,"wins":16},"inclusionai/ling-3.0-flash":{"draws":18,"losses":17,"wins":17},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":39,"wins":24},"meta/muse-glimmer-30b":{"draws":46,"losses":22,"wins":18},"meta/muse-spark-1.2":{"draws":28,"losses":57,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":77,"wins":9},"meta/muse-spark-open":{"draws":17,"losses":73,"wins":8},"meta/muse-wonder":{"draws":16,"losses":81,"wins":5},"minimax/minimax-m3":{"draws":17,"losses":22,"wins":15},"minimax/minimax-m3.1-flash":{"draws":23,"losses":45,"wins":18},"mistralai/mistral-large-4-0":{"draws":28,"losses":25,"wins":9},"mistralai/mistral-medium-3-5":{"draws":21,"losses":18,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":5},"moonshotai/kimi-k3":{"draws":27,"losses":56,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":84,"wins":5},"nex-agi/nex-n2-pro":{"draws":13,"losses":18,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":31,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":22,"wins":10},"o3":{"draws":26,"losses":91,"wins":23},"openai/gpt-oss-120b":{"draws":37,"losses":41,"wins":8},"poolside/laguna-s-2.1":{"draws":29,"losses":36,"wins":29},"qwen/qwen3.7-max":{"draws":19,"losses":30,"wins":11},"qwen/qwen3.7-plus":{"draws":16,"losses":18,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":60,"wins":4},"qwen/qwen3.8-27b":{"draws":14,"losses":46,"wins":14},"qwen/qwen3.8-flash":{"draws":21,"losses":38,"wins":9},"qwen/qwen3.8-max":{"draws":37,"losses":51,"wins":14},"qwen/qwen3.8-max-0902":{"draws":37,"losses":56,"wins":9},"recursive/flint-v1.0":{"draws":8,"losses":14,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":45,"wins":16},"stealth/ox-alpha":{"draws":84,"losses":211,"wins":33},"stealth/space-bunny-alpha":{"draws":30,"losses":33,"wins":13},"stepfun/step-3.7-flash":{"draws":26,"losses":30,"wins":20},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":24,"wins":8},"tencent/hy4-preview":{"draws":32,"losses":54,"wins":12},"thinkingmachines/inkling":{"draws":47,"losses":52,"wins":31},"thinkingmachines/inkling-small":{"draws":42,"losses":32,"wins":28},"unbiased/pareto-26.10":{"draws":2,"losses":32,"wins":0},"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":24,"losses":72,"wins":6},"x-ai/grok-4.6":{"draws":33,"losses":64,"wins":5},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":5},"x-ai/grok-build-0.1":{"draws":10,"losses":19,"wins":5},"xiaomi/mimo-v2.5":{"draws":68,"losses":54,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":26,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":42,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":49,"wins":5},"z-ai/glm-5.2":{"draws":85,"losses":78,"wins":41},"z-ai/glm-5.3":{"draws":21,"losses":72,"wins":3},"z-ai/glm-5.3-flash":{"draws":29,"losses":58,"wins":15},"z-ai/glm-5.3-flashx":{"draws":33,"losses":61,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":6,"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},"inception/mercury-3":{"draws":0,"losses":6,"wins":0},"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-spark-open":{"draws":0,"losses":6,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":2},"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},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"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":{"draws":0,"losses":2,"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":34,"losses":65,"wins":45},"claude-fable-5":{"draws":14,"losses":122,"wins":20},"claude-fable-5-1":{"draws":4,"losses":165,"wins":7},"claude-haiku-5-5":{"draws":32,"losses":97,"wins":21},"claude-opus-4-5":{"draws":61,"losses":154,"wins":39},"claude-opus-4-8":{"draws":28,"losses":92,"wins":24},"claude-opus-5":{"draws":22,"losses":213,"wins":21},"claude-opus-5-5":{"draws":11,"losses":155,"wins":6},"claude-sonnet-5":{"draws":38,"losses":85,"wins":33},"claude-sonnet-5-5":{"draws":19,"losses":106,"wins":31},"cohere/north-mini-code":{"draws":14,"losses":15,"wins":39},"deepseek/deepseek-v4-flash":{"draws":57,"losses":99,"wins":78},"deepseek/deepseek-v4-pro":{"draws":27,"losses":86,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":72,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":91,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":108,"wins":22},"elorian/glimpse":{"draws":17,"losses":47,"wins":20},"fireworks/ember-1":{"draws":36,"losses":88,"wins":32},"gemini-3.1-pro-preview":{"draws":36,"losses":71,"wins":49},"gemini-4-argon":{"draws":8,"losses":138,"wins":10},"google/gemini-3.1-flash-lite":{"draws":17,"losses":30,"wins":65},"google/gemini-3.5-flash":{"draws":36,"losses":119,"wins":43},"google/gemini-3.5-flash-lite":{"draws":73,"losses":112,"wins":93},"google/gemini-3.6-flash":{"draws":60,"losses":192,"wins":48},"google/gemini-3.8-flash":{"draws":25,"losses":112,"wins":19},"google/gemma-4-31b-it":{"draws":33,"losses":26,"wins":35},"gpt-4.1":{"draws":14,"losses":28,"wins":10},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":32,"losses":74,"wins":32},"gpt-5.4":{"draws":32,"losses":95,"wins":25},"gpt-5.4-mini":{"draws":33,"losses":40,"wins":31},"gpt-5.4-nano":{"draws":24,"losses":85,"wins":51},"gpt-5.5":{"draws":40,"losses":77,"wins":27},"gpt-5.6-luna":{"draws":38,"losses":68,"wins":50},"gpt-5.6-sol":{"draws":20,"losses":122,"wins":14},"gpt-5.6-terra":{"draws":39,"losses":73,"wins":36},"gpt-6-astra":{"draws":7,"losses":146,"wins":3},"gpt-6-luna":{"draws":35,"losses":86,"wins":35},"gpt-6-sol":{"draws":11,"losses":132,"wins":13},"gpt-6.1-sol":{"draws":6,"losses":139,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":37,"losses":31,"wins":44},"inception/mercury-3":{"draws":25,"losses":50,"wins":27},"inclusionai/ling-3.0-flash":{"draws":45,"losses":24,"wins":39},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":47,"wins":47},"meta/muse-glimmer-30b":{"draws":43,"losses":44,"wins":49},"meta/muse-spark-1.2":{"draws":27,"losses":94,"wins":27},"meta/muse-spark-1.3":{"draws":27,"losses":103,"wins":26},"meta/muse-spark-open":{"draws":28,"losses":106,"wins":18},"meta/muse-wonder":{"draws":31,"losses":105,"wins":20},"minimax/minimax-m3":{"draws":14,"losses":31,"wins":39},"minimax/minimax-m3.1-flash":{"draws":30,"losses":66,"wins":40},"mistralai/mistral-large-4-0":{"draws":34,"losses":46,"wins":16},"mistralai/mistral-medium-3-5":{"draws":29,"losses":24,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":24,"wins":7},"moonshotai/kimi-k3":{"draws":39,"losses":83,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":133,"wins":12},"nex-agi/nex-n2-pro":{"draws":10,"losses":31,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":44,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":36,"wins":16},"o3":{"draws":32,"losses":140,"wins":60},"openai/gpt-oss-120b":{"draws":37,"losses":39,"wins":62},"poolside/laguna-s-2.1":{"draws":45,"losses":55,"wins":50},"qwen/qwen3.7-max":{"draws":21,"losses":52,"wins":19},"qwen/qwen3.7-plus":{"draws":15,"losses":32,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":93,"wins":23},"qwen/qwen3.8-27b":{"draws":21,"losses":69,"wins":18},"qwen/qwen3.8-flash":{"draws":30,"losses":49,"wins":25},"qwen/qwen3.8-max":{"draws":41,"losses":87,"wins":28},"qwen/qwen3.8-max-0902":{"draws":23,"losses":106,"wins":27},"recursive/flint-v1.0":{"draws":11,"losses":13,"wins":22},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":85,"wins":29},"stealth/ox-alpha":{"draws":101,"losses":326,"wins":83},"stealth/space-bunny-alpha":{"draws":32,"losses":63,"wins":31},"stepfun/step-3.7-flash":{"draws":20,"losses":49,"wins":45},"stepfun/step-5-preview":{"draws":7,"losses":8,"wins":1},"tencent/hy3-preview":{"draws":24,"losses":35,"wins":23},"tencent/hy4-preview":{"draws":39,"losses":90,"wins":23},"thinkingmachines/inkling":{"draws":52,"losses":79,"wins":75},"thinkingmachines/inkling-small":{"draws":44,"losses":49,"wins":63},"unbiased/pareto-26.10":{"draws":1,"losses":51,"wins":0},"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":30,"losses":102,"wins":24},"x-ai/grok-4.6":{"draws":35,"losses":97,"wins":24},"x-ai/grok-4.7":{"draws":8,"losses":121,"wins":7},"x-ai/grok-build-0.1":{"draws":15,"losses":19,"wins":18},"xiaomi/mimo-v2.5":{"draws":67,"losses":86,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":43,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":58,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":74,"wins":11},"z-ai/glm-5.2":{"draws":81,"losses":154,"wins":77},"z-ai/glm-5.3":{"draws":22,"losses":117,"wins":13},"z-ai/glm-5.3-flash":{"draws":24,"losses":99,"wins":33},"z-ai/glm-5.3-flashx":{"draws":24,"losses":112,"wins":20}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":44,"wins":37},"claude-fable-5":{"draws":22,"losses":97,"wins":7},"claude-fable-5-1":{"draws":8,"losses":136,"wins":0},"claude-haiku-5-5":{"draws":36,"losses":69,"wins":15},"claude-opus-4-5":{"draws":67,"losses":109,"wins":28},"claude-opus-4-8":{"draws":24,"losses":71,"wins":19},"claude-opus-5":{"draws":15,"losses":193,"wins":22},"claude-opus-5-5":{"draws":7,"losses":131,"wins":0},"claude-sonnet-5":{"draws":39,"losses":68,"wins":19},"claude-sonnet-5-5":{"draws":21,"losses":84,"wins":21},"cohere/north-mini-code":{"draws":18,"losses":15,"wins":17},"deepseek/deepseek-v4-flash":{"draws":65,"losses":74,"wins":47},"deepseek/deepseek-v4-pro":{"draws":35,"losses":56,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":62,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":43,"losses":65,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":30,"losses":84,"wins":12},"elorian/glimpse":{"draws":19,"losses":36,"wins":17},"fireworks/ember-1":{"draws":38,"losses":69,"wins":19},"gemini-3.1-pro-preview":{"draws":44,"losses":61,"wins":21},"gemini-4-argon":{"draws":13,"losses":109,"wins":4},"google/gemini-3.1-flash-lite":{"draws":26,"losses":21,"wins":35},"google/gemini-3.5-flash":{"draws":40,"losses":89,"wins":29},"google/gemini-3.5-flash-lite":{"draws":74,"losses":84,"wins":62},"google/gemini-3.6-flash":{"draws":71,"losses":132,"wins":39},"google/gemini-3.8-flash":{"draws":29,"losses":82,"wins":15},"google/gemma-4-31b-it":{"draws":38,"losses":17,"wins":17},"gpt-4.1":{"draws":17,"losses":15,"wins":10},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":2},"gpt-5":{"draws":34,"losses":54,"wins":26},"gpt-5.4":{"draws":30,"losses":74,"wins":18},"gpt-5.4-mini":{"draws":37,"losses":32,"wins":15},"gpt-5.4-nano":{"draws":25,"losses":53,"wins":44},"gpt-5.5":{"draws":42,"losses":60,"wins":18},"gpt-5.6-luna":{"draws":40,"losses":54,"wins":32},"gpt-5.6-sol":{"draws":19,"losses":99,"wins":8},"gpt-5.6-terra":{"draws":39,"losses":63,"wins":18},"gpt-6-astra":{"draws":6,"losses":120,"wins":0},"gpt-6-luna":{"draws":39,"losses":64,"wins":23},"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":36,"losses":22,"wins":26},"inception/mercury-3":{"draws":24,"losses":41,"wins":17},"inclusionai/ling-3.0-flash":{"draws":46,"losses":18,"wins":22},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":43,"losses":49,"wins":44},"meta/muse-glimmer-30b":{"draws":40,"losses":18,"wins":18},"meta/muse-spark-1.2":{"draws":34,"losses":72,"wins":18},"meta/muse-spark-1.3":{"draws":34,"losses":76,"wins":16},"meta/muse-spark-open":{"draws":28,"losses":78,"wins":16},"meta/muse-wonder":{"draws":26,"losses":85,"wins":15},"minimax/minimax-m3":{"draws":21,"losses":27,"wins":22},"minimax/minimax-m3.1-flash":{"draws":28,"losses":55,"wins":27},"mistralai/mistral-large-4-0":{"draws":27,"losses":36,"wins":19},"mistralai/mistral-medium-3-5":{"draws":27,"losses":14,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":32,"losses":73,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":20,"losses":101,"wins":5},"nex-agi/nex-n2-pro":{"draws":18,"losses":22,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":10,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":34,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":31,"wins":11},"o3":{"draws":32,"losses":104,"wins":36},"openai/gpt-oss-120b":{"draws":39,"losses":41,"wins":32},"poolside/laguna-s-2.1":{"draws":40,"losses":48,"wins":36},"qwen/qwen3.7-max":{"draws":23,"losses":31,"wins":18},"qwen/qwen3.7-plus":{"draws":21,"losses":15,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":68,"wins":15},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":14},"qwen/qwen3.8-flash":{"draws":27,"losses":32,"wins":25},"qwen/qwen3.8-max":{"draws":33,"losses":69,"wins":24},"qwen/qwen3.8-max-0902":{"draws":38,"losses":75,"wins":13},"recursive/flint-v1.0":{"draws":11,"losses":8,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":62,"wins":20},"stealth/ox-alpha":{"draws":90,"losses":276,"wins":60},"stealth/space-bunny-alpha":{"draws":35,"losses":40,"wins":27},"stepfun/step-3.7-flash":{"draws":20,"losses":27,"wins":41},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":25,"losses":31,"wins":14},"tencent/hy4-preview":{"draws":33,"losses":75,"wins":14},"thinkingmachines/inkling":{"draws":56,"losses":57,"wins":61},"thinkingmachines/inkling-small":{"draws":44,"losses":28,"wins":54},"unbiased/pareto-26.10":{"draws":2,"losses":40,"wins":0},"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":31,"losses":81,"wins":14},"x-ai/grok-4.6":{"draws":36,"losses":80,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":92,"wins":14},"x-ai/grok-build-0.1":{"draws":14,"losses":16,"wins":12},"xiaomi/mimo-v2.5":{"draws":70,"losses":60,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":32,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":51,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":56,"wins":13},"z-ai/glm-5.2":{"draws":94,"losses":107,"wins":51},"z-ai/glm-5.3":{"draws":22,"losses":89,"wins":9},"z-ai/glm-5.3-flash":{"draws":26,"losses":82,"wins":18},"z-ai/glm-5.3-flashx":{"draws":28,"losses":78,"wins":20}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":31,"wins":64},"claude-fable-5":{"draws":19,"losses":88,"wins":31},"claude-fable-5-1":{"draws":8,"losses":139,"wins":9},"claude-haiku-5-5":{"draws":28,"losses":64,"wins":40},"claude-opus-4-5":{"draws":61,"losses":59,"wins":104},"claude-opus-4-8":{"draws":27,"losses":52,"wins":47},"claude-opus-5":{"draws":34,"losses":174,"wins":36},"claude-opus-5-5":{"draws":12,"losses":128,"wins":10},"claude-sonnet-5":{"draws":37,"losses":37,"wins":64},"claude-sonnet-5-5":{"draws":29,"losses":66,"wins":43},"cohere/north-mini-code":{"draws":4,"losses":9,"wins":39},"deepseek/deepseek-v4-flash":{"draws":53,"losses":33,"wins":120},"deepseek/deepseek-v4-pro":{"draws":21,"losses":46,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":38,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":51,"wins":52},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":68,"wins":44},"elorian/glimpse":{"draws":16,"losses":25,"wins":35},"fireworks/ember-1":{"draws":36,"losses":54,"wins":48},"gemini-3.1-pro-preview":{"draws":31,"losses":50,"wins":57},"gemini-4-argon":{"draws":10,"losses":114,"wins":14},"google/gemini-3.1-flash-lite":{"draws":22,"losses":8,"wins":60},"google/gemini-3.5-flash":{"draws":32,"losses":57,"wins":83},"google/gemini-3.5-flash-lite":{"draws":63,"losses":48,"wins":129},"google/gemini-3.6-flash":{"draws":56,"losses":103,"wins":105},"google/gemini-3.8-flash":{"draws":24,"losses":57,"wins":57},"google/gemma-4-31b-it":{"draws":24,"losses":17,"wins":39},"gpt-4.1":{"draws":16,"losses":8,"wins":22},"gpt-4.1-nano":{"draws":9,"losses":2,"wins":5},"gpt-5":{"draws":26,"losses":31,"wins":65},"gpt-5.4":{"draws":22,"losses":60,"wins":50},"gpt-5.4-mini":{"draws":26,"losses":18,"wins":48},"gpt-5.4-nano":{"draws":23,"losses":44,"wins":69},"gpt-5.5":{"draws":25,"losses":59,"wins":44},"gpt-5.6-luna":{"draws":39,"losses":34,"wins":65},"gpt-5.6-sol":{"draws":18,"losses":87,"wins":33},"gpt-5.6-terra":{"draws":38,"losses":37,"wins":57},"gpt-6-astra":{"draws":8,"losses":126,"wins":4},"gpt-6-luna":{"draws":37,"losses":39,"wins":62},"gpt-6-sol":{"draws":17,"losses":97,"wins":24},"gpt-6.1-sol":{"draws":13,"losses":108,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":33,"losses":12,"wins":51},"inception/mercury-3":{"draws":26,"losses":24,"wins":42},"inclusionai/ling-3.0-flash":{"draws":28,"losses":11,"wins":57},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":27,"losses":27,"wins":94},"meta/muse-glimmer-30b":{"draws":34,"losses":18,"wins":72},"meta/muse-spark-1.2":{"draws":22,"losses":33,"wins":33},"meta/muse-spark-1.3":{"draws":30,"losses":57,"wins":51},"meta/muse-spark-open":{"draws":27,"losses":62,"wins":43},"meta/muse-wonder":{"draws":26,"losses":69,"wins":43},"minimax/minimax-m3":{"draws":15,"losses":10,"wins":51},"minimax/minimax-m3.1-flash":{"draws":25,"losses":39,"wins":56},"mistralai/mistral-large-4-0":{"draws":18,"losses":26,"wins":44},"mistralai/mistral-medium-3-5":{"draws":21,"losses":12,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":11,"wins":16},"moonshotai/kimi-k3":{"draws":28,"losses":50,"wins":56},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":108,"wins":17},"nex-agi/nex-n2-pro":{"draws":11,"losses":11,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":4,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":19,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":13,"wins":32},"o3":{"draws":22,"losses":70,"wins":94},"openai/gpt-oss-120b":{"draws":32,"losses":13,"wins":77},"poolside/laguna-s-2.1":{"draws":27,"losses":21,"wins":86},"qwen/qwen3.7-max":{"draws":15,"losses":18,"wins":47},"qwen/qwen3.7-plus":{"draws":16,"losses":12,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":54,"wins":47},"qwen/qwen3.8-27b":{"draws":22,"losses":40,"wins":34},"qwen/qwen3.8-flash":{"draws":22,"losses":28,"wins":42},"qwen/qwen3.8-max":{"draws":37,"losses":52,"wins":49},"qwen/qwen3.8-max-0902":{"draws":32,"losses":55,"wins":51},"recursive/flint-v1.0":{"draws":7,"losses":3,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":44,"wins":55},"stealth/ox-alpha":{"draws":104,"losses":200,"wins":154},"stealth/space-bunny-alpha":{"draws":29,"losses":26,"wins":55},"stepfun/step-3.7-flash":{"draws":15,"losses":24,"wins":57},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":21,"losses":12,"wins":43},"tencent/hy4-preview":{"draws":24,"losses":59,"wins":49},"thinkingmachines/inkling":{"draws":50,"losses":33,"wins":103},"thinkingmachines/inkling-small":{"draws":37,"losses":26,"wins":75},"unbiased/pareto-26.10":{"draws":2,"losses":44,"wins":0},"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":32,"losses":69,"wins":37},"x-ai/grok-4.6":{"draws":29,"losses":79,"wins":30},"x-ai/grok-4.7":{"draws":7,"losses":85,"wins":30},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":29},"xiaomi/mimo-v2.5":{"draws":62,"losses":27,"wins":123},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":20,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":31,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":55,"wins":26},"z-ai/glm-5.2":{"draws":66,"losses":73,"wins":137},"z-ai/glm-5.3":{"draws":24,"losses":66,"wins":42},"z-ai/glm-5.3-flash":{"draws":21,"losses":60,"wins":57},"z-ai/glm-5.3-flashx":{"draws":29,"losses":58,"wins":51}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":83},"claude-fable-5":{"draws":22,"losses":79,"wins":43},"claude-fable-5-1":{"draws":10,"losses":135,"wins":17},"claude-haiku-5-5":{"draws":27,"losses":60,"wins":51},"claude-opus-4-5":{"draws":52,"losses":55,"wins":127},"claude-opus-4-8":{"draws":23,"losses":53,"wins":56},"claude-opus-5":{"draws":32,"losses":164,"wins":50},"claude-opus-5-5":{"draws":10,"losses":132,"wins":14},"claude-sonnet-5":{"draws":35,"losses":34,"wins":75},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":54},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":47},"deepseek/deepseek-v4-flash":{"draws":38,"losses":28,"wins":150},"deepseek/deepseek-v4-pro":{"draws":21,"losses":35,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":39,"wins":67},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":54,"wins":63},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":66,"wins":62},"elorian/glimpse":{"draws":16,"losses":25,"wins":37},"fireworks/ember-1":{"draws":33,"losses":44,"wins":67},"gemini-3.1-pro-preview":{"draws":22,"losses":39,"wins":83},"gemini-4-argon":{"draws":12,"losses":113,"wins":19},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":79},"google/gemini-3.5-flash":{"draws":31,"losses":47,"wins":102},"google/gemini-3.5-flash-lite":{"draws":44,"losses":38,"wins":170},"google/gemini-3.6-flash":{"draws":49,"losses":96,"wins":131},"google/gemini-3.8-flash":{"draws":33,"losses":59,"wins":52},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":53},"gpt-4.1":{"draws":16,"losses":5,"wins":27},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":12},"gpt-5":{"draws":25,"losses":28,"wins":73},"gpt-5.4":{"draws":30,"losses":54,"wins":54},"gpt-5.4-mini":{"draws":19,"losses":11,"wins":66},"gpt-5.4-nano":{"draws":22,"losses":29,"wins":93},"gpt-5.5":{"draws":32,"losses":48,"wins":52},"gpt-5.6-luna":{"draws":34,"losses":30,"wins":80},"gpt-5.6-sol":{"draws":21,"losses":75,"wins":48},"gpt-5.6-terra":{"draws":32,"losses":38,"wins":68},"gpt-6-astra":{"draws":14,"losses":117,"wins":13},"gpt-6-luna":{"draws":25,"losses":36,"wins":83},"gpt-6-sol":{"draws":22,"losses":99,"wins":23},"gpt-6.1-sol":{"draws":12,"losses":118,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":2,"wins":1},"inception/mercury-2.5-preview":{"draws":27,"losses":9,"wins":66},"inception/mercury-3":{"draws":19,"losses":22,"wins":55},"inclusionai/ling-3.0-flash":{"draws":16,"losses":9,"wins":77},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":27,"losses":26,"wins":103},"meta/muse-glimmer-30b":{"draws":34,"losses":16,"wins":76},"meta/muse-spark-1.2":{"draws":30,"losses":51,"wins":57},"meta/muse-spark-1.3":{"draws":16,"losses":40,"wins":40},"meta/muse-spark-open":{"draws":22,"losses":52,"wins":64},"meta/muse-wonder":{"draws":28,"losses":74,"wins":42},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":63},"minimax/minimax-m3.1-flash":{"draws":19,"losses":29,"wins":78},"mistralai/mistral-large-4-0":{"draws":24,"losses":22,"wins":44},"mistralai/mistral-medium-3-5":{"draws":16,"losses":4,"wins":64},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":16,"wins":13},"moonshotai/kimi-k3":{"draws":29,"losses":43,"wins":66},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":113,"wins":20},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":13,"wins":84},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":19,"wins":37},"o3":{"draws":20,"losses":52,"wins":126},"openai/gpt-oss-120b":{"draws":30,"losses":13,"wins":83},"poolside/laguna-s-2.1":{"draws":28,"losses":26,"wins":84},"qwen/qwen3.7-max":{"draws":16,"losses":21,"wins":47},"qwen/qwen3.7-plus":{"draws":14,"losses":13,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":50,"wins":59},"qwen/qwen3.8-27b":{"draws":19,"losses":31,"wins":52},"qwen/qwen3.8-flash":{"draws":21,"losses":28,"wins":47},"qwen/qwen3.8-max":{"draws":33,"losses":39,"wins":72},"qwen/qwen3.8-max-0902":{"draws":36,"losses":54,"wins":54},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":34},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":36,"wins":73},"stealth/ox-alpha":{"draws":90,"losses":165,"wins":219},"stealth/space-bunny-alpha":{"draws":18,"losses":22,"wins":74},"stepfun/step-3.7-flash":{"draws":10,"losses":13,"wins":79},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":15,"losses":15,"wins":48},"tencent/hy4-preview":{"draws":24,"losses":50,"wins":64},"thinkingmachines/inkling":{"draws":34,"losses":19,"wins":139},"thinkingmachines/inkling-small":{"draws":32,"losses":13,"wins":99},"unbiased/pareto-26.10":{"draws":3,"losses":45,"wins":0},"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":23,"losses":61,"wins":60},"x-ai/grok-4.6":{"draws":35,"losses":55,"wins":54},"x-ai/grok-4.7":{"draws":12,"losses":82,"wins":32},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":28},"xiaomi/mimo-v2.5":{"draws":49,"losses":23,"wins":150},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":56},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":30,"wins":51},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":49,"wins":32},"z-ai/glm-5.2":{"draws":56,"losses":69,"wins":163},"z-ai/glm-5.3":{"draws":23,"losses":76,"wins":39},"z-ai/glm-5.3-flash":{"draws":26,"losses":68,"wins":50},"z-ai/glm-5.3-flashx":{"draws":22,"losses":60,"wins":62}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":27,"wins":75},"claude-fable-5":{"draws":21,"losses":86,"wins":31},"claude-fable-5-1":{"draws":4,"losses":137,"wins":15},"claude-haiku-5-5":{"draws":19,"losses":58,"wins":55},"claude-opus-4-5":{"draws":61,"losses":61,"wins":102},"claude-opus-4-8":{"draws":27,"losses":52,"wins":47},"claude-opus-5":{"draws":24,"losses":168,"wins":42},"claude-opus-5-5":{"draws":10,"losses":125,"wins":15},"claude-sonnet-5":{"draws":32,"losses":32,"wins":74},"claude-sonnet-5-5":{"draws":24,"losses":62,"wins":52},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":41},"deepseek/deepseek-v4-flash":{"draws":39,"losses":31,"wins":136},"deepseek/deepseek-v4-pro":{"draws":27,"losses":30,"wins":71},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":35,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":56,"wins":55},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":73,"wins":38},"elorian/glimpse":{"draws":13,"losses":35,"wins":28},"fireworks/ember-1":{"draws":29,"losses":50,"wins":59},"gemini-3.1-pro-preview":{"draws":29,"losses":40,"wins":69},"gemini-4-argon":{"draws":11,"losses":106,"wins":21},"google/gemini-3.1-flash-lite":{"draws":15,"losses":6,"wins":73},"google/gemini-3.5-flash":{"draws":28,"losses":53,"wins":93},"google/gemini-3.5-flash-lite":{"draws":42,"losses":40,"wins":162},"google/gemini-3.6-flash":{"draws":50,"losses":106,"wins":110},"google/gemini-3.8-flash":{"draws":23,"losses":61,"wins":54},"google/gemma-4-31b-it":{"draws":20,"losses":6,"wins":54},"gpt-4.1":{"draws":7,"losses":11,"wins":28},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":6},"gpt-5":{"draws":27,"losses":24,"wins":71},"gpt-5.4":{"draws":27,"losses":52,"wins":55},"gpt-5.4-mini":{"draws":23,"losses":14,"wins":55},"gpt-5.4-nano":{"draws":20,"losses":24,"wins":94},"gpt-5.5":{"draws":24,"losses":49,"wins":55},"gpt-5.6-luna":{"draws":34,"losses":33,"wins":71},"gpt-5.6-sol":{"draws":22,"losses":73,"wins":43},"gpt-5.6-terra":{"draws":36,"losses":33,"wins":63},"gpt-6-astra":{"draws":7,"losses":128,"wins":3},"gpt-6-luna":{"draws":31,"losses":43,"wins":64},"gpt-6-sol":{"draws":12,"losses":104,"wins":22},"gpt-6.1-sol":{"draws":7,"losses":118,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":27,"losses":6,"wins":63},"inception/mercury-3":{"draws":18,"losses":22,"wins":50},"inclusionai/ling-3.0-flash":{"draws":17,"losses":8,"wins":73},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":28,"losses":18,"wins":106},"meta/muse-glimmer-30b":{"draws":28,"losses":16,"wins":78},"meta/muse-spark-1.2":{"draws":27,"losses":43,"wins":62},"meta/muse-spark-1.3":{"draws":22,"losses":64,"wins":52},"meta/muse-spark-open":{"draws":16,"losses":36,"wins":36},"meta/muse-wonder":{"draws":22,"losses":69,"wins":47},"minimax/minimax-m3":{"draws":15,"losses":5,"wins":54},"minimax/minimax-m3.1-flash":{"draws":22,"losses":34,"wins":66},"mistralai/mistral-large-4-0":{"draws":16,"losses":24,"wins":46},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":21},"moonshotai/kimi-k3":{"draws":30,"losses":44,"wins":58},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":110,"wins":16},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":16,"wins":76},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":11,"wins":40},"o3":{"draws":21,"losses":41,"wins":134},"openai/gpt-oss-120b":{"draws":27,"losses":10,"wins":83},"poolside/laguna-s-2.1":{"draws":25,"losses":21,"wins":86},"qwen/qwen3.7-max":{"draws":16,"losses":18,"wins":46},"qwen/qwen3.7-plus":{"draws":15,"losses":10,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":50,"wins":56},"qwen/qwen3.8-27b":{"draws":21,"losses":29,"wins":48},"qwen/qwen3.8-flash":{"draws":19,"losses":31,"wins":42},"qwen/qwen3.8-max":{"draws":28,"losses":44,"wins":66},"qwen/qwen3.8-max-0902":{"draws":30,"losses":56,"wins":52},"recursive/flint-v1.0":{"draws":5,"losses":3,"wins":32},"reflection/beam-1.0-501b-a23b":{"draws":27,"losses":34,"wins":65},"stealth/ox-alpha":{"draws":85,"losses":160,"wins":213},"stealth/space-bunny-alpha":{"draws":24,"losses":24,"wins":62},"stepfun/step-3.7-flash":{"draws":13,"losses":16,"wins":71},"stepfun/step-5-preview":{"draws":0,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":17,"losses":17,"wins":40},"tencent/hy4-preview":{"draws":22,"losses":48,"wins":64},"thinkingmachines/inkling":{"draws":40,"losses":23,"wins":123},"thinkingmachines/inkling-small":{"draws":30,"losses":15,"wins":93},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":43,"wins":3},"upstage/solar-mini4":{"draws":2,"losses":5,"wins":29},"x-ai/grok-4.5":{"draws":28,"losses":61,"wins":49},"x-ai/grok-4.6":{"draws":30,"losses":65,"wins":43},"x-ai/grok-4.7":{"draws":9,"losses":85,"wins":26},"x-ai/grok-build-0.1":{"draws":10,"losses":7,"wins":29},"xiaomi/mimo-v2.5":{"draws":53,"losses":19,"wins":140},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":11,"wins":51},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":29,"wins":47},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":42,"wins":37},"z-ai/glm-5.2":{"draws":69,"losses":61,"wins":146},"z-ai/glm-5.3":{"draws":19,"losses":78,"wins":35},"z-ai/glm-5.3-flash":{"draws":21,"losses":57,"wins":60},"z-ai/glm-5.3-flashx":{"draws":27,"losses":57,"wins":54}},"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":28,"losses":141,"wins":77},"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":25,"losses":29,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":36,"wins":71},"deepseek/deepseek-v4.1-flash-1017":{"draws":32,"losses":55,"wins":57},"elorian/glimpse":{"draws":15,"losses":21,"wins":42},"fireworks/ember-1":{"draws":38,"losses":30,"wins":76},"gemini-3.1-pro-preview":{"draws":25,"losses":25,"wins":94},"gemini-4-argon":{"draws":17,"losses":95,"wins":32},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":83},"google/gemini-3.5-flash":{"draws":27,"losses":30,"wins":123},"google/gemini-3.5-flash-lite":{"draws":43,"losses":27,"wins":182},"google/gemini-3.6-flash":{"draws":51,"losses":71,"wins":154},"google/gemini-3.8-flash":{"draws":36,"losses":41,"wins":67},"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":14,"losses":22,"wins":108},"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},"inception/mercury-3":{"draws":24,"losses":22,"wins":50},"inclusionai/ling-3.0-flash":{"draws":16,"losses":5,"wins":81},"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":43,"wins":69},"meta/muse-spark-1.3":{"draws":28,"losses":42,"wins":74},"meta/muse-spark-open":{"draws":22,"losses":47,"wins":69},"meta/muse-wonder":{"draws":18,"losses":39,"wins":39},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":53},"minimax/minimax-m3.1-flash":{"draws":22,"losses":22,"wins":82},"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},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":82,"wins":44},"nex-agi/nex-n2-pro":{"draws":13,"losses":6,"wins":53},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":8,"wins":82},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":10,"wins":44},"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},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":26,"wins":85},"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":{"draws":6,"losses":34,"wins":8},"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":63,"losses":47,"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":18,"losses":39,"wins":13},"claude-fable-5":{"draws":18,"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":38,"losses":78,"wins":12},"claude-opus-4-8":{"draws":17,"losses":47,"wins":10},"claude-opus-5":{"draws":17,"losses":115,"wins":6},"claude-opus-5-5":{"draws":2,"losses":83,"wins":1},"claude-sonnet-5":{"draws":21,"losses":42,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":52,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":32,"losses":42,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":48,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":41,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":45,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":62,"wins":5},"elorian/glimpse":{"draws":9,"losses":23,"wins":10},"fireworks/ember-1":{"draws":16,"losses":55,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":39,"wins":22},"gemini-4-argon":{"draws":2,"losses":75,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":16,"wins":25},"google/gemini-3.5-flash":{"draws":19,"losses":54,"wins":25},"google/gemini-3.5-flash-lite":{"draws":35,"losses":53,"wins":46},"google/gemini-3.6-flash":{"draws":28,"losses":91,"wins":29},"google/gemini-3.8-flash":{"draws":14,"losses":57,"wins":7},"google/gemma-4-31b-it":{"draws":19,"losses":11,"wins":16},"gpt-4.1":{"draws":8,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":5,"losses":1,"wins":2},"gpt-5":{"draws":15,"losses":39,"wins":16},"gpt-5.4":{"draws":14,"losses":45,"wins":15},"gpt-5.4-mini":{"draws":15,"losses":18,"wins":19},"gpt-5.4-nano":{"draws":15,"losses":40,"wins":29},"gpt-5.5":{"draws":22,"losses":40,"wins":10},"gpt-5.6-luna":{"draws":26,"losses":32,"wins":20},"gpt-5.6-sol":{"draws":13,"losses":61,"wins":4},"gpt-5.6-terra":{"draws":16,"losses":45,"wins":13},"gpt-6-astra":{"draws":1,"losses":76,"wins":1},"gpt-6-luna":{"draws":22,"losses":41,"wins":15},"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":24,"losses":11,"wins":19},"inception/mercury-3":{"draws":16,"losses":29,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":15,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":39,"wins":31},"meta/muse-glimmer-30b":{"draws":21,"losses":22,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":51,"wins":10},"meta/muse-spark-1.3":{"draws":8,"losses":63,"wins":7},"meta/muse-spark-open":{"draws":15,"losses":54,"wins":5},"meta/muse-wonder":{"draws":13,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":14,"losses":36,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":13},"mistralai/mistral-medium-3-5":{"draws":12,"losses":14,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":50,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":71,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":14,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":26,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":15,"wins":12},"o3":{"draws":13,"losses":71,"wins":28},"openai/gpt-oss-120b":{"draws":20,"losses":27,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":33,"wins":26},"qwen/qwen3.7-max":{"draws":13,"losses":24,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":18,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":52,"wins":8},"qwen/qwen3.8-27b":{"draws":13,"losses":33,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":25,"wins":18},"qwen/qwen3.8-max":{"draws":19,"losses":46,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":51,"wins":8},"recursive/flint-v1.0":{"draws":7,"losses":8,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":47,"wins":12},"stealth/ox-alpha":{"draws":50,"losses":152,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":34,"wins":15},"stepfun/step-3.7-flash":{"draws":11,"losses":17,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":50,"wins":9},"thinkingmachines/inkling":{"draws":26,"losses":44,"wins":34},"thinkingmachines/inkling-small":{"draws":21,"losses":21,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":25,"wins":1},"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":14,"losses":59,"wins":5},"x-ai/grok-4.6":{"draws":16,"losses":60,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":61,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":11,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":45,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":21,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":32,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":37,"wins":8},"z-ai/glm-5.2":{"draws":41,"losses":75,"wins":40},"z-ai/glm-5.3":{"draws":14,"losses":53,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":48,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":48,"wins":12}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":43,"wins":47},"claude-fable-5":{"draws":23,"losses":83,"wins":20},"claude-fable-5-1":{"draws":8,"losses":131,"wins":5},"claude-haiku-5-5":{"draws":24,"losses":68,"wins":28},"claude-opus-4-5":{"draws":53,"losses":85,"wins":66},"claude-opus-4-8":{"draws":26,"losses":60,"wins":28},"claude-opus-5":{"draws":29,"losses":160,"wins":21},"claude-opus-5-5":{"draws":7,"losses":121,"wins":2},"claude-sonnet-5":{"draws":32,"losses":57,"wins":37},"claude-sonnet-5-5":{"draws":25,"losses":79,"wins":22},"cohere/north-mini-code":{"draws":8,"losses":11,"wins":27},"deepseek/deepseek-v4-flash":{"draws":39,"losses":61,"wins":86},"deepseek/deepseek-v4-pro":{"draws":32,"losses":55,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":55,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":67,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":73,"wins":24},"elorian/glimpse":{"draws":18,"losses":35,"wins":15},"fireworks/ember-1":{"draws":31,"losses":57,"wins":38},"gemini-3.1-pro-preview":{"draws":34,"losses":49,"wins":43},"gemini-4-argon":{"draws":15,"losses":101,"wins":10},"google/gemini-3.1-flash-lite":{"draws":17,"losses":10,"wins":59},"google/gemini-3.5-flash":{"draws":32,"losses":73,"wins":53},"google/gemini-3.5-flash-lite":{"draws":54,"losses":69,"wins":101},"google/gemini-3.6-flash":{"draws":59,"losses":126,"wins":61},"google/gemini-3.8-flash":{"draws":26,"losses":75,"wins":25},"google/gemma-4-31b-it":{"draws":20,"losses":17,"wins":35},"gpt-4.1":{"draws":8,"losses":17,"wins":17},"gpt-4.1-nano":{"draws":9,"losses":1,"wins":6},"gpt-5":{"draws":25,"losses":51,"wins":34},"gpt-5.4":{"draws":24,"losses":73,"wins":25},"gpt-5.4-mini":{"draws":32,"losses":18,"wins":34},"gpt-5.4-nano":{"draws":16,"losses":49,"wins":57},"gpt-5.5":{"draws":38,"losses":50,"wins":28},"gpt-5.6-luna":{"draws":30,"losses":46,"wins":50},"gpt-5.6-sol":{"draws":15,"losses":86,"wins":25},"gpt-5.6-terra":{"draws":32,"losses":51,"wins":37},"gpt-6-astra":{"draws":9,"losses":117,"wins":0},"gpt-6-luna":{"draws":26,"losses":56,"wins":44},"gpt-6-sol":{"draws":15,"losses":102,"wins":9},"gpt-6.1-sol":{"draws":12,"losses":112,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":11,"wins":47},"inception/mercury-3":{"draws":18,"losses":39,"wins":21},"inclusionai/ling-3.0-flash":{"draws":23,"losses":18,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":30,"losses":40,"wins":66},"meta/muse-glimmer-30b":{"draws":28,"losses":27,"wins":55},"meta/muse-spark-1.2":{"draws":25,"losses":56,"wins":39},"meta/muse-spark-1.3":{"draws":19,"losses":78,"wins":29},"meta/muse-spark-open":{"draws":22,"losses":66,"wins":34},"meta/muse-wonder":{"draws":22,"losses":82,"wins":22},"minimax/minimax-m3":{"draws":14,"losses":16,"wins":36},"minimax/minimax-m3.1-flash":{"draws":12,"losses":32,"wins":32},"mistralai/mistral-large-4-0":{"draws":16,"losses":38,"wins":24},"mistralai/mistral-medium-3-5":{"draws":19,"losses":13,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":14,"wins":11},"moonshotai/kimi-k3":{"draws":29,"losses":51,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":99,"wins":15},"nex-agi/nex-n2-pro":{"draws":17,"losses":14,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":31,"wins":46},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":20,"wins":20},"o3":{"draws":20,"losses":81,"wins":75},"openai/gpt-oss-120b":{"draws":26,"losses":29,"wins":53},"poolside/laguna-s-2.1":{"draws":25,"losses":40,"wins":51},"qwen/qwen3.7-max":{"draws":11,"losses":31,"wins":30},"qwen/qwen3.7-plus":{"draws":11,"losses":16,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":62,"wins":29},"qwen/qwen3.8-27b":{"draws":20,"losses":39,"wins":35},"qwen/qwen3.8-flash":{"draws":23,"losses":34,"wins":27},"qwen/qwen3.8-max":{"draws":30,"losses":59,"wins":37},"qwen/qwen3.8-max-0902":{"draws":31,"losses":65,"wins":30},"recursive/flint-v1.0":{"draws":10,"losses":7,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":46,"wins":40},"stealth/ox-alpha":{"draws":87,"losses":224,"wins":115},"stealth/space-bunny-alpha":{"draws":24,"losses":41,"wins":37},"stepfun/step-3.7-flash":{"draws":12,"losses":26,"wins":54},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":16,"losses":28,"wins":22},"tencent/hy4-preview":{"draws":26,"losses":55,"wins":41},"thinkingmachines/inkling":{"draws":41,"losses":52,"wins":81},"thinkingmachines/inkling-small":{"draws":35,"losses":32,"wins":59},"unbiased/pareto-26.10":{"draws":1,"losses":40,"wins":1},"unbiased/pareto-26.10-preview":{"draws":1,"losses":40,"wins":1},"upstage/solar-mini4":{"draws":6,"losses":6,"wins":24},"x-ai/grok-4.5":{"draws":32,"losses":63,"wins":31},"x-ai/grok-4.6":{"draws":35,"losses":64,"wins":27},"x-ai/grok-4.7":{"draws":10,"losses":77,"wins":21},"x-ai/grok-build-0.1":{"draws":13,"losses":11,"wins":18},"xiaomi/mimo-v2.5":{"draws":46,"losses":55,"wins":91},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":29,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":44,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":50,"wins":19},"z-ai/glm-5.2":{"draws":62,"losses":97,"wins":93},"z-ai/glm-5.3":{"draws":17,"losses":78,"wins":25},"z-ai/glm-5.3-flash":{"draws":16,"losses":67,"wins":43},"z-ai/glm-5.3-flashx":{"draws":22,"losses":75,"wins":29}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":33},"claude-fable-5":{"draws":21,"losses":49,"wins":20},"claude-fable-5-1":{"draws":5,"losses":89,"wins":8},"claude-haiku-5-5":{"draws":29,"losses":29,"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":117,"wins":21},"claude-opus-5-5":{"draws":14,"losses":80,"wins":4},"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":43,"losses":20,"wins":71},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":51,"wins":23},"elorian/glimpse":{"draws":12,"losses":17,"wins":21},"fireworks/ember-1":{"draws":26,"losses":31,"wins":33},"gemini-3.1-pro-preview":{"draws":22,"losses":35,"wins":33},"gemini-4-argon":{"draws":8,"losses":73,"wins":9},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":37,"losses":36,"wins":39},"google/gemini-3.5-flash-lite":{"draws":50,"losses":29,"wins":77},"google/gemini-3.6-flash":{"draws":41,"losses":72,"wins":59},"google/gemini-3.8-flash":{"draws":29,"losses":36,"wins":25},"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":29,"losses":10,"wins":21},"gpt-5.4-nano":{"draws":17,"losses":24,"wins":47},"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},"inception/mercury-3":{"draws":17,"losses":25,"wins":18},"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":18,"losses":44,"wins":26},"meta/muse-spark-1.3":{"draws":24,"losses":44,"wins":22},"meta/muse-spark-open":{"draws":16,"losses":46,"wins":24},"meta/muse-wonder":{"draws":19,"losses":48,"wins":23},"minimax/minimax-m3":{"draws":12,"losses":13,"wins":25},"minimax/minimax-m3.1-flash":{"draws":16,"losses":24,"wins":38},"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":29,"losses":31,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":72,"wins":10},"nex-agi/nex-n2-pro":{"draws":13,"losses":5,"wins":26},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":4,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":18,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":11,"wins":17},"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},"recursive/flint-v1.0":{"draws":6,"losses":3,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":33,"wins":26},"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":{"draws":3,"losses":26,"wins":1},"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":30,"losses":29,"wins":19},"claude-fable-5":{"draws":17,"losses":61,"wins":6},"claude-fable-5-1":{"draws":6,"losses":87,"wins":1},"claude-haiku-5-5":{"draws":21,"losses":55,"wins":4},"claude-opus-4-5":{"draws":40,"losses":85,"wins":11},"claude-opus-4-8":{"draws":21,"losses":49,"wins":6},"claude-opus-5":{"draws":23,"losses":109,"wins":12},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":26,"losses":47,"wins":11},"claude-sonnet-5-5":{"draws":18,"losses":58,"wins":8},"cohere/north-mini-code":{"draws":9,"losses":12,"wins":11},"deepseek/deepseek-v4-flash":{"draws":46,"losses":48,"wins":30},"deepseek/deepseek-v4-pro":{"draws":19,"losses":46,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":43,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":51,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":63,"wins":5},"elorian/glimpse":{"draws":9,"losses":28,"wins":7},"fireworks/ember-1":{"draws":23,"losses":52,"wins":9},"gemini-3.1-pro-preview":{"draws":25,"losses":46,"wins":13},"gemini-4-argon":{"draws":3,"losses":79,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":14,"wins":25},"google/gemini-3.5-flash":{"draws":25,"losses":63,"wins":16},"google/gemini-3.5-flash-lite":{"draws":42,"losses":67,"wins":39},"google/gemini-3.6-flash":{"draws":45,"losses":95,"wins":20},"google/gemini-3.8-flash":{"draws":17,"losses":61,"wins":6},"google/gemma-4-31b-it":{"draws":22,"losses":21,"wins":7},"gpt-4.1":{"draws":10,"losses":13,"wins":5},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":4},"gpt-5":{"draws":19,"losses":37,"wins":16},"gpt-5.4":{"draws":22,"losses":45,"wins":13},"gpt-5.4-mini":{"draws":21,"losses":25,"wins":10},"gpt-5.4-nano":{"draws":15,"losses":48,"wins":19},"gpt-5.5":{"draws":23,"losses":44,"wins":9},"gpt-5.6-luna":{"draws":30,"losses":42,"wins":12},"gpt-5.6-sol":{"draws":13,"losses":66,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":49,"wins":11},"gpt-6-astra":{"draws":6,"losses":78,"wins":0},"gpt-6-luna":{"draws":27,"losses":50,"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":26,"losses":18,"wins":18},"inception/mercury-3":{"draws":16,"losses":34,"wins":6},"inclusionai/ling-3.0-flash":{"draws":21,"losses":19,"wins":18},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":29,"losses":39,"wins":24},"meta/muse-glimmer-30b":{"draws":27,"losses":31,"wins":14},"meta/muse-spark-1.2":{"draws":21,"losses":47,"wins":12},"meta/muse-spark-1.3":{"draws":16,"losses":64,"wins":4},"meta/muse-spark-open":{"draws":17,"losses":55,"wins":8},"meta/muse-wonder":{"draws":16,"losses":62,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":18,"wins":14},"minimax/minimax-m3.1-flash":{"draws":19,"losses":40,"wins":13},"mistralai/mistral-large-4-0":{"draws":22,"losses":23,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":23,"losses":48,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":78,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":32,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":20,"wins":5},"o3":{"draws":23,"losses":72,"wins":15},"openai/gpt-oss-120b":{"draws":30,"losses":28,"wins":16},"poolside/laguna-s-2.1":{"draws":25,"losses":39,"wins":18},"qwen/qwen3.7-max":{"draws":18,"losses":25,"wins":5},"qwen/qwen3.7-plus":{"draws":15,"losses":14,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":59,"wins":3},"qwen/qwen3.8-27b":{"draws":19,"losses":35,"wins":4},"qwen/qwen3.8-flash":{"draws":18,"losses":31,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":51,"wins":10},"qwen/qwen3.8-max-0902":{"draws":24,"losses":52,"wins":8},"recursive/flint-v1.0":{"draws":8,"losses":8,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":51,"wins":8},"stealth/ox-alpha":{"draws":66,"losses":173,"wins":43},"stealth/space-bunny-alpha":{"draws":18,"losses":36,"wins":12},"stepfun/step-3.7-flash":{"draws":19,"losses":24,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":16,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":49,"wins":12},"thinkingmachines/inkling":{"draws":35,"losses":49,"wins":26},"thinkingmachines/inkling-small":{"draws":33,"losses":32,"wins":19},"unbiased/pareto-26.10":{"draws":3,"losses":25,"wins":0},"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":19,"losses":58,"wins":7},"x-ai/grok-4.6":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":3},"x-ai/grok-build-0.1":{"draws":12,"losses":13,"wins":3},"xiaomi/mimo-v2.5":{"draws":50,"losses":49,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":24,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":37,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":42,"wins":7},"z-ai/glm-5.2":{"draws":61,"losses":83,"wins":24},"z-ai/glm-5.3":{"draws":13,"losses":66,"wins":3},"z-ai/glm-5.3-flash":{"draws":22,"losses":51,"wins":11},"z-ai/glm-5.3-flashx":{"draws":15,"losses":60,"wins":9}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":5,"losses":27,"wins":4},"claude-fable-5-1":{"draws":2,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":17,"losses":30,"wins":13},"claude-opus-4-8":{"draws":8,"losses":21,"wins":7},"claude-opus-5":{"draws":8,"losses":57,"wins":3},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":11,"losses":9,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":20,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":12,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":9,"wins":7},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":7,"losses":18,"wins":11},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":18,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":32},"google/gemini-3.6-flash":{"draws":19,"losses":32,"wins":17},"google/gemini-3.8-flash":{"draws":4,"losses":15,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":5,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":13},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":18},"gpt-5.5":{"draws":9,"losses":12,"wins":13},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":18},"gpt-5.6-sol":{"draws":4,"losses":25,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":13,"wins":12},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":11,"losses":13,"wins":12},"gpt-6-sol":{"draws":5,"losses":28,"wins":3},"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":10,"losses":2,"wins":14},"inception/mercury-3":{"draws":6,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":8,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":13,"wins":16},"meta/muse-spark-open":{"draws":7,"losses":21,"wins":6},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":14},"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":11,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":8},"o3":{"draws":5,"losses":22,"wins":23},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":16,"wins":8},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":9},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":13},"stealth/ox-alpha":{"draws":21,"losses":54,"wins":27},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":7,"losses":25,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":19,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":24,"wins":31},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":15}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":32,"wins":60},"claude-fable-5":{"draws":24,"losses":86,"wins":28},"claude-fable-5-1":{"draws":7,"losses":138,"wins":11},"claude-haiku-5-5":{"draws":34,"losses":59,"wins":39},"claude-opus-4-5":{"draws":74,"losses":68,"wins":82},"claude-opus-4-8":{"draws":34,"losses":49,"wins":43},"claude-opus-5":{"draws":36,"losses":168,"wins":40},"claude-opus-5-5":{"draws":4,"losses":136,"wins":10},"claude-sonnet-5":{"draws":38,"losses":42,"wins":58},"claude-sonnet-5-5":{"draws":28,"losses":64,"wins":46},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":35},"deepseek/deepseek-v4-flash":{"draws":59,"losses":41,"wins":106},"deepseek/deepseek-v4-pro":{"draws":28,"losses":40,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":51,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":58,"wins":45},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":81,"wins":39},"elorian/glimpse":{"draws":19,"losses":31,"wins":26},"fireworks/ember-1":{"draws":42,"losses":57,"wins":39},"gemini-3.1-pro-preview":{"draws":34,"losses":39,"wins":65},"gemini-4-argon":{"draws":6,"losses":117,"wins":15},"google/gemini-3.1-flash-lite":{"draws":25,"losses":9,"wins":56},"google/gemini-3.5-flash":{"draws":47,"losses":58,"wins":67},"google/gemini-3.5-flash-lite":{"draws":75,"losses":47,"wins":118},"google/gemini-3.6-flash":{"draws":70,"losses":105,"wins":89},"google/gemini-3.8-flash":{"draws":31,"losses":73,"wins":34},"google/gemma-4-31b-it":{"draws":29,"losses":13,"wins":38},"gpt-4.1":{"draws":13,"losses":11,"wins":22},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":8},"gpt-5":{"draws":28,"losses":44,"wins":50},"gpt-5.4":{"draws":25,"losses":69,"wins":38},"gpt-5.4-mini":{"draws":29,"losses":21,"wins":42},"gpt-5.4-nano":{"draws":32,"losses":34,"wins":70},"gpt-5.5":{"draws":34,"losses":48,"wins":46},"gpt-5.6-luna":{"draws":46,"losses":30,"wins":62},"gpt-5.6-sol":{"draws":23,"losses":85,"wins":30},"gpt-5.6-terra":{"draws":37,"losses":45,"wins":50},"gpt-6-astra":{"draws":11,"losses":118,"wins":9},"gpt-6-luna":{"draws":43,"losses":43,"wins":52},"gpt-6-sol":{"draws":14,"losses":98,"wins":26},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":44,"losses":8,"wins":44},"inception/mercury-3":{"draws":26,"losses":36,"wins":30},"inclusionai/ling-3.0-flash":{"draws":27,"losses":13,"wins":56},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":26,"wins":83},"meta/muse-glimmer-30b":{"draws":32,"losses":19,"wins":73},"meta/muse-spark-1.2":{"draws":28,"losses":56,"wins":50},"meta/muse-spark-1.3":{"draws":29,"losses":66,"wins":43},"meta/muse-spark-open":{"draws":30,"losses":58,"wins":44},"meta/muse-wonder":{"draws":26,"losses":85,"wins":27},"minimax/minimax-m3":{"draws":12,"losses":14,"wins":50},"minimax/minimax-m3.1-flash":{"draws":29,"losses":40,"wins":51},"mistralai/mistral-large-4-0":{"draws":29,"losses":28,"wins":31},"mistralai/mistral-medium-3-5":{"draws":23,"losses":9,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":15,"wins":11},"moonshotai/kimi-k3":{"draws":26,"losses":31,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":108,"wins":18},"nex-agi/nex-n2-pro":{"draws":15,"losses":10,"wins":43},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":6,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":28,"wins":58},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":16,"wins":29},"o3":{"draws":27,"losses":73,"wins":86},"openai/gpt-oss-120b":{"draws":34,"losses":19,"wins":69},"poolside/laguna-s-2.1":{"draws":40,"losses":24,"wins":70},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":43},"qwen/qwen3.7-plus":{"draws":24,"losses":14,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":52,"wins":51},"qwen/qwen3.8-27b":{"draws":27,"losses":28,"wins":41},"qwen/qwen3.8-flash":{"draws":25,"losses":32,"wins":35},"qwen/qwen3.8-max":{"draws":36,"losses":55,"wins":47},"qwen/qwen3.8-max-0902":{"draws":31,"losses":73,"wins":34},"recursive/flint-v1.0":{"draws":10,"losses":3,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":41,"wins":52},"stealth/ox-alpha":{"draws":103,"losses":185,"wins":170},"stealth/space-bunny-alpha":{"draws":35,"losses":22,"wins":53},"stepfun/step-3.7-flash":{"draws":21,"losses":16,"wins":59},"stepfun/step-5-preview":{"draws":2,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":28,"losses":20,"wins":28},"tencent/hy4-preview":{"draws":31,"losses":56,"wins":45},"thinkingmachines/inkling":{"draws":53,"losses":40,"wins":93},"thinkingmachines/inkling-small":{"draws":44,"losses":21,"wins":73},"unbiased/pareto-26.10":{"draws":3,"losses":42,"wins":1},"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":28,"losses":66,"wins":44},"x-ai/grok-4.6":{"draws":31,"losses":73,"wins":34},"x-ai/grok-4.7":{"draws":10,"losses":83,"wins":29},"x-ai/grok-build-0.1":{"draws":17,"losses":4,"wins":25},"xiaomi/mimo-v2.5":{"draws":74,"losses":31,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":22,"wins":35},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":37,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":50,"wins":24},"z-ai/glm-5.2":{"draws":88,"losses":75,"wins":113},"z-ai/glm-5.3":{"draws":30,"losses":63,"wins":39},"z-ai/glm-5.3-flash":{"draws":27,"losses":68,"wins":43},"z-ai/glm-5.3-flashx":{"draws":33,"losses":66,"wins":39}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":8,"wins":105},"claude-fable-5":{"draws":11,"losses":35,"wins":98},"claude-fable-5-1":{"draws":15,"losses":104,"wins":43},"claude-haiku-5-5":{"draws":16,"losses":23,"wins":99},"claude-opus-4-5":{"draws":25,"losses":20,"wins":189},"claude-opus-4-8":{"draws":13,"losses":13,"wins":106},"claude-opus-5":{"draws":26,"losses":109,"wins":111},"claude-opus-5-5":{"draws":12,"losses":94,"wins":50},"claude-sonnet-5":{"draws":15,"losses":11,"wins":118},"claude-sonnet-5-5":{"draws":14,"losses":40,"wins":90},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":53},"deepseek/deepseek-v4-flash":{"draws":19,"losses":9,"wins":188},"deepseek/deepseek-v4-pro":{"draws":13,"losses":16,"wins":103},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":105},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":25,"wins":96},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":29,"wins":102},"elorian/glimpse":{"draws":7,"losses":15,"wins":56},"fireworks/ember-1":{"draws":15,"losses":14,"wins":115},"gemini-3.1-pro-preview":{"draws":15,"losses":24,"wins":105},"gemini-4-argon":{"draws":15,"losses":72,"wins":57},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":91},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":148},"google/gemini-3.5-flash-lite":{"draws":31,"losses":12,"wins":209},"google/gemini-3.6-flash":{"draws":29,"losses":44,"wins":203},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":103},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":73},"gpt-4.1":{"draws":2,"losses":3,"wins":43},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":15},"gpt-5":{"draws":9,"losses":14,"wins":103},"gpt-5.4":{"draws":12,"losses":27,"wins":99},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":81},"gpt-5.4-nano":{"draws":11,"losses":5,"wins":128},"gpt-5.5":{"draws":10,"losses":28,"wins":94},"gpt-5.6-luna":{"draws":9,"losses":13,"wins":122},"gpt-5.6-sol":{"draws":12,"losses":35,"wins":97},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":112},"gpt-6-astra":{"draws":11,"losses":95,"wins":38},"gpt-6-luna":{"draws":14,"losses":11,"wins":119},"gpt-6-sol":{"draws":17,"losses":45,"wins":82},"gpt-6.1-sol":{"draws":14,"losses":83,"wins":47},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":3,"wins":81},"inception/mercury-3":{"draws":13,"losses":12,"wins":71},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":84},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":12,"wins":133},"meta/muse-glimmer-30b":{"draws":20,"losses":5,"wins":101},"meta/muse-spark-1.2":{"draws":13,"losses":17,"wins":108},"meta/muse-spark-1.3":{"draws":11,"losses":20,"wins":113},"meta/muse-spark-open":{"draws":12,"losses":16,"wins":110},"meta/muse-wonder":{"draws":18,"losses":44,"wins":82},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":71},"minimax/minimax-m3.1-flash":{"draws":12,"losses":15,"wins":99},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":72},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":78},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":32},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":108},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":43,"wins":43},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":61},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":108},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":56},"o3":{"draws":6,"losses":18,"wins":174},"openai/gpt-oss-120b":{"draws":15,"losses":5,"wins":106},"poolside/laguna-s-2.1":{"draws":18,"losses":11,"wins":109},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":69},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":108},"qwen/qwen3.8-27b":{"draws":12,"losses":8,"wins":82},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":75},"qwen/qwen3.8-max":{"draws":6,"losses":24,"wins":114},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":112},"recursive/flint-v1.0":{"draws":7,"losses":0,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":12,"wins":111},"stealth/ox-alpha":{"draws":54,"losses":68,"wins":352},"stealth/space-bunny-alpha":{"draws":7,"losses":10,"wins":97},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":96},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":63},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":103},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":163},"thinkingmachines/inkling-small":{"draws":11,"losses":9,"wins":124},"unbiased/pareto-26.10":{"draws":5,"losses":28,"wins":15},"unbiased/pareto-26.10-preview":{"draws":5,"losses":27,"wins":16},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":36},"x-ai/grok-4.5":{"draws":19,"losses":27,"wins":98},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":105},"x-ai/grok-4.7":{"draws":11,"losses":46,"wins":69},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":37},"xiaomi/mimo-v2.5":{"draws":26,"losses":6,"wins":190},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":65},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":10,"wins":70},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":27,"wins":53},"z-ai/glm-5.2":{"draws":32,"losses":26,"wins":230},"z-ai/glm-5.3":{"draws":19,"losses":38,"wins":81},"z-ai/glm-5.3-flash":{"draws":16,"losses":24,"wins":104},"z-ai/glm-5.3-flashx":{"draws":12,"losses":22,"wins":110}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":36,"wins":16},"claude-fable-5":{"draws":12,"losses":58,"wins":2},"claude-fable-5-1":{"draws":4,"losses":77,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":44,"wins":10},"claude-opus-4-5":{"draws":26,"losses":75,"wins":15},"claude-opus-4-8":{"draws":13,"losses":46,"wins":5},"claude-opus-5":{"draws":4,"losses":109,"wins":3},"claude-opus-5-5":{"draws":6,"losses":74,"wins":0},"claude-sonnet-5":{"draws":20,"losses":42,"wins":10},"claude-sonnet-5-5":{"draws":15,"losses":47,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":12,"wins":17},"deepseek/deepseek-v4-flash":{"draws":21,"losses":54,"wins":33},"deepseek/deepseek-v4-pro":{"draws":15,"losses":37,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":40,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":51,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":53,"wins":7},"elorian/glimpse":{"draws":8,"losses":20,"wins":10},"fireworks/ember-1":{"draws":19,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":19,"losses":42,"wins":11},"gemini-4-argon":{"draws":8,"losses":59,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":14,"wins":30},"google/gemini-3.5-flash":{"draws":17,"losses":53,"wins":20},"google/gemini-3.5-flash-lite":{"draws":24,"losses":57,"wins":47},"google/gemini-3.6-flash":{"draws":21,"losses":94,"wins":23},"google/gemini-3.8-flash":{"draws":12,"losses":54,"wins":6},"google/gemma-4-31b-it":{"draws":17,"losses":16,"wins":11},"gpt-4.1":{"draws":3,"losses":16,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":32,"wins":22},"gpt-5.4":{"draws":16,"losses":38,"wins":16},"gpt-5.4-mini":{"draws":15,"losses":16,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":35,"wins":27},"gpt-5.5":{"draws":13,"losses":44,"wins":9},"gpt-5.6-luna":{"draws":15,"losses":40,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":59,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":41,"wins":14},"gpt-6-astra":{"draws":4,"losses":68,"wins":0},"gpt-6-luna":{"draws":13,"losses":45,"wins":14},"gpt-6-sol":{"draws":7,"losses":62,"wins":3},"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":16,"losses":17,"wins":19},"inception/mercury-3":{"draws":10,"losses":30,"wins":8},"inclusionai/ling-3.0-flash":{"draws":13,"losses":17,"wins":18},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":45,"wins":31},"meta/muse-glimmer-30b":{"draws":18,"losses":22,"wins":22},"meta/muse-spark-1.2":{"draws":11,"losses":46,"wins":11},"meta/muse-spark-1.3":{"draws":9,"losses":55,"wins":8},"meta/muse-spark-open":{"draws":12,"losses":49,"wins":9},"meta/muse-wonder":{"draws":13,"losses":53,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":17,"wins":14},"minimax/minimax-m3.1-flash":{"draws":17,"losses":31,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":25,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":43,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":61,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":9,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":10,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":28,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":10},"o3":{"draws":8,"losses":76,"wins":22},"openai/gpt-oss-120b":{"draws":15,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":17,"losses":31,"wins":24},"qwen/qwen3.7-max":{"draws":9,"losses":25,"wins":8},"qwen/qwen3.7-plus":{"draws":5,"losses":18,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":48,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":28,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":46,"wins":8},"qwen/qwen3.8-max-0902":{"draws":18,"losses":44,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":8,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":42,"wins":12},"stealth/ox-alpha":{"draws":53,"losses":164,"wins":33},"stealth/space-bunny-alpha":{"draws":16,"losses":29,"wins":13},"stepfun/step-3.7-flash":{"draws":8,"losses":27,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":10,"wins":15},"tencent/hy4-preview":{"draws":12,"losses":49,"wins":9},"thinkingmachines/inkling":{"draws":23,"losses":42,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":32,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":24,"wins":0},"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":12,"losses":51,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":52,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":11,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":47,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":18,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":31,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":36,"wins":4},"z-ai/glm-5.2":{"draws":44,"losses":73,"wins":27},"z-ai/glm-5.3":{"draws":11,"losses":57,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":50,"wins":10},"z-ai/glm-5.3-flashx":{"draws":10,"losses":52,"wins":10}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":10,"wins":9},"claude-fable-5":{"draws":2,"losses":22,"wins":6},"claude-fable-5-1":{"draws":0,"losses":35,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":16,"wins":6},"claude-opus-4-5":{"draws":11,"losses":29,"wins":8},"claude-opus-4-8":{"draws":3,"losses":19,"wins":4},"claude-opus-5":{"draws":4,"losses":46,"wins":2},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":8,"losses":15,"wins":7},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4-pro":{"draws":7,"losses":16,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":17,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":23,"wins":2},"elorian/glimpse":{"draws":3,"losses":12,"wins":3},"fireworks/ember-1":{"draws":5,"losses":20,"wins":5},"gemini-3.1-pro-preview":{"draws":6,"losses":16,"wins":8},"gemini-4-argon":{"draws":0,"losses":29,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":5,"losses":17,"wins":14},"google/gemini-3.5-flash-lite":{"draws":13,"losses":18,"wins":17},"google/gemini-3.6-flash":{"draws":9,"losses":33,"wins":14},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":11},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":15,"wins":6},"gpt-5.4":{"draws":8,"losses":10,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":14},"gpt-5.5":{"draws":5,"losses":16,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":13},"gpt-5.6-sol":{"draws":2,"losses":26,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":11,"wins":11},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":7,"losses":15,"wins":8},"gpt-6-sol":{"draws":1,"losses":25,"wins":4},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":4,"wins":8},"inception/mercury-3":{"draws":6,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":17},"meta/muse-glimmer-30b":{"draws":8,"losses":10,"wins":10},"meta/muse-spark-1.2":{"draws":7,"losses":19,"wins":4},"meta/muse-spark-1.3":{"draws":3,"losses":21,"wins":6},"meta/muse-spark-open":{"draws":4,"losses":20,"wins":4},"meta/muse-wonder":{"draws":6,"losses":19,"wins":5},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":7},"mistralai/mistral-large-4-0":{"draws":7,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":17,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":27,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":7,"wins":6},"o3":{"draws":3,"losses":22,"wins":15},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":16},"poolside/laguna-s-2.1":{"draws":10,"losses":11,"wins":9},"qwen/qwen3.7-max":{"draws":3,"losses":10,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":16,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":11},"stealth/ox-alpha":{"draws":26,"losses":62,"wins":20},"stealth/space-bunny-alpha":{"draws":4,"losses":14,"wins":6},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":6},"thinkingmachines/inkling":{"draws":9,"losses":12,"wins":17},"thinkingmachines/inkling-small":{"draws":9,"losses":11,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.5":{"draws":6,"losses":21,"wins":3},"x-ai/grok-4.6":{"draws":5,"losses":22,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":26,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":11,"losses":9,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":15,"wins":1},"z-ai/glm-5.2":{"draws":16,"losses":23,"wins":21},"z-ai/glm-5.3":{"draws":3,"losses":24,"wins":3},"z-ai/glm-5.3-flash":{"draws":4,"losses":21,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":17,"wins":8}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":43,"wins":37},"claude-fable-5":{"draws":20,"losses":93,"wins":13},"claude-fable-5-1":{"draws":8,"losses":127,"wins":1},"claude-haiku-5-5":{"draws":32,"losses":66,"wins":26},"claude-opus-4-5":{"draws":69,"losses":109,"wins":30},"claude-opus-4-8":{"draws":22,"losses":80,"wins":20},"claude-opus-5":{"draws":26,"losses":183,"wins":5},"claude-opus-5-5":{"draws":4,"losses":136,"wins":2},"claude-sonnet-5":{"draws":42,"losses":55,"wins":29},"claude-sonnet-5-5":{"draws":22,"losses":82,"wins":22},"cohere/north-mini-code":{"draws":15,"losses":13,"wins":20},"deepseek/deepseek-v4-flash":{"draws":55,"losses":80,"wins":59},"deepseek/deepseek-v4-pro":{"draws":35,"losses":55,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":59,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":61,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":22,"losses":94,"wins":10},"elorian/glimpse":{"draws":15,"losses":44,"wins":7},"fireworks/ember-1":{"draws":41,"losses":62,"wins":23},"gemini-3.1-pro-preview":{"draws":42,"losses":53,"wins":31},"gemini-4-argon":{"draws":9,"losses":114,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":27,"wins":45},"google/gemini-3.5-flash":{"draws":36,"losses":86,"wins":38},"google/gemini-3.5-flash-lite":{"draws":67,"losses":77,"wins":76},"google/gemini-3.6-flash":{"draws":63,"losses":134,"wins":41},"google/gemini-3.8-flash":{"draws":33,"losses":84,"wins":9},"google/gemma-4-31b-it":{"draws":40,"losses":18,"wins":18},"gpt-4.1":{"draws":18,"losses":16,"wins":8},"gpt-4.1-nano":{"draws":8,"losses":2,"wins":4},"gpt-5":{"draws":34,"losses":57,"wins":19},"gpt-5.4":{"draws":36,"losses":72,"wins":12},"gpt-5.4-mini":{"draws":29,"losses":26,"wins":29},"gpt-5.4-nano":{"draws":25,"losses":65,"wins":50},"gpt-5.5":{"draws":44,"losses":58,"wins":12},"gpt-5.6-luna":{"draws":38,"losses":55,"wins":33},"gpt-5.6-sol":{"draws":16,"losses":100,"wins":10},"gpt-5.6-terra":{"draws":37,"losses":60,"wins":23},"gpt-6-astra":{"draws":9,"losses":116,"wins":1},"gpt-6-luna":{"draws":41,"losses":60,"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":38,"losses":26,"wins":28},"inception/mercury-3":{"draws":29,"losses":41,"wins":18},"inclusionai/ling-3.0-flash":{"draws":35,"losses":26,"wins":31},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":50,"wins":44},"meta/muse-glimmer-30b":{"draws":41,"losses":33,"wins":34},"meta/muse-spark-1.2":{"draws":32,"losses":69,"wins":19},"meta/muse-spark-1.3":{"draws":29,"losses":84,"wins":13},"meta/muse-spark-open":{"draws":28,"losses":76,"wins":16},"meta/muse-wonder":{"draws":36,"losses":82,"wins":8},"minimax/minimax-m3":{"draws":21,"losses":25,"wins":26},"minimax/minimax-m3.1-flash":{"draws":27,"losses":46,"wins":31},"mistralai/mistral-large-4-0":{"draws":28,"losses":32,"wins":18},"mistralai/mistral-medium-3-5":{"draws":26,"losses":16,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":20,"wins":5},"moonshotai/kimi-k3":{"draws":34,"losses":58,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":108,"wins":5},"nex-agi/nex-n2-pro":{"draws":13,"losses":21,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":11,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":28,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":33,"wins":12},"o3":{"draws":33,"losses":107,"wins":44},"openai/gpt-oss-120b":{"draws":40,"losses":40,"wins":30},"poolside/laguna-s-2.1":{"draws":40,"losses":44,"wins":40},"qwen/qwen3.7-max":{"draws":26,"losses":29,"wins":23},"qwen/qwen3.7-plus":{"draws":17,"losses":28,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":67,"wins":14},"qwen/qwen3.8-27b":{"draws":26,"losses":43,"wins":19},"qwen/qwen3.8-flash":{"draws":27,"losses":36,"wins":21},"qwen/qwen3.8-max":{"draws":36,"losses":68,"wins":22},"qwen/qwen3.8-max-0902":{"draws":42,"losses":70,"wins":14},"recursive/flint-v1.0":{"draws":10,"losses":13,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":27,"losses":69,"wins":18},"stealth/ox-alpha":{"draws":84,"losses":228,"wins":62},"stealth/space-bunny-alpha":{"draws":35,"losses":40,"wins":23},"stepfun/step-3.7-flash":{"draws":25,"losses":32,"wins":33},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":37,"losses":21,"wins":14},"tencent/hy4-preview":{"draws":33,"losses":67,"wins":20},"thinkingmachines/inkling":{"draws":46,"losses":54,"wins":62},"thinkingmachines/inkling-small":{"draws":39,"losses":38,"wins":49},"unbiased/pareto-26.10":{"draws":2,"losses":40,"wins":0},"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":29,"losses":84,"wins":13},"x-ai/grok-4.6":{"draws":40,"losses":74,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":99,"wins":9},"x-ai/grok-build-0.1":{"draws":15,"losses":15,"wins":12},"xiaomi/mimo-v2.5":{"draws":76,"losses":65,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":36,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":49,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":56,"wins":10},"z-ai/glm-5.2":{"draws":76,"losses":111,"wins":65},"z-ai/glm-5.3":{"draws":20,"losses":91,"wins":9},"z-ai/glm-5.3-flash":{"draws":22,"losses":64,"wins":40},"z-ai/glm-5.3-flashx":{"draws":24,"losses":80,"wins":22}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":22},"claude-fable-5":{"draws":13,"losses":49,"wins":4},"claude-fable-5-1":{"draws":4,"losses":71,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":33,"wins":20},"claude-opus-4-5":{"draws":36,"losses":39,"wins":33},"claude-opus-4-8":{"draws":15,"losses":35,"wins":12},"claude-opus-5":{"draws":18,"losses":81,"wins":15},"claude-opus-5-5":{"draws":4,"losses":66,"wins":4},"claude-sonnet-5":{"draws":18,"losses":31,"wins":17},"claude-sonnet-5-5":{"draws":16,"losses":39,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":22},"deepseek/deepseek-v4-flash":{"draws":22,"losses":32,"wins":44},"deepseek/deepseek-v4-pro":{"draws":17,"losses":25,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":23,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":34,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":41,"wins":11},"elorian/glimpse":{"draws":11,"losses":17,"wins":10},"fireworks/ember-1":{"draws":18,"losses":29,"wins":19},"gemini-3.1-pro-preview":{"draws":15,"losses":26,"wins":25},"gemini-4-argon":{"draws":4,"losses":55,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":31},"google/gemini-3.5-flash":{"draws":18,"losses":35,"wins":31},"google/gemini-3.5-flash-lite":{"draws":36,"losses":25,"wins":55},"google/gemini-3.6-flash":{"draws":33,"losses":62,"wins":31},"google/gemini-3.8-flash":{"draws":10,"losses":38,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":22},"gpt-4.1":{"draws":6,"losses":7,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":23,"wins":22},"gpt-5.4":{"draws":16,"losses":34,"wins":14},"gpt-5.4-mini":{"draws":14,"losses":6,"wins":24},"gpt-5.4-nano":{"draws":11,"losses":24,"wins":29},"gpt-5.5":{"draws":23,"losses":29,"wins":10},"gpt-5.6-luna":{"draws":21,"losses":17,"wins":28},"gpt-5.6-sol":{"draws":9,"losses":44,"wins":13},"gpt-5.6-terra":{"draws":24,"losses":22,"wins":18},"gpt-6-astra":{"draws":2,"losses":64,"wins":0},"gpt-6-luna":{"draws":18,"losses":33,"wins":15},"gpt-6-sol":{"draws":7,"losses":52,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":58,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":6,"wins":25},"inception/mercury-3":{"draws":13,"losses":21,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":10,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":22,"losses":16,"wins":36},"meta/muse-glimmer-30b":{"draws":18,"losses":11,"wins":31},"meta/muse-spark-1.2":{"draws":19,"losses":32,"wins":13},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":19},"meta/muse-spark-open":{"draws":13,"losses":40,"wins":11},"meta/muse-wonder":{"draws":12,"losses":44,"wins":10},"minimax/minimax-m3":{"draws":9,"losses":12,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":20,"wins":20},"mistralai/mistral-large-4-0":{"draws":14,"losses":17,"wins":11},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":29,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":56,"wins":6},"nex-agi/nex-n2-pro":{"draws":10,"losses":10,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":12,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":5},"o3":{"draws":10,"losses":33,"wins":49},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":14,"losses":15,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":16,"wins":14},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":33,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":21,"wins":13},"qwen/qwen3.8-flash":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.8-max":{"draws":17,"losses":31,"wins":18},"qwen/qwen3.8-max-0902":{"draws":18,"losses":32,"wins":16},"recursive/flint-v1.0":{"draws":6,"losses":1,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":28,"wins":18},"stealth/ox-alpha":{"draws":55,"losses":101,"wins":54},"stealth/space-bunny-alpha":{"draws":17,"losses":16,"wins":21},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":30},"stepfun/step-5-preview":{"draws":0,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":13,"losses":7,"wins":16},"tencent/hy4-preview":{"draws":15,"losses":33,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":19,"wins":42},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":38},"unbiased/pareto-26.10":{"draws":2,"losses":20,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":19,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":2,"wins":10},"x-ai/grok-4.5":{"draws":19,"losses":37,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":42,"wins":10},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":14},"xiaomi/mimo-v2.5":{"draws":33,"losses":24,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":18,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":27,"wins":13},"z-ai/glm-5.2":{"draws":42,"losses":44,"wins":46},"z-ai/glm-5.3":{"draws":9,"losses":51,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":35,"wins":21},"z-ai/glm-5.3-flashx":{"draws":13,"losses":39,"wins":14}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":56,"wins":90},"claude-fable-5":{"draws":16,"losses":152,"wins":30},"claude-fable-5-1":{"draws":3,"losses":206,"wins":9},"claude-haiku-5-5":{"draws":32,"losses":101,"wins":61},"claude-opus-4-5":{"draws":43,"losses":188,"wins":95},"claude-opus-4-8":{"draws":25,"losses":110,"wins":55},"claude-opus-5":{"draws":24,"losses":265,"wins":23},"claude-opus-5-5":{"draws":11,"losses":204,"wins":3},"claude-sonnet-5":{"draws":27,"losses":88,"wins":83},"claude-sonnet-5-5":{"draws":17,"losses":135,"wins":46},"cohere/north-mini-code":{"draws":13,"losses":14,"wins":61},"deepseek/deepseek-v4-flash":{"draws":43,"losses":80,"wins":183},"deepseek/deepseek-v4-pro":{"draws":20,"losses":92,"wins":72},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":101,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":38,"losses":95,"wins":65},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":124,"wins":56},"elorian/glimpse":{"draws":14,"losses":56,"wins":36},"fireworks/ember-1":{"draws":37,"losses":111,"wins":50},"gemini-3.1-pro-preview":{"draws":30,"losses":77,"wins":91},"gemini-4-argon":{"draws":2,"losses":187,"wins":9},"google/gemini-3.1-flash-lite":{"draws":24,"losses":11,"wins":123},"google/gemini-3.5-flash":{"draws":31,"losses":137,"wins":90},"google/gemini-3.5-flash-lite":{"draws":57,"losses":97,"wins":202},"google/gemini-3.6-flash":{"draws":50,"losses":207,"wins":127},"google/gemini-3.8-flash":{"draws":20,"losses":132,"wins":46},"google/gemma-4-31b-it":{"draws":26,"losses":21,"wins":71},"gpt-4.1":{"draws":13,"losses":27,"wins":26},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":10},"gpt-5":{"draws":23,"losses":89,"wins":68},"gpt-5.4":{"draws":19,"losses":128,"wins":49},"gpt-5.4-mini":{"draws":23,"losses":35,"wins":74},"gpt-5.4-nano":{"draws":16,"losses":103,"wins":107},"gpt-5.5":{"draws":35,"losses":105,"wins":44},"gpt-5.6-luna":{"draws":40,"losses":68,"wins":90},"gpt-5.6-sol":{"draws":11,"losses":156,"wins":31},"gpt-5.6-terra":{"draws":33,"losses":86,"wins":67},"gpt-6-astra":{"draws":7,"losses":190,"wins":1},"gpt-6-luna":{"draws":33,"losses":100,"wins":65},"gpt-6-sol":{"draws":10,"losses":171,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":187,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":30,"losses":17,"wins":89},"inception/mercury-3":{"draws":17,"losses":75,"wins":36},"inclusionai/ling-3.0-flash":{"draws":26,"losses":23,"wins":91},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":32,"losses":60,"wins":140},"meta/muse-glimmer-30b":{"draws":32,"losses":36,"wins":104},"meta/muse-spark-1.2":{"draws":22,"losses":94,"wins":70},"meta/muse-spark-1.3":{"draws":20,"losses":126,"wins":52},"meta/muse-spark-open":{"draws":21,"losses":134,"wins":41},"meta/muse-wonder":{"draws":13,"losses":151,"wins":34},"minimax/minimax-m3":{"draws":13,"losses":28,"wins":71},"minimax/minimax-m3.1-flash":{"draws":20,"losses":75,"wins":81},"mistralai/mistral-large-4-0":{"draws":28,"losses":53,"wins":39},"mistralai/mistral-medium-3-5":{"draws":23,"losses":15,"wins":72},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":23,"wins":22},"moonshotai/kimi-k3":{"draws":27,"losses":86,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":174,"wins":18},"nex-agi/nex-n2-pro":{"draws":8,"losses":22,"wins":76},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":15,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":44,"wins":107},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":49,"wins":33},"o3":{"draws":24,"losses":122,"wins":122},"openai/gpt-oss-120b":{"draws":24,"losses":29,"wins":119},"poolside/laguna-s-2.1":{"draws":30,"losses":63,"wins":99},"qwen/qwen3.7-max":{"draws":21,"losses":44,"wins":59},"qwen/qwen3.7-plus":{"draws":11,"losses":29,"wins":70},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":112,"wins":59},"qwen/qwen3.8-27b":{"draws":12,"losses":74,"wins":58},"qwen/qwen3.8-flash":{"draws":18,"losses":63,"wins":51},"qwen/qwen3.8-max":{"draws":34,"losses":100,"wins":64},"qwen/qwen3.8-max-0902":{"draws":35,"losses":99,"wins":64},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":52},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":88,"wins":64},"stealth/ox-alpha":{"draws":77,"losses":318,"wins":209},"stealth/space-bunny-alpha":{"draws":24,"losses":57,"wins":79},"stepfun/step-3.7-flash":{"draws":24,"losses":43,"wins":93},"stepfun/step-5-preview":{"draws":8,"losses":10,"wins":2},"tencent/hy3-preview":{"draws":22,"losses":39,"wins":43},"tencent/hy4-preview":{"draws":25,"losses":104,"wins":67},"thinkingmachines/inkling":{"draws":41,"losses":58,"wins":167},"thinkingmachines/inkling-small":{"draws":35,"losses":44,"wins":119},"unbiased/pareto-26.10":{"draws":0,"losses":66,"wins":0},"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":21,"losses":120,"wins":57},"x-ai/grok-4.6":{"draws":33,"losses":120,"wins":45},"x-ai/grok-4.7":{"draws":12,"losses":130,"wins":36},"x-ai/grok-build-0.1":{"draws":12,"losses":16,"wins":38},"xiaomi/mimo-v2.5":{"draws":53,"losses":63,"wins":200},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":44,"wins":62},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":74,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":96,"wins":25},"z-ai/glm-5.2":{"draws":66,"losses":151,"wins":179},"z-ai/glm-5.3":{"draws":15,"losses":138,"wins":35},"z-ai/glm-5.3-flash":{"draws":21,"losses":101,"wins":76},"z-ai/glm-5.3-flashx":{"draws":21,"losses":119,"wins":58}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":47,"wins":33},"claude-fable-5":{"draws":26,"losses":89,"wins":11},"claude-fable-5-1":{"draws":5,"losses":137,"wins":0},"claude-haiku-5-5":{"draws":29,"losses":79,"wins":12},"claude-opus-4-5":{"draws":63,"losses":109,"wins":32},"claude-opus-4-8":{"draws":33,"losses":68,"wins":13},"claude-opus-5":{"draws":26,"losses":183,"wins":11},"claude-opus-5-5":{"draws":9,"losses":129,"wins":0},"claude-sonnet-5":{"draws":35,"losses":74,"wins":17},"claude-sonnet-5-5":{"draws":25,"losses":83,"wins":18},"cohere/north-mini-code":{"draws":15,"losses":15,"wins":20},"deepseek/deepseek-v4-flash":{"draws":61,"losses":65,"wins":64},"deepseek/deepseek-v4-pro":{"draws":34,"losses":55,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":50,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":70,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":84,"wins":17},"elorian/glimpse":{"draws":14,"losses":36,"wins":18},"fireworks/ember-1":{"draws":43,"losses":65,"wins":18},"gemini-3.1-pro-preview":{"draws":34,"losses":59,"wins":33},"gemini-4-argon":{"draws":3,"losses":121,"wins":2},"google/gemini-3.1-flash-lite":{"draws":21,"losses":23,"wins":38},"google/gemini-3.5-flash":{"draws":36,"losses":82,"wins":38},"google/gemini-3.5-flash-lite":{"draws":62,"losses":77,"wins":79},"google/gemini-3.6-flash":{"draws":64,"losses":137,"wins":39},"google/gemini-3.8-flash":{"draws":26,"losses":92,"wins":8},"google/gemma-4-31b-it":{"draws":31,"losses":10,"wins":33},"gpt-4.1":{"draws":11,"losses":22,"wins":9},"gpt-4.1-nano":{"draws":12,"losses":0,"wins":4},"gpt-5":{"draws":33,"losses":57,"wins":22},"gpt-5.4":{"draws":31,"losses":69,"wins":20},"gpt-5.4-mini":{"draws":31,"losses":32,"wins":21},"gpt-5.4-nano":{"draws":35,"losses":44,"wins":47},"gpt-5.5":{"draws":42,"losses":58,"wins":16},"gpt-5.6-luna":{"draws":49,"losses":48,"wins":29},"gpt-5.6-sol":{"draws":15,"losses":104,"wins":7},"gpt-5.6-terra":{"draws":37,"losses":70,"wins":13},"gpt-6-astra":{"draws":12,"losses":114,"wins":0},"gpt-6-luna":{"draws":38,"losses":59,"wins":29},"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":32,"losses":25,"wins":31},"inception/mercury-3":{"draws":26,"losses":39,"wins":21},"inclusionai/ling-3.0-flash":{"draws":37,"losses":8,"wins":41},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":37,"losses":62,"wins":39},"meta/muse-glimmer-30b":{"draws":39,"losses":32,"wins":41},"meta/muse-spark-1.2":{"draws":32,"losses":77,"wins":13},"meta/muse-spark-1.3":{"draws":30,"losses":83,"wins":13},"meta/muse-spark-open":{"draws":27,"losses":83,"wins":10},"meta/muse-wonder":{"draws":23,"losses":93,"wins":10},"minimax/minimax-m3":{"draws":20,"losses":23,"wins":27},"minimax/minimax-m3.1-flash":{"draws":26,"losses":53,"wins":29},"mistralai/mistral-large-4-0":{"draws":31,"losses":35,"wins":14},"mistralai/mistral-medium-3-5":{"draws":30,"losses":16,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":6},"moonshotai/kimi-k3":{"draws":34,"losses":69,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":15,"losses":106,"wins":5},"nex-agi/nex-n2-pro":{"draws":15,"losses":28,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":16,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":30,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":35,"wins":10},"o3":{"draws":24,"losses":119,"wins":29},"openai/gpt-oss-120b":{"draws":18,"losses":27,"wins":27},"poolside/laguna-s-2.1":{"draws":47,"losses":42,"wins":37},"qwen/qwen3.7-max":{"draws":25,"losses":33,"wins":16},"qwen/qwen3.7-plus":{"draws":21,"losses":21,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":72,"wins":12},"qwen/qwen3.8-27b":{"draws":22,"losses":46,"wins":18},"qwen/qwen3.8-flash":{"draws":27,"losses":34,"wins":23},"qwen/qwen3.8-max":{"draws":38,"losses":78,"wins":10},"qwen/qwen3.8-max-0902":{"draws":33,"losses":77,"wins":16},"recursive/flint-v1.0":{"draws":8,"losses":9,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":36,"losses":65,"wins":17},"stealth/ox-alpha":{"draws":103,"losses":259,"wins":62},"stealth/space-bunny-alpha":{"draws":28,"losses":48,"wins":24},"stepfun/step-3.7-flash":{"draws":29,"losses":36,"wins":23},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":27,"wins":19},"tencent/hy4-preview":{"draws":38,"losses":61,"wins":21},"thinkingmachines/inkling":{"draws":44,"losses":65,"wins":59},"thinkingmachines/inkling-small":{"draws":44,"losses":33,"wins":49},"unbiased/pareto-26.10":{"draws":0,"losses":42,"wins":0},"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":34,"losses":79,"wins":13},"x-ai/grok-4.6":{"draws":35,"losses":80,"wins":11},"x-ai/grok-4.7":{"draws":9,"losses":98,"wins":5},"x-ai/grok-build-0.1":{"draws":15,"losses":17,"wins":10},"xiaomi/mimo-v2.5":{"draws":58,"losses":61,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":29,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":57,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":62,"wins":6},"z-ai/glm-5.2":{"draws":89,"losses":112,"wins":51},"z-ai/glm-5.3":{"draws":28,"losses":89,"wins":5},"z-ai/glm-5.3-flash":{"draws":26,"losses":80,"wins":20},"z-ai/glm-5.3-flashx":{"draws":27,"losses":85,"wins":14}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":47,"wins":41},"claude-fable-5":{"draws":20,"losses":98,"wins":20},"claude-fable-5-1":{"draws":5,"losses":145,"wins":2},"claude-haiku-5-5":{"draws":34,"losses":61,"wins":35},"claude-opus-4-5":{"draws":70,"losses":116,"wins":36},"claude-opus-4-8":{"draws":33,"losses":71,"wins":18},"claude-opus-5":{"draws":24,"losses":211,"wins":13},"claude-opus-5-5":{"draws":10,"losses":144,"wins":0},"claude-sonnet-5":{"draws":40,"losses":71,"wins":27},"claude-sonnet-5-5":{"draws":26,"losses":86,"wins":26},"cohere/north-mini-code":{"draws":13,"losses":22,"wins":19},"deepseek/deepseek-v4-flash":{"draws":64,"losses":74,"wins":72},"deepseek/deepseek-v4-pro":{"draws":30,"losses":51,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":62,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":54,"losses":59,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":93,"wins":18},"elorian/glimpse":{"draws":18,"losses":40,"wins":16},"fireworks/ember-1":{"draws":46,"losses":66,"wins":26},"gemini-3.1-pro-preview":{"draws":42,"losses":61,"wins":35},"gemini-4-argon":{"draws":8,"losses":127,"wins":3},"google/gemini-3.1-flash-lite":{"draws":24,"losses":22,"wins":40},"google/gemini-3.5-flash":{"draws":30,"losses":106,"wins":34},"google/gemini-3.5-flash-lite":{"draws":61,"losses":71,"wins":106},"google/gemini-3.6-flash":{"draws":61,"losses":145,"wins":56},"google/gemini-3.8-flash":{"draws":22,"losses":99,"wins":17},"google/gemma-4-31b-it":{"draws":33,"losses":20,"wins":25},"gpt-4.1":{"draws":14,"losses":19,"wins":13},"gpt-4.1-nano":{"draws":13,"losses":3,"wins":2},"gpt-5":{"draws":32,"losses":55,"wins":39},"gpt-5.4":{"draws":31,"losses":80,"wins":21},"gpt-5.4-mini":{"draws":28,"losses":34,"wins":30},"gpt-5.4-nano":{"draws":26,"losses":59,"wins":59},"gpt-5.5":{"draws":43,"losses":59,"wins":26},"gpt-5.6-luna":{"draws":47,"losses":50,"wins":41},"gpt-5.6-sol":{"draws":19,"losses":111,"wins":8},"gpt-5.6-terra":{"draws":40,"losses":73,"wins":17},"gpt-6-astra":{"draws":7,"losses":131,"wins":0},"gpt-6-luna":{"draws":42,"losses":58,"wins":38},"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":36,"losses":24,"wins":30},"inception/mercury-3":{"draws":30,"losses":49,"wins":17},"inclusionai/ling-3.0-flash":{"draws":29,"losses":29,"wins":36},"inclusionai/ling-3.1-flash":{"draws":8,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":45,"losses":50,"wins":55},"meta/muse-glimmer-30b":{"draws":40,"losses":36,"wins":48},"meta/muse-spark-1.2":{"draws":27,"losses":86,"wins":21},"meta/muse-spark-1.3":{"draws":28,"losses":84,"wins":26},"meta/muse-spark-open":{"draws":25,"losses":86,"wins":21},"meta/muse-wonder":{"draws":22,"losses":105,"wins":11},"minimax/minimax-m3":{"draws":19,"losses":26,"wins":33},"minimax/minimax-m3.1-flash":{"draws":25,"losses":51,"wins":40},"mistralai/mistral-large-4-0":{"draws":32,"losses":36,"wins":20},"mistralai/mistral-medium-3-5":{"draws":25,"losses":18,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":12},"moonshotai/kimi-k3":{"draws":40,"losses":70,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":18,"losses":109,"wins":11},"nex-agi/nex-n2-pro":{"draws":17,"losses":24,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":10,"losses":9,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":40,"wins":44},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":31,"wins":15},"o3":{"draws":30,"losses":99,"wins":63},"openai/gpt-oss-120b":{"draws":47,"losses":37,"wins":42},"poolside/laguna-s-2.1":{"draws":28,"losses":38,"wins":38},"qwen/qwen3.7-max":{"draws":24,"losses":35,"wins":23},"qwen/qwen3.7-plus":{"draws":16,"losses":13,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":86,"wins":15},"qwen/qwen3.8-27b":{"draws":23,"losses":49,"wins":22},"qwen/qwen3.8-flash":{"draws":23,"losses":42,"wins":27},"qwen/qwen3.8-max":{"draws":35,"losses":71,"wins":32},"qwen/qwen3.8-max-0902":{"draws":41,"losses":73,"wins":24},"recursive/flint-v1.0":{"draws":7,"losses":7,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":30,"losses":69,"wins":29},"stealth/ox-alpha":{"draws":107,"losses":279,"wins":92},"stealth/space-bunny-alpha":{"draws":31,"losses":46,"wins":29},"stepfun/step-3.7-flash":{"draws":31,"losses":30,"wins":37},"stepfun/step-5-preview":{"draws":8,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":27,"losses":26,"wins":23},"tencent/hy4-preview":{"draws":26,"losses":70,"wins":36},"thinkingmachines/inkling":{"draws":52,"losses":54,"wins":82},"thinkingmachines/inkling-small":{"draws":41,"losses":24,"wins":73},"unbiased/pareto-26.10":{"draws":1,"losses":45,"wins":0},"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":35,"losses":84,"wins":19},"x-ai/grok-4.6":{"draws":33,"losses":86,"wins":19},"x-ai/grok-4.7":{"draws":12,"losses":99,"wins":13},"x-ai/grok-build-0.1":{"draws":14,"losses":18,"wins":14},"xiaomi/mimo-v2.5":{"draws":57,"losses":60,"wins":85},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":25,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":54,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":64,"wins":18},"z-ai/glm-5.2":{"draws":87,"losses":105,"wins":84},"z-ai/glm-5.3":{"draws":24,"losses":94,"wins":14},"z-ai/glm-5.3-flash":{"draws":28,"losses":76,"wins":34},"z-ai/glm-5.3-flashx":{"draws":36,"losses":76,"wins":26}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":26,"wins":29},"claude-fable-5":{"draws":11,"losses":60,"wins":13},"claude-fable-5-1":{"draws":2,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":34,"wins":20},"claude-opus-4-5":{"draws":35,"losses":68,"wins":35},"claude-opus-4-8":{"draws":21,"losses":37,"wins":22},"claude-opus-5":{"draws":17,"losses":111,"wins":12},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":23,"losses":40,"wins":21},"claude-sonnet-5-5":{"draws":18,"losses":44,"wins":22},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":39,"losses":39,"wins":52},"deepseek/deepseek-v4-pro":{"draws":22,"losses":37,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":33,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":35,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":58,"wins":11},"elorian/glimpse":{"draws":8,"losses":22,"wins":14},"fireworks/ember-1":{"draws":21,"losses":42,"wins":21},"gemini-3.1-pro-preview":{"draws":21,"losses":34,"wins":29},"gemini-4-argon":{"draws":4,"losses":73,"wins":7},"google/gemini-3.1-flash-lite":{"draws":14,"losses":9,"wins":37},"google/gemini-3.5-flash":{"draws":25,"losses":42,"wins":39},"google/gemini-3.5-flash-lite":{"draws":34,"losses":43,"wins":69},"google/gemini-3.6-flash":{"draws":37,"losses":81,"wins":42},"google/gemini-3.8-flash":{"draws":24,"losses":40,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":13,"wins":20},"gpt-4.1":{"draws":11,"losses":5,"wins":12},"gpt-4.1-nano":{"draws":6,"losses":2,"wins":2},"gpt-5":{"draws":25,"losses":29,"wins":20},"gpt-5.4":{"draws":16,"losses":45,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":16,"wins":29},"gpt-5.4-nano":{"draws":20,"losses":33,"wins":39},"gpt-5.5":{"draws":24,"losses":38,"wins":14},"gpt-5.6-luna":{"draws":23,"losses":27,"wins":34},"gpt-5.6-sol":{"draws":11,"losses":59,"wins":14},"gpt-5.6-terra":{"draws":20,"losses":43,"wins":17},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":21,"losses":36,"wins":27},"gpt-6-sol":{"draws":16,"losses":58,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":76,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":21,"losses":16,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":18},"inclusionai/ling-3.0-flash":{"draws":19,"losses":11,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":21,"losses":19,"wins":52},"meta/muse-glimmer-30b":{"draws":23,"losses":18,"wins":31},"meta/muse-spark-1.2":{"draws":15,"losses":47,"wins":18},"meta/muse-spark-1.3":{"draws":16,"losses":47,"wins":21},"meta/muse-spark-open":{"draws":16,"losses":46,"wins":18},"meta/muse-wonder":{"draws":11,"losses":61,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":24},"minimax/minimax-m3.1-flash":{"draws":11,"losses":30,"wins":31},"mistralai/mistral-large-4-0":{"draws":21,"losses":26,"wins":5},"mistralai/mistral-medium-3-5":{"draws":18,"losses":5,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":11},"moonshotai/kimi-k3":{"draws":18,"losses":43,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":69,"wins":7},"nex-agi/nex-n2-pro":{"draws":9,"losses":8,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":23,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":16},"o3":{"draws":21,"losses":59,"wins":44},"openai/gpt-oss-120b":{"draws":25,"losses":16,"wins":33},"poolside/laguna-s-2.1":{"draws":24,"losses":23,"wins":35},"qwen/qwen3.7-max":{"draws":2,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":14,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":37,"wins":19},"qwen/qwen3.8-27b":{"draws":16,"losses":25,"wins":19},"qwen/qwen3.8-flash":{"draws":14,"losses":25,"wins":17},"qwen/qwen3.8-max":{"draws":22,"losses":38,"wins":24},"qwen/qwen3.8-max-0902":{"draws":26,"losses":41,"wins":17},"recursive/flint-v1.0":{"draws":5,"losses":8,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":19,"losses":36,"wins":21},"stealth/ox-alpha":{"draws":56,"losses":140,"wins":62},"stealth/space-bunny-alpha":{"draws":15,"losses":22,"wins":29},"stepfun/step-3.7-flash":{"draws":16,"losses":12,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":19,"losses":11,"wins":16},"tencent/hy4-preview":{"draws":11,"losses":47,"wins":22},"thinkingmachines/inkling":{"draws":29,"losses":19,"wins":62},"thinkingmachines/inkling-small":{"draws":22,"losses":20,"wins":42},"unbiased/pareto-26.10":{"draws":1,"losses":27,"wins":0},"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":21,"losses":44,"wins":19},"x-ai/grok-4.6":{"draws":20,"losses":48,"wins":16},"x-ai/grok-4.7":{"draws":10,"losses":50,"wins":16},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":11},"xiaomi/mimo-v2.5":{"draws":41,"losses":31,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":16,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":29,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":35,"wins":13},"z-ai/glm-5.2":{"draws":41,"losses":68,"wins":59},"z-ai/glm-5.3":{"draws":15,"losses":50,"wins":15},"z-ai/glm-5.3-flash":{"draws":23,"losses":42,"wins":19},"z-ai/glm-5.3-flashx":{"draws":18,"losses":47,"wins":19}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":25,"wins":21},"claude-fable-5":{"draws":10,"losses":54,"wins":8},"claude-fable-5-1":{"draws":3,"losses":74,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":50,"wins":8},"claude-opus-4-5":{"draws":38,"losses":55,"wins":27},"claude-opus-4-8":{"draws":18,"losses":43,"wins":11},"claude-opus-5":{"draws":15,"losses":93,"wins":8},"claude-opus-5-5":{"draws":5,"losses":71,"wins":0},"claude-sonnet-5":{"draws":20,"losses":36,"wins":16},"claude-sonnet-5-5":{"draws":15,"losses":44,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":31,"losses":43,"wins":38},"deepseek/deepseek-v4-pro":{"draws":14,"losses":35,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":29,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":40,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":50,"wins":9},"elorian/glimpse":{"draws":8,"losses":21,"wins":7},"fireworks/ember-1":{"draws":20,"losses":39,"wins":13},"gemini-3.1-pro-preview":{"draws":24,"losses":34,"wins":14},"gemini-4-argon":{"draws":3,"losses":68,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":32},"google/gemini-3.5-flash":{"draws":17,"losses":55,"wins":20},"google/gemini-3.5-flash-lite":{"draws":32,"losses":54,"wins":40},"google/gemini-3.6-flash":{"draws":33,"losses":82,"wins":23},"google/gemini-3.8-flash":{"draws":15,"losses":50,"wins":7},"google/gemma-4-31b-it":{"draws":16,"losses":13,"wins":15},"gpt-4.1":{"draws":8,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":14,"losses":38,"wins":10},"gpt-5.4":{"draws":10,"losses":50,"wins":8},"gpt-5.4-mini":{"draws":12,"losses":15,"wins":21},"gpt-5.4-nano":{"draws":15,"losses":33,"wins":34},"gpt-5.5":{"draws":22,"losses":36,"wins":6},"gpt-5.6-luna":{"draws":27,"losses":27,"wins":18},"gpt-5.6-sol":{"draws":13,"losses":52,"wins":7},"gpt-5.6-terra":{"draws":26,"losses":32,"wins":10},"gpt-6-astra":{"draws":3,"losses":69,"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":9,"wins":23},"inception/mercury-3":{"draws":15,"losses":25,"wins":8},"inclusionai/ling-3.0-flash":{"draws":16,"losses":16,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":31,"wins":32},"meta/muse-glimmer-30b":{"draws":21,"losses":24,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":40,"wins":12},"meta/muse-spark-1.3":{"draws":14,"losses":45,"wins":13},"meta/muse-spark-open":{"draws":15,"losses":43,"wins":10},"meta/muse-wonder":{"draws":15,"losses":55,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":15,"wins":18},"minimax/minimax-m3.1-flash":{"draws":11,"losses":37,"wins":16},"mistralai/mistral-large-4-0":{"draws":13,"losses":29,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":11,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":2},"moonshotai/kimi-k3":{"draws":24,"losses":30,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":60,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":11,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":23,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":16,"wins":9},"o3":{"draws":11,"losses":70,"wins":29},"openai/gpt-oss-120b":{"draws":21,"losses":20,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":37,"wins":13},"qwen/qwen3.7-max":{"draws":9,"losses":23,"wins":14},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":37,"wins":9},"qwen/qwen3.8-27b":{"draws":10,"losses":28,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-max":{"draws":25,"losses":30,"wins":17},"qwen/qwen3.8-max-0902":{"draws":26,"losses":37,"wins":9},"recursive/flint-v1.0":{"draws":7,"losses":8,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":30,"wins":17},"stealth/ox-alpha":{"draws":38,"losses":137,"wins":27},"stealth/space-bunny-alpha":{"draws":16,"losses":31,"wins":11},"stepfun/step-3.7-flash":{"draws":10,"losses":21,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":41,"wins":16},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":40},"thinkingmachines/inkling-small":{"draws":24,"losses":26,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":18,"losses":46,"wins":8},"x-ai/grok-4.6":{"draws":20,"losses":45,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":52,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":10,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":38,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":23,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":32,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":36,"losses":74,"wins":34},"z-ai/glm-5.3":{"draws":14,"losses":47,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":42,"wins":15},"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":39,"losses":30,"wins":63},"claude-fable-5":{"draws":32,"losses":76,"wins":36},"claude-fable-5-1":{"draws":8,"losses":147,"wins":7},"claude-haiku-5-5":{"draws":36,"losses":55,"wins":47},"claude-opus-4-5":{"draws":79,"losses":62,"wins":93},"claude-opus-4-8":{"draws":40,"losses":42,"wins":50},"claude-opus-5":{"draws":31,"losses":173,"wins":42},"claude-opus-5-5":{"draws":10,"losses":129,"wins":17},"claude-sonnet-5":{"draws":45,"losses":37,"wins":62},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":45},"deepseek/deepseek-v4-flash":{"draws":65,"losses":31,"wins":120},"deepseek/deepseek-v4-pro":{"draws":33,"losses":37,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":43,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":60,"wins":49},"deepseek/deepseek-v4.1-flash-1017":{"draws":28,"losses":73,"wins":43},"elorian/glimpse":{"draws":20,"losses":29,"wins":29},"fireworks/ember-1":{"draws":47,"losses":50,"wins":47},"gemini-3.1-pro-preview":{"draws":34,"losses":43,"wins":67},"gemini-4-argon":{"draws":9,"losses":112,"wins":23},"google/gemini-3.1-flash-lite":{"draws":23,"losses":7,"wins":66},"google/gemini-3.5-flash":{"draws":47,"losses":52,"wins":81},"google/gemini-3.5-flash-lite":{"draws":77,"losses":40,"wins":135},"google/gemini-3.6-flash":{"draws":63,"losses":118,"wins":95},"google/gemini-3.8-flash":{"draws":30,"losses":68,"wins":46},"google/gemma-4-31b-it":{"draws":29,"losses":10,"wins":45},"gpt-4.1":{"draws":17,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":11},"gpt-5":{"draws":36,"losses":35,"wins":55},"gpt-5.4":{"draws":28,"losses":58,"wins":52},"gpt-5.4-mini":{"draws":31,"losses":13,"wins":52},"gpt-5.4-nano":{"draws":34,"losses":26,"wins":84},"gpt-5.5":{"draws":39,"losses":47,"wins":46},"gpt-5.6-luna":{"draws":51,"losses":27,"wins":66},"gpt-5.6-sol":{"draws":20,"losses":87,"wins":37},"gpt-5.6-terra":{"draws":44,"losses":33,"wins":61},"gpt-6-astra":{"draws":5,"losses":133,"wins":6},"gpt-6-luna":{"draws":37,"losses":48,"wins":59},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":8,"losses":116,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":40,"losses":6,"wins":56},"inception/mercury-3":{"draws":32,"losses":30,"wins":34},"inclusionai/ling-3.0-flash":{"draws":38,"losses":4,"wins":60},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":40,"losses":23,"wins":93},"meta/muse-glimmer-30b":{"draws":43,"losses":15,"wins":68},"meta/muse-spark-1.2":{"draws":37,"losses":47,"wins":54},"meta/muse-spark-1.3":{"draws":35,"losses":59,"wins":50},"meta/muse-spark-open":{"draws":32,"losses":56,"wins":50},"meta/muse-wonder":{"draws":27,"losses":73,"wins":44},"minimax/minimax-m3":{"draws":18,"losses":8,"wins":52},"minimax/minimax-m3.1-flash":{"draws":35,"losses":29,"wins":62},"mistralai/mistral-large-4-0":{"draws":22,"losses":26,"wins":42},"mistralai/mistral-medium-3-5":{"draws":22,"losses":3,"wins":59},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":8,"wins":16},"moonshotai/kimi-k3":{"draws":35,"losses":51,"wins":52},"moonshotai/kimi-k3.1-pro":{"draws":17,"losses":108,"wins":19},"nex-agi/nex-n2-pro":{"draws":15,"losses":9,"wins":48},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":14,"wins":67},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":15,"wins":33},"o3":{"draws":27,"losses":59,"wins":112},"openai/gpt-oss-120b":{"draws":42,"losses":12,"wins":72},"poolside/laguna-s-2.1":{"draws":37,"losses":15,"wins":86},"qwen/qwen3.7-max":{"draws":28,"losses":19,"wins":37},"qwen/qwen3.7-plus":{"draws":26,"losses":9,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":35,"wins":35},"qwen/qwen3.8-27b":{"draws":38,"losses":28,"wins":36},"qwen/qwen3.8-flash":{"draws":23,"losses":31,"wins":42},"qwen/qwen3.8-max":{"draws":42,"losses":54,"wins":48},"qwen/qwen3.8-max-0902":{"draws":44,"losses":55,"wins":45},"recursive/flint-v1.0":{"draws":12,"losses":2,"wins":28},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":36,"wins":65},"stealth/ox-alpha":{"draws":118,"losses":175,"wins":181},"stealth/space-bunny-alpha":{"draws":41,"losses":28,"wins":45},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":71},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":28,"losses":15,"wins":35},"tencent/hy4-preview":{"draws":36,"losses":53,"wins":49},"thinkingmachines/inkling":{"draws":58,"losses":25,"wins":109},"thinkingmachines/inkling-small":{"draws":44,"losses":17,"wins":83},"unbiased/pareto-26.10":{"draws":5,"losses":42,"wins":1},"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":34,"losses":63,"wins":47},"x-ai/grok-4.6":{"draws":33,"losses":61,"wins":50},"x-ai/grok-4.7":{"draws":9,"losses":86,"wins":31},"x-ai/grok-build-0.1":{"draws":18,"losses":6,"wins":24},"xiaomi/mimo-v2.5":{"draws":86,"losses":24,"wins":112},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":18,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":19,"losses":37,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":24,"losses":42,"wins":30},"z-ai/glm-5.2":{"draws":94,"losses":71,"wins":123},"z-ai/glm-5.3":{"draws":25,"losses":83,"wins":30},"z-ai/glm-5.3-flash":{"draws":28,"losses":68,"wins":48},"z-ai/glm-5.3-flashx":{"draws":38,"losses":61,"wins":45}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":24,"wins":48},"claude-fable-5":{"draws":20,"losses":66,"wins":16},"claude-fable-5-1":{"draws":6,"losses":107,"wins":1},"claude-haiku-5-5":{"draws":22,"losses":46,"wins":30},"claude-opus-4-5":{"draws":48,"losses":49,"wins":69},"claude-opus-4-8":{"draws":20,"losses":43,"wins":31},"claude-opus-5":{"draws":30,"losses":123,"wins":13},"claude-opus-5-5":{"draws":5,"losses":98,"wins":3},"claude-sonnet-5":{"draws":24,"losses":38,"wins":40},"claude-sonnet-5-5":{"draws":17,"losses":59,"wins":26},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":25},"deepseek/deepseek-v4-flash":{"draws":38,"losses":35,"wins":81},"deepseek/deepseek-v4-pro":{"draws":26,"losses":31,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":30,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":50,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":61,"wins":26},"elorian/glimpse":{"draws":11,"losses":22,"wins":21},"fireworks/ember-1":{"draws":28,"losses":35,"wins":39},"gemini-3.1-pro-preview":{"draws":23,"losses":31,"wins":48},"gemini-4-argon":{"draws":7,"losses":88,"wins":7},"google/gemini-3.1-flash-lite":{"draws":15,"losses":9,"wins":46},"google/gemini-3.5-flash":{"draws":20,"losses":57,"wins":51},"google/gemini-3.5-flash-lite":{"draws":36,"losses":41,"wins":103},"google/gemini-3.6-flash":{"draws":41,"losses":91,"wins":66},"google/gemini-3.8-flash":{"draws":16,"losses":61,"wins":25},"google/gemma-4-31b-it":{"draws":19,"losses":10,"wins":29},"gpt-4.1":{"draws":8,"losses":11,"wins":15},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":6},"gpt-5":{"draws":17,"losses":30,"wins":41},"gpt-5.4":{"draws":20,"losses":58,"wins":20},"gpt-5.4-mini":{"draws":15,"losses":17,"wins":36},"gpt-5.4-nano":{"draws":19,"losses":34,"wins":51},"gpt-5.5":{"draws":26,"losses":38,"wins":28},"gpt-5.6-luna":{"draws":32,"losses":25,"wins":45},"gpt-5.6-sol":{"draws":15,"losses":71,"wins":16},"gpt-5.6-terra":{"draws":33,"losses":34,"wins":31},"gpt-6-astra":{"draws":4,"losses":97,"wins":1},"gpt-6-luna":{"draws":24,"losses":41,"wins":37},"gpt-6-sol":{"draws":16,"losses":72,"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":22,"losses":7,"wins":43},"inception/mercury-3":{"draws":20,"losses":21,"wins":25},"inclusionai/ling-3.0-flash":{"draws":14,"losses":14,"wins":46},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":21,"losses":18,"wins":69},"meta/muse-glimmer-30b":{"draws":23,"losses":14,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":34,"wins":40},"meta/muse-spark-1.3":{"draws":19,"losses":52,"wins":31},"meta/muse-spark-open":{"draws":21,"losses":48,"wins":29},"meta/muse-wonder":{"draws":19,"losses":69,"wins":14},"minimax/minimax-m3":{"draws":13,"losses":8,"wins":33},"minimax/minimax-m3.1-flash":{"draws":20,"losses":35,"wins":39},"mistralai/mistral-large-4-0":{"draws":19,"losses":22,"wins":21},"mistralai/mistral-medium-3-5":{"draws":19,"losses":4,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":11},"moonshotai/kimi-k3":{"draws":27,"losses":41,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":82,"wins":8},"nex-agi/nex-n2-pro":{"draws":10,"losses":11,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":19,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":13,"wins":21},"o3":{"draws":12,"losses":58,"wins":74},"openai/gpt-oss-120b":{"draws":22,"losses":18,"wins":46},"poolside/laguna-s-2.1":{"draws":23,"losses":22,"wins":49},"qwen/qwen3.7-max":{"draws":16,"losses":19,"wins":25},"qwen/qwen3.7-plus":{"draws":10,"losses":16,"wins":28},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":36,"wins":28},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":18},"qwen/qwen3.8-flash":{"draws":15,"losses":30,"wins":23},"qwen/qwen3.8-max":{"draws":30,"losses":33,"wins":39},"qwen/qwen3.8-max-0902":{"draws":24,"losses":51,"wins":27},"recursive/flint-v1.0":{"draws":5,"losses":7,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":34,"wins":34},"stealth/ox-alpha":{"draws":72,"losses":153,"wins":107},"stealth/space-bunny-alpha":{"draws":21,"losses":20,"wins":39},"stepfun/step-3.7-flash":{"draws":12,"losses":26,"wins":38},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":25,"losses":45,"wins":28},"thinkingmachines/inkling":{"draws":37,"losses":30,"wins":71},"thinkingmachines/inkling-small":{"draws":28,"losses":16,"wins":58},"unbiased/pareto-26.10":{"draws":2,"losses":32,"wins":0},"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":53,"wins":25},"x-ai/grok-4.6":{"draws":26,"losses":53,"wins":23},"x-ai/grok-4.7":{"draws":11,"losses":58,"wins":19},"x-ai/grok-build-0.1":{"draws":12,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":40,"losses":30,"wins":90},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":20,"wins":26},"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":64,"losses":70,"wins":70},"z-ai/glm-5.3":{"draws":24,"losses":60,"wins":12},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":32},"z-ai/glm-5.3-flashx":{"draws":22,"losses":54,"wins":26}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":22,"wins":40},"claude-fable-5":{"draws":18,"losses":56,"wins":22},"claude-fable-5-1":{"draws":7,"losses":96,"wins":5},"claude-haiku-5-5":{"draws":27,"losses":47,"wins":18},"claude-opus-4-5":{"draws":53,"losses":54,"wins":49},"claude-opus-4-8":{"draws":28,"losses":42,"wins":18},"claude-opus-5":{"draws":24,"losses":126,"wins":14},"claude-opus-5-5":{"draws":10,"losses":91,"wins":3},"claude-sonnet-5":{"draws":30,"losses":33,"wins":33},"claude-sonnet-5-5":{"draws":17,"losses":49,"wins":30},"cohere/north-mini-code":{"draws":7,"losses":11,"wins":18},"deepseek/deepseek-v4-flash":{"draws":42,"losses":32,"wins":70},"deepseek/deepseek-v4-pro":{"draws":18,"losses":30,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":31,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":40,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":51,"wins":24},"elorian/glimpse":{"draws":13,"losses":22,"wins":17},"fireworks/ember-1":{"draws":30,"losses":34,"wins":32},"gemini-3.1-pro-preview":{"draws":34,"losses":31,"wins":31},"gemini-4-argon":{"draws":12,"losses":73,"wins":11},"google/gemini-3.1-flash-lite":{"draws":19,"losses":10,"wins":35},"google/gemini-3.5-flash":{"draws":26,"losses":53,"wins":41},"google/gemini-3.5-flash-lite":{"draws":53,"losses":36,"wins":79},"google/gemini-3.6-flash":{"draws":50,"losses":86,"wins":48},"google/gemini-3.8-flash":{"draws":17,"losses":50,"wins":29},"google/gemma-4-31b-it":{"draws":27,"losses":6,"wins":23},"gpt-4.1":{"draws":11,"losses":6,"wins":15},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":7},"gpt-5":{"draws":16,"losses":32,"wins":36},"gpt-5.4":{"draws":18,"losses":45,"wins":29},"gpt-5.4-mini":{"draws":18,"losses":16,"wins":30},"gpt-5.4-nano":{"draws":17,"losses":29,"wins":50},"gpt-5.5":{"draws":29,"losses":39,"wins":20},"gpt-5.6-luna":{"draws":31,"losses":28,"wins":37},"gpt-5.6-sol":{"draws":17,"losses":61,"wins":18},"gpt-5.6-terra":{"draws":27,"losses":35,"wins":30},"gpt-6-astra":{"draws":12,"losses":81,"wins":3},"gpt-6-luna":{"draws":28,"losses":35,"wins":33},"gpt-6-sol":{"draws":9,"losses":68,"wins":19},"gpt-6.1-sol":{"draws":8,"losses":81,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":6,"wins":33},"inception/mercury-3":{"draws":19,"losses":21,"wins":24},"inclusionai/ling-3.0-flash":{"draws":21,"losses":9,"wins":38},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":25,"wins":49},"meta/muse-glimmer-30b":{"draws":27,"losses":25,"wins":32},"meta/muse-spark-1.2":{"draws":22,"losses":42,"wins":28},"meta/muse-spark-1.3":{"draws":21,"losses":47,"wins":28},"meta/muse-spark-open":{"draws":19,"losses":42,"wins":31},"meta/muse-wonder":{"draws":24,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":9,"losses":18,"wins":25},"minimax/minimax-m3.1-flash":{"draws":23,"losses":27,"wins":34},"mistralai/mistral-large-4-0":{"draws":22,"losses":21,"wins":17},"mistralai/mistral-medium-3-5":{"draws":18,"losses":7,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":25,"losses":35,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":75,"wins":14},"nex-agi/nex-n2-pro":{"draws":12,"losses":8,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":21,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":12,"wins":18},"o3":{"draws":18,"losses":51,"wins":63},"openai/gpt-oss-120b":{"draws":27,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":23,"losses":27,"wins":42},"qwen/qwen3.7-max":{"draws":14,"losses":17,"wins":25},"qwen/qwen3.7-plus":{"draws":11,"losses":18,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":42,"wins":31},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":30},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":28,"losses":39,"wins":29},"qwen/qwen3.8-max-0902":{"draws":31,"losses":33,"wins":32},"recursive/flint-v1.0":{"draws":8,"losses":3,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":34,"wins":33},"stealth/ox-alpha":{"draws":79,"losses":134,"wins":103},"stealth/space-bunny-alpha":{"draws":26,"losses":20,"wins":30},"stepfun/step-3.7-flash":{"draws":14,"losses":14,"wins":40},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":12,"wins":22},"tencent/hy4-preview":{"draws":22,"losses":43,"wins":27},"thinkingmachines/inkling":{"draws":41,"losses":26,"wins":61},"thinkingmachines/inkling-small":{"draws":32,"losses":20,"wins":44},"unbiased/pareto-26.10":{"draws":4,"losses":28,"wins":0},"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":25,"losses":44,"wins":27},"x-ai/grok-4.6":{"draws":33,"losses":47,"wins":16},"x-ai/grok-4.7":{"draws":8,"losses":63,"wins":13},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":54,"losses":34,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":21,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":59,"losses":62,"wins":71},"z-ai/glm-5.3":{"draws":23,"losses":55,"wins":14},"z-ai/glm-5.3-flash":{"draws":18,"losses":43,"wins":35},"z-ai/glm-5.3-flashx":{"draws":27,"losses":45,"wins":24}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":38,"wins":53},"claude-fable-5":{"draws":24,"losses":84,"wins":36},"claude-fable-5-1":{"draws":9,"losses":149,"wins":4},"claude-haiku-5-5":{"draws":34,"losses":67,"wins":37},"claude-opus-4-5":{"draws":69,"losses":70,"wins":95},"claude-opus-4-8":{"draws":25,"losses":60,"wins":47},"claude-opus-5":{"draws":36,"losses":179,"wins":31},"claude-opus-5-5":{"draws":13,"losses":130,"wins":13},"claude-sonnet-5":{"draws":44,"losses":41,"wins":59},"claude-sonnet-5-5":{"draws":20,"losses":82,"wins":42},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":42},"deepseek/deepseek-v4-flash":{"draws":59,"losses":38,"wins":119},"deepseek/deepseek-v4-pro":{"draws":37,"losses":36,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":39,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":53,"wins":56},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":82,"wins":33},"elorian/glimpse":{"draws":17,"losses":30,"wins":31},"fireworks/ember-1":{"draws":38,"losses":60,"wins":46},"gemini-3.1-pro-preview":{"draws":36,"losses":47,"wins":61},"gemini-4-argon":{"draws":9,"losses":123,"wins":12},"google/gemini-3.1-flash-lite":{"draws":23,"losses":1,"wins":72},"google/gemini-3.5-flash":{"draws":49,"losses":63,"wins":68},"google/gemini-3.5-flash-lite":{"draws":69,"losses":52,"wins":131},"google/gemini-3.6-flash":{"draws":59,"losses":119,"wins":98},"google/gemini-3.8-flash":{"draws":32,"losses":61,"wins":51},"google/gemma-4-31b-it":{"draws":33,"losses":8,"wins":43},"gpt-4.1":{"draws":16,"losses":14,"wins":18},"gpt-4.1-nano":{"draws":10,"losses":1,"wins":7},"gpt-5":{"draws":34,"losses":28,"wins":64},"gpt-5.4":{"draws":32,"losses":54,"wins":52},"gpt-5.4-mini":{"draws":35,"losses":20,"wins":41},"gpt-5.4-nano":{"draws":32,"losses":38,"wins":74},"gpt-5.5":{"draws":40,"losses":49,"wins":43},"gpt-5.6-luna":{"draws":43,"losses":29,"wins":72},"gpt-5.6-sol":{"draws":25,"losses":88,"wins":31},"gpt-5.6-terra":{"draws":46,"losses":41,"wins":51},"gpt-6-astra":{"draws":13,"losses":127,"wins":4},"gpt-6-luna":{"draws":35,"losses":48,"wins":61},"gpt-6-sol":{"draws":16,"losses":102,"wins":26},"gpt-6.1-sol":{"draws":10,"losses":128,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":37,"losses":8,"wins":57},"inception/mercury-3":{"draws":30,"losses":26,"wins":40},"inclusionai/ling-3.0-flash":{"draws":37,"losses":14,"wins":51},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":41,"losses":28,"wins":87},"meta/muse-glimmer-30b":{"draws":33,"losses":24,"wins":69},"meta/muse-spark-1.2":{"draws":37,"losses":49,"wins":52},"meta/muse-spark-1.3":{"draws":33,"losses":72,"wins":39},"meta/muse-spark-open":{"draws":28,"losses":66,"wins":44},"meta/muse-wonder":{"draws":31,"losses":81,"wins":32},"minimax/minimax-m3":{"draws":19,"losses":13,"wins":46},"minimax/minimax-m3.1-flash":{"draws":30,"losses":37,"wins":59},"mistralai/mistral-large-4-0":{"draws":31,"losses":30,"wins":29},"mistralai/mistral-medium-3-5":{"draws":23,"losses":10,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":12,"wins":15},"moonshotai/kimi-k3":{"draws":36,"losses":47,"wins":55},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":114,"wins":24},"nex-agi/nex-n2-pro":{"draws":18,"losses":8,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":7,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":22,"wins":68},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":18,"wins":31},"o3":{"draws":34,"losses":64,"wins":100},"openai/gpt-oss-120b":{"draws":38,"losses":10,"wins":78},"poolside/laguna-s-2.1":{"draws":35,"losses":32,"wins":71},"qwen/qwen3.7-max":{"draws":22,"losses":24,"wins":38},"qwen/qwen3.7-plus":{"draws":25,"losses":17,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":48,"wins":54},"qwen/qwen3.8-27b":{"draws":30,"losses":39,"wins":33},"qwen/qwen3.8-flash":{"draws":28,"losses":29,"wins":39},"qwen/qwen3.8-max":{"draws":24,"losses":36,"wins":36},"qwen/qwen3.8-max-0902":{"draws":35,"losses":62,"wins":47},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":39,"wins":65},"stealth/ox-alpha":{"draws":117,"losses":195,"wins":162},"stealth/space-bunny-alpha":{"draws":33,"losses":30,"wins":51},"stepfun/step-3.7-flash":{"draws":23,"losses":17,"wins":62},"stepfun/step-5-preview":{"draws":4,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":28,"losses":13,"wins":37},"tencent/hy4-preview":{"draws":31,"losses":60,"wins":47},"thinkingmachines/inkling":{"draws":56,"losses":30,"wins":106},"thinkingmachines/inkling-small":{"draws":37,"losses":39,"wins":68},"unbiased/pareto-26.10":{"draws":1,"losses":47,"wins":0},"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":32,"losses":68,"wins":44},"x-ai/grok-4.6":{"draws":37,"losses":63,"wins":44},"x-ai/grok-4.7":{"draws":11,"losses":90,"wins":25},"x-ai/grok-build-0.1":{"draws":15,"losses":7,"wins":26},"xiaomi/mimo-v2.5":{"draws":69,"losses":41,"wins":112},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":24,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":36,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":52,"wins":19},"z-ai/glm-5.2":{"draws":82,"losses":80,"wins":126},"z-ai/glm-5.3":{"draws":27,"losses":80,"wins":31},"z-ai/glm-5.3-flash":{"draws":28,"losses":58,"wins":58},"z-ai/glm-5.3-flashx":{"draws":35,"losses":57,"wins":52}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":24,"wins":77},"claude-fable-5":{"draws":28,"losses":81,"wins":35},"claude-fable-5-1":{"draws":10,"losses":137,"wins":15},"claude-haiku-5-5":{"draws":40,"losses":51,"wins":47},"claude-opus-4-5":{"draws":64,"losses":79,"wins":91},"claude-opus-4-8":{"draws":29,"losses":51,"wins":52},"claude-opus-5":{"draws":34,"losses":171,"wins":41},"claude-opus-5-5":{"draws":13,"losses":131,"wins":12},"claude-sonnet-5":{"draws":35,"losses":39,"wins":70},"claude-sonnet-5-5":{"draws":26,"losses":65,"wins":53},"cohere/north-mini-code":{"draws":8,"losses":5,"wins":41},"deepseek/deepseek-v4-flash":{"draws":57,"losses":36,"wins":123},"deepseek/deepseek-v4-pro":{"draws":34,"losses":35,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":38,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":42,"losses":49,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":32,"losses":72,"wins":40},"elorian/glimpse":{"draws":20,"losses":28,"wins":30},"fireworks/ember-1":{"draws":37,"losses":44,"wins":63},"gemini-3.1-pro-preview":{"draws":31,"losses":41,"wins":72},"gemini-4-argon":{"draws":12,"losses":118,"wins":14},"google/gemini-3.1-flash-lite":{"draws":24,"losses":3,"wins":69},"google/gemini-3.5-flash":{"draws":44,"losses":46,"wins":90},"google/gemini-3.5-flash-lite":{"draws":69,"losses":37,"wins":146},"google/gemini-3.6-flash":{"draws":69,"losses":99,"wins":108},"google/gemini-3.8-flash":{"draws":37,"losses":59,"wins":48},"google/gemma-4-31b-it":{"draws":29,"losses":9,"wins":46},"gpt-4.1":{"draws":14,"losses":10,"wins":24},"gpt-4.1-nano":{"draws":7,"losses":1,"wins":10},"gpt-5":{"draws":32,"losses":32,"wins":62},"gpt-5.4":{"draws":29,"losses":62,"wins":47},"gpt-5.4-mini":{"draws":38,"losses":15,"wins":43},"gpt-5.4-nano":{"draws":35,"losses":35,"wins":74},"gpt-5.5":{"draws":43,"losses":45,"wins":44},"gpt-5.6-luna":{"draws":43,"losses":36,"wins":65},"gpt-5.6-sol":{"draws":21,"losses":90,"wins":33},"gpt-5.6-terra":{"draws":43,"losses":37,"wins":58},"gpt-6-astra":{"draws":9,"losses":129,"wins":6},"gpt-6-luna":{"draws":38,"losses":48,"wins":58},"gpt-6-sol":{"draws":18,"losses":98,"wins":28},"gpt-6.1-sol":{"draws":11,"losses":121,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":39,"losses":10,"wins":53},"inception/mercury-3":{"draws":27,"losses":30,"wins":39},"inclusionai/ling-3.0-flash":{"draws":37,"losses":9,"wins":56},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":27,"wins":106},"meta/muse-glimmer-30b":{"draws":38,"losses":13,"wins":75},"meta/muse-spark-1.2":{"draws":32,"losses":51,"wins":55},"meta/muse-spark-1.3":{"draws":36,"losses":54,"wins":54},"meta/muse-spark-open":{"draws":30,"losses":52,"wins":56},"meta/muse-wonder":{"draws":33,"losses":78,"wins":33},"minimax/minimax-m3":{"draws":19,"losses":8,"wins":51},"minimax/minimax-m3.1-flash":{"draws":31,"losses":30,"wins":65},"mistralai/mistral-large-4-0":{"draws":32,"losses":18,"wins":40},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":52},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":9,"wins":18},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":112,"wins":20},"nex-agi/nex-n2-pro":{"draws":18,"losses":10,"wins":44},"nex-agi/nex-n2.5-pro":{"draws":7,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":14,"wins":70},"nvidia/nemotron-3.5-super-vl":{"draws":18,"losses":16,"wins":32},"o3":{"draws":35,"losses":64,"wins":99},"openai/gpt-oss-120b":{"draws":33,"losses":16,"wins":77},"poolside/laguna-s-2.1":{"draws":41,"losses":24,"wins":73},"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":44,"losses":45,"wins":55},"qwen/qwen3.8-27b":{"draws":24,"losses":27,"wins":51},"qwen/qwen3.8-flash":{"draws":31,"losses":32,"wins":33},"qwen/qwen3.8-max":{"draws":35,"losses":47,"wins":62},"qwen/qwen3.8-max-0902":{"draws":24,"losses":36,"wins":36},"recursive/flint-v1.0":{"draws":9,"losses":6,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":38,"wins":63},"stealth/ox-alpha":{"draws":101,"losses":186,"wins":187},"stealth/space-bunny-alpha":{"draws":30,"losses":22,"wins":62},"stepfun/step-3.7-flash":{"draws":25,"losses":19,"wins":58},"stepfun/step-5-preview":{"draws":5,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":25,"losses":13,"wins":40},"tencent/hy4-preview":{"draws":33,"losses":55,"wins":50},"thinkingmachines/inkling":{"draws":54,"losses":30,"wins":108},"thinkingmachines/inkling-small":{"draws":41,"losses":17,"wins":86},"unbiased/pareto-26.10":{"draws":2,"losses":44,"wins":2},"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":39,"losses":68,"wins":37},"x-ai/grok-4.7":{"draws":18,"losses":79,"wins":29},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":25},"xiaomi/mimo-v2.5":{"draws":73,"losses":30,"wins":119},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":20,"wins":45},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":41,"wins":36},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":52,"wins":29},"z-ai/glm-5.2":{"draws":91,"losses":59,"wins":138},"z-ai/glm-5.3":{"draws":31,"losses":76,"wins":31},"z-ai/glm-5.3-flash":{"draws":38,"losses":53,"wins":53},"z-ai/glm-5.3-flashx":{"draws":30,"losses":61,"wins":53}},"recursive/flint-v1.0":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":21,"wins":9},"claude-fable-5":{"draws":3,"losses":39,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":25,"wins":8},"claude-opus-4-5":{"draws":18,"losses":47,"wins":5},"claude-opus-4-8":{"draws":11,"losses":29,"wins":2},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":27,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":36,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":27,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":1},"elorian/glimpse":{"draws":5,"losses":13,"wins":4},"fireworks/ember-1":{"draws":10,"losses":27,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":27,"wins":4},"gemini-4-argon":{"draws":3,"losses":39,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":20,"losses":42,"wins":12},"google/gemini-3.6-flash":{"draws":26,"losses":45,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":7},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":10},"gpt-5.4":{"draws":6,"losses":30,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":17},"gpt-5.5":{"draws":11,"losses":25,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":23,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":38,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":28,"wins":2},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":11,"losses":26,"wins":5},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"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":12,"losses":8,"wins":12},"inception/mercury-3":{"draws":8,"losses":14,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":22,"wins":13},"meta/muse-glimmer-30b":{"draws":11,"losses":17,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":30,"wins":3},"meta/muse-spark-1.3":{"draws":4,"losses":34,"wins":4},"meta/muse-spark-open":{"draws":5,"losses":32,"wins":3},"meta/muse-wonder":{"draws":6,"losses":36,"wins":0},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":19,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":17,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":17,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":1},"o3":{"draws":4,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":19,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":24,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":17,"wins":3},"qwen/qwen3.8-max":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.8-max-0902":{"draws":9,"losses":27,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":29,"wins":1},"stealth/ox-alpha":{"draws":23,"losses":85,"wins":10},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":16,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":14},"thinkingmachines/inkling-small":{"draws":12,"losses":14,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":0},"x-ai/grok-4.6":{"draws":7,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":20,"losses":31,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":14,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":17,"losses":49,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":9},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":3}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":31,"wins":57},"claude-fable-5":{"draws":25,"losses":81,"wins":26},"claude-fable-5-1":{"draws":7,"losses":141,"wins":2},"claude-haiku-5-5":{"draws":25,"losses":66,"wins":35},"claude-opus-4-5":{"draws":74,"losses":68,"wins":72},"claude-opus-4-8":{"draws":26,"losses":62,"wins":32},"claude-opus-5":{"draws":29,"losses":180,"wins":23},"claude-opus-5-5":{"draws":14,"losses":126,"wins":4},"claude-sonnet-5":{"draws":39,"losses":47,"wins":46},"claude-sonnet-5-5":{"draws":31,"losses":67,"wins":34},"cohere/north-mini-code":{"draws":4,"losses":9,"wins":39},"deepseek/deepseek-v4-flash":{"draws":42,"losses":42,"wins":112},"deepseek/deepseek-v4-pro":{"draws":30,"losses":45,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":39,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":34,"losses":60,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":76,"wins":27},"elorian/glimpse":{"draws":18,"losses":33,"wins":21},"fireworks/ember-1":{"draws":36,"losses":45,"wins":51},"gemini-3.1-pro-preview":{"draws":31,"losses":48,"wins":53},"gemini-4-argon":{"draws":7,"losses":112,"wins":13},"google/gemini-3.1-flash-lite":{"draws":14,"losses":7,"wins":65},"google/gemini-3.5-flash":{"draws":41,"losses":55,"wins":68},"google/gemini-3.5-flash-lite":{"draws":63,"losses":47,"wins":120},"google/gemini-3.6-flash":{"draws":59,"losses":114,"wins":79},"google/gemini-3.8-flash":{"draws":26,"losses":71,"wins":35},"google/gemma-4-31b-it":{"draws":19,"losses":12,"wins":47},"gpt-4.1":{"draws":13,"losses":13,"wins":18},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":7},"gpt-5":{"draws":23,"losses":39,"wins":54},"gpt-5.4":{"draws":31,"losses":58,"wins":37},"gpt-5.4-mini":{"draws":28,"losses":18,"wins":42},"gpt-5.4-nano":{"draws":25,"losses":34,"wins":69},"gpt-5.5":{"draws":30,"losses":60,"wins":32},"gpt-5.6-luna":{"draws":43,"losses":34,"wins":55},"gpt-5.6-sol":{"draws":21,"losses":87,"wins":24},"gpt-5.6-terra":{"draws":35,"losses":43,"wins":48},"gpt-6-astra":{"draws":11,"losses":117,"wins":4},"gpt-6-luna":{"draws":28,"losses":57,"wins":47},"gpt-6-sol":{"draws":18,"losses":98,"wins":16},"gpt-6.1-sol":{"draws":6,"losses":120,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":36,"losses":6,"wins":52},"inception/mercury-3":{"draws":28,"losses":29,"wins":31},"inclusionai/ling-3.0-flash":{"draws":29,"losses":16,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":30,"losses":29,"wins":85},"meta/muse-glimmer-30b":{"draws":36,"losses":20,"wins":62},"meta/muse-spark-1.2":{"draws":29,"losses":55,"wins":44},"meta/muse-spark-1.3":{"draws":23,"losses":73,"wins":36},"meta/muse-spark-open":{"draws":27,"losses":65,"wins":34},"meta/muse-wonder":{"draws":21,"losses":85,"wins":26},"minimax/minimax-m3":{"draws":13,"losses":12,"wins":47},"minimax/minimax-m3.1-flash":{"draws":28,"losses":40,"wins":46},"mistralai/mistral-large-4-0":{"draws":25,"losses":26,"wins":33},"mistralai/mistral-medium-3-5":{"draws":19,"losses":8,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":13,"wins":11},"moonshotai/kimi-k3":{"draws":35,"losses":52,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":111,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":12,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":11,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":18,"wins":69},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":18,"wins":28},"o3":{"draws":24,"losses":64,"wins":88},"openai/gpt-oss-120b":{"draws":36,"losses":17,"wins":65},"poolside/laguna-s-2.1":{"draws":30,"losses":29,"wins":69},"qwen/qwen3.7-max":{"draws":19,"losses":21,"wins":36},"qwen/qwen3.7-plus":{"draws":17,"losses":17,"wins":30},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":65,"wins":36},"qwen/qwen3.8-27b":{"draws":22,"losses":34,"wins":34},"qwen/qwen3.8-flash":{"draws":21,"losses":33,"wins":34},"qwen/qwen3.8-max":{"draws":28,"losses":65,"wins":39},"qwen/qwen3.8-max-0902":{"draws":31,"losses":63,"wins":38},"recursive/flint-v1.0":{"draws":8,"losses":1,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":28,"wins":28},"stealth/ox-alpha":{"draws":93,"losses":200,"wins":149},"stealth/space-bunny-alpha":{"draws":32,"losses":22,"wins":52},"stepfun/step-3.7-flash":{"draws":16,"losses":31,"wins":43},"stepfun/step-5-preview":{"draws":0,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":18,"losses":19,"wins":35},"tencent/hy4-preview":{"draws":35,"losses":60,"wins":31},"thinkingmachines/inkling":{"draws":52,"losses":33,"wins":91},"thinkingmachines/inkling-small":{"draws":42,"losses":27,"wins":63},"unbiased/pareto-26.10":{"draws":2,"losses":42,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":43,"wins":0},"upstage/solar-mini4":{"draws":4,"losses":7,"wins":19},"x-ai/grok-4.5":{"draws":38,"losses":63,"wins":31},"x-ai/grok-4.6":{"draws":35,"losses":69,"wins":28},"x-ai/grok-4.7":{"draws":13,"losses":93,"wins":10},"x-ai/grok-build-0.1":{"draws":12,"losses":11,"wins":21},"xiaomi/mimo-v2.5":{"draws":65,"losses":32,"wins":103},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":21,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":35,"wins":35},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":47,"wins":26},"z-ai/glm-5.2":{"draws":75,"losses":84,"wins":105},"z-ai/glm-5.3":{"draws":18,"losses":88,"wins":22},"z-ai/glm-5.3-flash":{"draws":23,"losses":70,"wins":39},"z-ai/glm-5.3-flashx":{"draws":23,"losses":68,"wins":41}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":92,"losses":89,"wins":259},"claude-fable-5":{"draws":75,"losses":277,"wins":122},"claude-fable-5-1":{"draws":26,"losses":498,"wins":26},"claude-haiku-5-5":{"draws":95,"losses":174,"wins":165},"claude-opus-4-5":{"draws":187,"losses":224,"wins":339},"claude-opus-4-8":{"draws":76,"losses":156,"wins":162},"claude-opus-5":{"draws":133,"losses":577,"wins":122},"claude-opus-5-5":{"draws":45,"losses":433,"wins":28},"claude-sonnet-5":{"draws":102,"losses":131,"wins":241},"claude-sonnet-5-5":{"draws":78,"losses":233,"wins":163},"cohere/north-mini-code":{"draws":24,"losses":22,"wins":132},"deepseek/deepseek-v4-flash":{"draws":158,"losses":134,"wins":404},"deepseek/deepseek-v4-pro":{"draws":103,"losses":132,"wins":207},"deepseek/deepseek-v4-pro-0813":{"draws":101,"losses":152,"wins":187},"deepseek/deepseek-v4.1-flash":{"draws":103,"losses":184,"wins":187},"deepseek/deepseek-v4.1-flash-1017":{"draws":79,"losses":232,"wins":163},"elorian/glimpse":{"draws":65,"losses":94,"wins":107},"fireworks/ember-1":{"draws":112,"losses":177,"wins":185},"gemini-3.1-pro-preview":{"draws":94,"losses":148,"wins":232},"gemini-4-argon":{"draws":45,"losses":380,"wins":49},"google/gemini-3.1-flash-lite":{"draws":47,"losses":29,"wins":196},"google/gemini-3.5-flash":{"draws":94,"losses":203,"wins":279},"google/gemini-3.5-flash-lite":{"draws":172,"losses":168,"wins":486},"google/gemini-3.6-flash":{"draws":178,"losses":365,"wins":373},"google/gemini-3.8-flash":{"draws":93,"losses":228,"wins":153},"google/gemma-4-31b-it":{"draws":60,"losses":40,"wins":160},"gpt-4.1":{"draws":39,"losses":38,"wins":81},"gpt-4.1-nano":{"draws":33,"losses":5,"wins":34},"gpt-5":{"draws":89,"losses":133,"wins":202},"gpt-5.4":{"draws":113,"losses":184,"wins":161},"gpt-5.4-mini":{"draws":84,"losses":61,"wins":171},"gpt-5.4-nano":{"draws":69,"losses":123,"wins":232},"gpt-5.5":{"draws":110,"losses":160,"wins":172},"gpt-5.6-luna":{"draws":139,"losses":104,"wins":231},"gpt-5.6-sol":{"draws":68,"losses":292,"wins":114},"gpt-5.6-terra":{"draws":118,"losses":130,"wins":208},"gpt-6-astra":{"draws":35,"losses":417,"wins":22},"gpt-6-luna":{"draws":105,"losses":158,"wins":211},"gpt-6-sol":{"draws":61,"losses":341,"wins":72},"gpt-6.1-sol":{"draws":40,"losses":401,"wins":33},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":93,"losses":33,"wins":184},"inception/mercury-3":{"draws":79,"losses":103,"wins":130},"inclusionai/ling-3.0-flash":{"draws":84,"losses":33,"wins":211},"inclusionai/ling-3.1-flash":{"draws":6,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":101,"losses":83,"wins":326},"meta/muse-glimmer-30b":{"draws":90,"losses":60,"wins":276},"meta/muse-spark-1.2":{"draws":104,"losses":154,"wins":200},"meta/muse-spark-1.3":{"draws":90,"losses":219,"wins":165},"meta/muse-spark-open":{"draws":85,"losses":213,"wins":160},"meta/muse-wonder":{"draws":93,"losses":253,"wins":128},"minimax/minimax-m3":{"draws":50,"losses":40,"wins":152},"minimax/minimax-m3.1-flash":{"draws":87,"losses":115,"wins":224},"mistralai/mistral-large-4-0":{"draws":98,"losses":82,"wins":120},"mistralai/mistral-medium-3-5":{"draws":66,"losses":43,"wins":173},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":27,"wins":54},"moonshotai/kimi-k3":{"draws":103,"losses":170,"wins":185},"moonshotai/kimi-k3.1-pro":{"draws":54,"losses":352,"wins":68},"nex-agi/nex-n2-pro":{"draws":53,"losses":33,"wins":164},"nex-agi/nex-n2.5-pro":{"draws":26,"losses":20,"wins":62},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":84,"losses":62,"wins":228},"nvidia/nemotron-3.5-super-vl":{"draws":55,"losses":54,"wins":101},"o3":{"draws":77,"losses":209,"wins":318},"openai/gpt-oss-120b":{"draws":103,"losses":62,"wins":259},"poolside/laguna-s-2.1":{"draws":107,"losses":92,"wins":279},"qwen/qwen3.7-max":{"draws":56,"losses":62,"wins":140},"qwen/qwen3.7-plus":{"draws":38,"losses":27,"wins":137},"qwen/qwen3.8-2.4t-a95b":{"draws":118,"losses":181,"wins":175},"qwen/qwen3.8-27b":{"draws":72,"losses":107,"wins":153},"qwen/qwen3.8-flash":{"draws":79,"losses":103,"wins":134},"qwen/qwen3.8-max":{"draws":117,"losses":162,"wins":195},"qwen/qwen3.8-max-0902":{"draws":101,"losses":187,"wins":186},"recursive/flint-v1.0":{"draws":23,"losses":10,"wins":85},"reflection/beam-1.0-501b-a23b":{"draws":93,"losses":149,"wins":200},"stealth/ox-alpha":{"draws":274,"losses":683,"wins":683},"stealth/space-bunny-alpha":{"draws":92,"losses":85,"wins":193},"stepfun/step-3.7-flash":{"draws":51,"losses":57,"wins":224},"stepfun/step-5-preview":{"draws":8,"losses":15,"wins":9},"tencent/hy3-preview":{"draws":70,"losses":45,"wins":127},"tencent/hy4-preview":{"draws":95,"losses":194,"wins":169},"thinkingmachines/inkling":{"draws":159,"losses":123,"wins":376},"thinkingmachines/inkling-small":{"draws":118,"losses":73,"wins":283},"unbiased/pareto-26.10":{"draws":11,"losses":143,"wins":4},"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":98,"losses":211,"wins":165},"x-ai/grok-4.6":{"draws":128,"losses":197,"wins":149},"x-ai/grok-4.7":{"draws":42,"losses":282,"wins":76},"x-ai/grok-build-0.1":{"draws":33,"losses":20,"wins":105},"xiaomi/mimo-v2.5":{"draws":162,"losses":97,"wins":387},"xiaomi/mimo-v2.5-pro":{"draws":42,"losses":61,"wins":139},"xiaomi/mimo-v2.6-flash":{"draws":52,"losses":111,"wins":135},"xiaomi/mimo-v2.6-pro":{"draws":58,"losses":153,"wins":105},"z-ai/glm-5.2":{"draws":233,"losses":234,"wins":481},"z-ai/glm-5.3":{"draws":80,"losses":259,"wins":119},"z-ai/glm-5.3-flash":{"draws":74,"losses":213,"wins":187},"z-ai/glm-5.3-flashx":{"draws":83,"losses":224,"wins":167}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":34,"losses":30,"wins":40},"claude-fable-5":{"draws":29,"losses":70,"wins":15},"claude-fable-5-1":{"draws":3,"losses":125,"wins":2},"claude-haiku-5-5":{"draws":30,"losses":57,"wins":23},"claude-opus-4-5":{"draws":54,"losses":84,"wins":48},"claude-opus-4-8":{"draws":25,"losses":54,"wins":27},"claude-opus-5":{"draws":30,"losses":151,"wins":15},"claude-opus-5-5":{"draws":6,"losses":114,"wins":2},"claude-sonnet-5":{"draws":24,"losses":50,"wins":40},"claude-sonnet-5-5":{"draws":21,"losses":69,"wins":24},"cohere/north-mini-code":{"draws":11,"losses":7,"wins":28},"deepseek/deepseek-v4-flash":{"draws":48,"losses":49,"wins":71},"deepseek/deepseek-v4-pro":{"draws":30,"losses":47,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":48,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":62,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":76,"wins":18},"elorian/glimpse":{"draws":13,"losses":31,"wins":18},"fireworks/ember-1":{"draws":30,"losses":55,"wins":29},"gemini-3.1-pro-preview":{"draws":25,"losses":48,"wins":41},"gemini-4-argon":{"draws":7,"losses":103,"wins":4},"google/gemini-3.1-flash-lite":{"draws":17,"losses":13,"wins":50},"google/gemini-3.5-flash":{"draws":40,"losses":66,"wins":38},"google/gemini-3.5-flash-lite":{"draws":52,"losses":61,"wins":89},"google/gemini-3.6-flash":{"draws":54,"losses":117,"wins":49},"google/gemini-3.8-flash":{"draws":23,"losses":72,"wins":19},"google/gemma-4-31b-it":{"draws":26,"losses":16,"wins":26},"gpt-4.1":{"draws":11,"losses":14,"wins":13},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":5},"gpt-5":{"draws":20,"losses":41,"wins":39},"gpt-5.4":{"draws":30,"losses":61,"wins":19},"gpt-5.4-mini":{"draws":23,"losses":17,"wins":36},"gpt-5.4-nano":{"draws":23,"losses":39,"wins":50},"gpt-5.5":{"draws":38,"losses":47,"wins":21},"gpt-5.6-luna":{"draws":33,"losses":36,"wins":45},"gpt-5.6-sol":{"draws":19,"losses":81,"wins":14},"gpt-5.6-terra":{"draws":35,"losses":41,"wins":32},"gpt-6-astra":{"draws":6,"losses":108,"wins":0},"gpt-6-luna":{"draws":37,"losses":52,"wins":25},"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":31,"losses":13,"wins":38},"inception/mercury-3":{"draws":19,"losses":33,"wins":20},"inclusionai/ling-3.0-flash":{"draws":30,"losses":13,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":32,"losses":31,"wins":63},"meta/muse-glimmer-30b":{"draws":35,"losses":27,"wins":40},"meta/muse-spark-1.2":{"draws":29,"losses":55,"wins":26},"meta/muse-spark-1.3":{"draws":18,"losses":74,"wins":22},"meta/muse-spark-open":{"draws":24,"losses":62,"wins":24},"meta/muse-wonder":{"draws":28,"losses":68,"wins":18},"minimax/minimax-m3":{"draws":13,"losses":15,"wins":34},"minimax/minimax-m3.1-flash":{"draws":24,"losses":37,"wins":41},"mistralai/mistral-large-4-0":{"draws":26,"losses":32,"wins":14},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":14,"wins":7},"moonshotai/kimi-k3":{"draws":35,"losses":53,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":97,"wins":10},"nex-agi/nex-n2-pro":{"draws":16,"losses":13,"wins":29},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":23,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":21,"wins":16},"o3":{"draws":24,"losses":79,"wins":57},"openai/gpt-oss-120b":{"draws":28,"losses":24,"wins":48},"poolside/laguna-s-2.1":{"draws":31,"losses":29,"wins":46},"qwen/qwen3.7-max":{"draws":15,"losses":29,"wins":22},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":45,"wins":28},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":20},"qwen/qwen3.8-flash":{"draws":26,"losses":30,"wins":20},"qwen/qwen3.8-max":{"draws":33,"losses":51,"wins":30},"qwen/qwen3.8-max-0902":{"draws":30,"losses":62,"wins":22},"recursive/flint-v1.0":{"draws":9,"losses":10,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":32,"losses":52,"wins":22},"stealth/ox-alpha":{"draws":92,"losses":193,"wins":85},"stealth/space-bunny-alpha":{"draws":16,"losses":20,"wins":20},"stepfun/step-3.7-flash":{"draws":19,"losses":23,"wins":38},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":23,"losses":17,"wins":22},"tencent/hy4-preview":{"draws":30,"losses":53,"wins":27},"thinkingmachines/inkling":{"draws":48,"losses":46,"wins":60},"thinkingmachines/inkling-small":{"draws":34,"losses":27,"wins":53},"unbiased/pareto-26.10":{"draws":3,"losses":35,"wins":0},"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":30,"losses":63,"wins":21},"x-ai/grok-4.6":{"draws":30,"losses":63,"wins":21},"x-ai/grok-4.7":{"draws":10,"losses":73,"wins":17},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":19},"xiaomi/mimo-v2.5":{"draws":60,"losses":43,"wins":75},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":17,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":42,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":38,"wins":19},"z-ai/glm-5.2":{"draws":75,"losses":77,"wins":76},"z-ai/glm-5.3":{"draws":21,"losses":80,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":66,"wins":20},"z-ai/glm-5.3-flashx":{"draws":24,"losses":66,"wins":24}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":38,"wins":33},"claude-fable-5":{"draws":13,"losses":82,"wins":7},"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":32,"losses":94,"wins":40},"claude-opus-4-8":{"draws":16,"losses":60,"wins":18},"claude-opus-5":{"draws":15,"losses":140,"wins":7},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":21,"losses":54,"wins":27},"claude-sonnet-5-5":{"draws":11,"losses":65,"wins":26},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":25},"deepseek/deepseek-v4-flash":{"draws":34,"losses":66,"wins":58},"deepseek/deepseek-v4-pro":{"draws":17,"losses":55,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":56,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":63,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":74,"wins":15},"elorian/glimpse":{"draws":5,"losses":38,"wins":13},"fireworks/ember-1":{"draws":23,"losses":61,"wins":18},"gemini-3.1-pro-preview":{"draws":21,"losses":49,"wins":32},"gemini-4-argon":{"draws":0,"losses":98,"wins":4},"google/gemini-3.1-flash-lite":{"draws":16,"losses":10,"wins":48},"google/gemini-3.5-flash":{"draws":22,"losses":81,"wins":27},"google/gemini-3.5-flash-lite":{"draws":49,"losses":71,"wins":60},"google/gemini-3.6-flash":{"draws":34,"losses":132,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":77,"wins":9},"google/gemma-4-31b-it":{"draws":18,"losses":13,"wins":27},"gpt-4.1":{"draws":7,"losses":21,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":21,"losses":53,"wins":18},"gpt-5.4":{"draws":18,"losses":66,"wins":16},"gpt-5.4-mini":{"draws":21,"losses":24,"wins":23},"gpt-5.4-nano":{"draws":16,"losses":60,"wins":34},"gpt-5.5":{"draws":26,"losses":54,"wins":14},"gpt-5.6-luna":{"draws":27,"losses":44,"wins":31},"gpt-5.6-sol":{"draws":11,"losses":85,"wins":6},"gpt-5.6-terra":{"draws":24,"losses":53,"wins":21},"gpt-6-astra":{"draws":6,"losses":96,"wins":0},"gpt-6-luna":{"draws":21,"losses":57,"wins":24},"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":20,"losses":10,"wins":38},"inception/mercury-3":{"draws":15,"losses":39,"wins":14},"inclusionai/ling-3.0-flash":{"draws":26,"losses":20,"wins":30},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":45,"wins":49},"meta/muse-glimmer-30b":{"draws":20,"losses":41,"wins":27},"meta/muse-spark-1.2":{"draws":15,"losses":57,"wins":24},"meta/muse-spark-1.3":{"draws":10,"losses":79,"wins":13},"meta/muse-spark-open":{"draws":13,"losses":71,"wins":16},"meta/muse-wonder":{"draws":12,"losses":80,"wins":10},"minimax/minimax-m3":{"draws":11,"losses":28,"wins":17},"minimax/minimax-m3.1-flash":{"draws":12,"losses":54,"wins":26},"mistralai/mistral-large-4-0":{"draws":20,"losses":33,"wins":9},"mistralai/mistral-medium-3-5":{"draws":19,"losses":13,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":15,"wins":5},"moonshotai/kimi-k3":{"draws":21,"losses":59,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":96,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":17,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":11,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":33,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":30,"wins":7},"o3":{"draws":24,"losses":93,"wins":43},"openai/gpt-oss-120b":{"draws":29,"losses":23,"wins":36},"poolside/laguna-s-2.1":{"draws":31,"losses":37,"wins":30},"qwen/qwen3.7-max":{"draws":16,"losses":34,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":23,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":71,"wins":15},"qwen/qwen3.8-27b":{"draws":12,"losses":38,"wins":26},"qwen/qwen3.8-flash":{"draws":14,"losses":40,"wins":14},"qwen/qwen3.8-max":{"draws":23,"losses":62,"wins":17},"qwen/qwen3.8-max-0902":{"draws":25,"losses":58,"wins":19},"recursive/flint-v1.0":{"draws":3,"losses":11,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":43,"wins":31},"stealth/ox-alpha":{"draws":51,"losses":224,"wins":57},"stealth/space-bunny-alpha":{"draws":19,"losses":38,"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":18,"losses":22,"wins":12},"tencent/hy4-preview":{"draws":20,"losses":63,"wins":17},"thinkingmachines/inkling":{"draws":37,"losses":39,"wins":62},"thinkingmachines/inkling-small":{"draws":28,"losses":37,"wins":37},"unbiased/pareto-26.10":{"draws":3,"losses":31,"wins":0},"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":71,"wins":19},"x-ai/grok-4.6":{"draws":21,"losses":67,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":75,"wins":10},"x-ai/grok-build-0.1":{"draws":10,"losses":9,"wins":15},"xiaomi/mimo-v2.5":{"draws":44,"losses":53,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":34,"wins":16},"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":50,"losses":105,"wins":49},"z-ai/glm-5.3":{"draws":15,"losses":78,"wins":3},"z-ai/glm-5.3-flash":{"draws":15,"losses":67,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":75,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":8,"wins":4},"elorian/glimpse":{"draws":0,"losses":6,"wins":2},"fireworks/ember-1":{"draws":3,"losses":5,"wins":4},"gemini-3.1-pro-preview":{"draws":4,"losses":4,"wins":4},"gemini-4-argon":{"draws":0,"losses":10,"wins":2},"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},"inception/mercury-3":{"draws":0,"losses":5,"wins":7},"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-spark-open":{"draws":0,"losses":7,"wins":5},"meta/muse-wonder":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":3},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":5},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"wins":6},"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":{"draws":0,"losses":4,"wins":0},"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":22,"losses":26,"wins":24},"claude-fable-5":{"draws":21,"losses":45,"wins":12},"claude-fable-5-1":{"draws":7,"losses":75,"wins":4},"claude-haiku-5-5":{"draws":25,"losses":31,"wins":20},"claude-opus-4-5":{"draws":46,"losses":54,"wins":28},"claude-opus-4-8":{"draws":17,"losses":40,"wins":17},"claude-opus-5":{"draws":24,"losses":106,"wins":12},"claude-opus-5-5":{"draws":8,"losses":78,"wins":0},"claude-sonnet-5":{"draws":25,"losses":32,"wins":21},"claude-sonnet-5-5":{"draws":19,"losses":49,"wins":10},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":13},"deepseek/deepseek-v4-flash":{"draws":34,"losses":40,"wins":42},"deepseek/deepseek-v4-pro":{"draws":24,"losses":29,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":24,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":39,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":48,"wins":10},"elorian/glimpse":{"draws":12,"losses":19,"wins":11},"fireworks/ember-1":{"draws":29,"losses":35,"wins":14},"gemini-3.1-pro-preview":{"draws":21,"losses":33,"wins":24},"gemini-4-argon":{"draws":4,"losses":71,"wins":3},"google/gemini-3.1-flash-lite":{"draws":17,"losses":13,"wins":22},"google/gemini-3.5-flash":{"draws":26,"losses":43,"wins":29},"google/gemini-3.5-flash-lite":{"draws":49,"losses":27,"wins":60},"google/gemini-3.6-flash":{"draws":44,"losses":74,"wins":30},"google/gemini-3.8-flash":{"draws":31,"losses":39,"wins":8},"google/gemma-4-31b-it":{"draws":21,"losses":9,"wins":16},"gpt-4.1":{"draws":10,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":20,"losses":21,"wins":27},"gpt-5.4":{"draws":26,"losses":34,"wins":14},"gpt-5.4-mini":{"draws":21,"losses":14,"wins":17},"gpt-5.4-nano":{"draws":20,"losses":23,"wins":37},"gpt-5.5":{"draws":33,"losses":30,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":23,"wins":30},"gpt-5.6-sol":{"draws":14,"losses":56,"wins":8},"gpt-5.6-terra":{"draws":29,"losses":29,"wins":16},"gpt-6-astra":{"draws":10,"losses":68,"wins":0},"gpt-6-luna":{"draws":25,"losses":32,"wins":21},"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":27,"losses":14,"wins":15},"inception/mercury-3":{"draws":17,"losses":22,"wins":13},"inclusionai/ling-3.0-flash":{"draws":22,"losses":8,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":23,"wins":35},"meta/muse-glimmer-30b":{"draws":25,"losses":14,"wins":31},"meta/muse-spark-1.2":{"draws":21,"losses":43,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":48,"wins":15},"meta/muse-spark-open":{"draws":17,"losses":40,"wins":17},"meta/muse-wonder":{"draws":15,"losses":51,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":12,"wins":18},"minimax/minimax-m3.1-flash":{"draws":16,"losses":22,"wins":28},"mistralai/mistral-large-4-0":{"draws":20,"losses":14,"wins":16},"mistralai/mistral-medium-3-5":{"draws":17,"losses":13,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":8,"wins":6},"moonshotai/kimi-k3":{"draws":28,"losses":28,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":63,"wins":5},"nex-agi/nex-n2-pro":{"draws":11,"losses":15,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":14,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":16,"wins":7},"o3":{"draws":22,"losses":43,"wins":39},"openai/gpt-oss-120b":{"draws":22,"losses":19,"wins":27},"poolside/laguna-s-2.1":{"draws":27,"losses":23,"wins":26},"qwen/qwen3.7-max":{"draws":19,"losses":16,"wins":11},"qwen/qwen3.7-plus":{"draws":16,"losses":11,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":35,"wins":15},"qwen/qwen3.8-27b":{"draws":15,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":18,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":28,"losses":37,"wins":13},"qwen/qwen3.8-max-0902":{"draws":25,"losses":40,"wins":13},"recursive/flint-v1.0":{"draws":8,"losses":5,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":35,"wins":19},"stealth/ox-alpha":{"draws":70,"losses":127,"wins":45},"stealth/space-bunny-alpha":{"draws":23,"losses":22,"wins":17},"stepfun/step-3.7-flash":{"draws":18,"losses":12,"wins":22},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":31,"wins":19},"thinkingmachines/inkling":{"draws":32,"losses":26,"wins":46},"thinkingmachines/inkling-small":{"draws":31,"losses":18,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"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":24,"losses":47,"wins":7},"x-ai/grok-4.6":{"draws":22,"losses":45,"wins":11},"x-ai/grok-4.7":{"draws":12,"losses":54,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.5":{"draws":49,"losses":34,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":17,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":26,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.2":{"draws":51,"losses":57,"wins":48},"z-ai/glm-5.3":{"draws":13,"losses":52,"wins":9},"z-ai/glm-5.3-flash":{"draws":22,"losses":42,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":49,"wins":13}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":18,"wins":75},"claude-fable-5":{"draws":18,"losses":90,"wins":30},"claude-fable-5-1":{"draws":9,"losses":134,"wins":13},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":54},"claude-opus-4-5":{"draws":57,"losses":63,"wins":104},"claude-opus-4-8":{"draws":29,"losses":48,"wins":49},"claude-opus-5":{"draws":21,"losses":177,"wins":36},"claude-opus-5-5":{"draws":10,"losses":125,"wins":15},"claude-sonnet-5":{"draws":35,"losses":39,"wins":64},"claude-sonnet-5-5":{"draws":22,"losses":68,"wins":48},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":36},"deepseek/deepseek-v4-flash":{"draws":48,"losses":41,"wins":117},"deepseek/deepseek-v4-pro":{"draws":26,"losses":39,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":46,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":39,"losses":41,"wins":58},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":71,"wins":43},"elorian/glimpse":{"draws":13,"losses":33,"wins":30},"fireworks/ember-1":{"draws":36,"losses":47,"wins":55},"gemini-3.1-pro-preview":{"draws":30,"losses":44,"wins":64},"gemini-4-argon":{"draws":15,"losses":105,"wins":18},"google/gemini-3.1-flash-lite":{"draws":19,"losses":6,"wins":69},"google/gemini-3.5-flash":{"draws":34,"losses":56,"wins":84},"google/gemini-3.5-flash-lite":{"draws":57,"losses":55,"wins":132},"google/gemini-3.6-flash":{"draws":51,"losses":116,"wins":99},"google/gemini-3.8-flash":{"draws":29,"losses":56,"wins":53},"google/gemma-4-31b-it":{"draws":26,"losses":11,"wins":43},"gpt-4.1":{"draws":13,"losses":10,"wins":23},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":11},"gpt-5":{"draws":32,"losses":37,"wins":53},"gpt-5.4":{"draws":27,"losses":60,"wins":47},"gpt-5.4-mini":{"draws":27,"losses":16,"wins":49},"gpt-5.4-nano":{"draws":17,"losses":29,"wins":92},"gpt-5.5":{"draws":38,"losses":42,"wins":48},"gpt-5.6-luna":{"draws":40,"losses":29,"wins":69},"gpt-5.6-sol":{"draws":19,"losses":72,"wins":47},"gpt-5.6-terra":{"draws":33,"losses":43,"wins":56},"gpt-6-astra":{"draws":10,"losses":123,"wins":5},"gpt-6-luna":{"draws":40,"losses":37,"wins":61},"gpt-6-sol":{"draws":18,"losses":95,"wins":25},"gpt-6.1-sol":{"draws":6,"losses":119,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":35,"losses":11,"wins":50},"inception/mercury-3":{"draws":22,"losses":28,"wins":40},"inclusionai/ling-3.0-flash":{"draws":32,"losses":12,"wins":54},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":39,"losses":23,"wins":90},"meta/muse-glimmer-30b":{"draws":33,"losses":14,"wins":75},"meta/muse-spark-1.2":{"draws":24,"losses":49,"wins":59},"meta/muse-spark-1.3":{"draws":24,"losses":64,"wins":50},"meta/muse-spark-open":{"draws":22,"losses":64,"wins":48},"meta/muse-wonder":{"draws":28,"losses":71,"wins":39},"minimax/minimax-m3":{"draws":15,"losses":9,"wins":50},"minimax/minimax-m3.1-flash":{"draws":26,"losses":41,"wins":55},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":36},"mistralai/mistral-medium-3-5":{"draws":19,"losses":12,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":10,"wins":17},"moonshotai/kimi-k3":{"draws":31,"losses":45,"wins":56},"moonshotai/kimi-k3.1-pro":{"draws":13,"losses":103,"wins":22},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":49},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":20,"wins":67},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":16,"wins":33},"o3":{"draws":25,"losses":67,"wins":104},"openai/gpt-oss-120b":{"draws":38,"losses":21,"wins":61},"poolside/laguna-s-2.1":{"draws":26,"losses":36,"wins":70},"qwen/qwen3.7-max":{"draws":11,"losses":22,"wins":47},"qwen/qwen3.7-plus":{"draws":11,"losses":16,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":49,"wins":53},"qwen/qwen3.8-27b":{"draws":25,"losses":28,"wins":45},"qwen/qwen3.8-flash":{"draws":22,"losses":27,"wins":43},"qwen/qwen3.8-max":{"draws":31,"losses":47,"wins":60},"qwen/qwen3.8-max-0902":{"draws":33,"losses":50,"wins":55},"recursive/flint-v1.0":{"draws":9,"losses":4,"wins":27},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":31,"wins":60},"stealth/ox-alpha":{"draws":95,"losses":169,"wins":194},"stealth/space-bunny-alpha":{"draws":30,"losses":27,"wins":53},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":63},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":19,"wins":31},"tencent/hy4-preview":{"draws":16,"losses":36,"wins":36},"thinkingmachines/inkling":{"draws":47,"losses":29,"wins":110},"thinkingmachines/inkling-small":{"draws":36,"losses":18,"wins":84},"unbiased/pareto-26.10":{"draws":3,"losses":41,"wins":2},"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":28,"losses":56,"wins":54},"x-ai/grok-4.6":{"draws":40,"losses":65,"wins":33},"x-ai/grok-4.7":{"draws":12,"losses":74,"wins":34},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":26},"xiaomi/mimo-v2.5":{"draws":57,"losses":30,"wins":125},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":16,"wins":49},"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":55,"losses":69,"wins":152},"z-ai/glm-5.3":{"draws":19,"losses":84,"wins":29},"z-ai/glm-5.3-flash":{"draws":21,"losses":63,"wins":54},"z-ai/glm-5.3-flashx":{"draws":32,"losses":51,"wins":55}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":57,"losses":73,"wins":48},"claude-fable-5":{"draws":36,"losses":144,"wins":12},"claude-fable-5-1":{"draws":8,"losses":209,"wins":1},"claude-haiku-5-5":{"draws":50,"losses":109,"wins":23},"claude-opus-4-5":{"draws":100,"losses":163,"wins":47},"claude-opus-4-8":{"draws":42,"losses":108,"wins":22},"claude-opus-5":{"draws":48,"losses":260,"wins":30},"claude-opus-5-5":{"draws":19,"losses":185,"wins":0},"claude-sonnet-5":{"draws":61,"losses":103,"wins":28},"claude-sonnet-5-5":{"draws":41,"losses":111,"wins":40},"cohere/north-mini-code":{"draws":18,"losses":21,"wins":33},"deepseek/deepseek-v4-flash":{"draws":85,"losses":100,"wins":99},"deepseek/deepseek-v4-pro":{"draws":58,"losses":92,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":57,"losses":76,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":61,"losses":100,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":46,"losses":121,"wins":25},"elorian/glimpse":{"draws":27,"losses":53,"wins":26},"fireworks/ember-1":{"draws":57,"losses":107,"wins":28},"gemini-3.1-pro-preview":{"draws":59,"losses":85,"wins":48},"gemini-4-argon":{"draws":17,"losses":164,"wins":11},"google/gemini-3.1-flash-lite":{"draws":33,"losses":35,"wins":58},"google/gemini-3.5-flash":{"draws":50,"losses":142,"wins":48},"google/gemini-3.5-flash-lite":{"draws":88,"losses":136,"wins":114},"google/gemini-3.6-flash":{"draws":103,"losses":217,"wins":52},"google/gemini-3.8-flash":{"draws":48,"losses":124,"wins":20},"google/gemma-4-31b-it":{"draws":40,"losses":32,"wins":36},"gpt-4.1":{"draws":16,"losses":28,"wins":20},"gpt-4.1-nano":{"draws":14,"losses":1,"wins":7},"gpt-5":{"draws":38,"losses":95,"wins":39},"gpt-5.4":{"draws":49,"losses":108,"wins":29},"gpt-5.4-mini":{"draws":45,"losses":47,"wins":36},"gpt-5.4-nano":{"draws":39,"losses":79,"wins":70},"gpt-5.5":{"draws":55,"losses":98,"wins":27},"gpt-5.6-luna":{"draws":58,"losses":88,"wins":46},"gpt-5.6-sol":{"draws":28,"losses":147,"wins":17},"gpt-5.6-terra":{"draws":53,"losses":91,"wins":38},"gpt-6-astra":{"draws":11,"losses":180,"wins":1},"gpt-6-luna":{"draws":56,"losses":95,"wins":41},"gpt-6-sol":{"draws":25,"losses":154,"wins":13},"gpt-6.1-sol":{"draws":12,"losses":175,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":48,"losses":34,"wins":46},"inception/mercury-3":{"draws":43,"losses":53,"wins":26},"inclusionai/ling-3.0-flash":{"draws":47,"losses":31,"wins":52},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":52,"losses":75,"wins":79},"meta/muse-glimmer-30b":{"draws":56,"losses":61,"wins":57},"meta/muse-spark-1.2":{"draws":50,"losses":103,"wins":33},"meta/muse-spark-1.3":{"draws":34,"losses":139,"wins":19},"meta/muse-spark-open":{"draws":40,"losses":123,"wins":23},"meta/muse-wonder":{"draws":44,"losses":126,"wins":22},"minimax/minimax-m3":{"draws":26,"losses":34,"wins":44},"minimax/minimax-m3.1-flash":{"draws":41,"losses":81,"wins":52},"mistralai/mistral-large-4-0":{"draws":42,"losses":58,"wins":22},"mistralai/mistral-medium-3-5":{"draws":35,"losses":26,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":29,"wins":9},"moonshotai/kimi-k3":{"draws":53,"losses":93,"wins":40},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":163,"wins":10},"nex-agi/nex-n2-pro":{"draws":23,"losses":29,"wins":42},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":17,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":62,"wins":54},"nvidia/nemotron-3.5-super-vl":{"draws":25,"losses":42,"wins":19},"o3":{"draws":41,"losses":167,"wins":58},"openai/gpt-oss-120b":{"draws":44,"losses":59,"wins":65},"poolside/laguna-s-2.1":{"draws":52,"losses":82,"wins":54},"qwen/qwen3.7-max":{"draws":29,"losses":62,"wins":19},"qwen/qwen3.7-plus":{"draws":25,"losses":40,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":58,"losses":109,"wins":25},"qwen/qwen3.8-27b":{"draws":37,"losses":71,"wins":30},"qwen/qwen3.8-flash":{"draws":41,"losses":61,"wins":26},"qwen/qwen3.8-max":{"draws":56,"losses":106,"wins":30},"qwen/qwen3.8-max-0902":{"draws":54,"losses":108,"wins":30},"recursive/flint-v1.0":{"draws":16,"losses":14,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":52,"losses":91,"wins":33},"stealth/ox-alpha":{"draws":159,"losses":376,"wins":123},"stealth/space-bunny-alpha":{"draws":48,"losses":60,"wins":46},"stepfun/step-3.7-flash":{"draws":37,"losses":62,"wins":39},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":32,"losses":46,"wins":26},"tencent/hy4-preview":{"draws":47,"losses":110,"wins":29},"thinkingmachines/inkling":{"draws":68,"losses":68,"wins":68},"thinkingmachines/inkling-small":{"draws":68,"losses":48,"wins":76},"unbiased/pareto-26.10":{"draws":1,"losses":63,"wins":0},"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":53,"losses":115,"wins":24},"x-ai/grok-4.6":{"draws":63,"losses":109,"wins":20},"x-ai/grok-4.7":{"draws":21,"losses":134,"wins":13},"x-ai/grok-build-0.1":{"draws":20,"losses":28,"wins":16},"xiaomi/mimo-v2.5":{"draws":89,"losses":119,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":57,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":29,"losses":69,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":25,"losses":90,"wins":13},"z-ai/glm-5.2":{"draws":110,"losses":179,"wins":95},"z-ai/glm-5.3":{"draws":33,"losses":126,"wins":23},"z-ai/glm-5.3-flash":{"draws":40,"losses":122,"wins":30},"z-ai/glm-5.3-flashx":{"draws":42,"losses":124,"wins":26}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":42,"losses":60,"wins":30},"claude-fable-5":{"draws":23,"losses":107,"wins":14},"claude-fable-5-1":{"draws":12,"losses":150,"wins":0},"claude-haiku-5-5":{"draws":33,"losses":92,"wins":13},"claude-opus-4-5":{"draws":71,"losses":131,"wins":32},"claude-opus-4-8":{"draws":35,"losses":84,"wins":13},"claude-opus-5":{"draws":40,"losses":195,"wins":11},"claude-opus-5-5":{"draws":10,"losses":146,"wins":0},"claude-sonnet-5":{"draws":44,"losses":76,"wins":24},"claude-sonnet-5-5":{"draws":31,"losses":92,"wins":21},"cohere/north-mini-code":{"draws":15,"losses":17,"wins":22},"deepseek/deepseek-v4-flash":{"draws":82,"losses":86,"wins":48},"deepseek/deepseek-v4-pro":{"draws":44,"losses":69,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":68,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":82,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":105,"wins":14},"elorian/glimpse":{"draws":18,"losses":48,"wins":12},"fireworks/ember-1":{"draws":43,"losses":81,"wins":20},"gemini-3.1-pro-preview":{"draws":39,"losses":77,"wins":28},"gemini-4-argon":{"draws":16,"losses":124,"wins":4},"google/gemini-3.1-flash-lite":{"draws":29,"losses":31,"wins":36},"google/gemini-3.5-flash":{"draws":43,"losses":102,"wins":35},"google/gemini-3.5-flash-lite":{"draws":71,"losses":105,"wins":76},"google/gemini-3.6-flash":{"draws":76,"losses":154,"wins":46},"google/gemini-3.8-flash":{"draws":35,"losses":90,"wins":19},"google/gemma-4-31b-it":{"draws":35,"losses":24,"wins":25},"gpt-4.1":{"draws":13,"losses":20,"wins":15},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":5},"gpt-5":{"draws":40,"losses":63,"wins":23},"gpt-5.4":{"draws":37,"losses":84,"wins":17},"gpt-5.4-mini":{"draws":37,"losses":32,"wins":27},"gpt-5.4-nano":{"draws":40,"losses":63,"wins":41},"gpt-5.5":{"draws":42,"losses":69,"wins":21},"gpt-5.6-luna":{"draws":54,"losses":53,"wins":37},"gpt-5.6-sol":{"draws":22,"losses":109,"wins":13},"gpt-5.6-terra":{"draws":38,"losses":77,"wins":23},"gpt-6-astra":{"draws":9,"losses":135,"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":42,"losses":29,"wins":31},"inception/mercury-3":{"draws":29,"losses":52,"wins":15},"inclusionai/ling-3.0-flash":{"draws":42,"losses":28,"wins":32},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":44,"losses":63,"wins":49},"meta/muse-glimmer-30b":{"draws":44,"losses":54,"wins":28},"meta/muse-spark-1.2":{"draws":37,"losses":75,"wins":26},"meta/muse-spark-1.3":{"draws":32,"losses":99,"wins":13},"meta/muse-spark-open":{"draws":30,"losses":93,"wins":15},"meta/muse-wonder":{"draws":33,"losses":96,"wins":15},"minimax/minimax-m3":{"draws":21,"losses":36,"wins":21},"minimax/minimax-m3.1-flash":{"draws":35,"losses":59,"wins":32},"mistralai/mistral-large-4-0":{"draws":31,"losses":45,"wins":14},"mistralai/mistral-medium-3-5":{"draws":33,"losses":19,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":44,"losses":73,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":124,"wins":9},"nex-agi/nex-n2-pro":{"draws":17,"losses":23,"wins":32},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":10,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":39,"losses":49,"wins":38},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":38,"wins":9},"o3":{"draws":35,"losses":119,"wins":44},"openai/gpt-oss-120b":{"draws":44,"losses":49,"wins":33},"poolside/laguna-s-2.1":{"draws":41,"losses":73,"wins":24},"qwen/qwen3.7-max":{"draws":22,"losses":42,"wins":20},"qwen/qwen3.7-plus":{"draws":24,"losses":22,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":83,"wins":17},"qwen/qwen3.8-27b":{"draws":28,"losses":58,"wins":16},"qwen/qwen3.8-flash":{"draws":32,"losses":44,"wins":20},"qwen/qwen3.8-max":{"draws":37,"losses":68,"wins":39},"qwen/qwen3.8-max-0902":{"draws":41,"losses":86,"wins":17},"recursive/flint-v1.0":{"draws":12,"losses":16,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":42,"losses":63,"wins":27},"stealth/ox-alpha":{"draws":118,"losses":283,"wins":73},"stealth/space-bunny-alpha":{"draws":34,"losses":53,"wins":27},"stepfun/step-3.7-flash":{"draws":28,"losses":37,"wins":37},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":31,"losses":29,"wins":18},"tencent/hy4-preview":{"draws":36,"losses":84,"wins":18},"thinkingmachines/inkling":{"draws":68,"losses":76,"wins":48},"thinkingmachines/inkling-small":{"draws":34,"losses":31,"wins":31},"unbiased/pareto-26.10":{"draws":3,"losses":45,"wins":0},"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":37,"losses":90,"wins":17},"x-ai/grok-4.6":{"draws":37,"losses":90,"wins":17},"x-ai/grok-4.7":{"draws":14,"losses":111,"wins":1},"x-ai/grok-build-0.1":{"draws":16,"losses":17,"wins":15},"xiaomi/mimo-v2.5":{"draws":79,"losses":84,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":36,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":22,"losses":60,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":70,"wins":13},"z-ai/glm-5.2":{"draws":91,"losses":138,"wins":59},"z-ai/glm-5.3":{"draws":22,"losses":107,"wins":9},"z-ai/glm-5.3-flash":{"draws":30,"losses":92,"wins":22},"z-ai/glm-5.3-flashx":{"draws":26,"losses":96,"wins":22}},"unbiased/pareto-26.10":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":42},"claude-fable-5":{"draws":1,"losses":4,"wins":43},"claude-fable-5-1":{"draws":7,"losses":21,"wins":26},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":6,"losses":0,"wins":72},"claude-opus-4-8":{"draws":4,"losses":4,"wins":36},"claude-opus-5":{"draws":7,"losses":24,"wins":51},"claude-opus-5-5":{"draws":4,"losses":27,"wins":21},"claude-sonnet-5":{"draws":4,"losses":1,"wins":43},"claude-sonnet-5-5":{"draws":4,"losses":8,"wins":36},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":68},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":2,"losses":1,"wins":45},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":42},"gemini-4-argon":{"draws":4,"losses":13,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":50},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":79},"google/gemini-3.6-flash":{"draws":8,"losses":3,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":39},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":4,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":43},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":44},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":42},"gpt-6-astra":{"draws":8,"losses":22,"wins":18},"gpt-6-luna":{"draws":3,"losses":1,"wins":44},"gpt-6-sol":{"draws":3,"losses":7,"wins":38},"gpt-6.1-sol":{"draws":6,"losses":17,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"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":0,"wins":51},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":44},"meta/muse-spark-1.3":{"draws":3,"losses":0,"wins":45},"meta/muse-spark-open":{"draws":2,"losses":2,"wins":42},"meta/muse-wonder":{"draws":6,"losses":8,"wins":34},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"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":3,"losses":1,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":15,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"o3":{"draws":0,"losses":0,"wins":66},"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":5,"losses":1,"wins":42},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":28},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":44},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":42},"stealth/ox-alpha":{"draws":11,"losses":4,"wins":143},"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":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":41},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.6":{"draws":6,"losses":2,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":10,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":15},"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":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":30},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":91},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":39}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":10,"wins":37},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"gemini-4-argon":{"draws":3,"losses":18,"wins":27},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":3,"losses":9,"wins":80},"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},"inception/mercury-3":{"draws":0,"losses":2,"wins":30},"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-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":16,"wins":27},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":0,"wins":43},"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},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":8},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":31,"wins":1},"elorian/glimpse":{"draws":4,"losses":10,"wins":4},"fireworks/ember-1":{"draws":5,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":5,"losses":18,"wins":13},"gemini-4-argon":{"draws":3,"losses":33,"wins":0},"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},"inception/mercury-3":{"draws":2,"losses":15,"wins":3},"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-spark-open":{"draws":2,"losses":29,"wins":5},"meta/muse-wonder":{"draws":3,"losses":32,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":10},"minimax/minimax-m3.1-flash":{"draws":6,"losses":24,"wins":6},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":36,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":2},"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},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":19,"wins":7},"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":{"draws":0,"losses":12,"wins":0},"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":30,"losses":17,"wins":85},"claude-fable-5":{"draws":24,"losses":73,"wins":47},"claude-fable-5-1":{"draws":12,"losses":139,"wins":11},"claude-haiku-5-5":{"draws":30,"losses":48,"wins":60},"claude-opus-4-5":{"draws":63,"losses":65,"wins":106},"claude-opus-4-8":{"draws":36,"losses":44,"wins":52},"claude-opus-5":{"draws":38,"losses":156,"wins":52},"claude-opus-5-5":{"draws":18,"losses":120,"wins":18},"claude-sonnet-5":{"draws":38,"losses":33,"wins":73},"claude-sonnet-5-5":{"draws":31,"losses":63,"wins":50},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":44},"deepseek/deepseek-v4-flash":{"draws":39,"losses":32,"wins":145},"deepseek/deepseek-v4-pro":{"draws":33,"losses":37,"wins":62},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":44,"wins":59},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":46,"wins":67},"deepseek/deepseek-v4.1-flash-1017":{"draws":27,"losses":61,"wins":56},"elorian/glimpse":{"draws":14,"losses":28,"wins":36},"fireworks/ember-1":{"draws":32,"losses":40,"wins":72},"gemini-3.1-pro-preview":{"draws":30,"losses":44,"wins":70},"gemini-4-argon":{"draws":10,"losses":108,"wins":26},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":77},"google/gemini-3.5-flash":{"draws":33,"losses":62,"wins":85},"google/gemini-3.5-flash-lite":{"draws":60,"losses":47,"wins":145},"google/gemini-3.6-flash":{"draws":58,"losses":104,"wins":114},"google/gemini-3.8-flash":{"draws":24,"losses":53,"wins":67},"google/gemma-4-31b-it":{"draws":18,"losses":10,"wins":56},"gpt-4.1":{"draws":11,"losses":9,"wins":28},"gpt-4.1-nano":{"draws":9,"losses":0,"wins":9},"gpt-5":{"draws":25,"losses":34,"wins":67},"gpt-5.4":{"draws":33,"losses":59,"wins":46},"gpt-5.4-mini":{"draws":29,"losses":15,"wins":52},"gpt-5.4-nano":{"draws":31,"losses":29,"wins":84},"gpt-5.5":{"draws":35,"losses":42,"wins":55},"gpt-5.6-luna":{"draws":36,"losses":36,"wins":72},"gpt-5.6-sol":{"draws":18,"losses":82,"wins":44},"gpt-5.6-terra":{"draws":39,"losses":33,"wins":66},"gpt-6-astra":{"draws":9,"losses":120,"wins":15},"gpt-6-luna":{"draws":33,"losses":45,"wins":66},"gpt-6-sol":{"draws":19,"losses":93,"wins":32},"gpt-6.1-sol":{"draws":10,"losses":116,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":34,"losses":4,"wins":64},"inception/mercury-3":{"draws":31,"losses":23,"wins":42},"inclusionai/ling-3.0-flash":{"draws":24,"losses":6,"wins":72},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":30,"losses":24,"wins":102},"meta/muse-glimmer-30b":{"draws":31,"losses":14,"wins":81},"meta/muse-spark-1.2":{"draws":32,"losses":37,"wins":69},"meta/muse-spark-1.3":{"draws":23,"losses":60,"wins":61},"meta/muse-spark-open":{"draws":28,"losses":49,"wins":61},"meta/muse-wonder":{"draws":29,"losses":79,"wins":36},"minimax/minimax-m3":{"draws":14,"losses":5,"wins":59},"minimax/minimax-m3.1-flash":{"draws":32,"losses":31,"wins":63},"mistralai/mistral-large-4-0":{"draws":20,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":19,"losses":7,"wins":58},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":4,"wins":25},"moonshotai/kimi-k3":{"draws":28,"losses":44,"wins":66},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":98,"wins":27},"nex-agi/nex-n2-pro":{"draws":12,"losses":9,"wins":51},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":13,"wins":84},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":10,"wins":37},"o3":{"draws":21,"losses":57,"wins":120},"openai/gpt-oss-120b":{"draws":34,"losses":13,"wins":79},"poolside/laguna-s-2.1":{"draws":35,"losses":19,"wins":84},"qwen/qwen3.7-max":{"draws":21,"losses":19,"wins":44},"qwen/qwen3.7-plus":{"draws":18,"losses":8,"wins":46},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":47,"wins":63},"qwen/qwen3.8-27b":{"draws":24,"losses":25,"wins":53},"qwen/qwen3.8-flash":{"draws":25,"losses":27,"wins":44},"qwen/qwen3.8-max":{"draws":32,"losses":44,"wins":68},"qwen/qwen3.8-max-0902":{"draws":31,"losses":52,"wins":61},"recursive/flint-v1.0":{"draws":12,"losses":0,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":38,"losses":31,"wins":63},"stealth/ox-alpha":{"draws":98,"losses":165,"wins":211},"stealth/space-bunny-alpha":{"draws":30,"losses":21,"wins":63},"stepfun/step-3.7-flash":{"draws":12,"losses":19,"wins":71},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":24,"losses":7,"wins":47},"tencent/hy4-preview":{"draws":28,"losses":54,"wins":56},"thinkingmachines/inkling":{"draws":53,"losses":24,"wins":115},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":90},"unbiased/pareto-26.10":{"draws":3,"losses":44,"wins":1},"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":28,"losses":34,"wins":34},"x-ai/grok-4.6":{"draws":42,"losses":54,"wins":48},"x-ai/grok-4.7":{"draws":16,"losses":83,"wins":27},"x-ai/grok-build-0.1":{"draws":13,"losses":5,"wins":30},"xiaomi/mimo-v2.5":{"draws":59,"losses":18,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":22,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":32,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":42,"wins":37},"z-ai/glm-5.2":{"draws":70,"losses":59,"wins":159},"z-ai/glm-5.3":{"draws":26,"losses":78,"wins":34},"z-ai/glm-5.3-flash":{"draws":19,"losses":65,"wins":60},"z-ai/glm-5.3-flashx":{"draws":25,"losses":60,"wins":59}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":17,"wins":85},"claude-fable-5":{"draws":31,"losses":64,"wins":49},"claude-fable-5-1":{"draws":9,"losses":129,"wins":24},"claude-haiku-5-5":{"draws":36,"losses":42,"wins":60},"claude-opus-4-5":{"draws":55,"losses":55,"wins":124},"claude-opus-4-8":{"draws":31,"losses":44,"wins":57},"claude-opus-5":{"draws":37,"losses":161,"wins":48},"claude-opus-5-5":{"draws":16,"losses":126,"wins":14},"claude-sonnet-5":{"draws":38,"losses":33,"wins":73},"claude-sonnet-5-5":{"draws":22,"losses":61,"wins":61},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":41},"deepseek/deepseek-v4-flash":{"draws":50,"losses":25,"wins":141},"deepseek/deepseek-v4-pro":{"draws":32,"losses":27,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":29,"wins":68},"deepseek/deepseek-v4.1-flash":{"draws":36,"losses":48,"wins":60},"deepseek/deepseek-v4.1-flash-1017":{"draws":40,"losses":57,"wins":47},"elorian/glimpse":{"draws":20,"losses":25,"wins":33},"fireworks/ember-1":{"draws":36,"losses":43,"wins":65},"gemini-3.1-pro-preview":{"draws":34,"losses":30,"wins":80},"gemini-4-argon":{"draws":19,"losses":105,"wins":20},"google/gemini-3.1-flash-lite":{"draws":17,"losses":4,"wins":75},"google/gemini-3.5-flash":{"draws":41,"losses":39,"wins":100},"google/gemini-3.5-flash-lite":{"draws":56,"losses":34,"wins":162},"google/gemini-3.6-flash":{"draws":66,"losses":82,"wins":128},"google/gemini-3.8-flash":{"draws":40,"losses":53,"wins":51},"google/gemma-4-31b-it":{"draws":24,"losses":6,"wins":54},"gpt-4.1":{"draws":19,"losses":6,"wins":23},"gpt-4.1-nano":{"draws":10,"losses":2,"wins":6},"gpt-5":{"draws":34,"losses":20,"wins":72},"gpt-5.4":{"draws":37,"losses":46,"wins":55},"gpt-5.4-mini":{"draws":31,"losses":12,"wins":53},"gpt-5.4-nano":{"draws":21,"losses":26,"wins":97},"gpt-5.5":{"draws":37,"losses":39,"wins":56},"gpt-5.6-luna":{"draws":32,"losses":22,"wins":90},"gpt-5.6-sol":{"draws":28,"losses":57,"wins":59},"gpt-5.6-terra":{"draws":43,"losses":20,"wins":75},"gpt-6-astra":{"draws":12,"losses":121,"wins":11},"gpt-6-luna":{"draws":36,"losses":25,"wins":83},"gpt-6-sol":{"draws":21,"losses":95,"wins":28},"gpt-6.1-sol":{"draws":17,"losses":115,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":28,"losses":7,"wins":67},"inception/mercury-3":{"draws":29,"losses":19,"wins":48},"inclusionai/ling-3.0-flash":{"draws":33,"losses":5,"wins":64},"inclusionai/ling-3.1-flash":{"draws":3,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":35,"losses":24,"wins":97},"meta/muse-glimmer-30b":{"draws":36,"losses":10,"wins":80},"meta/muse-spark-1.2":{"draws":29,"losses":30,"wins":79},"meta/muse-spark-1.3":{"draws":35,"losses":54,"wins":55},"meta/muse-spark-open":{"draws":30,"losses":43,"wins":65},"meta/muse-wonder":{"draws":41,"losses":62,"wins":41},"minimax/minimax-m3":{"draws":16,"losses":2,"wins":60},"minimax/minimax-m3.1-flash":{"draws":35,"losses":27,"wins":64},"mistralai/mistral-large-4-0":{"draws":30,"losses":17,"wins":43},"mistralai/mistral-medium-3-5":{"draws":21,"losses":7,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":19},"moonshotai/kimi-k3":{"draws":31,"losses":34,"wins":73},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":105,"wins":28},"nex-agi/nex-n2-pro":{"draws":15,"losses":5,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":12,"wins":74},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":10,"wins":42},"o3":{"draws":33,"losses":45,"wins":120},"openai/gpt-oss-120b":{"draws":35,"losses":11,"wins":80},"poolside/laguna-s-2.1":{"draws":33,"losses":19,"wins":86},"qwen/qwen3.7-max":{"draws":20,"losses":16,"wins":48},"qwen/qwen3.7-plus":{"draws":20,"losses":7,"wins":45},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":50,"wins":61},"qwen/qwen3.8-27b":{"draws":26,"losses":23,"wins":53},"qwen/qwen3.8-flash":{"draws":33,"losses":16,"wins":47},"qwen/qwen3.8-max":{"draws":37,"losses":44,"wins":63},"qwen/qwen3.8-max-0902":{"draws":39,"losses":37,"wins":68},"recursive/flint-v1.0":{"draws":7,"losses":5,"wins":30},"reflection/beam-1.0-501b-a23b":{"draws":35,"losses":28,"wins":69},"stealth/ox-alpha":{"draws":128,"losses":149,"wins":197},"stealth/space-bunny-alpha":{"draws":30,"losses":21,"wins":63},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":67},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":45},"tencent/hy4-preview":{"draws":40,"losses":33,"wins":65},"thinkingmachines/inkling":{"draws":63,"losses":20,"wins":109},"thinkingmachines/inkling-small":{"draws":37,"losses":17,"wins":90},"unbiased/pareto-26.10":{"draws":6,"losses":40,"wins":2},"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":42,"losses":48,"wins":54},"x-ai/grok-4.6":{"draws":38,"losses":29,"wins":29},"x-ai/grok-4.7":{"draws":15,"losses":79,"wins":32},"x-ai/grok-build-0.1":{"draws":15,"losses":6,"wins":27},"xiaomi/mimo-v2.5":{"draws":69,"losses":20,"wins":133},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":11,"wins":50},"xiaomi/mimo-v2.6-flash":{"draws":17,"losses":34,"wins":39},"xiaomi/mimo-v2.6-pro":{"draws":21,"losses":42,"wins":33},"z-ai/glm-5.2":{"draws":72,"losses":53,"wins":163},"z-ai/glm-5.3":{"draws":26,"losses":69,"wins":43},"z-ai/glm-5.3-flash":{"draws":33,"losses":50,"wins":61},"z-ai/glm-5.3-flashx":{"draws":26,"losses":55,"wins":63}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":15,"wins":93},"claude-fable-5":{"draws":7,"losses":42,"wins":77},"claude-fable-5-1":{"draws":6,"losses":100,"wins":34},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":92},"claude-opus-4-5":{"draws":16,"losses":36,"wins":154},"claude-opus-4-8":{"draws":15,"losses":31,"wins":72},"claude-opus-5":{"draws":21,"losses":102,"wins":97},"claude-opus-5-5":{"draws":10,"losses":98,"wins":30},"claude-sonnet-5":{"draws":12,"losses":26,"wins":88},"claude-sonnet-5-5":{"draws":15,"losses":48,"wins":63},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":45},"deepseek/deepseek-v4-flash":{"draws":18,"losses":15,"wins":159},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":86},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":24,"wins":82},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":32,"wins":82},"deepseek/deepseek-v4.1-flash-1017":{"draws":20,"losses":38,"wins":68},"elorian/glimpse":{"draws":7,"losses":17,"wins":44},"fireworks/ember-1":{"draws":10,"losses":28,"wins":88},"gemini-3.1-pro-preview":{"draws":12,"losses":25,"wins":89},"gemini-4-argon":{"draws":16,"losses":70,"wins":40},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":78},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":118},"google/gemini-3.5-flash-lite":{"draws":20,"losses":28,"wins":170},"google/gemini-3.6-flash":{"draws":14,"losses":58,"wins":168},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":90},"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":9,"losses":18,"wins":85},"gpt-5.4":{"draws":12,"losses":27,"wins":81},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":66},"gpt-5.4-nano":{"draws":14,"losses":8,"wins":110},"gpt-5.5":{"draws":10,"losses":37,"wins":69},"gpt-5.6-luna":{"draws":13,"losses":17,"wins":96},"gpt-5.6-sol":{"draws":16,"losses":42,"wins":68},"gpt-5.6-terra":{"draws":11,"losses":22,"wins":87},"gpt-6-astra":{"draws":10,"losses":94,"wins":22},"gpt-6-luna":{"draws":10,"losses":20,"wins":96},"gpt-6-sol":{"draws":13,"losses":53,"wins":60},"gpt-6.1-sol":{"draws":6,"losses":82,"wins":38},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":72},"inception/mercury-3":{"draws":10,"losses":10,"wins":66},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":73},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":121},"meta/muse-glimmer-30b":{"draws":6,"losses":14,"wins":92},"meta/muse-spark-1.2":{"draws":7,"losses":30,"wins":85},"meta/muse-spark-1.3":{"draws":12,"losses":32,"wins":82},"meta/muse-spark-open":{"draws":9,"losses":26,"wins":85},"meta/muse-wonder":{"draws":16,"losses":38,"wins":72},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":61},"minimax/minimax-m3.1-flash":{"draws":10,"losses":21,"wins":77},"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":3,"losses":8,"wins":23},"moonshotai/kimi-k3":{"draws":10,"losses":29,"wins":83},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":69,"wins":46},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":54},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":9,"wins":99},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":11,"wins":43},"o3":{"draws":12,"losses":36,"wins":130},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":98},"poolside/laguna-s-2.1":{"draws":12,"losses":13,"wins":99},"qwen/qwen3.7-max":{"draws":10,"losses":16,"wins":50},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":52},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":31,"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":11,"losses":25,"wins":90},"qwen/qwen3.8-max-0902":{"draws":18,"losses":29,"wins":79},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":35},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":10,"wins":93},"stealth/ox-alpha":{"draws":42,"losses":76,"wins":282},"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":4,"wins":54},"tencent/hy4-preview":{"draws":12,"losses":34,"wins":74},"thinkingmachines/inkling":{"draws":21,"losses":13,"wins":134},"thinkingmachines/inkling-small":{"draws":14,"losses":1,"wins":111},"unbiased/pareto-26.10":{"draws":5,"losses":27,"wins":10},"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":16,"losses":27,"wins":83},"x-ai/grok-4.6":{"draws":15,"losses":32,"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":22,"wins":56},"z-ai/glm-5.2":{"draws":29,"losses":37,"wins":186},"z-ai/glm-5.3":{"draws":17,"losses":33,"wins":70},"z-ai/glm-5.3-flash":{"draws":16,"losses":34,"wins":76},"z-ai/glm-5.3-flashx":{"draws":17,"losses":27,"wins":82}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":21,"wins":11},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":30,"wins":4},"claude-opus-4-5":{"draws":24,"losses":41,"wins":13},"claude-opus-4-8":{"draws":9,"losses":28,"wins":7},"claude-opus-5":{"draws":15,"losses":64,"wins":3},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":17,"losses":27,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":31,"wins":19},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":7},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":14},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":14,"losses":37,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":27,"wins":27},"google/gemini-3.6-flash":{"draws":27,"losses":58,"wins":7},"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":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":21,"wins":8},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":26,"wins":15},"gpt-5.5":{"draws":19,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":26,"wins":6},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"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":16,"losses":8,"wins":10},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":19},"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":14,"losses":12,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":10,"losses":29,"wins":7},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":13,"losses":18,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":37,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":12,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":12,"losses":38,"wins":16},"openai/gpt-oss-120b":{"draws":15,"losses":10,"wins":17},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":12,"losses":21,"wins":1},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":33,"losses":105,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":16,"losses":15,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":30,"losses":18,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"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":36,"losses":38,"wins":22},"z-ai/glm-5.3":{"draws":10,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":30,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":66,"losses":83,"wins":55},"claude-fable-5":{"draws":38,"losses":178,"wins":6},"claude-fable-5-1":{"draws":12,"losses":226,"wins":6},"claude-haiku-5-5":{"draws":57,"losses":132,"wins":31},"claude-opus-4-5":{"draws":123,"losses":187,"wins":58},"claude-opus-4-8":{"draws":59,"losses":129,"wins":30},"claude-opus-5":{"draws":56,"losses":299,"wins":23},"claude-opus-5-5":{"draws":11,"losses":227,"wins":4},"claude-sonnet-5":{"draws":71,"losses":107,"wins":44},"claude-sonnet-5-5":{"draws":47,"losses":146,"wins":29},"cohere/north-mini-code":{"draws":21,"losses":28,"wins":31},"deepseek/deepseek-v4-flash":{"draws":105,"losses":119,"wins":110},"deepseek/deepseek-v4-pro":{"draws":71,"losses":99,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":62,"losses":99,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":66,"losses":122,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":47,"losses":159,"wins":16},"elorian/glimpse":{"draws":34,"losses":64,"wins":20},"fireworks/ember-1":{"draws":70,"losses":114,"wins":38},"gemini-3.1-pro-preview":{"draws":66,"losses":97,"wins":59},"gemini-4-argon":{"draws":16,"losses":205,"wins":1},"google/gemini-3.1-flash-lite":{"draws":47,"losses":39,"wins":76},"google/gemini-3.5-flash":{"draws":76,"losses":154,"wins":54},"google/gemini-3.5-flash-lite":{"draws":112,"losses":139,"wins":141},"google/gemini-3.6-flash":{"draws":119,"losses":246,"wins":59},"google/gemini-3.8-flash":{"draws":57,"losses":145,"wins":20},"google/gemma-4-31b-it":{"draws":60,"losses":33,"wins":41},"gpt-4.1":{"draws":26,"losses":32,"wins":16},"gpt-4.1-nano":{"draws":11,"losses":2,"wins":9},"gpt-5":{"draws":53,"losses":95,"wins":42},"gpt-5.4":{"draws":54,"losses":136,"wins":22},"gpt-5.4-mini":{"draws":50,"losses":57,"wins":41},"gpt-5.4-nano":{"draws":51,"losses":110,"wins":75},"gpt-5.5":{"draws":79,"losses":100,"wins":23},"gpt-5.6-luna":{"draws":76,"losses":92,"wins":54},"gpt-5.6-sol":{"draws":36,"losses":174,"wins":12},"gpt-5.6-terra":{"draws":69,"losses":125,"wins":18},"gpt-6-astra":{"draws":14,"losses":206,"wins":2},"gpt-6-luna":{"draws":73,"losses":117,"wins":32},"gpt-6-sol":{"draws":36,"losses":169,"wins":17},"gpt-6.1-sol":{"draws":18,"losses":196,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":70,"losses":25,"wins":71},"inception/mercury-3":{"draws":52,"losses":70,"wins":24},"inclusionai/ling-3.0-flash":{"draws":68,"losses":38,"wins":54},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":67,"losses":85,"wins":86},"meta/muse-glimmer-30b":{"draws":70,"losses":62,"wins":60},"meta/muse-spark-1.2":{"draws":62,"losses":123,"wins":27},"meta/muse-spark-1.3":{"draws":49,"losses":150,"wins":23},"meta/muse-spark-open":{"draws":53,"losses":140,"wins":19},"meta/muse-wonder":{"draws":45,"losses":160,"wins":17},"minimax/minimax-m3":{"draws":39,"losses":40,"wins":45},"minimax/minimax-m3.1-flash":{"draws":46,"losses":91,"wins":55},"mistralai/mistral-large-4-0":{"draws":58,"losses":61,"wins":19},"mistralai/mistral-medium-3-5":{"draws":50,"losses":29,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":19,"losses":31,"wins":12},"moonshotai/kimi-k3":{"draws":74,"losses":107,"wins":31},"moonshotai/kimi-k3.1-pro":{"draws":26,"losses":190,"wins":6},"nex-agi/nex-n2-pro":{"draws":21,"losses":34,"wins":47},"nex-agi/nex-n2.5-pro":{"draws":11,"losses":18,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":76,"losses":67,"wins":65},"nvidia/nemotron-3.5-super-vl":{"draws":33,"losses":47,"wins":24},"o3":{"draws":53,"losses":200,"wins":63},"openai/gpt-oss-120b":{"draws":58,"losses":69,"wins":61},"poolside/laguna-s-2.1":{"draws":57,"losses":85,"wins":60},"qwen/qwen3.7-max":{"draws":41,"losses":62,"wins":31},"qwen/qwen3.7-plus":{"draws":39,"losses":45,"wins":38},"qwen/qwen3.8-2.4t-a95b":{"draws":86,"losses":112,"wins":24},"qwen/qwen3.8-27b":{"draws":40,"losses":90,"wins":30},"qwen/qwen3.8-flash":{"draws":54,"losses":60,"wins":34},"qwen/qwen3.8-max":{"draws":69,"losses":112,"wins":41},"qwen/qwen3.8-max-0902":{"draws":73,"losses":119,"wins":30},"recursive/flint-v1.0":{"draws":20,"losses":21,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":65,"losses":103,"wins":32},"stealth/ox-alpha":{"draws":162,"losses":387,"wins":97},"stealth/space-bunny-alpha":{"draws":60,"losses":75,"wins":43},"stepfun/step-3.7-flash":{"draws":44,"losses":59,"wins":53},"stepfun/step-5-preview":{"draws":8,"losses":12,"wins":0},"tencent/hy3-preview":{"draws":49,"losses":45,"wins":34},"tencent/hy4-preview":{"draws":57,"losses":125,"wins":30},"thinkingmachines/inkling":{"draws":89,"losses":82,"wins":119},"thinkingmachines/inkling-small":{"draws":79,"losses":59,"wins":84},"unbiased/pareto-26.10":{"draws":4,"losses":70,"wins":0},"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":59,"losses":145,"wins":18},"x-ai/grok-4.6":{"draws":69,"losses":133,"wins":20},"x-ai/grok-4.7":{"draws":22,"losses":160,"wins":16},"x-ai/grok-build-0.1":{"draws":30,"losses":26,"wins":18},"xiaomi/mimo-v2.5":{"draws":108,"losses":98,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":31,"losses":65,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":25,"losses":92,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":36,"losses":98,"wins":14},"z-ai/glm-5.2":{"draws":149,"losses":199,"wins":96},"z-ai/glm-5.3":{"draws":41,"losses":164,"wins":5},"z-ai/glm-5.3-flash":{"draws":49,"losses":135,"wins":38},"z-ai/glm-5.3-flashx":{"draws":56,"losses":145,"wins":21}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":25,"wins":25},"claude-fable-5":{"draws":7,"losses":66,"wins":5},"claude-fable-5-1":{"draws":2,"losses":84,"wins":0},"claude-haiku-5-5":{"draws":17,"losses":41,"wins":18},"claude-opus-4-5":{"draws":26,"losses":63,"wins":39},"claude-opus-4-8":{"draws":13,"losses":45,"wins":16},"claude-opus-5":{"draws":13,"losses":110,"wins":5},"claude-opus-5-5":{"draws":3,"losses":82,"wins":1},"claude-sonnet-5":{"draws":9,"losses":48,"wins":21},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":15},"deepseek/deepseek-v4-flash":{"draws":27,"losses":48,"wins":45},"deepseek/deepseek-v4-pro":{"draws":13,"losses":38,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":38,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":42,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":54,"wins":14},"elorian/glimpse":{"draws":6,"losses":22,"wins":14},"fireworks/ember-1":{"draws":22,"losses":36,"wins":20},"gemini-3.1-pro-preview":{"draws":12,"losses":37,"wins":29},"gemini-4-argon":{"draws":2,"losses":72,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":44},"google/gemini-3.5-flash":{"draws":17,"losses":53,"wins":30},"google/gemini-3.5-flash-lite":{"draws":33,"losses":53,"wins":52},"google/gemini-3.6-flash":{"draws":27,"losses":89,"wins":34},"google/gemini-3.8-flash":{"draws":14,"losses":51,"wins":13},"google/gemma-4-31b-it":{"draws":19,"losses":5,"wins":22},"gpt-4.1":{"draws":5,"losses":14,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":16,"losses":31,"wins":23},"gpt-5.4":{"draws":11,"losses":51,"wins":14},"gpt-5.4-mini":{"draws":8,"losses":22,"wins":22},"gpt-5.4-nano":{"draws":12,"losses":36,"wins":38},"gpt-5.5":{"draws":18,"losses":39,"wins":15},"gpt-5.6-luna":{"draws":20,"losses":29,"wins":29},"gpt-5.6-sol":{"draws":10,"losses":54,"wins":14},"gpt-5.6-terra":{"draws":13,"losses":47,"wins":14},"gpt-6-astra":{"draws":3,"losses":74,"wins":1},"gpt-6-luna":{"draws":16,"losses":43,"wins":19},"gpt-6-sol":{"draws":5,"losses":64,"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":15,"losses":14,"wins":25},"inception/mercury-3":{"draws":13,"losses":25,"wins":14},"inclusionai/ling-3.0-flash":{"draws":19,"losses":11,"wins":26},"inclusionai/ling-3.1-flash":{"draws":3,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":27,"wins":43},"meta/muse-glimmer-30b":{"draws":15,"losses":21,"wins":32},"meta/muse-spark-1.2":{"draws":11,"losses":43,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":56,"wins":13},"meta/muse-spark-open":{"draws":14,"losses":51,"wins":11},"meta/muse-wonder":{"draws":7,"losses":56,"wins":15},"minimax/minimax-m3":{"draws":8,"losses":15,"wins":21},"minimax/minimax-m3.1-flash":{"draws":9,"losses":30,"wins":29},"mistralai/mistral-large-4-0":{"draws":12,"losses":25,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":9,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":35,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":65,"wins":8},"nex-agi/nex-n2-pro":{"draws":8,"losses":14,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":21,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":19,"wins":10},"o3":{"draws":16,"losses":62,"wins":44},"openai/gpt-oss-120b":{"draws":14,"losses":25,"wins":29},"poolside/laguna-s-2.1":{"draws":15,"losses":36,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":22,"wins":16},"qwen/qwen3.7-plus":{"draws":10,"losses":9,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":44,"wins":18},"qwen/qwen3.8-27b":{"draws":10,"losses":26,"wins":20},"qwen/qwen3.8-flash":{"draws":9,"losses":30,"wins":13},"qwen/qwen3.8-max":{"draws":9,"losses":45,"wins":24},"qwen/qwen3.8-max-0902":{"draws":13,"losses":45,"wins":20},"recursive/flint-v1.0":{"draws":3,"losses":7,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":37,"wins":21},"stealth/ox-alpha":{"draws":42,"losses":139,"wins":61},"stealth/space-bunny-alpha":{"draws":20,"losses":25,"wins":17},"stepfun/step-3.7-flash":{"draws":10,"losses":16,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":14,"wins":17},"tencent/hy4-preview":{"draws":11,"losses":49,"wins":16},"thinkingmachines/inkling":{"draws":20,"losses":27,"wins":57},"thinkingmachines/inkling-small":{"draws":22,"losses":20,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":25,"wins":1},"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":13,"losses":43,"wins":22},"x-ai/grok-4.6":{"draws":17,"losses":50,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":60,"wins":7},"x-ai/grok-build-0.1":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.5":{"draws":31,"losses":28,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":30,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":29,"wins":16},"z-ai/glm-5.2":{"draws":39,"losses":67,"wins":50},"z-ai/glm-5.3":{"draws":13,"losses":57,"wins":4},"z-ai/glm-5.3-flash":{"draws":9,"losses":55,"wins":14},"z-ai/glm-5.3-flashx":{"draws":14,"losses":46,"wins":18}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":20,"wins":51},"claude-fable-5":{"draws":16,"losses":53,"wins":21},"claude-fable-5-1":{"draws":5,"losses":87,"wins":8},"claude-haiku-5-5":{"draws":22,"losses":37,"wins":27},"claude-opus-4-5":{"draws":30,"losses":45,"wins":71},"claude-opus-4-8":{"draws":14,"losses":26,"wins":42},"claude-opus-5":{"draws":15,"losses":120,"wins":17},"claude-opus-5-5":{"draws":7,"losses":89,"wins":2},"claude-sonnet-5":{"draws":12,"losses":28,"wins":50},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":33},"cohere/north-mini-code":{"draws":8,"losses":3,"wins":23},"deepseek/deepseek-v4-flash":{"draws":18,"losses":34,"wins":86},"deepseek/deepseek-v4-pro":{"draws":18,"losses":26,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":38,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":40,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":53,"wins":22},"elorian/glimpse":{"draws":5,"losses":17,"wins":26},"fireworks/ember-1":{"draws":11,"losses":37,"wins":42},"gemini-3.1-pro-preview":{"draws":12,"losses":29,"wins":49},"gemini-4-argon":{"draws":3,"losses":79,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":49},"google/gemini-3.5-flash":{"draws":16,"losses":41,"wins":55},"google/gemini-3.5-flash-lite":{"draws":27,"losses":20,"wins":109},"google/gemini-3.6-flash":{"draws":21,"losses":72,"wins":79},"google/gemini-3.8-flash":{"draws":19,"losses":42,"wins":29},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":32},"gpt-4.1":{"draws":6,"losses":7,"wins":17},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":9,"losses":27,"wins":44},"gpt-5.4":{"draws":22,"losses":39,"wins":25},"gpt-5.4-mini":{"draws":9,"losses":15,"wins":36},"gpt-5.4-nano":{"draws":21,"losses":21,"wins":52},"gpt-5.5":{"draws":20,"losses":37,"wins":25},"gpt-5.6-luna":{"draws":11,"losses":32,"wins":47},"gpt-5.6-sol":{"draws":9,"losses":61,"wins":20},"gpt-5.6-terra":{"draws":17,"losses":33,"wins":36},"gpt-6-astra":{"draws":3,"losses":82,"wins":5},"gpt-6-luna":{"draws":18,"losses":32,"wins":40},"gpt-6-sol":{"draws":9,"losses":62,"wins":19},"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":9,"losses":8,"wins":45},"inception/mercury-3":{"draws":12,"losses":28,"wins":22},"inclusionai/ling-3.0-flash":{"draws":17,"losses":5,"wins":42},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":22,"wins":58},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":51},"meta/muse-spark-1.2":{"draws":10,"losses":45,"wins":31},"meta/muse-spark-1.3":{"draws":9,"losses":51,"wins":30},"meta/muse-spark-open":{"draws":10,"losses":47,"wins":29},"meta/muse-wonder":{"draws":5,"losses":63,"wins":22},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":32},"minimax/minimax-m3.1-flash":{"draws":10,"losses":24,"wins":44},"mistralai/mistral-large-4-0":{"draws":17,"losses":19,"wins":20},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":12},"moonshotai/kimi-k3":{"draws":19,"losses":30,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":70,"wins":10},"nex-agi/nex-n2-pro":{"draws":6,"losses":9,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":13,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":13,"wins":18},"o3":{"draws":16,"losses":38,"wins":74},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":57},"poolside/laguna-s-2.1":{"draws":22,"losses":14,"wins":54},"qwen/qwen3.7-max":{"draws":14,"losses":11,"wins":29},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":32},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":34,"wins":37},"qwen/qwen3.8-27b":{"draws":15,"losses":23,"wins":26},"qwen/qwen3.8-flash":{"draws":14,"losses":25,"wins":21},"qwen/qwen3.8-max":{"draws":18,"losses":36,"wins":36},"qwen/qwen3.8-max-0902":{"draws":13,"losses":36,"wins":41},"recursive/flint-v1.0":{"draws":0,"losses":6,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":35,"wins":35},"stealth/ox-alpha":{"draws":52,"losses":135,"wins":111},"stealth/space-bunny-alpha":{"draws":11,"losses":17,"wins":42},"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":9,"losses":13,"wins":26},"tencent/hy4-preview":{"draws":14,"losses":37,"wins":35},"thinkingmachines/inkling":{"draws":29,"losses":22,"wins":69},"thinkingmachines/inkling-small":{"draws":22,"losses":8,"wins":60},"unbiased/pareto-26.10":{"draws":2,"losses":27,"wins":1},"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":45,"wins":32},"x-ai/grok-4.6":{"draws":17,"losses":39,"wins":34},"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":25,"losses":19,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":13,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":30,"wins":18},"z-ai/glm-5.2":{"draws":28,"losses":56,"wins":96},"z-ai/glm-5.3":{"draws":10,"losses":54,"wins":22},"z-ai/glm-5.3-flash":{"draws":12,"losses":44,"wins":34},"z-ai/glm-5.3-flashx":{"draws":9,"losses":45,"wins":36}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":57},"claude-fable-5":{"draws":8,"losses":48,"wins":40},"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":9,"losses":37,"wins":42},"claude-opus-5":{"draws":26,"losses":97,"wins":41},"claude-opus-5-5":{"draws":9,"losses":81,"wins":14},"claude-sonnet-5":{"draws":15,"losses":25,"wins":56},"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":12,"losses":27,"wins":49},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":31,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":42,"wins":44},"elorian/glimpse":{"draws":8,"losses":22,"wins":22},"fireworks/ember-1":{"draws":21,"losses":29,"wins":46},"gemini-3.1-pro-preview":{"draws":15,"losses":24,"wins":57},"gemini-4-argon":{"draws":9,"losses":64,"wins":23},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":50},"google/gemini-3.5-flash":{"draws":20,"losses":37,"wins":63},"google/gemini-3.5-flash-lite":{"draws":21,"losses":30,"wins":117},"google/gemini-3.6-flash":{"draws":39,"losses":59,"wins":86},"google/gemini-3.8-flash":{"draws":20,"losses":29,"wins":47},"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":10,"losses":23,"wins":51},"gpt-5.4":{"draws":15,"losses":38,"wins":39},"gpt-5.4-mini":{"draws":15,"losses":9,"wins":40},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":66},"gpt-5.5":{"draws":21,"losses":30,"wins":37},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":62},"gpt-5.6-sol":{"draws":17,"losses":44,"wins":35},"gpt-5.6-terra":{"draws":24,"losses":23,"wins":45},"gpt-6-astra":{"draws":9,"losses":80,"wins":7},"gpt-6-luna":{"draws":20,"losses":26,"wins":50},"gpt-6-sol":{"draws":18,"losses":52,"wins":26},"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":18,"losses":1,"wins":49},"inception/mercury-3":{"draws":14,"losses":18,"wins":32},"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":11,"wins":74},"meta/muse-glimmer-30b":{"draws":15,"losses":13,"wins":56},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":55},"meta/muse-spark-1.3":{"draws":15,"losses":32,"wins":49},"meta/muse-spark-open":{"draws":13,"losses":37,"wins":42},"meta/muse-wonder":{"draws":17,"losses":43,"wins":36},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":37},"minimax/minimax-m3.1-flash":{"draws":15,"losses":19,"wins":50},"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":24,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":53,"wins":27},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":10,"wins":56},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":13,"wins":27},"o3":{"draws":11,"losses":25,"wins":96},"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":8,"losses":13,"wins":35},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-2.4t-a95b":{"draws":24,"losses":30,"wins":42},"qwen/qwen3.8-27b":{"draws":12,"losses":20,"wins":36},"qwen/qwen3.8-flash":{"draws":14,"losses":14,"wins":36},"qwen/qwen3.8-max":{"draws":25,"losses":19,"wins":52},"qwen/qwen3.8-max-0902":{"draws":15,"losses":29,"wins":52},"recursive/flint-v1.0":{"draws":6,"losses":2,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":26,"wins":47},"stealth/ox-alpha":{"draws":58,"losses":105,"wins":153},"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":13,"wins":90},"thinkingmachines/inkling-small":{"draws":13,"losses":13,"wins":70},"unbiased/pareto-26.10":{"draws":1,"losses":30,"wins":1},"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":37,"wins":42},"x-ai/grok-4.6":{"draws":21,"losses":33,"wins":42},"x-ai/grok-4.7":{"draws":6,"losses":56,"wins":22},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":22},"xiaomi/mimo-v2.5":{"draws":36,"losses":14,"wins":98},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":16,"wins":29},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":18,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":15},"z-ai/glm-5.2":{"draws":48,"losses":37,"wins":107},"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":88,"losses":76,"wins":100},"claude-fable-5":{"draws":58,"losses":188,"wins":42},"claude-fable-5-1":{"draws":16,"losses":303,"wins":5},"claude-haiku-5-5":{"draws":64,"losses":147,"wins":65},"claude-opus-4-5":{"draws":136,"losses":196,"wins":136},"claude-opus-4-8":{"draws":69,"losses":133,"wins":62},"claude-opus-5":{"draws":74,"losses":384,"wins":34},"claude-opus-5-5":{"draws":17,"losses":283,"wins":12},"claude-sonnet-5":{"draws":75,"losses":119,"wins":94},"claude-sonnet-5-5":{"draws":55,"losses":168,"wins":65},"cohere/north-mini-code":{"draws":30,"losses":18,"wins":60},"deepseek/deepseek-v4-flash":{"draws":134,"losses":113,"wins":185},"deepseek/deepseek-v4-pro":{"draws":79,"losses":101,"wins":84},"deepseek/deepseek-v4-pro-0813":{"draws":82,"losses":103,"wins":79},"deepseek/deepseek-v4.1-flash":{"draws":95,"losses":126,"wins":67},"deepseek/deepseek-v4.1-flash-1017":{"draws":62,"losses":173,"wins":53},"elorian/glimpse":{"draws":35,"losses":72,"wins":49},"fireworks/ember-1":{"draws":82,"losses":131,"wins":75},"gemini-3.1-pro-preview":{"draws":75,"losses":116,"wins":97},"gemini-4-argon":{"draws":27,"losses":247,"wins":14},"google/gemini-3.1-flash-lite":{"draws":39,"losses":26,"wins":127},"google/gemini-3.5-flash":{"draws":82,"losses":159,"wins":119},"google/gemini-3.5-flash-lite":{"draws":145,"losses":149,"wins":210},"google/gemini-3.6-flash":{"draws":135,"losses":257,"wins":160},"google/gemini-3.8-flash":{"draws":68,"losses":161,"wins":59},"google/gemma-4-31b-it":{"draws":69,"losses":29,"wins":70},"gpt-4.1":{"draws":33,"losses":23,"wins":40},"gpt-4.1-nano":{"draws":21,"losses":0,"wins":15},"gpt-5":{"draws":73,"losses":102,"wins":77},"gpt-5.4":{"draws":76,"losses":140,"wins":60},"gpt-5.4-mini":{"draws":71,"losses":39,"wins":82},"gpt-5.4-nano":{"draws":59,"losses":99,"wins":130},"gpt-5.5":{"draws":91,"losses":123,"wins":50},"gpt-5.6-luna":{"draws":95,"losses":78,"wins":115},"gpt-5.6-sol":{"draws":37,"losses":206,"wins":45},"gpt-5.6-terra":{"draws":99,"losses":104,"wins":73},"gpt-6-astra":{"draws":21,"losses":259,"wins":8},"gpt-6-luna":{"draws":100,"losses":115,"wins":73},"gpt-6-sol":{"draws":42,"losses":212,"wins":34},"gpt-6.1-sol":{"draws":30,"losses":248,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":79,"losses":22,"wins":103},"inception/mercury-3":{"draws":64,"losses":80,"wins":48},"inclusionai/ling-3.0-flash":{"draws":85,"losses":41,"wins":78},"inclusionai/ling-3.1-flash":{"draws":10,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":81,"losses":77,"wins":154},"meta/muse-glimmer-30b":{"draws":94,"losses":51,"wins":107},"meta/muse-spark-1.2":{"draws":66,"losses":137,"wins":73},"meta/muse-spark-1.3":{"draws":56,"losses":163,"wins":69},"meta/muse-spark-open":{"draws":69,"losses":146,"wins":61},"meta/muse-wonder":{"draws":63,"losses":178,"wins":47},"minimax/minimax-m3":{"draws":41,"losses":40,"wins":75},"minimax/minimax-m3.1-flash":{"draws":62,"losses":93,"wins":97},"mistralai/mistral-large-4-0":{"draws":71,"losses":72,"wins":37},"mistralai/mistral-medium-3-5":{"draws":61,"losses":24,"wins":83},"moonshotai/kimi-k2.7-code":{"draws":17,"losses":31,"wins":24},"moonshotai/kimi-k3":{"draws":88,"losses":113,"wins":75},"moonshotai/kimi-k3.1-pro":{"draws":32,"losses":230,"wins":26},"nex-agi/nex-n2-pro":{"draws":44,"losses":27,"wins":73},"nex-agi/nex-n2.5-pro":{"draws":16,"losses":21,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":76,"losses":65,"wins":111},"nvidia/nemotron-3.5-super-vl":{"draws":42,"losses":46,"wins":44},"o3":{"draws":66,"losses":179,"wins":151},"openai/gpt-oss-120b":{"draws":89,"losses":51,"wins":112},"poolside/laguna-s-2.1":{"draws":87,"losses":84,"wins":105},"qwen/qwen3.7-max":{"draws":41,"losses":59,"wins":68},"qwen/qwen3.7-plus":{"draws":36,"losses":34,"wins":74},"qwen/qwen3.8-2.4t-a95b":{"draws":94,"losses":123,"wins":71},"qwen/qwen3.8-27b":{"draws":64,"losses":70,"wins":70},"qwen/qwen3.8-flash":{"draws":59,"losses":71,"wins":62},"qwen/qwen3.8-max":{"draws":82,"losses":126,"wins":80},"qwen/qwen3.8-max-0902":{"draws":91,"losses":138,"wins":59},"recursive/flint-v1.0":{"draws":17,"losses":18,"wins":49},"reflection/beam-1.0-501b-a23b":{"draws":75,"losses":105,"wins":84},"stealth/ox-alpha":{"draws":233,"losses":481,"wins":234},"stealth/space-bunny-alpha":{"draws":75,"losses":76,"wins":77},"stepfun/step-3.7-flash":{"draws":50,"losses":49,"wins":105},"stepfun/step-5-preview":{"draws":8,"losses":13,"wins":3},"tencent/hy3-preview":{"draws":51,"losses":48,"wins":57},"tencent/hy4-preview":{"draws":55,"losses":152,"wins":69},"thinkingmachines/inkling":{"draws":110,"losses":95,"wins":179},"thinkingmachines/inkling-small":{"draws":91,"losses":59,"wins":138},"unbiased/pareto-26.10":{"draws":4,"losses":91,"wins":1},"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":70,"losses":159,"wins":59},"x-ai/grok-4.6":{"draws":72,"losses":163,"wins":53},"x-ai/grok-4.7":{"draws":29,"losses":186,"wins":37},"x-ai/grok-build-0.1":{"draws":36,"losses":22,"wins":38},"xiaomi/mimo-v2.5":{"draws":149,"losses":96,"wins":199},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":50,"wins":67},"xiaomi/mimo-v2.6-flash":{"draws":28,"losses":96,"wins":56},"xiaomi/mimo-v2.6-pro":{"draws":48,"losses":107,"wins":37},"z-ai/glm-5.2":{"draws":148,"losses":166,"wins":166},"z-ai/glm-5.3":{"draws":58,"losses":180,"wins":38},"z-ai/glm-5.3-flash":{"draws":61,"losses":162,"wins":65},"z-ai/glm-5.3-flashx":{"draws":71,"losses":148,"wins":69}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":88},"claude-fable-5":{"draws":21,"losses":54,"wins":63},"claude-fable-5-1":{"draws":13,"losses":123,"wins":20},"claude-haiku-5-5":{"draws":24,"losses":32,"wins":76},"claude-opus-4-5":{"draws":46,"losses":31,"wins":147},"claude-opus-4-8":{"draws":19,"losses":30,"wins":77},"claude-opus-5":{"draws":29,"losses":141,"wins":64},"claude-opus-5-5":{"draws":12,"losses":113,"wins":25},"claude-sonnet-5":{"draws":25,"losses":19,"wins":94},"claude-sonnet-5-5":{"draws":21,"losses":54,"wins":63},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":44},"deepseek/deepseek-v4-flash":{"draws":39,"losses":17,"wins":150},"deepseek/deepseek-v4-pro":{"draws":22,"losses":27,"wins":77},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":26,"wins":77},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":29,"wins":88},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":41,"wins":73},"elorian/glimpse":{"draws":13,"losses":15,"wins":46},"fireworks/ember-1":{"draws":23,"losses":26,"wins":89},"gemini-3.1-pro-preview":{"draws":24,"losses":27,"wins":87},"gemini-4-argon":{"draws":15,"losses":83,"wins":40},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":83},"google/gemini-3.5-flash":{"draws":28,"losses":35,"wins":109},"google/gemini-3.5-flash-lite":{"draws":38,"losses":14,"wins":190},"google/gemini-3.6-flash":{"draws":50,"losses":59,"wins":155},"google/gemini-3.8-flash":{"draws":28,"losses":38,"wins":72},"google/gemma-4-31b-it":{"draws":22,"losses":7,"wins":53},"gpt-4.1":{"draws":6,"losses":8,"wins":32},"gpt-4.1-nano":{"draws":7,"losses":0,"wins":11},"gpt-5":{"draws":16,"losses":20,"wins":84},"gpt-5.4":{"draws":25,"losses":38,"wins":69},"gpt-5.4-mini":{"draws":20,"losses":8,"wins":64},"gpt-5.4-nano":{"draws":19,"losses":21,"wins":96},"gpt-5.5":{"draws":27,"losses":23,"wins":76},"gpt-5.6-luna":{"draws":23,"losses":18,"wins":97},"gpt-5.6-sol":{"draws":22,"losses":61,"wins":55},"gpt-5.6-terra":{"draws":29,"losses":21,"wins":82},"gpt-6-astra":{"draws":17,"losses":110,"wins":11},"gpt-6-luna":{"draws":23,"losses":29,"wins":86},"gpt-6-sol":{"draws":20,"losses":73,"wins":45},"gpt-6.1-sol":{"draws":21,"losses":93,"wins":24},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":24,"losses":7,"wins":69},"inception/mercury-3":{"draws":22,"losses":21,"wins":49},"inclusionai/ling-3.0-flash":{"draws":21,"losses":3,"wins":72},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":117},"meta/muse-glimmer-30b":{"draws":22,"losses":9,"wins":89},"meta/muse-spark-1.2":{"draws":24,"losses":42,"wins":66},"meta/muse-spark-1.3":{"draws":23,"losses":39,"wins":76},"meta/muse-spark-open":{"draws":19,"losses":35,"wins":78},"meta/muse-wonder":{"draws":17,"losses":62,"wins":59},"minimax/minimax-m3":{"draws":14,"losses":7,"wins":53},"minimax/minimax-m3.1-flash":{"draws":17,"losses":25,"wins":78},"mistralai/mistral-large-4-0":{"draws":15,"losses":20,"wins":51},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":5,"wins":22},"moonshotai/kimi-k3":{"draws":30,"losses":39,"wins":63},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":81,"wins":38},"nex-agi/nex-n2-pro":{"draws":11,"losses":4,"wins":57},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":24},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":9,"wins":91},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":51},"o3":{"draws":15,"losses":35,"wins":138},"openai/gpt-oss-120b":{"draws":28,"losses":5,"wins":89},"poolside/laguna-s-2.1":{"draws":24,"losses":14,"wins":94},"qwen/qwen3.7-max":{"draws":15,"losses":15,"wins":50},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":30,"wins":83},"qwen/qwen3.8-27b":{"draws":24,"losses":12,"wins":60},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":55},"qwen/qwen3.8-max":{"draws":27,"losses":31,"wins":80},"qwen/qwen3.8-max-0902":{"draws":31,"losses":31,"wins":76},"recursive/flint-v1.0":{"draws":7,"losses":2,"wins":31},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":22,"wins":88},"stealth/ox-alpha":{"draws":80,"losses":119,"wins":259},"stealth/space-bunny-alpha":{"draws":21,"losses":9,"wins":80},"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":13,"losses":9,"wins":52},"tencent/hy4-preview":{"draws":19,"losses":29,"wins":84},"thinkingmachines/inkling":{"draws":33,"losses":23,"wins":126},"thinkingmachines/inkling-small":{"draws":22,"losses":9,"wins":107},"unbiased/pareto-26.10":{"draws":5,"losses":37,"wins":4},"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":26,"losses":34,"wins":78},"x-ai/grok-4.6":{"draws":26,"losses":43,"wins":69},"x-ai/grok-4.7":{"draws":17,"losses":70,"wins":33},"x-ai/grok-build-0.1":{"draws":10,"losses":0,"wins":36},"xiaomi/mimo-v2.5":{"draws":41,"losses":5,"wins":164},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":4,"wins":57},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":22,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":34,"wins":43},"z-ai/glm-5.2":{"draws":58,"losses":38,"wins":180},"z-ai/glm-5.3":{"draws":20,"losses":34,"wins":34},"z-ai/glm-5.3-flash":{"draws":31,"losses":32,"wins":75},"z-ai/glm-5.3-flashx":{"draws":19,"losses":36,"wins":83}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":30,"wins":74},"claude-fable-5":{"draws":22,"losses":76,"wins":46},"claude-fable-5-1":{"draws":9,"losses":141,"wins":12},"claude-haiku-5-5":{"draws":27,"losses":55,"wins":56},"claude-opus-4-5":{"draws":53,"losses":56,"wins":125},"claude-opus-4-8":{"draws":19,"losses":51,"wins":62},"claude-opus-5":{"draws":35,"losses":165,"wins":46},"claude-opus-5-5":{"draws":11,"losses":134,"wins":11},"claude-sonnet-5":{"draws":23,"losses":41,"wins":80},"claude-sonnet-5-5":{"draws":19,"losses":70,"wins":55},"cohere/north-mini-code":{"draws":6,"losses":12,"wins":36},"deepseek/deepseek-v4-flash":{"draws":51,"losses":45,"wins":120},"deepseek/deepseek-v4-pro":{"draws":20,"losses":39,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":36,"wins":78},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":58,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":25,"losses":74,"wins":45},"elorian/glimpse":{"draws":12,"losses":31,"wins":35},"fireworks/ember-1":{"draws":24,"losses":47,"wins":73},"gemini-3.1-pro-preview":{"draws":31,"losses":40,"wins":73},"gemini-4-argon":{"draws":15,"losses":110,"wins":19},"google/gemini-3.1-flash-lite":{"draws":19,"losses":13,"wins":64},"google/gemini-3.5-flash":{"draws":21,"losses":57,"wins":102},"google/gemini-3.5-flash-lite":{"draws":46,"losses":48,"wins":158},"google/gemini-3.6-flash":{"draws":41,"losses":93,"wins":142},"google/gemini-3.8-flash":{"draws":18,"losses":72,"wins":54},"google/gemma-4-31b-it":{"draws":25,"losses":14,"wins":45},"gpt-4.1":{"draws":5,"losses":15,"wins":28},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":9},"gpt-5":{"draws":18,"losses":35,"wins":73},"gpt-5.4":{"draws":16,"losses":63,"wins":59},"gpt-5.4-mini":{"draws":21,"losses":21,"wins":54},"gpt-5.4-nano":{"draws":20,"losses":40,"wins":84},"gpt-5.5":{"draws":25,"losses":50,"wins":57},"gpt-5.6-luna":{"draws":37,"losses":28,"wins":79},"gpt-5.6-sol":{"draws":24,"losses":73,"wins":47},"gpt-5.6-terra":{"draws":30,"losses":42,"wins":66},"gpt-6-astra":{"draws":12,"losses":124,"wins":8},"gpt-6-luna":{"draws":39,"losses":34,"wins":71},"gpt-6-sol":{"draws":19,"losses":90,"wins":35},"gpt-6.1-sol":{"draws":12,"losses":116,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":24,"losses":12,"wins":66},"inception/mercury-3":{"draws":22,"losses":36,"wins":38},"inclusionai/ling-3.0-flash":{"draws":29,"losses":15,"wins":58},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":33,"wins":99},"meta/muse-glimmer-30b":{"draws":26,"losses":18,"wins":82},"meta/muse-spark-1.2":{"draws":21,"losses":57,"wins":60},"meta/muse-spark-1.3":{"draws":26,"losses":50,"wins":68},"meta/muse-spark-open":{"draws":21,"losses":60,"wins":57},"meta/muse-wonder":{"draws":30,"losses":71,"wins":43},"minimax/minimax-m3":{"draws":15,"losses":15,"wins":48},"minimax/minimax-m3.1-flash":{"draws":16,"losses":43,"wins":67},"mistralai/mistral-large-4-0":{"draws":26,"losses":22,"wins":42},"mistralai/mistral-medium-3-5":{"draws":22,"losses":11,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":13,"wins":17},"moonshotai/kimi-k3":{"draws":27,"losses":43,"wins":68},"moonshotai/kimi-k3.1-pro":{"draws":16,"losses":104,"wins":24},"nex-agi/nex-n2-pro":{"draws":12,"losses":10,"wins":50},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":40,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":21,"wins":35},"o3":{"draws":21,"losses":76,"wins":101},"openai/gpt-oss-120b":{"draws":26,"losses":20,"wins":80},"poolside/laguna-s-2.1":{"draws":28,"losses":34,"wins":76},"qwen/qwen3.7-max":{"draws":23,"losses":19,"wins":42},"qwen/qwen3.7-plus":{"draws":15,"losses":15,"wins":42},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":48,"wins":68},"qwen/qwen3.8-27b":{"draws":19,"losses":32,"wins":51},"qwen/qwen3.8-flash":{"draws":18,"losses":35,"wins":43},"qwen/qwen3.8-max":{"draws":28,"losses":58,"wins":58},"qwen/qwen3.8-max-0902":{"draws":38,"losses":53,"wins":53},"recursive/flint-v1.0":{"draws":9,"losses":9,"wins":24},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":39,"wins":70},"stealth/ox-alpha":{"draws":74,"losses":187,"wins":213},"stealth/space-bunny-alpha":{"draws":28,"losses":20,"wins":66},"stepfun/step-3.7-flash":{"draws":15,"losses":20,"wins":67},"stepfun/step-5-preview":{"draws":5,"losses":7,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":14,"wins":42},"tencent/hy4-preview":{"draws":21,"losses":54,"wins":63},"thinkingmachines/inkling":{"draws":40,"losses":30,"wins":122},"thinkingmachines/inkling-small":{"draws":30,"losses":22,"wins":92},"unbiased/pareto-26.10":{"draws":3,"losses":39,"wins":6},"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":19,"losses":60,"wins":65},"x-ai/grok-4.6":{"draws":33,"losses":61,"wins":50},"x-ai/grok-4.7":{"draws":16,"losses":76,"wins":34},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":30},"xiaomi/mimo-v2.5":{"draws":49,"losses":38,"wins":135},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":14,"wins":55},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":34,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":16,"losses":50,"wins":30},"z-ai/glm-5.2":{"draws":61,"losses":65,"wins":162},"z-ai/glm-5.3":{"draws":31,"losses":75,"wins":32},"z-ai/glm-5.3-flash":{"draws":12,"losses":42,"wins":42},"z-ai/glm-5.3-flashx":{"draws":30,"losses":57,"wins":57}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":26,"wins":86},"claude-fable-5":{"draws":22,"losses":79,"wins":43},"claude-fable-5-1":{"draws":10,"losses":138,"wins":14},"claude-haiku-5-5":{"draws":29,"losses":57,"wins":52},"claude-opus-4-5":{"draws":51,"losses":55,"wins":128},"claude-opus-4-8":{"draws":21,"losses":58,"wins":53},"claude-opus-5":{"draws":38,"losses":166,"wins":42},"claude-opus-5-5":{"draws":15,"losses":132,"wins":9},"claude-sonnet-5":{"draws":31,"losses":35,"wins":78},"claude-sonnet-5-5":{"draws":24,"losses":66,"wins":54},"cohere/north-mini-code":{"draws":9,"losses":5,"wins":40},"deepseek/deepseek-v4-flash":{"draws":45,"losses":43,"wins":128},"deepseek/deepseek-v4-pro":{"draws":31,"losses":41,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":40,"wins":66},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":52,"wins":68},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":72,"wins":48},"elorian/glimpse":{"draws":17,"losses":29,"wins":32},"fireworks/ember-1":{"draws":28,"losses":49,"wins":67},"gemini-3.1-pro-preview":{"draws":28,"losses":41,"wins":75},"gemini-4-argon":{"draws":12,"losses":110,"wins":22},"google/gemini-3.1-flash-lite":{"draws":21,"losses":9,"wins":66},"google/gemini-3.5-flash":{"draws":35,"losses":51,"wins":94},"google/gemini-3.5-flash-lite":{"draws":58,"losses":47,"wins":147},"google/gemini-3.6-flash":{"draws":62,"losses":100,"wins":114},"google/gemini-3.8-flash":{"draws":27,"losses":66,"wins":51},"google/gemma-4-31b-it":{"draws":28,"losses":11,"wins":45},"gpt-4.1":{"draws":8,"losses":10,"wins":30},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":13},"gpt-5":{"draws":27,"losses":35,"wins":64},"gpt-5.4":{"draws":29,"losses":54,"wins":55},"gpt-5.4-mini":{"draws":24,"losses":13,"wins":59},"gpt-5.4-nano":{"draws":28,"losses":36,"wins":80},"gpt-5.5":{"draws":34,"losses":47,"wins":51},"gpt-5.6-luna":{"draws":31,"losses":36,"wins":77},"gpt-5.6-sol":{"draws":24,"losses":79,"wins":41},"gpt-5.6-terra":{"draws":32,"losses":42,"wins":64},"gpt-6-astra":{"draws":15,"losses":121,"wins":8},"gpt-6-luna":{"draws":27,"losses":46,"wins":71},"gpt-6-sol":{"draws":16,"losses":86,"wins":42},"gpt-6.1-sol":{"draws":15,"losses":111,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":21,"losses":9,"wins":72},"inception/mercury-3":{"draws":21,"losses":33,"wins":42},"inclusionai/ling-3.0-flash":{"draws":33,"losses":8,"wins":61},"inclusionai/ling-3.1-flash":{"draws":4,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":20,"wins":112},"meta/muse-glimmer-30b":{"draws":28,"losses":20,"wins":78},"meta/muse-spark-1.2":{"draws":29,"losses":51,"wins":58},"meta/muse-spark-1.3":{"draws":22,"losses":62,"wins":60},"meta/muse-spark-open":{"draws":27,"losses":54,"wins":57},"meta/muse-wonder":{"draws":34,"losses":73,"wins":37},"minimax/minimax-m3":{"draws":18,"losses":12,"wins":48},"minimax/minimax-m3.1-flash":{"draws":22,"losses":29,"wins":75},"mistralai/mistral-large-4-0":{"draws":29,"losses":27,"wins":34},"mistralai/mistral-medium-3-5":{"draws":15,"losses":9,"wins":60},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":15,"wins":13},"moonshotai/kimi-k3":{"draws":33,"losses":39,"wins":66},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":110,"wins":22},"nex-agi/nex-n2-pro":{"draws":10,"losses":10,"wins":52},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":8,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":22,"wins":80},"nvidia/nemotron-3.5-super-vl":{"draws":13,"losses":14,"wins":39},"o3":{"draws":21,"losses":58,"wins":119},"openai/gpt-oss-120b":{"draws":27,"losses":14,"wins":85},"poolside/laguna-s-2.1":{"draws":36,"losses":26,"wins":76},"qwen/qwen3.7-max":{"draws":18,"losses":19,"wins":47},"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":22,"losses":26,"wins":54},"qwen/qwen3.8-flash":{"draws":27,"losses":24,"wins":45},"qwen/qwen3.8-max":{"draws":35,"losses":52,"wins":57},"qwen/qwen3.8-max-0902":{"draws":30,"losses":53,"wins":61},"recursive/flint-v1.0":{"draws":10,"losses":3,"wins":29},"reflection/beam-1.0-501b-a23b":{"draws":23,"losses":41,"wins":68},"stealth/ox-alpha":{"draws":83,"losses":167,"wins":224},"stealth/space-bunny-alpha":{"draws":24,"losses":24,"wins":66},"stepfun/step-3.7-flash":{"draws":13,"losses":14,"wins":75},"stepfun/step-5-preview":{"draws":4,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":13,"wins":49},"tencent/hy4-preview":{"draws":32,"losses":55,"wins":51},"thinkingmachines/inkling":{"draws":42,"losses":26,"wins":124},"thinkingmachines/inkling-small":{"draws":26,"losses":22,"wins":96},"unbiased/pareto-26.10":{"draws":4,"losses":39,"wins":5},"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":26,"losses":63,"wins":55},"x-ai/grok-4.7":{"draws":17,"losses":82,"wins":27},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":30},"xiaomi/mimo-v2.5":{"draws":56,"losses":21,"wins":145},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":18,"wins":46},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":36,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":44,"wins":35},"z-ai/glm-5.2":{"draws":71,"losses":69,"wins":148},"z-ai/glm-5.3":{"draws":19,"losses":83,"wins":36},"z-ai/glm-5.3-flash":{"draws":30,"losses":57,"wins":57},"z-ai/glm-5.3-flashx":{"draws":20,"losses":38,"wins":38}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":9,"wins":9},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":29,"losses":31,"wins":18},"claude-opus-4-8":{"draws":15,"losses":23,"wins":6},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":15,"losses":23,"wins":10},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":18,"wins":14},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":14,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":35,"losses":18,"wins":31},"google/gemini-3.6-flash":{"draws":23,"losses":45,"wins":24},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":9},"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":15,"losses":15,"wins":12},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":19},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":10,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":21,"wins":12},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":15,"losses":17,"wins":16},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"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":15,"losses":6,"wins":13},"inception/mercury-3":{"draws":15,"losses":7,"wins":10},"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":13,"losses":11,"wins":28},"meta/muse-glimmer-30b":{"draws":15,"losses":9,"wins":18},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":16,"losses":25,"wins":7},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":11},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":10,"losses":16,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":9,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":22,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":12,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":5,"wins":7},"o3":{"draws":14,"losses":29,"wins":23},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":21},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":18},"qwen/qwen3.8-max-0902":{"draws":15,"losses":23,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":19,"wins":11},"stealth/ox-alpha":{"draws":36,"losses":87,"wins":35},"stealth/space-bunny-alpha":{"draws":18,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":10,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":23,"wins":8},"thinkingmachines/inkling":{"draws":25,"losses":11,"wins":28},"thinkingmachines/inkling-small":{"draws":18,"losses":8,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":28,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":34,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":26,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.2":{"draws":35,"losses":30,"wins":31},"z-ai/glm-5.3":{"draws":9,"losses":34,"wins":3},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":9}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":36},"claude-fable-5":{"draws":2,"losses":12,"wins":18},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":8,"losses":12,"wins":26},"claude-opus-4-5":{"draws":1,"losses":12,"wins":65},"claude-opus-4-8":{"draws":1,"losses":12,"wins":31},"claude-opus-5":{"draws":10,"losses":40,"wins":32},"claude-opus-5-5":{"draws":6,"losses":38,"wins":8},"claude-sonnet-5":{"draws":3,"losses":5,"wins":40},"claude-sonnet-5-5":{"draws":2,"losses":20,"wins":26},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":64},"deepseek/deepseek-v4-pro":{"draws":2,"losses":9,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":7,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":27},"elorian/glimpse":{"draws":0,"losses":6,"wins":20},"fireworks/ember-1":{"draws":7,"losses":5,"wins":36},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":35},"gemini-4-argon":{"draws":7,"losses":28,"wins":13},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":30},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":54},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":78},"google/gemini-3.6-flash":{"draws":4,"losses":18,"wins":70},"google/gemini-3.8-flash":{"draws":4,"losses":19,"wins":25},"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":1,"losses":9,"wins":32},"gpt-5.4":{"draws":7,"losses":16,"wins":23},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":25},"gpt-5.4-nano":{"draws":1,"losses":6,"wins":41},"gpt-5.5":{"draws":3,"losses":18,"wins":23},"gpt-5.6-luna":{"draws":2,"losses":5,"wins":41},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":26},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":35},"gpt-6-astra":{"draws":5,"losses":37,"wins":6},"gpt-6-luna":{"draws":6,"losses":10,"wins":32},"gpt-6-sol":{"draws":4,"losses":27,"wins":17},"gpt-6.1-sol":{"draws":2,"losses":32,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":31},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":31},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":5,"wins":46},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":38},"meta/muse-spark-1.2":{"draws":2,"losses":8,"wins":36},"meta/muse-spark-1.3":{"draws":3,"losses":8,"wins":37},"meta/muse-spark-open":{"draws":1,"losses":11,"wins":34},"meta/muse-wonder":{"draws":5,"losses":15,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"minimax/minimax-m3.1-flash":{"draws":3,"losses":4,"wins":35},"mistralai/mistral-large-4-0":{"draws":7,"losses":3,"wins":20},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":8,"wins":35},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":5,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":21},"o3":{"draws":3,"losses":11,"wins":52},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":38},"poolside/laguna-s-2.1":{"draws":1,"losses":3,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":11,"wins":35},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":29},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":23},"qwen/qwen3.8-max":{"draws":4,"losses":9,"wins":35},"qwen/qwen3.8-max-0902":{"draws":4,"losses":11,"wins":33},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":8,"wins":33},"stealth/ox-alpha":{"draws":11,"losses":23,"wins":124},"stealth/space-bunny-alpha":{"draws":6,"losses":2,"wins":30},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":31},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":19},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":38},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":44},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"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":10,"wins":35},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":4,"losses":23,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":20},"z-ai/glm-5.2":{"draws":8,"losses":10,"wins":78},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":7,"losses":7,"wins":34},"z-ai/glm-5.3-flashx":{"draws":3,"losses":11,"wins":34}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":56},"claude-fable-5":{"draws":0,"losses":4,"wins":62},"claude-fable-5-1":{"draws":3,"losses":10,"wins":43},"claude-haiku-5-5":{"draws":4,"losses":1,"wins":57},"claude-opus-4-5":{"draws":0,"losses":3,"wins":103},"claude-opus-4-8":{"draws":2,"losses":3,"wins":53},"claude-opus-5":{"draws":7,"losses":16,"wins":91},"claude-opus-5-5":{"draws":8,"losses":27,"wins":35},"claude-sonnet-5":{"draws":0,"losses":1,"wins":65},"claude-sonnet-5-5":{"draws":1,"losses":12,"wins":53},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":95},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":61},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":5,"wins":60},"elorian/glimpse":{"draws":1,"losses":2,"wins":35},"fireworks/ember-1":{"draws":1,"losses":1,"wins":64},"gemini-3.1-pro-preview":{"draws":2,"losses":1,"wins":63},"gemini-4-argon":{"draws":3,"losses":13,"wins":50},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":41},"google/gemini-3.5-flash":{"draws":2,"losses":1,"wins":79},"google/gemini-3.5-flash-lite":{"draws":1,"losses":3,"wins":112},"google/gemini-3.6-flash":{"draws":1,"losses":5,"wins":122},"google/gemini-3.8-flash":{"draws":5,"losses":1,"wins":60},"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":0,"losses":3,"wins":61},"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":65},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":59},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":64},"gpt-6-astra":{"draws":6,"losses":20,"wins":40},"gpt-6-luna":{"draws":1,"losses":2,"wins":63},"gpt-6-sol":{"draws":0,"losses":12,"wins":54},"gpt-6.1-sol":{"draws":5,"losses":22,"wins":39},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":45},"inception/mercury-3":{"draws":0,"losses":0,"wins":42},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":45},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":68},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":60},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":60},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":60},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":61},"meta/muse-wonder":{"draws":4,"losses":7,"wins":55},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":33},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":59},"mistralai/mistral-large-4-0":{"draws":0,"losses":4,"wins":38},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":16},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":61},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":8,"wins":54},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":50},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":32},"o3":{"draws":0,"losses":1,"wins":85},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":56},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":58},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":66},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":46},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":65},"qwen/qwen3.8-max-0902":{"draws":2,"losses":3,"wins":61},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":61},"stealth/ox-alpha":{"draws":5,"losses":6,"wins":223},"stealth/space-bunny-alpha":{"draws":0,"losses":0,"wins":54},"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":1,"losses":1,"wins":32},"tencent/hy4-preview":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":89},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":65},"unbiased/pareto-26.10":{"draws":5,"losses":7,"wins":10},"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":63},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":57},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":51},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":21},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":94},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":38},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":3,"wins":36},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":132},"z-ai/glm-5.3":{"draws":5,"losses":2,"wins":57},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":62},"z-ai/glm-5.3-flashx":{"draws":1,"losses":4,"wins":61}},"claude-haiku-5-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":33},"claude-fable-5":{"draws":6,"losses":13,"wins":23},"claude-fable-5-1":{"draws":4,"losses":37,"wins":5},"claude-haiku-5-5":{"draws":5,"losses":5,"wins":18},"claude-opus-4-5":{"draws":12,"losses":6,"wins":52},"claude-opus-4-8":{"draws":6,"losses":10,"wins":26},"claude-opus-5":{"draws":11,"losses":38,"wins":21},"claude-opus-5-5":{"draws":6,"losses":33,"wins":7},"claude-sonnet-5":{"draws":5,"losses":4,"wins":33},"claude-sonnet-5-5":{"draws":4,"losses":14,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":3,"wins":52},"deepseek/deepseek-v4-pro":{"draws":4,"losses":5,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":10,"wins":23},"elorian/glimpse":{"draws":2,"losses":6,"wins":14},"fireworks/ember-1":{"draws":6,"losses":8,"wins":28},"gemini-3.1-pro-preview":{"draws":6,"losses":9,"wins":27},"gemini-4-argon":{"draws":8,"losses":16,"wins":18},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":41},"google/gemini-3.5-flash-lite":{"draws":5,"losses":5,"wins":64},"google/gemini-3.6-flash":{"draws":8,"losses":18,"wins":54},"google/gemini-3.8-flash":{"draws":8,"losses":8,"wins":26},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":24},"gpt-4.1":{"draws":0,"losses":1,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":3,"losses":3,"wins":30},"gpt-5.4":{"draws":2,"losses":10,"wins":28},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":22},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":38},"gpt-5.5":{"draws":5,"losses":10,"wins":23},"gpt-5.6-luna":{"draws":5,"losses":2,"wins":35},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":22},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":26},"gpt-6-astra":{"draws":2,"losses":35,"wins":5},"gpt-6-luna":{"draws":5,"losses":6,"wins":31},"gpt-6-sol":{"draws":10,"losses":16,"wins":16},"gpt-6.1-sol":{"draws":3,"losses":31,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":29},"inception/mercury-3":{"draws":5,"losses":4,"wins":19},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":26},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":40},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":31},"meta/muse-spark-1.2":{"draws":6,"losses":5,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-open":{"draws":3,"losses":8,"wins":29},"meta/muse-wonder":{"draws":9,"losses":16,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":21},"minimax/minimax-m3.1-flash":{"draws":2,"losses":2,"wins":32},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":2,"losses":8,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":22,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":3,"wins":16},"o3":{"draws":2,"losses":11,"wins":49},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":32},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":17},"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":7,"wins":20},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":22},"qwen/qwen3.8-max":{"draws":3,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":6,"losses":9,"wins":27},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":4,"wins":31},"stealth/ox-alpha":{"draws":16,"losses":21,"wins":81},"stealth/space-bunny-alpha":{"draws":3,"losses":5,"wins":26},"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":8,"losses":2,"wins":44},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":40},"unbiased/pareto-26.10":{"draws":3,"losses":8,"wins":3},"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":24,"wins":10},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":7,"losses":6,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":16},"z-ai/glm-5.2":{"draws":5,"losses":10,"wins":69},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":9,"wins":30},"z-ai/glm-5.3-flashx":{"draws":5,"losses":10,"wins":27}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":28},"claude-fable-5":{"draws":7,"losses":32,"wins":9},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":16,"wins":16},"claude-opus-4-5":{"draws":20,"losses":19,"wins":23},"claude-opus-4-8":{"draws":13,"losses":17,"wins":14},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":18},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":17,"losses":12,"wins":43},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":19,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":28,"wins":12},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":14,"losses":16,"wins":18},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":27},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":25,"wins":26},"google/gemini-3.5-flash-lite":{"draws":25,"losses":18,"wins":41},"google/gemini-3.6-flash":{"draws":20,"losses":44,"wins":28},"google/gemini-3.8-flash":{"draws":13,"losses":27,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":13,"wins":18},"gpt-5.4":{"draws":12,"losses":23,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":12,"wins":24},"gpt-5.5":{"draws":14,"losses":20,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"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":14,"losses":2,"wins":18},"inception/mercury-3":{"draws":9,"losses":12,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":34},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":27},"meta/muse-spark-1.2":{"draws":10,"losses":25,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":22,"wins":15},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":7,"losses":19,"wins":40},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":26},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":12,"losses":23,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":16},"stealth/ox-alpha":{"draws":32,"losses":63,"wins":63},"stealth/space-bunny-alpha":{"draws":8,"losses":8,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":22},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":38},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":14,"losses":21,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":27,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":24,"losses":11,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":15},"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":24,"losses":23,"wins":49},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":20,"wins":12}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":29},"claude-fable-5":{"draws":4,"losses":15,"wins":23},"claude-fable-5-1":{"draws":5,"losses":31,"wins":10},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":26},"claude-opus-4-5":{"draws":14,"losses":9,"wins":47},"claude-opus-4-8":{"draws":4,"losses":3,"wins":21},"claude-opus-5":{"draws":12,"losses":39,"wins":19},"claude-opus-5-5":{"draws":8,"losses":29,"wins":9},"claude-sonnet-5":{"draws":8,"losses":4,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":12,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":55},"deepseek/deepseek-v4-pro":{"draws":3,"losses":7,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":13,"wins":25},"elorian/glimpse":{"draws":3,"losses":8,"wins":11},"fireworks/ember-1":{"draws":10,"losses":7,"wins":25},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":29},"gemini-4-argon":{"draws":4,"losses":22,"wins":16},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":37},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":62},"google/gemini-3.6-flash":{"draws":14,"losses":20,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":12,"wins":23},"google/gemma-4-31b-it":{"draws":3,"losses":2,"wins":21},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":2,"losses":5,"wins":29},"gpt-5.4":{"draws":5,"losses":14,"wins":21},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":3,"wins":37},"gpt-5.5":{"draws":6,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":5,"losses":5,"wins":32},"gpt-5.6-sol":{"draws":6,"losses":14,"wins":22},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":31},"gpt-6-astra":{"draws":5,"losses":32,"wins":5},"gpt-6-luna":{"draws":5,"losses":6,"wins":31},"gpt-6-sol":{"draws":5,"losses":19,"wins":18},"gpt-6.1-sol":{"draws":4,"losses":28,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":25},"inception/mercury-3":{"draws":4,"losses":2,"wins":22},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":38},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":33},"meta/muse-spark-1.2":{"draws":4,"losses":9,"wins":27},"meta/muse-spark-1.3":{"draws":6,"losses":11,"wins":25},"meta/muse-spark-open":{"draws":5,"losses":5,"wins":30},"meta/muse-wonder":{"draws":7,"losses":14,"wins":21},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":4,"wins":25},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":11},"moonshotai/kimi-k3":{"draws":8,"losses":10,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":12},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":17},"o3":{"draws":4,"losses":7,"wins":51},"openai/gpt-oss-120b":{"draws":5,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":32},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":11,"wins":20},"qwen/qwen3.8-27b":{"draws":4,"losses":5,"wins":21},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.8-max":{"draws":1,"losses":10,"wins":31},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":20},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":30},"stealth/ox-alpha":{"draws":21,"losses":23,"wins":74},"stealth/space-bunny-alpha":{"draws":5,"losses":5,"wins":24},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":19},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":26},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":45},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":36},"unbiased/pareto-26.10":{"draws":4,"losses":7,"wins":3},"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":11,"losses":9,"wins":22},"x-ai/grok-4.6":{"draws":8,"losses":12,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":18,"wins":13},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":10,"losses":9,"wins":65},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":20},"z-ai/glm-5.3-flash":{"draws":3,"losses":14,"wins":25},"z-ai/glm-5.3-flashx":{"draws":7,"losses":6,"wins":29}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":8,"wins":62},"claude-fable-5":{"draws":5,"losses":21,"wins":52},"claude-fable-5-1":{"draws":8,"losses":43,"wins":37},"claude-haiku-5-5":{"draws":5,"losses":9,"wins":60},"claude-opus-4-5":{"draws":9,"losses":9,"wins":108},"claude-opus-4-8":{"draws":2,"losses":11,"wins":57},"claude-opus-5":{"draws":13,"losses":38,"wins":75},"claude-opus-5-5":{"draws":5,"losses":42,"wins":39},"claude-sonnet-5":{"draws":5,"losses":6,"wins":67},"claude-sonnet-5-5":{"draws":2,"losses":18,"wins":58},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":2,"losses":8,"wins":104},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":3,"wins":64},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":62},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":12,"wins":60},"elorian/glimpse":{"draws":3,"losses":8,"wins":33},"fireworks/ember-1":{"draws":2,"losses":13,"wins":63},"gemini-3.1-pro-preview":{"draws":2,"losses":6,"wins":70},"gemini-4-argon":{"draws":6,"losses":23,"wins":49},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":42},"google/gemini-3.5-flash":{"draws":7,"losses":4,"wins":85},"google/gemini-3.5-flash-lite":{"draws":2,"losses":6,"wins":126},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":121},"google/gemini-3.8-flash":{"draws":4,"losses":11,"wins":63},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":40},"gpt-4.1":{"draws":0,"losses":1,"wins":25},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":1,"losses":4,"wins":65},"gpt-5.4":{"draws":3,"losses":8,"wins":63},"gpt-5.4-mini":{"draws":1,"losses":3,"wins":48},"gpt-5.4-nano":{"draws":3,"losses":6,"wins":65},"gpt-5.5":{"draws":5,"losses":7,"wins":62},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":71},"gpt-5.6-sol":{"draws":7,"losses":16,"wins":55},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":65},"gpt-6-astra":{"draws":6,"losses":51,"wins":21},"gpt-6-luna":{"draws":9,"losses":6,"wins":63},"gpt-6-sol":{"draws":11,"losses":22,"wins":45},"gpt-6.1-sol":{"draws":13,"losses":34,"wins":31},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":3,"losses":2,"wins":47},"inception/mercury-3":{"draws":3,"losses":2,"wins":47},"inclusionai/ling-3.0-flash":{"draws":2,"losses":4,"wins":46},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":1,"losses":6,"wins":73},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":69},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":68},"meta/muse-spark-1.3":{"draws":2,"losses":10,"wins":66},"meta/muse-spark-open":{"draws":2,"losses":8,"wins":64},"meta/muse-wonder":{"draws":4,"losses":18,"wins":56},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":41},"minimax/minimax-m3.1-flash":{"draws":5,"losses":5,"wins":56},"mistralai/mistral-large-4-0":{"draws":3,"losses":6,"wins":43},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":20},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":65},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":25,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":36},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":62},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":5,"wins":30},"o3":{"draws":1,"losses":6,"wins":89},"openai/gpt-oss-120b":{"draws":2,"losses":4,"wins":64},"poolside/laguna-s-2.1":{"draws":3,"losses":4,"wins":73},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":38},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":9,"wins":66},"qwen/qwen3.8-27b":{"draws":3,"losses":3,"wins":46},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":47},"qwen/qwen3.8-max":{"draws":1,"losses":5,"wins":72},"qwen/qwen3.8-max-0902":{"draws":5,"losses":8,"wins":65},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":68},"stealth/ox-alpha":{"draws":21,"losses":25,"wins":220},"stealth/space-bunny-alpha":{"draws":4,"losses":2,"wins":56},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":45},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":5,"wins":39},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":64},"thinkingmachines/inkling":{"draws":6,"losses":7,"wins":95},"thinkingmachines/inkling-small":{"draws":7,"losses":6,"wins":65},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":10},"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":10,"losses":13,"wins":55},"x-ai/grok-4.6":{"draws":5,"losses":11,"wins":62},"x-ai/grok-4.7":{"draws":6,"losses":18,"wins":46},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":25},"xiaomi/mimo-v2.5":{"draws":4,"losses":7,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":44},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":39},"z-ai/glm-5.2":{"draws":9,"losses":10,"wins":137},"z-ai/glm-5.3":{"draws":6,"losses":7,"wins":61},"z-ai/glm-5.3-flash":{"draws":8,"losses":7,"wins":63},"z-ai/glm-5.3-flashx":{"draws":8,"losses":6,"wins":64}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":1,"losses":3,"wins":44},"claude-fable-5-1":{"draws":5,"losses":8,"wins":41},"claude-haiku-5-5":{"draws":2,"losses":0,"wins":44},"claude-opus-4-5":{"draws":0,"losses":1,"wins":77},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":4,"losses":9,"wins":69},"claude-opus-5-5":{"draws":2,"losses":9,"wins":25},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":3,"losses":3,"wins":42},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":4,"wins":44},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":0,"losses":2,"wins":46},"gemini-3.1-pro-preview":{"draws":0,"losses":0,"wins":48},"gemini-4-argon":{"draws":1,"losses":5,"wins":42},"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":4,"wins":87},"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":0,"losses":2,"wins":46},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":45},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":5,"losses":13,"wins":30},"gpt-6-luna":{"draws":0,"losses":0,"wins":48},"gpt-6-sol":{"draws":3,"losses":1,"wins":44},"gpt-6.1-sol":{"draws":7,"losses":8,"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},"inception/mercury-3":{"draws":0,"losses":0,"wins":32},"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-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":1,"losses":4,"wins":43},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":42},"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},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":6,"wins":38},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":20},"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":0,"losses":0,"wins":24},"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":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":43},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":1,"losses":1,"wins":156},"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":2,"wins":44},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":2,"losses":4,"wins":10},"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":3,"losses":3,"wins":42},"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":0,"losses":3,"wins":29},"z-ai/glm-5.2":{"draws":1,"losses":1,"wins":94},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":42},"z-ai/glm-5.3-flash":{"draws":1,"losses":1,"wins":46},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":43}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":29},"claude-fable-5":{"draws":8,"losses":25,"wins":15},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":23},"claude-opus-4-5":{"draws":23,"losses":19,"wins":36},"claude-opus-4-8":{"draws":9,"losses":16,"wins":19},"claude-opus-5":{"draws":13,"losses":58,"wins":11},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":8,"losses":5,"wins":19},"claude-sonnet-5-5":{"draws":6,"losses":22,"wins":20},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":47},"deepseek/deepseek-v4-pro":{"draws":9,"losses":13,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":19},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":11,"losses":17,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":6,"losses":36,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":15,"losses":21,"wins":24},"google/gemini-3.5-flash-lite":{"draws":19,"losses":11,"wins":54},"google/gemini-3.6-flash":{"draws":14,"losses":32,"wins":46},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":8,"wins":23},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":16},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":11,"losses":17,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":22},"gpt-5.6-sol":{"draws":7,"losses":33,"wins":8},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":23},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":10,"losses":18,"wins":20},"gpt-6-sol":{"draws":7,"losses":32,"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":10,"losses":3,"wins":21},"inception/mercury-3":{"draws":10,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":37},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":28},"meta/muse-spark-1.2":{"draws":15,"losses":14,"wins":17},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":16},"meta/muse-spark-open":{"draws":10,"losses":20,"wins":16},"meta/muse-wonder":{"draws":11,"losses":23,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":11,"losses":13,"wins":18},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":40,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":11,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":18},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":16},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":32,"losses":64,"wins":62},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":22},"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":7,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":19,"losses":7,"wins":38},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":30},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":15,"losses":20,"wins":13},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":17},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":8,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":50},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":4,"losses":25,"wins":19},"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":1,"wins":42},"claude-fable-5-1":{"draws":4,"losses":17,"wins":33},"claude-haiku-5-5":{"draws":3,"losses":3,"wins":40},"claude-opus-4-5":{"draws":8,"losses":2,"wins":68},"claude-opus-4-8":{"draws":4,"losses":1,"wins":39},"claude-opus-5":{"draws":7,"losses":14,"wins":61},"claude-opus-5-5":{"draws":8,"losses":18,"wins":26},"claude-sonnet-5":{"draws":1,"losses":0,"wins":47},"claude-sonnet-5-5":{"draws":0,"losses":2,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":5,"losses":0,"wins":43},"gemini-3.1-pro-preview":{"draws":1,"losses":3,"wins":44},"gemini-4-argon":{"draws":7,"losses":7,"wins":34},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":54},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":79},"google/gemini-3.6-flash":{"draws":7,"losses":5,"wins":80},"google/gemini-3.8-flash":{"draws":4,"losses":2,"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":2,"losses":0,"wins":40},"gpt-5.4":{"draws":8,"losses":0,"wins":38},"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":5,"losses":16,"wins":27},"gpt-6-luna":{"draws":8,"losses":1,"wins":39},"gpt-6-sol":{"draws":4,"losses":6,"wins":38},"gpt-6.1-sol":{"draws":1,"losses":15,"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},"inception/mercury-3":{"draws":4,"losses":0,"wins":28},"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":4,"losses":1,"wins":41},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":45},"meta/muse-spark-open":{"draws":4,"losses":1,"wins":41},"meta/muse-wonder":{"draws":5,"losses":1,"wins":42},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"minimax/minimax-m3.1-flash":{"draws":2,"losses":0,"wins":40},"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":1,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":5,"wins":35},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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":6,"losses":2,"wins":40},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":0,"wins":40},"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":{"draws":2,"losses":7,"wins":7},"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":6,"losses":0,"wins":90},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":36},"z-ai/glm-5.3-flash":{"draws":4,"losses":4,"wins":40},"z-ai/glm-5.3-flashx":{"draws":5,"losses":3,"wins":40}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":9,"wins":14},"claude-fable-5":{"draws":8,"losses":28,"wins":6},"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":20,"losses":31,"wins":17},"claude-opus-4-8":{"draws":8,"losses":21,"wins":9},"claude-opus-5":{"draws":13,"losses":49,"wins":8},"claude-opus-5-5":{"draws":2,"losses":41,"wins":3},"claude-sonnet-5":{"draws":12,"losses":19,"wins":11},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":15,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":15,"losses":15,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":10,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":7},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":13,"losses":19,"wins":10},"gemini-3.1-pro-preview":{"draws":13,"losses":12,"wins":17},"gemini-4-argon":{"draws":8,"losses":34,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":17,"losses":20,"wins":15},"google/gemini-3.5-flash-lite":{"draws":23,"losses":24,"wins":25},"google/gemini-3.6-flash":{"draws":21,"losses":45,"wins":14},"google/gemini-3.8-flash":{"draws":10,"losses":27,"wins":5},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":9},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":15,"wins":8},"gpt-5.4":{"draws":16,"losses":17,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":12},"gpt-5.5":{"draws":14,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":16,"losses":9,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":28,"wins":7},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":14},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":17,"losses":13,"wins":12},"gpt-6-sol":{"draws":9,"losses":28,"wins":5},"gpt-6.1-sol":{"draws":7,"losses":34,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":14},"inception/mercury-3":{"draws":11,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":15,"losses":9,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":9,"wins":21},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":12},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":9,"losses":26,"wins":7},"meta/muse-spark-open":{"draws":10,"losses":22,"wins":8},"meta/muse-wonder":{"draws":8,"losses":25,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":6,"wins":7},"minimax/minimax-m3.1-flash":{"draws":7,"losses":12,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":8,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":13,"losses":22,"wins":19},"openai/gpt-oss-120b":{"draws":14,"losses":12,"wins":10},"poolside/laguna-s-2.1":{"draws":17,"losses":10,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":15,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-max-0902":{"draws":14,"losses":16,"wins":12},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":35,"losses":72,"wins":33},"stealth/space-bunny-alpha":{"draws":13,"losses":8,"wins":11},"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":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":17,"wins":11},"thinkingmachines/inkling":{"draws":26,"losses":11,"wins":17},"thinkingmachines/inkling-small":{"draws":20,"losses":7,"wins":15},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":11,"losses":22,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":16,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":33,"losses":27,"wins":24},"z-ai/glm-5.3":{"draws":6,"losses":30,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":11,"losses":21,"wins":10}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":24},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":22,"losses":25,"wins":31},"claude-opus-4-8":{"draws":9,"losses":20,"wins":15},"claude-opus-5":{"draws":8,"losses":65,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":13,"losses":20,"wins":15},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":36},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":24,"wins":10},"elorian/glimpse":{"draws":9,"losses":13,"wins":4},"fireworks/ember-1":{"draws":15,"losses":16,"wins":17},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":16,"losses":23,"wins":21},"google/gemini-3.5-flash-lite":{"draws":26,"losses":22,"wins":36},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":29},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":10},"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":11,"losses":10,"wins":21},"gpt-5.4":{"draws":15,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":15,"wins":28},"gpt-5.5":{"draws":15,"losses":23,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":14,"losses":17,"wins":15},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":12,"losses":20,"wins":16},"gpt-6-sol":{"draws":6,"losses":32,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":42,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":10,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":11,"wins":19},"meta/muse-spark-1.2":{"draws":9,"losses":23,"wins":14},"meta/muse-spark-1.3":{"draws":9,"losses":27,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":12},"meta/muse-wonder":{"draws":14,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":23},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":36,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":8,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":8,"losses":23,"wins":35},"openai/gpt-oss-120b":{"draws":14,"losses":10,"wins":18},"poolside/laguna-s-2.1":{"draws":13,"losses":17,"wins":16},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":25,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":7},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":24,"wins":13},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":18,"wins":14},"stealth/ox-alpha":{"draws":35,"losses":79,"wins":44},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"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":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":9,"losses":22,"wins":15},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":2,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":19,"wins":17},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":31,"losses":29,"wins":36},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"wins":19}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":26},"claude-fable-5":{"draws":7,"losses":28,"wins":13},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":21,"wins":14},"claude-opus-4-5":{"draws":16,"losses":20,"wins":42},"claude-opus-4-8":{"draws":11,"losses":14,"wins":19},"claude-opus-5":{"draws":5,"losses":67,"wins":10},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":13,"losses":12,"wins":23},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":15,"losses":15,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":8,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":24,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":25,"wins":16},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":9,"losses":14,"wins":25},"gemini-4-argon":{"draws":4,"losses":40,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":21,"wins":27},"google/gemini-3.5-flash-lite":{"draws":20,"losses":8,"wins":56},"google/gemini-3.6-flash":{"draws":18,"losses":35,"wins":39},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":20},"google/gemma-4-31b-it":{"draws":12,"losses":0,"wins":16},"gpt-4.1":{"draws":3,"losses":3,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":10,"wins":26},"gpt-5.4":{"draws":8,"losses":19,"wins":19},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":13,"wins":27},"gpt-5.5":{"draws":8,"losses":22,"wins":14},"gpt-5.6-luna":{"draws":16,"losses":8,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":20},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":13,"wins":23},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":4,"wins":19},"inception/mercury-3":{"draws":6,"losses":14,"wins":12},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":21},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":5,"wins":26},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":21},"meta/muse-spark-1.3":{"draws":11,"losses":17,"wins":20},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":26},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":10,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":39,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":6,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":8,"losses":12,"wins":46},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":8,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":3,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":21},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":16},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":21},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":18,"wins":18},"stealth/ox-alpha":{"draws":29,"losses":54,"wins":75},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":24},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":4,"losses":18,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":39},"thinkingmachines/inkling-small":{"draws":13,"losses":9,"wins":26},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":9,"losses":18,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":12},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":11,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":19,"wins":11},"z-ai/glm-5.2":{"draws":22,"losses":28,"wins":46},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":17,"wins":19}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":33},"claude-fable-5":{"draws":10,"losses":18,"wins":20},"claude-fable-5-1":{"draws":5,"losses":42,"wins":7},"claude-haiku-5-5":{"draws":14,"losses":11,"wins":21},"claude-opus-4-5":{"draws":13,"losses":12,"wins":53},"claude-opus-4-8":{"draws":4,"losses":12,"wins":28},"claude-opus-5":{"draws":9,"losses":54,"wins":19},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":13,"losses":1,"wins":58},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":14,"wins":25},"elorian/glimpse":{"draws":3,"losses":7,"wins":16},"fireworks/ember-1":{"draws":8,"losses":10,"wins":30},"gemini-3.1-pro-preview":{"draws":5,"losses":13,"wins":30},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":10,"losses":9,"wins":41},"google/gemini-3.5-flash-lite":{"draws":11,"losses":7,"wins":66},"google/gemini-3.6-flash":{"draws":17,"losses":25,"wins":50},"google/gemini-3.8-flash":{"draws":8,"losses":11,"wins":29},"google/gemma-4-31b-it":{"draws":7,"losses":1,"wins":20},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":4,"wins":26},"gpt-5.4":{"draws":8,"losses":13,"wins":25},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":6,"losses":6,"wins":36},"gpt-5.5":{"draws":8,"losses":9,"wins":27},"gpt-5.6-luna":{"draws":9,"losses":3,"wins":36},"gpt-5.6-sol":{"draws":5,"losses":21,"wins":22},"gpt-5.6-terra":{"draws":13,"losses":4,"wins":29},"gpt-6-astra":{"draws":4,"losses":39,"wins":5},"gpt-6-luna":{"draws":10,"losses":6,"wins":32},"gpt-6-sol":{"draws":8,"losses":28,"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":9,"losses":1,"wins":24},"inception/mercury-3":{"draws":5,"losses":6,"wins":21},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":29},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":3,"wins":40},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":30},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":25},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-open":{"draws":4,"losses":13,"wins":29},"meta/muse-wonder":{"draws":12,"losses":17,"wins":19},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":8,"losses":4,"wins":30},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":20},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":37},"poolside/laguna-s-2.1":{"draws":13,"losses":4,"wins":29},"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":12,"losses":7,"wins":29},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":24},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":13,"wins":25},"qwen/qwen3.8-max-0902":{"draws":10,"losses":12,"wins":26},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":10,"wins":28},"stealth/ox-alpha":{"draws":27,"losses":42,"wins":89},"stealth/space-bunny-alpha":{"draws":3,"losses":5,"wins":30},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":20},"tencent/hy4-preview":{"draws":8,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":16,"losses":5,"wins":43},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":39},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":7,"losses":13,"wins":28},"x-ai/grok-4.6":{"draws":8,"losses":11,"wins":29},"x-ai/grok-4.7":{"draws":1,"losses":24,"wins":17},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":13,"losses":3,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":20,"losses":10,"wins":66},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":7,"losses":13,"wins":28},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":27}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":31},"claude-fable-5":{"draws":10,"losses":14,"wins":24},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":10,"losses":10,"wins":26},"claude-opus-4-5":{"draws":11,"losses":11,"wins":56},"claude-opus-4-8":{"draws":9,"losses":9,"wins":26},"claude-opus-5":{"draws":10,"losses":50,"wins":22},"claude-opus-5-5":{"draws":4,"losses":38,"wins":10},"claude-sonnet-5":{"draws":7,"losses":9,"wins":32},"claude-sonnet-5-5":{"draws":3,"losses":21,"wins":24},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":7,"losses":5,"wins":60},"deepseek/deepseek-v4-pro":{"draws":7,"losses":5,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":12,"wins":30},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":6,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":9,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":7,"wins":37},"gemini-4-argon":{"draws":9,"losses":31,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":12,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":6,"wins":71},"google/gemini-3.6-flash":{"draws":8,"losses":23,"wins":61},"google/gemini-3.8-flash":{"draws":8,"losses":8,"wins":32},"google/gemma-4-31b-it":{"draws":1,"losses":3,"wins":24},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":8,"wins":29},"gpt-5.4":{"draws":6,"losses":11,"wins":29},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":40},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":4,"losses":6,"wins":38},"gpt-5.6-sol":{"draws":9,"losses":21,"wins":18},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":37},"gpt-6-astra":{"draws":7,"losses":36,"wins":5},"gpt-6-luna":{"draws":9,"losses":8,"wins":31},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":3,"losses":34,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":9,"losses":2,"wins":21},"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":9,"losses":5,"wins":38},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":8,"losses":14,"wins":24},"meta/muse-spark-1.3":{"draws":3,"losses":15,"wins":30},"meta/muse-spark-open":{"draws":8,"losses":8,"wins":30},"meta/muse-wonder":{"draws":12,"losses":14,"wins":22},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":12,"losses":2,"wins":28},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":10,"wins":33},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":13},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":4,"wins":14},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":32},"poolside/laguna-s-2.1":{"draws":6,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":8,"wins":36},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.8-flash":{"draws":7,"losses":6,"wins":19},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":7,"losses":9,"wins":32},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":4,"wins":32},"stealth/ox-alpha":{"draws":20,"losses":43,"wins":95},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":8,"wins":32},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":41},"thinkingmachines/inkling-small":{"draws":5,"losses":2,"wins":41},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":4,"losses":15,"wins":29},"x-ai/grok-4.6":{"draws":12,"losses":12,"wins":24},"x-ai/grok-4.7":{"draws":8,"losses":20,"wins":14},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":14,"losses":2,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":16},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":66},"z-ai/glm-5.3":{"draws":10,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":34},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":30}},"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":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":19,"losses":14,"wins":45},"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":41,"wins":8},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"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":15,"losses":7,"wins":50},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":20,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":6,"losses":6,"wins":20},"gemini-3.1-pro-preview":{"draws":8,"losses":10,"wins":30},"gemini-4-argon":{"draws":4,"losses":32,"wins":12},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":10,"losses":14,"wins":36},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":17,"losses":27,"wins":48},"google/gemini-3.8-flash":{"draws":11,"losses":14,"wins":23},"google/gemma-4-31b-it":{"draws":7,"losses":3,"wins":18},"gpt-4.1":{"draws":5,"losses":1,"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":16,"wins":22},"gpt-5.4-mini":{"draws":10,"losses":1,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"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":9,"wins":27},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":1,"losses":37,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":8,"losses":5,"wins":19},"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":8,"losses":10,"wins":34},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":9,"losses":10,"wins":27},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":22},"meta/muse-spark-open":{"draws":9,"losses":12,"wins":25},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":9,"losses":8,"wins":25},"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":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":9,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":7,"losses":5,"wins":54},"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":14,"losses":10,"wins":24},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":10,"losses":14,"wins":24},"qwen/qwen3.8-max-0902":{"draws":8,"losses":15,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":22},"stealth/ox-alpha":{"draws":22,"losses":44,"wins":92},"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":14,"wins":24},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":12,"losses":1,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":27,"wins":13},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":5,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":17},"z-ai/glm-5.2":{"draws":18,"losses":16,"wins":62},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":24}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":33},"claude-fable-5":{"draws":6,"losses":23,"wins":19},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":6,"losses":14,"wins":26},"claude-opus-4-5":{"draws":12,"losses":18,"wins":48},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":9,"losses":51,"wins":22},"claude-opus-5-5":{"draws":3,"losses":41,"wins":8},"claude-sonnet-5":{"draws":7,"losses":11,"wins":30},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":23},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":51},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":14,"wins":28},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":15,"wins":25},"elorian/glimpse":{"draws":4,"losses":6,"wins":16},"fireworks/ember-1":{"draws":3,"losses":15,"wins":30},"gemini-3.1-pro-preview":{"draws":4,"losses":6,"wins":22},"gemini-4-argon":{"draws":3,"losses":35,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":39},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":56},"google/gemini-3.6-flash":{"draws":12,"losses":24,"wins":56},"google/gemini-3.8-flash":{"draws":7,"losses":13,"wins":28},"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":6,"losses":5,"wins":31},"gpt-5.4":{"draws":5,"losses":16,"wins":25},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":23},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":4,"losses":16,"wins":24},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":30},"gpt-5.6-sol":{"draws":3,"losses":20,"wins":25},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":26},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":6,"losses":9,"wins":33},"gpt-6-sol":{"draws":3,"losses":26,"wins":19},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":24},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"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":7,"losses":7,"wins":38},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":33},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":3,"losses":19,"wins":26},"meta/muse-spark-open":{"draws":6,"losses":11,"wins":29},"meta/muse-wonder":{"draws":8,"losses":20,"wins":20},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"minimax/minimax-m3.1-flash":{"draws":6,"losses":8,"wins":28},"mistralai/mistral-large-4-0":{"draws":6,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":29,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":5,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":2,"losses":15,"wins":49},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":28},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":12,"wins":26},"qwen/qwen3.8-max-0902":{"draws":10,"losses":14,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":6,"wins":31},"stealth/ox-alpha":{"draws":19,"losses":46,"wins":93},"stealth/space-bunny-alpha":{"draws":5,"losses":7,"wins":26},"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":5,"losses":1,"wins":20},"tencent/hy4-preview":{"draws":3,"losses":14,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":7,"losses":4,"wins":37},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":3},"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":5,"losses":14,"wins":29},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":14},"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":1,"losses":5,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":15,"losses":16,"wins":65},"z-ai/glm-5.3":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":24},"z-ai/glm-5.3-flashx":{"draws":7,"losses":13,"wins":28}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":4,"losses":5,"wins":39},"claude-fable-5-1":{"draws":4,"losses":19,"wins":31},"claude-haiku-5-5":{"draws":2,"losses":8,"wins":36},"claude-opus-4-5":{"draws":1,"losses":2,"wins":75},"claude-opus-4-8":{"draws":0,"losses":5,"wins":39},"claude-opus-5":{"draws":8,"losses":19,"wins":55},"claude-opus-5-5":{"draws":5,"losses":24,"wins":23},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":2,"losses":9,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":16},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":70},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":43},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":3,"wins":40},"elorian/glimpse":{"draws":0,"losses":4,"wins":22},"fireworks/ember-1":{"draws":1,"losses":6,"wins":41},"gemini-3.1-pro-preview":{"draws":1,"losses":4,"wins":43},"gemini-4-argon":{"draws":3,"losses":5,"wins":24},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":56},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":1,"losses":6,"wins":85},"google/gemini-3.8-flash":{"draws":4,"losses":3,"wins":41},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":27},"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":1,"losses":4,"wins":41},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":27},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":0,"wins":43},"gpt-6-astra":{"draws":3,"losses":22,"wins":23},"gpt-6-luna":{"draws":0,"losses":1,"wins":47},"gpt-6-sol":{"draws":4,"losses":8,"wins":36},"gpt-6.1-sol":{"draws":9,"losses":13,"wins":26},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":31},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":4,"wins":47},"meta/muse-glimmer-30b":{"draws":3,"losses":4,"wins":35},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":41},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":45},"meta/muse-spark-open":{"draws":1,"losses":2,"wins":43},"meta/muse-wonder":{"draws":2,"losses":6,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":3,"losses":3,"wins":36},"mistralai/mistral-large-4-0":{"draws":2,"losses":0,"wins":28},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":1,"losses":4,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":7,"wins":38},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":0,"losses":0,"wins":66},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":40},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":44},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":27},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":44},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":44},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":43},"stealth/ox-alpha":{"draws":10,"losses":10,"wins":138},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":36},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":3,"losses":4,"wins":39},"thinkingmachines/inkling":{"draws":4,"losses":4,"wins":56},"thinkingmachines/inkling-small":{"draws":2,"losses":3,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"unbiased/pareto-26.10-preview":{"draws":2,"losses":6,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":0,"losses":8,"wins":40},"x-ai/grok-4.6":{"draws":4,"losses":1,"wins":43},"x-ai/grok-4.7":{"draws":4,"losses":8,"wins":30},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":71},"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":2,"wins":29},"z-ai/glm-5.2":{"draws":3,"losses":4,"wins":89},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":36},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":39},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":44}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":16,"wins":5},"claude-fable-5":{"draws":2,"losses":25,"wins":3},"claude-fable-5-1":{"draws":3,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":20,"wins":4},"claude-opus-4-5":{"draws":9,"losses":37,"wins":4},"claude-opus-4-8":{"draws":4,"losses":23,"wins":3},"claude-opus-5":{"draws":6,"losses":38,"wins":2},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":6,"losses":23,"wins":1},"claude-sonnet-5-5":{"draws":3,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":8,"losses":24,"wins":12},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":23,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":24,"wins":3},"elorian/glimpse":{"draws":4,"losses":9,"wins":3},"fireworks/ember-1":{"draws":5,"losses":22,"wins":3},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":7},"gemini-4-argon":{"draws":2,"losses":28,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":6,"wins":8},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":4},"google/gemini-3.5-flash-lite":{"draws":16,"losses":28,"wins":12},"google/gemini-3.6-flash":{"draws":10,"losses":41,"wins":7},"google/gemini-3.8-flash":{"draws":6,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":4},"gpt-4.1":{"draws":2,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":15,"wins":4},"gpt-5.4":{"draws":8,"losses":17,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":12,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":22,"wins":6},"gpt-5.5":{"draws":6,"losses":21,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":15,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":24,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":20,"wins":2},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":7,"losses":17,"wins":6},"gpt-6-sol":{"draws":3,"losses":27,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":9,"wins":9},"inception/mercury-3":{"draws":2,"losses":16,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":19,"wins":13},"meta/muse-glimmer-30b":{"draws":6,"losses":12,"wins":8},"meta/muse-spark-1.2":{"draws":6,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":2,"losses":24,"wins":4},"meta/muse-spark-open":{"draws":4,"losses":21,"wins":5},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":17,"wins":4},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":2},"mistralai/mistral-medium-3-5":{"draws":6,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":27,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":12,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":10,"wins":3},"o3":{"draws":11,"losses":34,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":8,"wins":13},"poolside/laguna-s-2.1":{"draws":8,"losses":12,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":19,"wins":5},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":4},"qwen/qwen3.8-max":{"draws":7,"losses":22,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":22,"wins":3},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":15,"losses":62,"wins":9},"stealth/space-bunny-alpha":{"draws":6,"losses":14,"wins":6},"stepfun/step-3.7-flash":{"draws":5,"losses":12,"wins":5},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":20,"wins":3},"thinkingmachines/inkling":{"draws":9,"losses":16,"wins":13},"thinkingmachines/inkling-small":{"draws":9,"losses":9,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"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":5,"losses":25,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":25,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":25,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":17,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":14,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":39,"wins":7},"z-ai/glm-5.3":{"draws":3,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":22,"wins":4}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":9,"wins":28},"claude-fable-5":{"draws":7,"losses":26,"wins":15},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":9,"losses":15,"wins":22},"claude-opus-4-5":{"draws":22,"losses":11,"wins":45},"claude-opus-4-8":{"draws":9,"losses":15,"wins":20},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":11,"losses":9,"wins":28},"claude-sonnet-5-5":{"draws":7,"losses":24,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":10,"losses":8,"wins":54},"deepseek/deepseek-v4-pro":{"draws":7,"losses":13,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":13,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":27},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":8,"losses":14,"wins":26},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":5,"losses":38,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":9,"losses":3,"wins":32},"google/gemini-3.5-flash-lite":{"draws":20,"losses":7,"wins":57},"google/gemini-3.6-flash":{"draws":13,"losses":24,"wins":55},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":1,"wins":13},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":8,"wins":24},"gpt-5.4":{"draws":4,"losses":20,"wins":22},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":19},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":7,"losses":14,"wins":23},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":18},"gpt-5.6-terra":{"draws":9,"losses":15,"wins":22},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":8,"losses":15,"wins":25},"gpt-6-sol":{"draws":5,"losses":30,"wins":13},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":22},"inception/mercury-3":{"draws":6,"losses":4,"wins":22},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":5,"wins":41},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":15,"wins":23},"meta/muse-spark-1.3":{"draws":7,"losses":21,"wins":20},"meta/muse-spark-open":{"draws":7,"losses":16,"wins":23},"meta/muse-wonder":{"draws":6,"losses":27,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":21},"minimax/minimax-m3.1-flash":{"draws":8,"losses":7,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":4,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":6,"losses":12,"wins":48},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":40},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":16,"wins":23},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":21},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":14,"losses":13,"wins":21},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":14},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":12,"wins":24},"stealth/ox-alpha":{"draws":26,"losses":51,"wins":81},"stealth/space-bunny-alpha":{"draws":11,"losses":3,"wins":24},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":19,"wins":20},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":36},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"unbiased/pareto-26.10-preview":{"draws":2,"losses":11,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":11},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":26},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":12,"losses":2,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":15},"z-ai/glm-5.2":{"draws":16,"losses":22,"wins":58},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":20,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":18,"wins":20}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":26,"wins":27},"claude-fable-5":{"draws":11,"losses":57,"wins":10},"claude-fable-5-1":{"draws":4,"losses":86,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":49,"wins":11},"claude-opus-4-5":{"draws":33,"losses":61,"wins":32},"claude-opus-4-8":{"draws":13,"losses":47,"wins":10},"claude-opus-5":{"draws":11,"losses":104,"wins":13},"claude-opus-5-5":{"draws":7,"losses":75,"wins":0},"claude-sonnet-5":{"draws":16,"losses":40,"wins":22},"claude-sonnet-5-5":{"draws":15,"losses":50,"wins":13},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":14},"deepseek/deepseek-v4-flash":{"draws":25,"losses":41,"wins":48},"deepseek/deepseek-v4-pro":{"draws":18,"losses":34,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":23,"losses":32,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":33,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":61,"wins":7},"elorian/glimpse":{"draws":11,"losses":22,"wins":9},"fireworks/ember-1":{"draws":24,"losses":38,"wins":16},"gemini-3.1-pro-preview":{"draws":17,"losses":37,"wins":24},"gemini-4-argon":{"draws":5,"losses":68,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":30},"google/gemini-3.5-flash":{"draws":24,"losses":50,"wins":24},"google/gemini-3.5-flash-lite":{"draws":23,"losses":46,"wins":45},"google/gemini-3.6-flash":{"draws":30,"losses":87,"wins":35},"google/gemini-3.8-flash":{"draws":11,"losses":58,"wins":9},"google/gemma-4-31b-it":{"draws":15,"losses":12,"wins":19},"gpt-4.1":{"draws":9,"losses":8,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":36,"wins":18},"gpt-5.4":{"draws":12,"losses":46,"wins":18},"gpt-5.4-mini":{"draws":15,"losses":17,"wins":20},"gpt-5.4-nano":{"draws":10,"losses":28,"wins":36},"gpt-5.5":{"draws":20,"losses":34,"wins":18},"gpt-5.6-luna":{"draws":20,"losses":33,"wins":25},"gpt-5.6-sol":{"draws":13,"losses":59,"wins":6},"gpt-5.6-terra":{"draws":17,"losses":40,"wins":17},"gpt-6-astra":{"draws":5,"losses":73,"wins":0},"gpt-6-luna":{"draws":21,"losses":41,"wins":16},"gpt-6-sol":{"draws":9,"losses":64,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":75,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":20,"losses":11,"wins":25},"inception/mercury-3":{"draws":10,"losses":26,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":14,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":24,"losses":26,"wins":38},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":29},"meta/muse-spark-1.2":{"draws":21,"losses":37,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":52,"wins":14},"meta/muse-spark-open":{"draws":11,"losses":48,"wins":17},"meta/muse-wonder":{"draws":10,"losses":59,"wins":9},"minimax/minimax-m3":{"draws":11,"losses":14,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":33,"wins":23},"mistralai/mistral-large-4-0":{"draws":12,"losses":23,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":12,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":39,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":66,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":12,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":23,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":17,"losses":61,"wins":32},"openai/gpt-oss-120b":{"draws":19,"losses":22,"wins":27},"poolside/laguna-s-2.1":{"draws":17,"losses":33,"wins":22},"qwen/qwen3.7-max":{"draws":8,"losses":22,"wins":14},"qwen/qwen3.7-plus":{"draws":9,"losses":11,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":42,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":36,"wins":11},"qwen/qwen3.8-flash":{"draws":16,"losses":25,"wins":11},"qwen/qwen3.8-max":{"draws":20,"losses":42,"wins":16},"qwen/qwen3.8-max-0902":{"draws":22,"losses":43,"wins":13},"recursive/flint-v1.0":{"draws":7,"losses":4,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":35,"wins":22},"stealth/ox-alpha":{"draws":43,"losses":162,"wins":63},"stealth/space-bunny-alpha":{"draws":13,"losses":31,"wins":20},"stepfun/step-3.7-flash":{"draws":13,"losses":19,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":11},"tencent/hy4-preview":{"draws":10,"losses":47,"wins":19},"thinkingmachines/inkling":{"draws":25,"losses":35,"wins":46},"thinkingmachines/inkling-small":{"draws":21,"losses":31,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":25,"wins":0},"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":18,"losses":41,"wins":19},"x-ai/grok-4.6":{"draws":18,"losses":49,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.5":{"draws":37,"losses":38,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":15,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":31,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":37,"wins":10},"z-ai/glm-5.2":{"draws":30,"losses":72,"wins":54},"z-ai/glm-5.3":{"draws":9,"losses":61,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":53,"wins":12},"z-ai/glm-5.3-flashx":{"draws":14,"losses":49,"wins":15}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":13,"wins":59},"claude-fable-5":{"draws":10,"losses":46,"wins":40},"claude-fable-5-1":{"draws":4,"losses":97,"wins":7},"claude-haiku-5-5":{"draws":21,"losses":25,"wins":46},"claude-opus-4-5":{"draws":39,"losses":26,"wins":91},"claude-opus-4-8":{"draws":16,"losses":26,"wins":46},"claude-opus-5":{"draws":24,"losses":105,"wins":35},"claude-opus-5-5":{"draws":12,"losses":82,"wins":10},"claude-sonnet-5":{"draws":15,"losses":23,"wins":58},"claude-sonnet-5-5":{"draws":19,"losses":37,"wins":40},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":29},"deepseek/deepseek-v4-flash":{"draws":23,"losses":8,"wins":113},"deepseek/deepseek-v4-pro":{"draws":17,"losses":16,"wins":55},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":19,"wins":54},"deepseek/deepseek-v4.1-flash":{"draws":27,"losses":21,"wins":48},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":36,"wins":46},"elorian/glimpse":{"draws":10,"losses":16,"wins":26},"fireworks/ember-1":{"draws":24,"losses":24,"wins":48},"gemini-3.1-pro-preview":{"draws":20,"losses":27,"wins":49},"gemini-4-argon":{"draws":6,"losses":79,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":54},"google/gemini-3.5-flash":{"draws":22,"losses":29,"wins":69},"google/gemini-3.5-flash-lite":{"draws":36,"losses":17,"wins":115},"google/gemini-3.6-flash":{"draws":27,"losses":43,"wins":82},"google/gemini-3.8-flash":{"draws":18,"losses":38,"wins":40},"google/gemma-4-31b-it":{"draws":15,"losses":2,"wins":39},"gpt-4.1":{"draws":6,"losses":5,"wins":21},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":9},"gpt-5":{"draws":10,"losses":19,"wins":55},"gpt-5.4":{"draws":17,"losses":32,"wins":43},"gpt-5.4-mini":{"draws":16,"losses":7,"wins":41},"gpt-5.4-nano":{"draws":14,"losses":13,"wins":69},"gpt-5.5":{"draws":18,"losses":30,"wins":40},"gpt-5.6-luna":{"draws":19,"losses":17,"wins":60},"gpt-5.6-sol":{"draws":12,"losses":44,"wins":40},"gpt-5.6-terra":{"draws":17,"losses":15,"wins":60},"gpt-6-astra":{"draws":6,"losses":78,"wins":12},"gpt-6-luna":{"draws":22,"losses":21,"wins":53},"gpt-6-sol":{"draws":12,"losses":54,"wins":30},"gpt-6.1-sol":{"draws":9,"losses":78,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":49},"inception/mercury-3":{"draws":14,"losses":9,"wins":41},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":47},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":80},"meta/muse-glimmer-30b":{"draws":21,"losses":9,"wins":54},"meta/muse-spark-1.2":{"draws":19,"losses":26,"wins":47},"meta/muse-spark-1.3":{"draws":17,"losses":37,"wins":42},"meta/muse-spark-open":{"draws":12,"losses":31,"wins":49},"meta/muse-wonder":{"draws":21,"losses":44,"wins":31},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":36},"minimax/minimax-m3.1-flash":{"draws":17,"losses":14,"wins":53},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":32},"mistralai/mistral-medium-3-5":{"draws":15,"losses":2,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":16},"moonshotai/kimi-k3":{"draws":22,"losses":20,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":66,"wins":21},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":59},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":4,"wins":30},"o3":{"draws":14,"losses":22,"wins":96},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":62},"poolside/laguna-s-2.1":{"draws":20,"losses":12,"wins":60},"qwen/qwen3.7-max":{"draws":19,"losses":6,"wins":31},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":36},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":25,"wins":56},"qwen/qwen3.8-27b":{"draws":14,"losses":13,"wins":41},"qwen/qwen3.8-flash":{"draws":14,"losses":12,"wins":38},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":57},"qwen/qwen3.8-max-0902":{"draws":26,"losses":33,"wins":37},"recursive/flint-v1.0":{"draws":8,"losses":3,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":16,"wins":56},"stealth/ox-alpha":{"draws":50,"losses":102,"wins":164},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":52},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":58},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":32},"tencent/hy4-preview":{"draws":16,"losses":19,"wins":57},"thinkingmachines/inkling":{"draws":34,"losses":13,"wins":81},"thinkingmachines/inkling-small":{"draws":27,"losses":6,"wins":63},"unbiased/pareto-26.10":{"draws":3,"losses":28,"wins":1},"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":17,"losses":32,"wins":47},"x-ai/grok-4.6":{"draws":20,"losses":32,"wins":44},"x-ai/grok-4.7":{"draws":7,"losses":52,"wins":25},"x-ai/grok-build-0.1":{"draws":10,"losses":0,"wins":22},"xiaomi/mimo-v2.5":{"draws":33,"losses":6,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":36},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":24,"wins":30},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":29,"wins":21},"z-ai/glm-5.2":{"draws":42,"losses":26,"wins":124},"z-ai/glm-5.3":{"draws":19,"losses":40,"wins":33},"z-ai/glm-5.3-flash":{"draws":15,"losses":40,"wins":41},"z-ai/glm-5.3-flashx":{"draws":23,"losses":35,"wins":38}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":6,"wins":34},"claude-fable-5":{"draws":6,"losses":20,"wins":22},"claude-fable-5-1":{"draws":6,"losses":40,"wins":8},"claude-haiku-5-5":{"draws":10,"losses":14,"wins":22},"claude-opus-4-5":{"draws":11,"losses":20,"wins":47},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":4,"losses":57,"wins":21},"claude-opus-5-5":{"draws":4,"losses":36,"wins":12},"claude-sonnet-5":{"draws":4,"losses":12,"wins":32},"claude-sonnet-5-5":{"draws":3,"losses":22,"wins":23},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":64},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":16,"wins":25},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":21,"wins":20},"elorian/glimpse":{"draws":1,"losses":7,"wins":18},"fireworks/ember-1":{"draws":5,"losses":18,"wins":25},"gemini-3.1-pro-preview":{"draws":4,"losses":11,"wins":33},"gemini-4-argon":{"draws":2,"losses":31,"wins":15},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":44},"google/gemini-3.5-flash-lite":{"draws":6,"losses":8,"wins":70},"google/gemini-3.6-flash":{"draws":9,"losses":28,"wins":55},"google/gemini-3.8-flash":{"draws":4,"losses":12,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":21},"gpt-4.1":{"draws":2,"losses":4,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":3,"losses":9,"wins":30},"gpt-5.4":{"draws":3,"losses":19,"wins":24},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":6,"losses":18,"wins":20},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":33},"gpt-5.6-sol":{"draws":4,"losses":20,"wins":24},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":24},"gpt-6-astra":{"draws":5,"losses":40,"wins":3},"gpt-6-luna":{"draws":11,"losses":7,"wins":30},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":33,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":26},"inception/mercury-3":{"draws":5,"losses":8,"wins":19},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":3,"losses":7,"wins":42},"meta/muse-glimmer-30b":{"draws":4,"losses":7,"wins":31},"meta/muse-spark-1.2":{"draws":3,"losses":16,"wins":27},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":1,"losses":16,"wins":29},"meta/muse-wonder":{"draws":12,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":26},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":12},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":9,"wins":12},"o3":{"draws":4,"losses":10,"wins":52},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":38},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":38},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":14,"wins":31},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":23},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":19},"qwen/qwen3.8-max":{"draws":7,"losses":20,"wins":21},"qwen/qwen3.8-max-0902":{"draws":9,"losses":15,"wins":24},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":8,"wins":31},"stealth/ox-alpha":{"draws":22,"losses":42,"wins":94},"stealth/space-bunny-alpha":{"draws":2,"losses":8,"wins":28},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":28},"stepfun/step-5-preview":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":3,"wins":16},"tencent/hy4-preview":{"draws":5,"losses":20,"wins":21},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":10,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"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":4,"losses":22,"wins":22},"x-ai/grok-4.6":{"draws":4,"losses":16,"wins":28},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":7,"losses":15,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":5,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":17,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":18,"wins":67},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":15,"wins":27},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":27}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":11,"wins":17},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":33,"losses":18,"wins":27},"claude-opus-4-8":{"draws":12,"losses":17,"wins":15},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":15,"losses":14,"wins":19},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":21,"losses":7,"wins":44},"deepseek/deepseek-v4-pro":{"draws":15,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":12},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":12,"losses":19,"wins":17},"gemini-3.1-pro-preview":{"draws":12,"losses":24,"wins":12},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":16,"losses":22,"wins":22},"google/gemini-3.5-flash-lite":{"draws":28,"losses":19,"wins":37},"google/gemini-3.6-flash":{"draws":27,"losses":40,"wins":25},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":1,"wins":14},"gpt-4.1":{"draws":5,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":5,"wins":13},"gpt-5.4":{"draws":7,"losses":20,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":9,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":9,"wins":31},"gpt-5.5":{"draws":19,"losses":15,"wins":10},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":17},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":17,"losses":14,"wins":17},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"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":13,"losses":2,"wins":19},"inception/mercury-3":{"draws":11,"losses":8,"wins":13},"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":12,"losses":14,"wins":26},"meta/muse-glimmer-30b":{"draws":17,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":19,"wins":14},"meta/muse-spark-open":{"draws":16,"losses":18,"wins":12},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":17,"losses":13,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":42,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":3,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":7},"o3":{"draws":9,"losses":24,"wins":33},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":16,"wins":15},"qwen/qwen3.8-27b":{"draws":8,"losses":12,"wins":14},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":23,"losses":13,"wins":12},"qwen/qwen3.8-max-0902":{"draws":11,"losses":23,"wins":14},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":15,"wins":15},"stealth/ox-alpha":{"draws":38,"losses":69,"wins":51},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"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":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":16,"losses":16,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":12,"losses":23,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":24,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":24,"losses":14,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":35,"losses":23,"wins":38},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":13,"losses":17,"wins":18}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":27},"claude-fable-5":{"draws":11,"losses":13,"wins":18},"claude-fable-5-1":{"draws":2,"losses":38,"wins":8},"claude-haiku-5-5":{"draws":6,"losses":11,"wins":23},"claude-opus-4-5":{"draws":11,"losses":8,"wins":49},"claude-opus-4-8":{"draws":4,"losses":9,"wins":25},"claude-opus-5":{"draws":8,"losses":46,"wins":16},"claude-opus-5-5":{"draws":3,"losses":36,"wins":7},"claude-sonnet-5":{"draws":6,"losses":5,"wins":31},"claude-sonnet-5-5":{"draws":9,"losses":13,"wins":20},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":51},"deepseek/deepseek-v4-pro":{"draws":9,"losses":7,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":8,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":11,"wins":25},"elorian/glimpse":{"draws":3,"losses":6,"wins":15},"fireworks/ember-1":{"draws":3,"losses":8,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":9,"wins":31},"gemini-4-argon":{"draws":3,"losses":27,"wins":12},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":6,"wins":59},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":53},"google/gemini-3.8-flash":{"draws":2,"losses":13,"wins":27},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":19},"gpt-4.1":{"draws":2,"losses":0,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":4,"wins":32},"gpt-5.4":{"draws":5,"losses":2,"wins":21},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":21},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":36},"gpt-5.5":{"draws":8,"losses":10,"wins":22},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":33},"gpt-5.6-sol":{"draws":7,"losses":14,"wins":21},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":32},"gpt-6-astra":{"draws":2,"losses":34,"wins":6},"gpt-6-luna":{"draws":8,"losses":9,"wins":25},"gpt-6-sol":{"draws":2,"losses":29,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":1,"losses":4,"wins":21},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":39},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":33},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":7,"wins":27},"meta/muse-spark-open":{"draws":8,"losses":9,"wins":25},"meta/muse-wonder":{"draws":5,"losses":17,"wins":20},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":4,"losses":5,"wins":29},"mistralai/mistral-large-4-0":{"draws":4,"losses":3,"wins":19},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":27,"wins":13},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":15},"o3":{"draws":2,"losses":7,"wins":55},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":34},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":10,"wins":26},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":3,"wins":21},"qwen/qwen3.8-max":{"draws":6,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":5,"losses":10,"wins":27},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":7,"wins":23},"stealth/ox-alpha":{"draws":32,"losses":27,"wins":83},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":28},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":28},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":30},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":33},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":2},"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":9,"losses":8,"wins":25},"x-ai/grok-4.6":{"draws":8,"losses":9,"wins":25},"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":9,"losses":2,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":18,"losses":11,"wins":55},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":19},"z-ai/glm-5.3-flash":{"draws":3,"losses":10,"wins":29},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":24}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":26},"claude-fable-5":{"draws":7,"losses":18,"wins":17},"claude-fable-5-1":{"draws":1,"losses":36,"wins":11},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":22},"claude-opus-4-5":{"draws":15,"losses":9,"wins":44},"claude-opus-4-8":{"draws":7,"losses":6,"wins":25},"claude-opus-5":{"draws":4,"losses":36,"wins":30},"claude-opus-5-5":{"draws":1,"losses":36,"wins":9},"claude-sonnet-5":{"draws":7,"losses":8,"wins":27},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":51},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":7,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":10,"wins":22},"elorian/glimpse":{"draws":6,"losses":5,"wins":13},"fireworks/ember-1":{"draws":8,"losses":8,"wins":26},"gemini-3.1-pro-preview":{"draws":6,"losses":7,"wins":29},"gemini-4-argon":{"draws":3,"losses":21,"wins":18},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":37},"google/gemini-3.5-flash-lite":{"draws":16,"losses":6,"wins":54},"google/gemini-3.6-flash":{"draws":17,"losses":14,"wins":51},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":22},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":17},"gpt-4.1":{"draws":1,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":8,"losses":5,"wins":25},"gpt-5.4":{"draws":11,"losses":12,"wins":19},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":19},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":36},"gpt-5.5":{"draws":8,"losses":6,"wins":12},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":26},"gpt-5.6-sol":{"draws":6,"losses":15,"wins":21},"gpt-5.6-terra":{"draws":7,"losses":6,"wins":27},"gpt-6-astra":{"draws":1,"losses":37,"wins":4},"gpt-6-luna":{"draws":11,"losses":5,"wins":26},"gpt-6-sol":{"draws":3,"losses":23,"wins":16},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":19},"inception/mercury-3":{"draws":4,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":6,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":30},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":24},"meta/muse-spark-open":{"draws":3,"losses":10,"wins":29},"meta/muse-wonder":{"draws":8,"losses":14,"wins":20},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":10,"losses":8,"wins":20},"mistralai/mistral-large-4-0":{"draws":4,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":24,"wins":16},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":15},"o3":{"draws":6,"losses":6,"wins":52},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":19},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":10,"losses":10,"wins":22},"qwen/qwen3.8-max-0902":{"draws":8,"losses":10,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":7,"wins":25},"stealth/ox-alpha":{"draws":28,"losses":33,"wins":81},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":22},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":11,"wins":23},"thinkingmachines/inkling":{"draws":9,"losses":5,"wins":44},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":2},"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":12,"losses":7,"wins":23},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":21},"x-ai/grok-4.7":{"draws":3,"losses":17,"wins":16},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":20,"losses":1,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":9,"wins":13},"z-ai/glm-5.2":{"draws":21,"losses":7,"wins":56},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":10},"z-ai/glm-5.3-flash":{"draws":3,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":24}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":9,"wins":21},"claude-fable-5":{"draws":7,"losses":29,"wins":12},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":26,"losses":19,"wins":33},"claude-opus-4-8":{"draws":12,"losses":10,"wins":22},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":7,"losses":41,"wins":4},"claude-sonnet-5":{"draws":9,"losses":15,"wins":24},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":8,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":7,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":23,"wins":16},"elorian/glimpse":{"draws":8,"losses":8,"wins":10},"fireworks/ember-1":{"draws":14,"losses":9,"wins":25},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":19,"losses":10,"wins":31},"google/gemini-3.5-flash-lite":{"draws":23,"losses":12,"wins":49},"google/gemini-3.6-flash":{"draws":21,"losses":34,"wins":37},"google/gemini-3.8-flash":{"draws":13,"losses":17,"wins":18},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":14},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":9,"wins":21},"gpt-5.4":{"draws":18,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":6,"losses":11,"wins":31},"gpt-5.5":{"draws":15,"losses":16,"wins":13},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":10,"losses":23,"wins":15},"gpt-5.6-terra":{"draws":13,"losses":8,"wins":25},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":12,"losses":17,"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":12,"losses":4,"wins":18},"inception/mercury-3":{"draws":9,"losses":10,"wins":13},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":35},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":17},"meta/muse-spark-1.3":{"draws":12,"losses":20,"wins":16},"meta/muse-spark-open":{"draws":14,"losses":14,"wins":18},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":10,"losses":10,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":13,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":1,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":9},"o3":{"draws":17,"losses":15,"wins":34},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":17,"losses":5,"wins":24},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":11,"wins":20},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":15,"losses":12,"wins":21},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":12,"wins":18},"stealth/ox-alpha":{"draws":42,"losses":57,"wins":59},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":17},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":39},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":9,"losses":13,"wins":26},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":28,"wins":9},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":7,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":10,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":27,"wins":38},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":10},"z-ai/glm-5.3-flash":{"draws":13,"losses":21,"wins":14},"z-ai/glm-5.3-flashx":{"draws":8,"losses":20,"wins":20}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":38},"claude-fable-5":{"draws":2,"losses":14,"wins":32},"claude-fable-5-1":{"draws":6,"losses":35,"wins":13},"claude-haiku-5-5":{"draws":7,"losses":5,"wins":34},"claude-opus-4-5":{"draws":6,"losses":12,"wins":60},"claude-opus-4-8":{"draws":6,"losses":4,"wins":34},"claude-opus-5":{"draws":6,"losses":37,"wins":39},"claude-opus-5-5":{"draws":5,"losses":33,"wins":14},"claude-sonnet-5":{"draws":0,"losses":2,"wins":46},"claude-sonnet-5-5":{"draws":2,"losses":13,"wins":33},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":67},"deepseek/deepseek-v4-pro":{"draws":1,"losses":5,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":3,"wins":40},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":8,"wins":33},"elorian/glimpse":{"draws":2,"losses":6,"wins":18},"fireworks/ember-1":{"draws":5,"losses":6,"wins":37},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":42},"gemini-4-argon":{"draws":1,"losses":30,"wins":17},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":51},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":78},"google/gemini-3.6-flash":{"draws":7,"losses":15,"wins":70},"google/gemini-3.8-flash":{"draws":4,"losses":10,"wins":34},"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":2,"losses":12,"wins":32},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":27},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":44},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":39},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":26},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":40},"gpt-6-astra":{"draws":5,"losses":32,"wins":11},"gpt-6-luna":{"draws":9,"losses":1,"wins":38},"gpt-6-sol":{"draws":6,"losses":17,"wins":25},"gpt-6.1-sol":{"draws":5,"losses":29,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":46},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":39},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":42},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":36},"meta/muse-wonder":{"draws":2,"losses":16,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":3,"wins":38},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":8},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":25,"wins":20},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"o3":{"draws":1,"losses":7,"wins":58},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":37},"poolside/laguna-s-2.1":{"draws":1,"losses":1,"wins":44},"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":3,"losses":6,"wins":39},"qwen/qwen3.8-27b":{"draws":3,"losses":4,"wins":27},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":25},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-max-0902":{"draws":2,"losses":7,"wins":39},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":7,"wins":31},"stealth/ox-alpha":{"draws":14,"losses":17,"wins":127},"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":3,"losses":14,"wins":29},"thinkingmachines/inkling":{"draws":2,"losses":4,"wins":58},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":46},"unbiased/pareto-26.10":{"draws":3,"losses":11,"wins":2},"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":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":6,"losses":14,"wins":28},"x-ai/grok-4.7":{"draws":5,"losses":17,"wins":20},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":87},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":27},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":33}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":28},"claude-fable-5":{"draws":12,"losses":25,"wins":11},"claude-fable-5-1":{"draws":1,"losses":50,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":24,"losses":26,"wins":28},"claude-opus-4-8":{"draws":5,"losses":19,"wins":20},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":12,"wins":19},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":10,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":13,"losses":15,"wins":20},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":21},"gemini-4-argon":{"draws":3,"losses":40,"wins":5},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":15,"wins":30},"google/gemini-3.5-flash-lite":{"draws":19,"losses":11,"wins":54},"google/gemini-3.6-flash":{"draws":25,"losses":37,"wins":30},"google/gemini-3.8-flash":{"draws":9,"losses":21,"wins":18},"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":10,"losses":11,"wins":21},"gpt-5.4":{"draws":12,"losses":21,"wins":13},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":5,"losses":8,"wins":35},"gpt-5.5":{"draws":10,"losses":21,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":10,"wins":11},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"gpt-6-sol":{"draws":10,"losses":29,"wins":9},"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":11,"losses":4,"wins":19},"inception/mercury-3":{"draws":7,"losses":10,"wins":15},"inclusionai/ling-3.0-flash":{"draws":10,"losses":0,"wins":24},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":9,"wins":30},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":15},"meta/muse-spark-open":{"draws":14,"losses":19,"wins":13},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":19},"minimax/minimax-m3.1-flash":{"draws":9,"losses":11,"wins":22},"mistralai/mistral-large-4-0":{"draws":15,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":16,"losses":11,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":38,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":4,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":3,"wins":10},"o3":{"draws":10,"losses":19,"wins":37},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":28},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":19},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":22,"wins":15},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":18},"qwen/qwen3.8-max":{"draws":14,"losses":19,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":21},"stealth/ox-alpha":{"draws":34,"losses":65,"wins":59},"stealth/space-bunny-alpha":{"draws":11,"losses":7,"wins":20},"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":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":8,"losses":18,"wins":20},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":39},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":13,"losses":20,"wins":15},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":23,"losses":2,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":11},"z-ai/glm-5.2":{"draws":30,"losses":22,"wins":44},"z-ai/glm-5.3":{"draws":9,"losses":24,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":20},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":17}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":43},"claude-fable-5":{"draws":1,"losses":7,"wins":40},"claude-fable-5-1":{"draws":6,"losses":16,"wins":32},"claude-haiku-5-5":{"draws":1,"losses":2,"wins":43},"claude-opus-4-5":{"draws":0,"losses":2,"wins":76},"claude-opus-4-8":{"draws":3,"losses":1,"wins":40},"claude-opus-5":{"draws":3,"losses":11,"wins":68},"claude-opus-5-5":{"draws":4,"losses":16,"wins":32},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":1,"losses":10,"wins":37},"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":3,"losses":2,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":46},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":1,"wins":45},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":0,"losses":0,"wins":48},"gemini-3.1-pro-preview":{"draws":0,"losses":0,"wins":48},"gemini-4-argon":{"draws":6,"losses":9,"wins":33},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":1,"wins":59},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":83},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":83},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":44},"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":5,"wins":41},"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":3,"wins":41},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":47},"gpt-5.6-sol":{"draws":3,"losses":5,"wins":40},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":46},"gpt-6-astra":{"draws":2,"losses":5,"wins":25},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":7,"losses":6,"wins":35},"gpt-6.1-sol":{"draws":6,"losses":9,"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},"inception/mercury-3":{"draws":1,"losses":1,"wins":30},"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":0,"wins":45},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":45},"meta/muse-spark-open":{"draws":2,"losses":0,"wins":44},"meta/muse-wonder":{"draws":3,"losses":3,"wins":42},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":42},"mistralai/mistral-large-4-0":{"draws":2,"losses":1,"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":0,"losses":0,"wins":46},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":7,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"o3":{"draws":1,"losses":0,"wins":65},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":42},"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":0,"losses":0,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":30},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":46},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":43},"stealth/ox-alpha":{"draws":6,"losses":3,"wins":149},"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":0,"losses":0,"wins":64},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":4,"losses":1,"wins":11},"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":3,"wins":44},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":48},"x-ai/grok-4.7":{"draws":2,"losses":1,"wins":39},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":15},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":72},"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":3,"wins":28},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":95},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":40},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":45},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":44}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":24},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":6,"losses":43,"wins":5},"claude-haiku-5-5":{"draws":4,"losses":21,"wins":21},"claude-opus-4-5":{"draws":15,"losses":26,"wins":37},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":8,"losses":59,"wins":15},"claude-opus-5-5":{"draws":6,"losses":43,"wins":3},"claude-sonnet-5":{"draws":8,"losses":16,"wins":24},"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":9,"losses":13,"wins":50},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":13,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":19,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":23,"wins":14},"elorian/glimpse":{"draws":3,"losses":14,"wins":9},"fireworks/ember-1":{"draws":6,"losses":21,"wins":21},"gemini-3.1-pro-preview":{"draws":4,"losses":20,"wins":24},"gemini-4-argon":{"draws":6,"losses":36,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":9,"losses":20,"wins":31},"google/gemini-3.5-flash-lite":{"draws":9,"losses":20,"wins":55},"google/gemini-3.6-flash":{"draws":12,"losses":34,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":20},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":19},"gpt-4.1":{"draws":1,"losses":6,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":14,"wins":24},"gpt-5.4":{"draws":11,"losses":15,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":4,"losses":12,"wins":32},"gpt-5.5":{"draws":5,"losses":20,"wins":19},"gpt-5.6-luna":{"draws":9,"losses":11,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":8,"losses":14,"wins":24},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":5,"losses":13,"wins":14},"gpt-6-sol":{"draws":5,"losses":35,"wins":8},"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},"inception/mercury-3":{"draws":6,"losses":8,"wins":18},"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":9,"wins":38},"meta/muse-glimmer-30b":{"draws":4,"losses":8,"wins":30},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":19},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":20},"meta/muse-wonder":{"draws":7,"losses":26,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"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":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":16,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":8,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"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":1,"losses":8,"wins":19},"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":7,"losses":19,"wins":22},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":23},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":14,"wins":26},"stealth/ox-alpha":{"draws":25,"losses":58,"wins":75},"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":7,"losses":17,"wins":22},"thinkingmachines/inkling":{"draws":8,"losses":12,"wins":44},"thinkingmachines/inkling-small":{"draws":4,"losses":10,"wins":34},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":7,"losses":21,"wins":20},"x-ai/grok-4.6":{"draws":9,"losses":27,"wins":12},"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":13,"losses":12,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":7,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":9},"z-ai/glm-5.2":{"draws":20,"losses":26,"wins":50},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":36},"claude-fable-5":{"draws":3,"losses":11,"wins":34},"claude-fable-5-1":{"draws":3,"losses":24,"wins":27},"claude-haiku-5-5":{"draws":5,"losses":7,"wins":34},"claude-opus-4-5":{"draws":3,"losses":11,"wins":64},"claude-opus-4-8":{"draws":2,"losses":10,"wins":32},"claude-opus-5":{"draws":14,"losses":25,"wins":43},"claude-opus-5-5":{"draws":6,"losses":26,"wins":20},"claude-sonnet-5":{"draws":1,"losses":6,"wins":41},"claude-sonnet-5-5":{"draws":4,"losses":11,"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":4,"losses":6,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":8,"wins":37},"elorian/glimpse":{"draws":1,"losses":5,"wins":20},"fireworks/ember-1":{"draws":3,"losses":6,"wins":39},"gemini-3.1-pro-preview":{"draws":4,"losses":8,"wins":36},"gemini-4-argon":{"draws":3,"losses":20,"wins":25},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":28},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":45},"google/gemini-3.5-flash-lite":{"draws":4,"losses":10,"wins":70},"google/gemini-3.6-flash":{"draws":4,"losses":19,"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":1,"losses":6,"wins":39},"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":8,"wins":37},"gpt-5.6-terra":{"draws":3,"losses":6,"wins":37},"gpt-6-astra":{"draws":5,"losses":32,"wins":11},"gpt-6-luna":{"draws":5,"losses":4,"wins":39},"gpt-6-sol":{"draws":3,"losses":9,"wins":20},"gpt-6.1-sol":{"draws":3,"losses":23,"wins":22},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":31},"inception/mercury-3":{"draws":2,"losses":5,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":25},"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-spark-open":{"draws":2,"losses":7,"wins":37},"meta/muse-wonder":{"draws":2,"losses":8,"wins":38},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":21},"minimax/minimax-m3.1-flash":{"draws":1,"losses":4,"wins":37},"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":7,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":18,"wins":23},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":5,"wins":36},"stealth/ox-alpha":{"draws":13,"losses":20,"wins":125},"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":6,"wins":36},"thinkingmachines/inkling":{"draws":4,"losses":5,"wins":55},"thinkingmachines/inkling-small":{"draws":1,"losses":2,"wins":45},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"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":10,"wins":37},"x-ai/grok-4.6":{"draws":2,"losses":6,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":12,"wins":25},"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":2,"losses":3,"wins":25},"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":5,"losses":7,"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":5,"losses":17,"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":7,"losses":14,"wins":61},"claude-opus-5-5":{"draws":4,"losses":22,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"claude-sonnet-5-5":{"draws":1,"losses":9,"wins":38},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":5,"wins":43},"elorian/glimpse":{"draws":0,"losses":3,"wins":23},"fireworks/ember-1":{"draws":0,"losses":3,"wins":45},"gemini-3.1-pro-preview":{"draws":0,"losses":1,"wins":47},"gemini-4-argon":{"draws":2,"losses":11,"wins":35},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":57},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":84},"google/gemini-3.6-flash":{"draws":3,"losses":5,"wins":84},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":43},"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":5,"wins":38},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":48},"gpt-5.5":{"draws":0,"losses":6,"wins":38},"gpt-5.6-luna":{"draws":0,"losses":3,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":37},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":43},"gpt-6-astra":{"draws":8,"losses":14,"wins":26},"gpt-6-luna":{"draws":2,"losses":1,"wins":45},"gpt-6-sol":{"draws":2,"losses":5,"wins":41},"gpt-6.1-sol":{"draws":0,"losses":8,"wins":24},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":34},"inception/mercury-3":{"draws":0,"losses":4,"wins":28},"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":1,"losses":1,"wins":50},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":42},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":41},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":47},"meta/muse-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":4,"losses":4,"wins":40},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":42},"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":1,"losses":2,"wins":43},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":7,"wins":36},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"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":0,"losses":3,"wins":45},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":32},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":29},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":44},"stealth/ox-alpha":{"draws":2,"losses":5,"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":1,"losses":3,"wins":42},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":62},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":48},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"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":4,"wins":44},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":42},"x-ai/grok-4.7":{"draws":2,"losses":5,"wins":35},"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":1,"wins":94},"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":1,"losses":4,"wins":43}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":8},"claude-fable-5":{"draws":9,"losses":27,"wins":0},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":25,"wins":0},"claude-opus-4-5":{"draws":28,"losses":30,"wins":2},"claude-opus-4-8":{"draws":9,"losses":23,"wins":4},"claude-opus-5":{"draws":12,"losses":44,"wins":2},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":12,"losses":23,"wins":1},"claude-sonnet-5-5":{"draws":11,"losses":24,"wins":1},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":20,"losses":29,"wins":7},"deepseek/deepseek-v4-pro":{"draws":13,"losses":17,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":19,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":0},"elorian/glimpse":{"draws":4,"losses":12,"wins":4},"fireworks/ember-1":{"draws":13,"losses":20,"wins":3},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":9},"gemini-4-argon":{"draws":4,"losses":32,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":16,"losses":27,"wins":3},"google/gemini-3.5-flash-lite":{"draws":26,"losses":28,"wins":8},"google/gemini-3.6-flash":{"draws":22,"losses":42,"wins":4},"google/gemini-3.8-flash":{"draws":8,"losses":27,"wins":1},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":8},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":12,"losses":16,"wins":2},"gpt-5.4":{"draws":11,"losses":21,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":19,"wins":4},"gpt-5.5":{"draws":13,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":23,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":3},"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":8,"losses":6,"wins":2},"inception/mercury-3":{"draws":12,"losses":12,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":11,"wins":6},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":7},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":6},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":2},"meta/muse-spark-1.3":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":0},"meta/muse-wonder":{"draws":8,"losses":28,"wins":0},"minimax/minimax-m3":{"draws":10,"losses":7,"wins":3},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":7,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":3},"o3":{"draws":9,"losses":37,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":19,"wins":2},"qwen/qwen3.8-max-0902":{"draws":15,"losses":18,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":17,"wins":1},"stealth/ox-alpha":{"draws":29,"losses":60,"wins":11},"stealth/space-bunny-alpha":{"draws":12,"losses":12,"wins":4},"stepfun/step-3.7-flash":{"draws":8,"losses":13,"wins":5},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":4},"tencent/hy4-preview":{"draws":14,"losses":18,"wins":2},"thinkingmachines/inkling":{"draws":17,"losses":20,"wins":7},"thinkingmachines/inkling-small":{"draws":14,"losses":13,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":24,"wins":0},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":27,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":36,"wins":6},"z-ai/glm-5.3":{"draws":8,"losses":24,"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}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":14},"claude-fable-5":{"draws":10,"losses":14,"wins":6},"claude-fable-5-1":{"draws":2,"losses":30,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":12},"claude-opus-4-5":{"draws":15,"losses":12,"wins":21},"claude-opus-4-8":{"draws":9,"losses":9,"wins":8},"claude-opus-5":{"draws":5,"losses":37,"wins":8},"claude-opus-5-5":{"draws":2,"losses":31,"wins":1},"claude-sonnet-5":{"draws":11,"losses":6,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":15,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":29},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":3,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":7,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":11,"wins":6},"elorian/glimpse":{"draws":2,"losses":7,"wins":7},"fireworks/ember-1":{"draws":13,"losses":7,"wins":10},"gemini-3.1-pro-preview":{"draws":9,"losses":4,"wins":17},"gemini-4-argon":{"draws":5,"losses":24,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":10,"losses":7,"wins":19},"google/gemini-3.5-flash-lite":{"draws":16,"losses":4,"wins":30},"google/gemini-3.6-flash":{"draws":12,"losses":24,"wins":20},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":12},"google/gemma-4-31b-it":{"draws":7,"losses":0,"wins":9},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":4,"wins":17},"gpt-5.4":{"draws":7,"losses":12,"wins":9},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":15},"gpt-5.5":{"draws":10,"losses":8,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":4,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":16,"wins":8},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":14},"gpt-6-astra":{"draws":4,"losses":24,"wins":2},"gpt-6-luna":{"draws":9,"losses":6,"wins":15},"gpt-6-sol":{"draws":6,"losses":17,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":20,"wins":6},"inception/mercury-2.5-preview":{"draws":10,"losses":0,"wins":10},"inception/mercury-3":{"draws":6,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":22},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":14},"meta/muse-spark-1.2":{"draws":9,"losses":10,"wins":9},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":8},"meta/muse-spark-open":{"draws":8,"losses":12,"wins":8},"meta/muse-wonder":{"draws":7,"losses":11,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":9},"minimax/minimax-m3.1-flash":{"draws":7,"losses":5,"wins":12},"mistralai/mistral-large-4-0":{"draws":6,"losses":0,"wins":12},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":8},"o3":{"draws":5,"losses":3,"wins":30},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":13},"poolside/laguna-s-2.1":{"draws":15,"losses":1,"wins":16},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.8-max":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":4,"wins":12},"stealth/ox-alpha":{"draws":28,"losses":34,"wins":42},"stealth/space-bunny-alpha":{"draws":8,"losses":2,"wins":10},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":9,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":2,"wins":19},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":9,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":10},"x-ai/grok-4.6":{"draws":13,"losses":9,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":18,"wins":5},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":2,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":12,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":7,"wins":31},"z-ai/glm-5.3":{"draws":6,"losses":13,"wins":9},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":14},"z-ai/glm-5.3-flashx":{"draws":8,"losses":10,"wins":12}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":17},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":17,"wins":8},"claude-opus-4-5":{"draws":27,"losses":28,"wins":13},"claude-opus-4-8":{"draws":10,"losses":19,"wins":9},"claude-opus-5":{"draws":10,"losses":64,"wins":6},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":14,"losses":19,"wins":9},"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":25,"losses":16,"wins":21},"deepseek/deepseek-v4-pro":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":14,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":28,"wins":4},"elorian/glimpse":{"draws":5,"losses":12,"wins":7},"fireworks/ember-1":{"draws":13,"losses":18,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":13},"gemini-4-argon":{"draws":5,"losses":36,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":13},"google/gemini-3.5-flash-lite":{"draws":24,"losses":21,"wins":27},"google/gemini-3.6-flash":{"draws":29,"losses":30,"wins":21},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":6},"google/gemma-4-31b-it":{"draws":15,"losses":4,"wins":5},"gpt-4.1":{"draws":7,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":16,"losses":14,"wins":8},"gpt-5.4":{"draws":11,"losses":22,"wins":7},"gpt-5.4-mini":{"draws":17,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":16,"losses":9,"wins":15},"gpt-5.5":{"draws":21,"losses":16,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":14,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":19,"losses":14,"wins":7},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":15,"losses":18,"wins":9},"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":14,"losses":4,"wins":10},"inception/mercury-3":{"draws":9,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":3},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":19,"losses":9,"wins":16},"meta/muse-glimmer-30b":{"draws":15,"losses":2,"wins":9},"meta/muse-spark-1.2":{"draws":14,"losses":21,"wins":7},"meta/muse-spark-1.3":{"draws":14,"losses":20,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":20,"wins":11},"meta/muse-wonder":{"draws":12,"losses":25,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":8},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":5,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":11,"wins":4},"o3":{"draws":11,"losses":27,"wins":16},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":13},"poolside/laguna-s-2.1":{"draws":19,"losses":12,"wins":11},"qwen/qwen3.7-max":{"draws":11,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":14,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":11},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":6},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":35,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":15,"losses":20,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":23},"thinkingmachines/inkling-small":{"draws":18,"losses":4,"wins":20},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"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":13,"losses":23,"wins":6},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":29,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":24,"losses":13,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":6},"z-ai/glm-5.2":{"draws":39,"losses":30,"wins":15},"z-ai/glm-5.3":{"draws":11,"losses":25,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":7},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"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":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":18,"losses":18,"wins":42},"claude-opus-4-8":{"draws":5,"losses":15,"wins":24},"claude-opus-5":{"draws":14,"losses":59,"wins":9},"claude-opus-5-5":{"draws":4,"losses":42,"wins":6},"claude-sonnet-5":{"draws":11,"losses":7,"wins":30},"claude-sonnet-5-5":{"draws":8,"losses":19,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":9,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":9,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":15,"wins":21},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":19,"wins":20},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":10,"losses":15,"wins":23},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":23},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":7,"losses":18,"wins":35},"google/gemini-3.5-flash-lite":{"draws":15,"losses":18,"wins":51},"google/gemini-3.6-flash":{"draws":19,"losses":27,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":18,"wins":23},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":17},"gpt-4.1":{"draws":8,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":7,"losses":5,"wins":30},"gpt-5.4":{"draws":8,"losses":21,"wins":17},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":6,"losses":15,"wins":27},"gpt-5.5":{"draws":8,"losses":20,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":8,"losses":26,"wins":14},"gpt-5.6-terra":{"draws":12,"losses":10,"wins":24},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":11,"losses":12,"wins":25},"gpt-6-sol":{"draws":7,"losses":31,"wins":10},"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":9,"losses":7,"wins":18},"inception/mercury-3":{"draws":7,"losses":4,"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":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":6,"losses":20,"wins":20},"meta/muse-wonder":{"draws":9,"losses":19,"wins":20},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":18},"minimax/minimax-m3.1-flash":{"draws":7,"losses":12,"wins":23},"mistralai/mistral-large-4-0":{"draws":5,"losses":7,"wins":18},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":37,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":9,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":14},"o3":{"draws":5,"losses":22,"wins":39},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":27},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":18},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":20},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":8,"losses":17,"wins":23},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":26,"losses":58,"wins":74},"stealth/space-bunny-alpha":{"draws":8,"losses":10,"wins":20},"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":7,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":17,"wins":23},"thinkingmachines/inkling":{"draws":12,"losses":12,"wins":40},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":2,"losses":29,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":6,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":10,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.2":{"draws":21,"losses":24,"wins":51},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":21},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":11,"losses":18,"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":1,"losses":0,"wins":17},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":18,"wins":24},"elorian/glimpse":{"draws":3,"losses":6,"wins":17},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":6,"losses":11,"wins":31},"gemini-4-argon":{"draws":2,"losses":35,"wins":11},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":12,"wins":40},"google/gemini-3.5-flash-lite":{"draws":11,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":11,"losses":22,"wins":59},"google/gemini-3.8-flash":{"draws":11,"losses":14,"wins":23},"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},"inception/mercury-3":{"draws":4,"losses":4,"wins":24},"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":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":5,"losses":3,"wins":24},"meta/muse-spark-open":{"draws":5,"losses":9,"wins":32},"meta/muse-wonder":{"draws":8,"losses":21,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":5,"losses":6,"wins":31},"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},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":3,"wins":17},"o3":{"draws":3,"losses":8,"wins":55},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":8,"wins":31},"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":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":13,"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":9,"losses":4,"wins":61},"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":7,"losses":16,"wins":25},"z-ai/glm-5.3-flashx":{"draws":5,"losses":14,"wins":29}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":25},"claude-fable-5":{"draws":2,"losses":26,"wins":14},"claude-fable-5-1":{"draws":1,"losses":38,"wins":9},"claude-haiku-5-5":{"draws":2,"losses":20,"wins":18},"claude-opus-4-5":{"draws":9,"losses":16,"wins":43},"claude-opus-4-8":{"draws":4,"losses":15,"wins":19},"claude-opus-5":{"draws":2,"losses":53,"wins":15},"claude-opus-5-5":{"draws":3,"losses":33,"wins":10},"claude-sonnet-5":{"draws":4,"losses":10,"wins":28},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":5,"losses":8,"wins":49},"deepseek/deepseek-v4-pro":{"draws":6,"losses":7,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":18,"wins":18},"elorian/glimpse":{"draws":2,"losses":12,"wins":10},"fireworks/ember-1":{"draws":3,"losses":15,"wins":24},"gemini-3.1-pro-preview":{"draws":3,"losses":11,"wins":28},"gemini-4-argon":{"draws":3,"losses":30,"wins":9},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":7,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":5,"losses":14,"wins":57},"google/gemini-3.6-flash":{"draws":6,"losses":30,"wins":46},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":24},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":18},"gpt-4.1":{"draws":1,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":4,"losses":8,"wins":26},"gpt-5.4":{"draws":6,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":33},"gpt-5.5":{"draws":3,"losses":13,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":10,"wins":26},"gpt-5.6-sol":{"draws":4,"losses":18,"wins":20},"gpt-5.6-terra":{"draws":8,"losses":6,"wins":26},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":6,"losses":13,"wins":23},"gpt-6-sol":{"draws":3,"losses":30,"wins":9},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":21},"inception/mercury-3":{"draws":1,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":1,"losses":4,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":33},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":24},"meta/muse-spark-1.3":{"draws":3,"losses":15,"wins":24},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":14},"meta/muse-wonder":{"draws":6,"losses":18,"wins":18},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":20},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":2,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":16,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":32,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":2,"wins":15},"o3":{"draws":3,"losses":10,"wins":51},"openai/gpt-oss-120b":{"draws":4,"losses":4,"wins":28},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":34},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":16,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":19},"qwen/qwen3.8-flash":{"draws":4,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":5,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":21},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":9,"wins":23},"stealth/ox-alpha":{"draws":17,"losses":39,"wins":86},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":23},"stepfun/step-3.7-flash":{"draws":1,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":17},"tencent/hy4-preview":{"draws":4,"losses":15,"wins":23},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":41},"thinkingmachines/inkling-small":{"draws":4,"losses":6,"wins":32},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":12,"wins":2},"upstage/solar-mini4":{"draws":0,"losses":5,"wins":7},"x-ai/grok-4.5":{"draws":3,"losses":19,"wins":20},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":16},"x-ai/grok-4.7":{"draws":3,"losses":22,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":6,"losses":11,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":9,"losses":21,"wins":54},"z-ai/glm-5.3":{"draws":1,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":3,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":5,"losses":16,"wins":21}},"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":7,"losses":6,"wins":33},"claude-opus-4-5":{"draws":9,"losses":9,"wins":60},"claude-opus-4-8":{"draws":9,"losses":8,"wins":27},"claude-opus-5":{"draws":9,"losses":35,"wins":38},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":11,"wins":24},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":12,"losses":5,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":8,"wins":32},"gemini-4-argon":{"draws":6,"losses":23,"wins":19},"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},"inception/mercury-3":{"draws":8,"losses":1,"wins":23},"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":5,"wins":40},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":1,"losses":11,"wins":34},"meta/muse-spark-1.3":{"draws":6,"losses":6,"wins":36},"meta/muse-spark-open":{"draws":6,"losses":9,"wins":31},"meta/muse-wonder":{"draws":6,"losses":7,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":21},"minimax/minimax-m3.1-flash":{"draws":4,"losses":1,"wins":37},"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},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":21},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"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},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":4,"wins":35},"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":{"draws":4,"losses":10,"wins":2},"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":14,"losses":6,"wins":76},"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}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":10,"wins":20},"claude-fable-5":{"draws":9,"losses":24,"wins":9},"claude-fable-5-1":{"draws":2,"losses":44,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":7},"claude-opus-4-5":{"draws":20,"losses":24,"wins":24},"claude-opus-4-8":{"draws":12,"losses":15,"wins":11},"claude-opus-5":{"draws":17,"losses":45,"wins":8},"claude-opus-5-5":{"draws":2,"losses":40,"wins":0},"claude-sonnet-5":{"draws":12,"losses":16,"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":15,"losses":18,"wins":29},"deepseek/deepseek-v4-pro":{"draws":11,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":24,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":19,"wins":9},"elorian/glimpse":{"draws":7,"losses":10,"wins":5},"fireworks/ember-1":{"draws":9,"losses":20,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":15,"wins":15},"gemini-4-argon":{"draws":6,"losses":31,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":18},"google/gemini-3.5-flash":{"draws":11,"losses":20,"wins":21},"google/gemini-3.5-flash-lite":{"draws":20,"losses":24,"wins":30},"google/gemini-3.6-flash":{"draws":20,"losses":40,"wins":22},"google/gemini-3.8-flash":{"draws":9,"losses":25,"wins":8},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":4,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":7,"losses":20,"wins":13},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":7,"losses":18,"wins":15},"gpt-5.5":{"draws":15,"losses":10,"wins":13},"gpt-5.6-luna":{"draws":8,"losses":17,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":27,"wins":11},"gpt-5.6-terra":{"draws":9,"losses":15,"wins":16},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":10,"losses":15,"wins":17},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":14},"inception/mercury-3":{"draws":6,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":16},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":16},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":9},"meta/muse-spark-open":{"draws":5,"losses":21,"wins":14},"meta/muse-wonder":{"draws":9,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":6,"losses":12,"wins":8},"mistralai/mistral-large-4-0":{"draws":7,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":34,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":11,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":8},"o3":{"draws":8,"losses":23,"wins":25},"openai/gpt-oss-120b":{"draws":9,"losses":9,"wins":18},"poolside/laguna-s-2.1":{"draws":8,"losses":13,"wins":17},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":13},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":14,"losses":19,"wins":9},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":16},"stealth/ox-alpha":{"draws":28,"losses":73,"wins":41},"stealth/space-bunny-alpha":{"draws":9,"losses":10,"wins":15},"stepfun/step-3.7-flash":{"draws":4,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":16,"wins":13},"thinkingmachines/inkling":{"draws":15,"losses":15,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":10,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":10,"losses":22,"wins":10},"x-ai/grok-4.6":{"draws":8,"losses":23,"wins":11},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":17,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":18,"wins":5},"z-ai/glm-5.2":{"draws":23,"losses":24,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":8,"losses":26,"wins":8}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":10,"wins":23},"claude-fable-5":{"draws":12,"losses":24,"wins":12},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"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":12,"losses":56,"wins":14},"claude-opus-5-5":{"draws":9,"losses":39,"wins":4},"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":17,"losses":8,"wins":47},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":22,"wins":19},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":10,"losses":14,"wins":24},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":24},"gemini-4-argon":{"draws":7,"losses":33,"wins":8},"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":15,"losses":14,"wins":55},"google/gemini-3.6-flash":{"draws":14,"losses":30,"wins":48},"google/gemini-3.8-flash":{"draws":15,"losses":15,"wins":18},"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":12,"losses":5,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":30},"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},"inception/mercury-3":{"draws":6,"losses":14,"wins":12},"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":6,"losses":21,"wins":19},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":17},"meta/muse-spark-open":{"draws":7,"losses":25,"wins":14},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":6,"losses":10,"wins":26},"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":14,"losses":15,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":36,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":9,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"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},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":20},"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":{"draws":2,"losses":13,"wins":1},"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":15,"losses":12,"wins":11},"claude-fable-5":{"draws":12,"losses":26,"wins":4},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":28,"wins":2},"claude-opus-4-5":{"draws":18,"losses":40,"wins":10},"claude-opus-4-8":{"draws":10,"losses":26,"wins":2},"claude-opus-5":{"draws":13,"losses":51,"wins":6},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":13,"losses":20,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":25,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":20,"losses":22,"wins":20},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":18,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":27,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":2},"elorian/glimpse":{"draws":5,"losses":12,"wins":5},"fireworks/ember-1":{"draws":11,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":10},"gemini-4-argon":{"draws":1,"losses":39,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":7,"wins":15},"google/gemini-3.5-flash":{"draws":13,"losses":28,"wins":11},"google/gemini-3.5-flash-lite":{"draws":25,"losses":30,"wins":19},"google/gemini-3.6-flash":{"draws":22,"losses":47,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":27,"wins":4},"google/gemma-4-31b-it":{"draws":11,"losses":10,"wins":5},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":17,"wins":9},"gpt-5.4":{"draws":14,"losses":22,"wins":4},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":13},"gpt-5.5":{"draws":12,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":23,"wins":4},"gpt-5.6-sol":{"draws":9,"losses":31,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":8},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"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":11,"losses":8,"wins":13},"inception/mercury-3":{"draws":8,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":20,"wins":13},"meta/muse-glimmer-30b":{"draws":12,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":30,"wins":3},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":6},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":11,"losses":18,"wins":7},"mistralai/mistral-large-4-0":{"draws":11,"losses":12,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":14,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":2},"o3":{"draws":14,"losses":33,"wins":9},"openai/gpt-oss-120b":{"draws":15,"losses":10,"wins":13},"poolside/laguna-s-2.1":{"draws":14,"losses":18,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":13,"wins":3},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":27,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":13,"wins":3},"qwen/qwen3.8-max":{"draws":14,"losses":22,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":24,"wins":5},"stealth/ox-alpha":{"draws":35,"losses":80,"wins":27},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"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":6,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":22,"wins":16},"thinkingmachines/inkling-small":{"draws":17,"losses":18,"wins":7},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"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":10,"losses":28,"wins":4},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":6,"wins":3},"xiaomi/mimo-v2.5":{"draws":24,"losses":22,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":32,"losses":39,"wins":13},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":5}},"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":17,"wins":13},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":21,"wins":15},"elorian/glimpse":{"draws":4,"losses":7,"wins":13},"fireworks/ember-1":{"draws":13,"losses":14,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":19},"gemini-4-argon":{"draws":3,"losses":31,"wins":8},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":17,"losses":13,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":11,"wins":34},"google/gemini-3.6-flash":{"draws":17,"losses":31,"wins":32},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":15},"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},"inception/mercury-3":{"draws":2,"losses":11,"wins":15},"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":7,"losses":16,"wins":19},"meta/muse-spark-1.3":{"draws":10,"losses":17,"wins":15},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":19},"meta/muse-wonder":{"draws":6,"losses":27,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":19},"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},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":16,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":9},"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},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":10,"wins":19},"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":9,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":14,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":1},"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":21,"wins":13},"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}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":0,"wins":41},"claude-fable-5":{"draws":2,"losses":9,"wins":37},"claude-fable-5-1":{"draws":4,"losses":30,"wins":20},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":4,"losses":4,"wins":70},"claude-opus-4-8":{"draws":2,"losses":2,"wins":40},"claude-opus-5":{"draws":8,"losses":32,"wins":42},"claude-opus-5-5":{"draws":7,"losses":27,"wins":18},"claude-sonnet-5":{"draws":4,"losses":0,"wins":44},"claude-sonnet-5-5":{"draws":5,"losses":13,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":67},"deepseek/deepseek-v4-pro":{"draws":6,"losses":3,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":1,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":5,"wins":37},"elorian/glimpse":{"draws":2,"losses":4,"wins":20},"fireworks/ember-1":{"draws":4,"losses":3,"wins":41},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"gemini-4-argon":{"draws":8,"losses":19,"wins":21},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":52},"google/gemini-3.5-flash-lite":{"draws":5,"losses":2,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":10,"wins":76},"google/gemini-3.8-flash":{"draws":5,"losses":7,"wins":36},"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":3,"losses":2,"wins":37},"gpt-5.4":{"draws":4,"losses":6,"wins":36},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":28},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":46},"gpt-5.5":{"draws":2,"losses":8,"wins":34},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":43},"gpt-5.6-sol":{"draws":7,"losses":7,"wins":34},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":38},"gpt-6-astra":{"draws":8,"losses":25,"wins":15},"gpt-6-luna":{"draws":4,"losses":1,"wins":43},"gpt-6-sol":{"draws":5,"losses":14,"wins":29},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":5,"losses":3,"wins":24},"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":3,"losses":2,"wins":47},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":35},"meta/muse-spark-1.2":{"draws":5,"losses":2,"wins":39},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":41},"meta/muse-spark-open":{"draws":2,"losses":3,"wins":41},"meta/muse-wonder":{"draws":9,"losses":11,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":5,"losses":2,"wins":35},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":26},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":13,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":21},"o3":{"draws":0,"losses":1,"wins":65},"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":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":6,"wins":39},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":31},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":24},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":41},"qwen/qwen3.8-max-0902":{"draws":4,"losses":3,"wins":41},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":13,"losses":8,"wins":137},"stealth/space-bunny-alpha":{"draws":0,"losses":1,"wins":37},"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":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":32},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":57},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":4},"unbiased/pareto-26.10-preview":{"draws":3,"losses":7,"wins":6},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":1,"losses":7,"wins":40},"x-ai/grok-4.7":{"draws":7,"losses":14,"wins":21},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":67},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":8,"wins":19},"z-ai/glm-5.2":{"draws":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":6,"losses":11,"wins":29},"z-ai/glm-5.3-flash":{"draws":5,"losses":6,"wins":37},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":42}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":3},"claude-fable-5":{"draws":0,"losses":4,"wins":2},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":2},"claude-opus-4-5":{"draws":0,"losses":7,"wins":3},"claude-opus-4-8":{"draws":0,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":7,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":4,"wins":2},"claude-sonnet-5-5":{"draws":0,"losses":5,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":6,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":5,"wins":1},"elorian/glimpse":{"draws":0,"losses":3,"wins":1},"fireworks/ember-1":{"draws":0,"losses":4,"wins":2},"gemini-3.1-pro-preview":{"draws":0,"losses":4,"wins":2},"gemini-4-argon":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":6},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":7},"google/gemini-3.6-flash":{"draws":0,"losses":8,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":5,"wins":1},"gpt-5.4":{"draws":0,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":5},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":0,"losses":4,"wins":2},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"gpt-6.1-sol":{"draws":0,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":3},"inception/mercury-3":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":4,"wins":2},"meta/muse-spark-open":{"draws":0,"losses":5,"wins":1},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":4,"wins":2},"mistralai/mistral-large-4-0":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":1},"o3":{"draws":0,"losses":2,"wins":10},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":6,"wins":0},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":4},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":0,"losses":13,"wins":5},"stealth/space-bunny-alpha":{"draws":0,"losses":3,"wins":3},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":4},"unbiased/pareto-26.10":{"draws":0,"losses":2,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":2,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":0,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":5,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":0,"losses":8,"wins":4},"z-ai/glm-5.3":{"draws":0,"losses":5,"wins":1},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":16,"wins":15},"claude-fable-5":{"draws":10,"losses":40,"wins":4},"claude-fable-5-1":{"draws":6,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":31,"wins":7},"claude-opus-4-5":{"draws":35,"losses":45,"wins":10},"claude-opus-4-8":{"draws":12,"losses":33,"wins":9},"claude-opus-5":{"draws":13,"losses":83,"wins":2},"claude-opus-5-5":{"draws":2,"losses":59,"wins":1},"claude-sonnet-5":{"draws":23,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":31,"losses":30,"wins":21},"deepseek/deepseek-v4-pro":{"draws":17,"losses":23,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":22,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":24,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":40,"wins":2},"elorian/glimpse":{"draws":7,"losses":19,"wins":0},"fireworks/ember-1":{"draws":22,"losses":26,"wins":6},"gemini-3.1-pro-preview":{"draws":19,"losses":20,"wins":15},"gemini-4-argon":{"draws":6,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":31,"wins":18},"google/gemini-3.5-flash-lite":{"draws":34,"losses":30,"wins":30},"google/gemini-3.6-flash":{"draws":37,"losses":51,"wins":12},"google/gemini-3.8-flash":{"draws":19,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":21,"losses":7,"wins":6},"gpt-4.1":{"draws":10,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":17,"losses":24,"wins":5},"gpt-5.4":{"draws":18,"losses":30,"wins":2},"gpt-5.4-mini":{"draws":16,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":17,"losses":27,"wins":18},"gpt-5.5":{"draws":23,"losses":23,"wins":2},"gpt-5.6-luna":{"draws":18,"losses":25,"wins":11},"gpt-5.6-sol":{"draws":9,"losses":43,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":24,"wins":7},"gpt-6-astra":{"draws":4,"losses":50,"wins":0},"gpt-6-luna":{"draws":18,"losses":28,"wins":8},"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":21,"losses":10,"wins":11},"inception/mercury-3":{"draws":16,"losses":17,"wins":5},"inclusionai/ling-3.0-flash":{"draws":21,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":16,"wins":19},"meta/muse-glimmer-30b":{"draws":22,"losses":14,"wins":10},"meta/muse-spark-1.2":{"draws":15,"losses":32,"wins":5},"meta/muse-spark-1.3":{"draws":17,"losses":36,"wins":1},"meta/muse-spark-open":{"draws":12,"losses":35,"wins":3},"meta/muse-wonder":{"draws":20,"losses":33,"wins":1},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":14},"minimax/minimax-m3.1-flash":{"draws":16,"losses":16,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":17,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":8,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":24,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":47,"wins":0},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":17,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":4},"o3":{"draws":17,"losses":44,"wins":13},"openai/gpt-oss-120b":{"draws":21,"losses":12,"wins":15},"poolside/laguna-s-2.1":{"draws":22,"losses":20,"wins":14},"qwen/qwen3.7-max":{"draws":16,"losses":10,"wins":8},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":26,"wins":3},"qwen/qwen3.8-27b":{"draws":14,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":15,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":22,"losses":28,"wins":4},"qwen/qwen3.8-max-0902":{"draws":24,"losses":25,"wins":5},"recursive/flint-v1.0":{"draws":5,"losses":7,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":29,"wins":6},"stealth/ox-alpha":{"draws":45,"losses":91,"wins":14},"stealth/space-bunny-alpha":{"draws":16,"losses":19,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":13,"wins":10},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":18,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":16,"losses":28,"wins":6},"thinkingmachines/inkling":{"draws":23,"losses":19,"wins":26},"thinkingmachines/inkling-small":{"draws":21,"losses":15,"wins":18},"unbiased/pareto-26.10":{"draws":2,"losses":16,"wins":0},"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":14,"losses":37,"wins":3},"x-ai/grok-4.6":{"draws":23,"losses":26,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":43,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":42,"losses":26,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":13,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":24,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.2":{"draws":41,"losses":49,"wins":18},"z-ai/glm-5.3":{"draws":11,"losses":40,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":13,"losses":36,"wins":5}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":36,"wins":59},"claude-fable-5":{"draws":2,"losses":93,"wins":19},"claude-fable-5-1":{"draws":0,"losses":117,"wins":7},"claude-haiku-5-5":{"draws":11,"losses":57,"wins":44},"claude-opus-4-5":{"draws":9,"losses":123,"wins":56},"claude-opus-4-8":{"draws":7,"losses":67,"wins":36},"claude-opus-5":{"draws":6,"losses":154,"wins":12},"claude-opus-5-5":{"draws":2,"losses":122,"wins":2},"claude-sonnet-5":{"draws":7,"losses":51,"wins":56},"claude-sonnet-5-5":{"draws":4,"losses":82,"wins":28},"cohere/north-mini-code":{"draws":4,"losses":11,"wins":39},"deepseek/deepseek-v4-flash":{"draws":12,"losses":53,"wins":115},"deepseek/deepseek-v4-pro":{"draws":1,"losses":55,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":65,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":57,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":73,"wins":37},"elorian/glimpse":{"draws":4,"losses":33,"wins":23},"fireworks/ember-1":{"draws":7,"losses":71,"wins":36},"gemini-3.1-pro-preview":{"draws":9,"losses":47,"wins":58},"gemini-4-argon":{"draws":0,"losses":108,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":9,"wins":82},"google/gemini-3.5-flash":{"draws":3,"losses":90,"wins":57},"google/gemini-3.5-flash-lite":{"draws":13,"losses":64,"wins":129},"google/gemini-3.6-flash":{"draws":9,"losses":132,"wins":81},"google/gemini-3.8-flash":{"draws":2,"losses":79,"wins":33},"google/gemma-4-31b-it":{"draws":9,"losses":13,"wins":46},"gpt-4.1":{"draws":4,"losses":18,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":6},"gpt-5":{"draws":1,"losses":63,"wins":42},"gpt-5.4":{"draws":1,"losses":84,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":18,"wins":52},"gpt-5.4-nano":{"draws":1,"losses":67,"wins":70},"gpt-5.5":{"draws":12,"losses":66,"wins":28},"gpt-5.6-luna":{"draws":14,"losses":43,"wins":57},"gpt-5.6-sol":{"draws":2,"losses":91,"wins":21},"gpt-5.6-terra":{"draws":9,"losses":53,"wins":44},"gpt-6-astra":{"draws":4,"losses":110,"wins":0},"gpt-6-luna":{"draws":14,"losses":62,"wins":38},"gpt-6-sol":{"draws":2,"losses":100,"wins":12},"gpt-6.1-sol":{"draws":0,"losses":108,"wins":6},"inception/mercury-2.5-preview":{"draws":8,"losses":11,"wins":57},"inception/mercury-3":{"draws":5,"losses":44,"wins":25},"inclusionai/ling-3.0-flash":{"draws":6,"losses":18,"wins":56},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":40,"wins":88},"meta/muse-glimmer-30b":{"draws":8,"losses":21,"wins":69},"meta/muse-spark-1.2":{"draws":3,"losses":49,"wins":54},"meta/muse-spark-1.3":{"draws":2,"losses":73,"wins":39},"meta/muse-spark-open":{"draws":3,"losses":82,"wins":29},"meta/muse-wonder":{"draws":4,"losses":86,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":19,"wins":46},"minimax/minimax-m3.1-flash":{"draws":1,"losses":45,"wins":56},"mistralai/mistral-large-4-0":{"draws":10,"losses":34,"wins":24},"mistralai/mistral-medium-3-5":{"draws":4,"losses":9,"wins":49},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":12,"wins":16},"moonshotai/kimi-k3":{"draws":5,"losses":53,"wins":48},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":96,"wins":16},"nex-agi/nex-n2-pro":{"draws":1,"losses":17,"wins":46},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":9,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":28,"wins":76},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":30,"wins":21},"o3":{"draws":8,"losses":78,"wins":84},"openai/gpt-oss-120b":{"draws":6,"losses":21,"wins":73},"poolside/laguna-s-2.1":{"draws":7,"losses":44,"wins":63},"qwen/qwen3.7-max":{"draws":5,"losses":31,"wins":38},"qwen/qwen3.7-plus":{"draws":0,"losses":17,"wins":49},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":68,"wins":39},"qwen/qwen3.8-27b":{"draws":2,"losses":44,"wins":38},"qwen/qwen3.8-flash":{"draws":2,"losses":38,"wins":36},"qwen/qwen3.8-max":{"draws":10,"losses":63,"wins":41},"qwen/qwen3.8-max-0902":{"draws":13,"losses":55,"wins":46},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":33},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":49,"wins":45},"stealth/ox-alpha":{"draws":18,"losses":176,"wins":150},"stealth/space-bunny-alpha":{"draws":5,"losses":37,"wins":50},"stepfun/step-3.7-flash":{"draws":8,"losses":32,"wins":58},"stepfun/step-5-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":22,"wins":29},"tencent/hy4-preview":{"draws":7,"losses":64,"wins":43},"thinkingmachines/inkling":{"draws":11,"losses":35,"wins":108},"thinkingmachines/inkling-small":{"draws":9,"losses":30,"wins":75},"unbiased/pareto-26.10":{"draws":0,"losses":38,"wins":0},"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":5,"losses":72,"wins":37},"x-ai/grok-4.6":{"draws":12,"losses":71,"wins":31},"x-ai/grok-4.7":{"draws":3,"losses":76,"wins":25},"x-ai/grok-build-0.1":{"draws":3,"losses":13,"wins":22},"xiaomi/mimo-v2.5":{"draws":12,"losses":33,"wins":135},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":25,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":45,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":52,"wins":20},"z-ai/glm-5.2":{"draws":14,"losses":97,"wins":117},"z-ai/glm-5.3":{"draws":2,"losses":82,"wins":24},"z-ai/glm-5.3-flash":{"draws":0,"losses":59,"wins":55},"z-ai/glm-5.3-flashx":{"draws":7,"losses":68,"wins":39}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":11},"claude-fable-5":{"draws":10,"losses":25,"wins":7},"claude-fable-5-1":{"draws":3,"losses":45,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":26,"wins":4},"claude-opus-4-5":{"draws":19,"losses":31,"wins":18},"claude-opus-4-8":{"draws":14,"losses":16,"wins":8},"claude-opus-5":{"draws":11,"losses":57,"wins":2},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":11,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":25,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":17,"wins":23},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":26,"wins":7},"elorian/glimpse":{"draws":7,"losses":9,"wins":6},"fireworks/ember-1":{"draws":15,"losses":19,"wins":8},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":15},"gemini-4-argon":{"draws":2,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":14},"google/gemini-3.5-flash":{"draws":14,"losses":20,"wins":18},"google/gemini-3.5-flash-lite":{"draws":24,"losses":18,"wins":32},"google/gemini-3.6-flash":{"draws":20,"losses":45,"wins":15},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":18,"wins":9},"gpt-5.4":{"draws":10,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":16,"wins":16},"gpt-5.5":{"draws":14,"losses":16,"wins":8},"gpt-5.6-luna":{"draws":22,"losses":8,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":18,"wins":7},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":18,"wins":11},"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":13,"losses":7,"wins":12},"inception/mercury-3":{"draws":7,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":18,"wins":17},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":15},"meta/muse-spark-1.2":{"draws":11,"losses":21,"wins":8},"meta/muse-spark-1.3":{"draws":8,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":5},"meta/muse-wonder":{"draws":9,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":12,"losses":16,"wins":8},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":13,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":22,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":35,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":11,"wins":4},"o3":{"draws":6,"losses":33,"wins":17},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":10,"losses":27,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":10},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":34,"losses":73,"wins":35},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":9},"thinkingmachines/inkling":{"draws":15,"losses":16,"wins":23},"thinkingmachines/inkling-small":{"draws":15,"losses":11,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":10,"losses":27,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":8},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":35,"wins":21},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"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":11,"losses":3,"wins":30},"claude-fable-5":{"draws":11,"losses":13,"wins":24},"claude-fable-5-1":{"draws":5,"losses":44,"wins":5},"claude-haiku-5-5":{"draws":11,"losses":10,"wins":25},"claude-opus-4-5":{"draws":22,"losses":7,"wins":49},"claude-opus-4-8":{"draws":10,"losses":5,"wins":29},"claude-opus-5":{"draws":10,"losses":52,"wins":20},"claude-opus-5-5":{"draws":3,"losses":39,"wins":10},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":9,"losses":17,"wins":22},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":10,"losses":4,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":20,"wins":21},"elorian/glimpse":{"draws":5,"losses":8,"wins":13},"fireworks/ember-1":{"draws":11,"losses":8,"wins":29},"gemini-3.1-pro-preview":{"draws":8,"losses":9,"wins":31},"gemini-4-argon":{"draws":4,"losses":31,"wins":13},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":18,"losses":5,"wins":61},"google/gemini-3.6-flash":{"draws":21,"losses":22,"wins":49},"google/gemini-3.8-flash":{"draws":12,"losses":13,"wins":23},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":10,"losses":6,"wins":26},"gpt-5.4":{"draws":8,"losses":11,"wins":27},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":1,"wins":39},"gpt-5.5":{"draws":11,"losses":12,"wins":21},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":7,"losses":19,"wins":22},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":28},"gpt-6-astra":{"draws":1,"losses":42,"wins":5},"gpt-6-luna":{"draws":12,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":22,"wins":19},"gpt-6.1-sol":{"draws":1,"losses":34,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":11,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":0,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":38},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":32},"meta/muse-spark-1.2":{"draws":12,"losses":11,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":11,"wins":28},"meta/muse-spark-open":{"draws":11,"losses":10,"wins":25},"meta/muse-wonder":{"draws":8,"losses":16,"wins":24},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":10,"losses":4,"wins":28},"mistralai/mistral-large-4-0":{"draws":3,"losses":8,"wins":19},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":12,"losses":8,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":31,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":2,"wins":14},"o3":{"draws":3,"losses":12,"wins":51},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":2,"wins":35},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":21},"qwen/qwen3.8-27b":{"draws":13,"losses":3,"wins":18},"qwen/qwen3.8-flash":{"draws":6,"losses":6,"wins":20},"qwen/qwen3.8-max":{"draws":13,"losses":11,"wins":24},"qwen/qwen3.8-max-0902":{"draws":13,"losses":10,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":5,"wins":32},"stealth/ox-alpha":{"draws":31,"losses":37,"wins":90},"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":4,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":19,"losses":2,"wins":43},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":13,"losses":11,"wins":24},"x-ai/grok-4.6":{"draws":8,"losses":13,"wins":27},"x-ai/grok-4.7":{"draws":1,"losses":26,"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":5,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":11,"wins":14},"z-ai/glm-5.2":{"draws":27,"losses":12,"wins":57},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":16},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":16,"losses":10,"wins":22}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":7,"wins":24},"claude-fable-5":{"draws":3,"losses":22,"wins":11},"claude-fable-5-1":{"draws":3,"losses":36,"wins":1},"claude-haiku-5-5":{"draws":4,"losses":13,"wins":19},"claude-opus-4-5":{"draws":5,"losses":16,"wins":39},"claude-opus-4-8":{"draws":4,"losses":14,"wins":18},"claude-opus-5":{"draws":8,"losses":44,"wins":6},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":4,"losses":11,"wins":21},"claude-sonnet-5-5":{"draws":3,"losses":17,"wins":16},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":13,"wins":39},"deepseek/deepseek-v4-pro":{"draws":2,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":9,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":23,"wins":11},"elorian/glimpse":{"draws":2,"losses":7,"wins":11},"fireworks/ember-1":{"draws":2,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":23},"gemini-4-argon":{"draws":3,"losses":29,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":2,"losses":13,"wins":33},"google/gemini-3.5-flash-lite":{"draws":5,"losses":7,"wins":54},"google/gemini-3.6-flash":{"draws":4,"losses":27,"wins":39},"google/gemini-3.8-flash":{"draws":2,"losses":17,"wins":17},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":16},"gpt-4.1":{"draws":1,"losses":1,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":8,"wins":23},"gpt-5.4":{"draws":3,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":0,"losses":13,"wins":27},"gpt-5.5":{"draws":1,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":10},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":18},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":2,"losses":13,"wins":21},"gpt-6-sol":{"draws":4,"losses":24,"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":2,"losses":2,"wins":22},"inception/mercury-3":{"draws":1,"losses":7,"wins":14},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":2,"losses":5,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":29},"meta/muse-spark-1.2":{"draws":2,"losses":10,"wins":22},"meta/muse-spark-1.3":{"draws":4,"losses":12,"wins":20},"meta/muse-spark-open":{"draws":2,"losses":17,"wins":17},"meta/muse-wonder":{"draws":3,"losses":28,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":18},"minimax/minimax-m3.1-flash":{"draws":3,"losses":12,"wins":17},"mistralai/mistral-large-4-0":{"draws":5,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":3,"losses":16,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":29,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":5,"wins":13},"o3":{"draws":1,"losses":19,"wins":40},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":1,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":0,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":13,"wins":17},"qwen/qwen3.8-27b":{"draws":1,"losses":7,"wins":6},"qwen/qwen3.8-flash":{"draws":1,"losses":9,"wins":14},"qwen/qwen3.8-max":{"draws":5,"losses":12,"wins":19},"qwen/qwen3.8-max-0902":{"draws":4,"losses":15,"wins":17},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":9,"wins":22},"stealth/ox-alpha":{"draws":14,"losses":38,"wins":50},"stealth/space-bunny-alpha":{"draws":2,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":0,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":14},"tencent/hy4-preview":{"draws":5,"losses":13,"wins":18},"thinkingmachines/inkling":{"draws":2,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":34},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":21,"wins":15},"x-ai/grok-4.6":{"draws":5,"losses":17,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":1,"losses":6,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":14},"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":10,"losses":21,"wins":41},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":11,"wins":21},"z-ai/glm-5.3-flashx":{"draws":3,"losses":15,"wins":18}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":14,"wins":19},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":23,"losses":20,"wins":35},"claude-opus-4-8":{"draws":6,"losses":19,"wins":19},"claude-opus-5":{"draws":7,"losses":63,"wins":12},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":12,"losses":14,"wins":22},"claude-sonnet-5-5":{"draws":6,"losses":25,"wins":17},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":11,"losses":15,"wins":46},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":11,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":15,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":29,"wins":11},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":10,"losses":19,"wins":19},"gemini-3.1-pro-preview":{"draws":11,"losses":12,"wins":25},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":23},"google/gemini-3.5-flash-lite":{"draws":14,"losses":13,"wins":57},"google/gemini-3.6-flash":{"draws":13,"losses":37,"wins":42},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":16},"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":9,"losses":14,"wins":19},"gpt-5.4":{"draws":8,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":28},"gpt-5.5":{"draws":12,"losses":14,"wins":18},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":30},"gpt-5.6-sol":{"draws":10,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":18},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":9,"losses":17,"wins":22},"gpt-6-sol":{"draws":5,"losses":36,"wins":7},"gpt-6.1-sol":{"draws":2,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":22},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":20},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":36},"meta/muse-glimmer-30b":{"draws":9,"losses":8,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-spark-open":{"draws":3,"losses":22,"wins":21},"meta/muse-wonder":{"draws":9,"losses":27,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":38,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":7,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":6,"losses":24,"wins":36},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":29},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-27b":{"draws":7,"losses":10,"wins":17},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max-0902":{"draws":8,"losses":23,"wins":17},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":15,"wins":22},"stealth/ox-alpha":{"draws":36,"losses":63,"wins":59},"stealth/space-bunny-alpha":{"draws":8,"losses":9,"wins":21},"stepfun/step-3.7-flash":{"draws":6,"losses":5,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":19,"wins":19},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":38},"thinkingmachines/inkling-small":{"draws":11,"losses":10,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":9,"losses":20,"wins":19},"x-ai/grok-4.6":{"draws":12,"losses":17,"wins":19},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":22,"losses":8,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":22,"losses":30,"wins":44},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":11},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":24},"z-ai/glm-5.3-flashx":{"draws":14,"losses":17,"wins":17}},"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":11,"losses":9,"wins":26},"claude-opus-4-5":{"draws":14,"losses":12,"wins":52},"claude-opus-4-8":{"draws":4,"losses":14,"wins":26},"claude-opus-5":{"draws":9,"losses":44,"wins":29},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":20},"elorian/glimpse":{"draws":6,"losses":5,"wins":15},"fireworks/ember-1":{"draws":12,"losses":9,"wins":27},"gemini-3.1-pro-preview":{"draws":11,"losses":6,"wins":31},"gemini-4-argon":{"draws":7,"losses":32,"wins":9},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":5,"wins":43},"google/gemini-3.5-flash-lite":{"draws":13,"losses":4,"wins":67},"google/gemini-3.6-flash":{"draws":19,"losses":17,"wins":56},"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":5,"losses":8,"wins":35},"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},"inception/mercury-3":{"draws":8,"losses":7,"wins":17},"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":8,"losses":8,"wins":30},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":31},"meta/muse-spark-open":{"draws":6,"losses":8,"wins":32},"meta/muse-wonder":{"draws":13,"losses":19,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"wins":27},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":30},"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":{"draws":2,"losses":12,"wins":2},"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":21,"losses":3,"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}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":23,"wins":15},"claude-opus-4-5":{"draws":23,"losses":19,"wins":36},"claude-opus-4-8":{"draws":8,"losses":22,"wins":14},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":7,"losses":45,"wins":0},"claude-sonnet-5":{"draws":11,"losses":13,"wins":24},"claude-sonnet-5-5":{"draws":8,"losses":26,"wins":14},"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":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":22,"wins":15},"elorian/glimpse":{"draws":5,"losses":12,"wins":9},"fireworks/ember-1":{"draws":9,"losses":15,"wins":24},"gemini-3.1-pro-preview":{"draws":9,"losses":15,"wins":24},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":13,"losses":15,"wins":32},"google/gemini-3.5-flash-lite":{"draws":12,"losses":16,"wins":56},"google/gemini-3.6-flash":{"draws":18,"losses":38,"wins":36},"google/gemini-3.8-flash":{"draws":10,"losses":22,"wins":16},"google/gemma-4-31b-it":{"draws":4,"losses":6,"wins":18},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":5,"losses":12,"wins":25},"gpt-5.4":{"draws":10,"losses":22,"wins":14},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":10,"wins":33},"gpt-5.5":{"draws":12,"losses":17,"wins":15},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":29,"wins":12},"gpt-5.6-terra":{"draws":7,"losses":19,"wins":20},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":11,"losses":15,"wins":22},"gpt-6-sol":{"draws":5,"losses":37,"wins":6},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":11,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":6,"losses":6,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":9,"wins":36},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":14,"wins":23},"meta/muse-spark-1.3":{"draws":6,"losses":25,"wins":17},"meta/muse-spark-open":{"draws":11,"losses":18,"wins":17},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":21},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"mistralai/mistral-large-4-0":{"draws":6,"losses":13,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":14,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":40,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":6,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":4,"losses":25,"wins":37},"openai/gpt-oss-120b":{"draws":8,"losses":5,"wins":29},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":17,"wins":19},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-flash":{"draws":5,"losses":8,"wins":19},"qwen/qwen3.8-max":{"draws":13,"losses":14,"wins":21},"qwen/qwen3.8-max-0902":{"draws":12,"losses":16,"wins":20},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":10,"wins":9},"stealth/ox-alpha":{"draws":29,"losses":62,"wins":67},"stealth/space-bunny-alpha":{"draws":9,"losses":3,"wins":26},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":7,"wins":13},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":1,"losses":15,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":18},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":7,"losses":29,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":18,"losses":9,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":12,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.2":{"draws":17,"losses":26,"wins":53},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":16},"z-ai/glm-5.3-flashx":{"draws":6,"losses":21,"wins":21}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":110},"claude-fable-5":{"draws":16,"losses":74,"wins":60},"claude-fable-5-1":{"draws":14,"losses":141,"wins":17},"claude-haiku-5-5":{"draws":16,"losses":43,"wins":81},"claude-opus-4-5":{"draws":25,"losses":51,"wins":164},"claude-opus-4-8":{"draws":14,"losses":40,"wins":76},"claude-opus-5":{"draws":35,"losses":168,"wins":55},"claude-opus-5-5":{"draws":7,"losses":133,"wins":22},"claude-sonnet-5":{"draws":13,"losses":28,"wins":109},"claude-sonnet-5-5":{"draws":10,"losses":66,"wins":74},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":51},"deepseek/deepseek-v4-flash":{"draws":15,"losses":22,"wins":185},"deepseek/deepseek-v4-pro":{"draws":13,"losses":35,"wins":92},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":34,"wins":90},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":43,"wins":92},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":57,"wins":77},"elorian/glimpse":{"draws":10,"losses":23,"wins":51},"fireworks/ember-1":{"draws":20,"losses":36,"wins":94},"gemini-3.1-pro-preview":{"draws":16,"losses":37,"wins":97},"gemini-4-argon":{"draws":16,"losses":108,"wins":26},"google/gemini-3.1-flash-lite":{"draws":7,"losses":6,"wins":81},"google/gemini-3.5-flash":{"draws":17,"losses":40,"wins":129},"google/gemini-3.5-flash-lite":{"draws":21,"losses":32,"wins":211},"google/gemini-3.6-flash":{"draws":26,"losses":82,"wins":182},"google/gemini-3.8-flash":{"draws":14,"losses":58,"wins":78},"google/gemma-4-31b-it":{"draws":7,"losses":8,"wins":69},"gpt-4.1":{"draws":8,"losses":10,"wins":32},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":14},"gpt-5":{"draws":10,"losses":30,"wins":94},"gpt-5.4":{"draws":18,"losses":48,"wins":80},"gpt-5.4-mini":{"draws":13,"losses":11,"wins":76},"gpt-5.4-nano":{"draws":7,"losses":36,"wins":99},"gpt-5.5":{"draws":16,"losses":42,"wins":82},"gpt-5.6-luna":{"draws":23,"losses":23,"wins":104},"gpt-5.6-sol":{"draws":15,"losses":74,"wins":61},"gpt-5.6-terra":{"draws":15,"losses":39,"wins":90},"gpt-6-astra":{"draws":14,"losses":120,"wins":16},"gpt-6-luna":{"draws":16,"losses":32,"wins":102},"gpt-6-sol":{"draws":18,"losses":92,"wins":40},"gpt-6.1-sol":{"draws":15,"losses":118,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":9,"wins":77},"inception/mercury-3":{"draws":8,"losses":26,"wins":64},"inclusionai/ling-3.0-flash":{"draws":7,"losses":6,"wins":93},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":11,"losses":19,"wins":134},"meta/muse-glimmer-30b":{"draws":9,"losses":9,"wins":116},"meta/muse-spark-1.2":{"draws":19,"losses":29,"wins":96},"meta/muse-spark-1.3":{"draws":18,"losses":48,"wins":84},"meta/muse-spark-open":{"draws":12,"losses":50,"wins":84},"meta/muse-wonder":{"draws":12,"losses":76,"wins":62},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":65},"minimax/minimax-m3.1-flash":{"draws":13,"losses":30,"wins":91},"mistralai/mistral-large-4-0":{"draws":15,"losses":24,"wins":55},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":69},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":24},"moonshotai/kimi-k3":{"draws":15,"losses":39,"wins":90},"moonshotai/kimi-k3.1-pro":{"draws":21,"losses":101,"wins":28},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":64},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":18,"wins":93},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":11,"wins":48},"o3":{"draws":7,"losses":41,"wins":156},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":111},"poolside/laguna-s-2.1":{"draws":13,"losses":18,"wins":117},"qwen/qwen3.7-max":{"draws":5,"losses":11,"wins":68},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":60},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":45,"wins":86},"qwen/qwen3.8-27b":{"draws":7,"losses":22,"wins":77},"qwen/qwen3.8-flash":{"draws":8,"losses":23,"wins":69},"qwen/qwen3.8-max":{"draws":18,"losses":35,"wins":97},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":90},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":36},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":30,"wins":95},"stealth/ox-alpha":{"draws":46,"losses":131,"wins":311},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":91},"stepfun/step-3.7-flash":{"draws":1,"losses":13,"wins":94},"stepfun/step-5-preview":{"draws":2,"losses":5,"wins":5},"tencent/hy3-preview":{"draws":13,"losses":11,"wins":54},"tencent/hy4-preview":{"draws":17,"losses":50,"wins":79},"thinkingmachines/inkling":{"draws":21,"losses":24,"wins":161},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":128},"unbiased/pareto-26.10":{"draws":3,"losses":46,"wins":1},"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":14,"losses":65,"wins":71},"x-ai/grok-4.6":{"draws":26,"losses":57,"wins":67},"x-ai/grok-4.7":{"draws":8,"losses":78,"wins":42},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":45},"xiaomi/mimo-v2.5":{"draws":24,"losses":18,"wins":174},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":13,"wins":67},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":22,"wins":64},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":39,"wins":46},"z-ai/glm-5.2":{"draws":28,"losses":49,"wins":223},"z-ai/glm-5.3":{"draws":18,"losses":62,"wins":64},"z-ai/glm-5.3-flash":{"draws":15,"losses":43,"wins":92},"z-ai/glm-5.3-flashx":{"draws":16,"losses":52,"wins":82}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":17},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":0,"losses":38,"wins":2},"claude-haiku-5-5":{"draws":7,"losses":18,"wins":11},"claude-opus-4-5":{"draws":17,"losses":29,"wins":14},"claude-opus-4-8":{"draws":6,"losses":15,"wins":15},"claude-opus-5":{"draws":11,"losses":41,"wins":6},"claude-opus-5-5":{"draws":1,"losses":38,"wins":1},"claude-sonnet-5":{"draws":3,"losses":13,"wins":20},"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":11,"losses":15,"wins":28},"deepseek/deepseek-v4-pro":{"draws":8,"losses":12,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":6},"elorian/glimpse":{"draws":2,"losses":11,"wins":7},"fireworks/ember-1":{"draws":5,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":3,"losses":11,"wins":22},"gemini-4-argon":{"draws":1,"losses":31,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":14,"losses":15,"wins":37},"google/gemini-3.6-flash":{"draws":15,"losses":31,"wins":24},"google/gemini-3.8-flash":{"draws":5,"losses":21,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":13,"wins":17},"gpt-5.4":{"draws":3,"losses":26,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":20},"gpt-5.5":{"draws":10,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":5,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":8},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":12},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":14},"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":8,"losses":4,"wins":14},"inception/mercury-3":{"draws":3,"losses":11,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":21},"meta/muse-glimmer-30b":{"draws":7,"losses":2,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":15},"meta/muse-spark-1.3":{"draws":4,"losses":16,"wins":16},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":9},"meta/muse-wonder":{"draws":5,"losses":24,"wins":7},"minimax/minimax-m3":{"draws":1,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":6,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":6,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":12,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":9},"o3":{"draws":8,"losses":27,"wins":25},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":2,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":14},"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":6,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":7,"losses":19,"wins":10},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":15,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":47,"wins":36},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":13},"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":5,"losses":13,"wins":18},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":24},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":26},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":22,"wins":7},"x-ai/grok-4.6":{"draws":4,"losses":20,"wins":12},"x-ai/grok-4.7":{"draws":1,"losses":20,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":13,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":10,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":15,"losses":23,"wins":34},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":21,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":21,"wins":11}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":17,"wins":9},"claude-fable-5":{"draws":0,"losses":28,"wins":2},"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":4,"losses":37,"wins":9},"claude-opus-4-8":{"draws":2,"losses":23,"wins":5},"claude-opus-5":{"draws":1,"losses":44,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":0,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":0,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":4,"losses":30,"wins":14},"deepseek/deepseek-v4-pro":{"draws":0,"losses":25,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":25,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":28,"wins":2},"elorian/glimpse":{"draws":0,"losses":13,"wins":3},"fireworks/ember-1":{"draws":4,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":0,"losses":19,"wins":11},"gemini-4-argon":{"draws":0,"losses":30,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":2,"losses":28,"wins":10},"google/gemini-3.5-flash-lite":{"draws":6,"losses":32,"wins":16},"google/gemini-3.6-flash":{"draws":3,"losses":49,"wins":6},"google/gemini-3.8-flash":{"draws":0,"losses":29,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":3,"wins":10},"gpt-4.1":{"draws":0,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":27,"wins":1},"gpt-5.4":{"draws":0,"losses":24,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":11,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":25,"wins":13},"gpt-5.5":{"draws":4,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":17,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":20,"wins":6},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":20,"wins":8},"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":3,"wins":13},"inception/mercury-3":{"draws":0,"losses":17,"wins":3},"inclusionai/ling-3.0-flash":{"draws":2,"losses":11,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":23,"wins":12},"meta/muse-glimmer-30b":{"draws":0,"losses":19,"wins":7},"meta/muse-spark-1.2":{"draws":1,"losses":20,"wins":7},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-spark-open":{"draws":0,"losses":23,"wins":7},"meta/muse-wonder":{"draws":1,"losses":28,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":13,"wins":3},"minimax/minimax-m3.1-flash":{"draws":0,"losses":20,"wins":6},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":17,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":12,"wins":2},"o3":{"draws":3,"losses":41,"wins":12},"openai/gpt-oss-120b":{"draws":2,"losses":12,"wins":12},"poolside/laguna-s-2.1":{"draws":2,"losses":19,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":12,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":24,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":0,"losses":14,"wins":6},"qwen/qwen3.8-max":{"draws":2,"losses":27,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":6},"recursive/flint-v1.0":{"draws":0,"losses":5,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":18,"wins":8},"stealth/ox-alpha":{"draws":2,"losses":68,"wins":14},"stealth/space-bunny-alpha":{"draws":2,"losses":14,"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":4,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":13,"wins":21},"thinkingmachines/inkling-small":{"draws":3,"losses":17,"wins":10},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"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":28,"wins":2},"x-ai/grok-4.6":{"draws":1,"losses":26,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"losses":25,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":15,"wins":4},"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":5,"losses":42,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":26,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":26,"wins":4},"z-ai/glm-5.3-flashx":{"draws":0,"losses":25,"wins":5}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":15},"claude-fable-5":{"draws":10,"losses":26,"wins":6},"claude-fable-5-1":{"draws":3,"losses":42,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":17,"wins":13},"claude-opus-4-5":{"draws":23,"losses":31,"wins":16},"claude-opus-4-8":{"draws":8,"losses":23,"wins":11},"claude-opus-5":{"draws":12,"losses":55,"wins":3},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":18,"wins":12},"claude-sonnet-5-5":{"draws":7,"losses":30,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":16,"losses":23,"wins":25},"deepseek/deepseek-v4-pro":{"draws":11,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":24,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":6},"elorian/glimpse":{"draws":6,"losses":9,"wins":7},"fireworks/ember-1":{"draws":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":11,"losses":16,"wins":15},"gemini-4-argon":{"draws":3,"losses":38,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":9,"wins":16},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":18,"wins":36},"google/gemini-3.6-flash":{"draws":22,"losses":41,"wins":17},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":1},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":21},"gpt-5.5":{"draws":17,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":13,"losses":17,"wins":10},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":13,"losses":16,"wins":13},"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":12,"losses":10,"wins":10},"inception/mercury-3":{"draws":8,"losses":13,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":13,"wins":23},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":22,"wins":7},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":9},"meta/muse-spark-open":{"draws":8,"losses":24,"wins":8},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":10},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":1},"nex-agi/nex-n2-pro":{"draws":5,"losses":8,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":4},"o3":{"draws":10,"losses":25,"wins":27},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":11,"losses":11,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":12,"losses":22,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":7},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":15,"wins":14},"stealth/ox-alpha":{"draws":34,"losses":60,"wins":24},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":11,"losses":17,"wins":12},"thinkingmachines/inkling":{"draws":15,"losses":10,"wins":29},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":10,"losses":29,"wins":3},"x-ai/grok-4.6":{"draws":9,"losses":24,"wins":9},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":21,"losses":23,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":15,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":20,"losses":34,"wins":30},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":24,"wins":8},"z-ai/glm-5.3-flashx":{"draws":6,"losses":28,"wins":8}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":3,"wins":27},"claude-fable-5":{"draws":8,"losses":21,"wins":19},"claude-fable-5-1":{"draws":6,"losses":39,"wins":9},"claude-haiku-5-5":{"draws":14,"losses":15,"wins":17},"claude-opus-4-5":{"draws":17,"losses":18,"wins":43},"claude-opus-4-8":{"draws":10,"losses":13,"wins":21},"claude-opus-5":{"draws":10,"losses":58,"wins":14},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":10,"losses":7,"wins":31},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":21},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":46},"deepseek/deepseek-v4-pro":{"draws":8,"losses":10,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":6,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":8,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":17,"wins":24},"elorian/glimpse":{"draws":2,"losses":9,"wins":15},"fireworks/ember-1":{"draws":10,"losses":11,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":23},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":9,"wins":38},"google/gemini-3.5-flash-lite":{"draws":21,"losses":13,"wins":50},"google/gemini-3.6-flash":{"draws":17,"losses":33,"wins":42},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":25},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":15,"losses":8,"wins":19},"gpt-5.4":{"draws":11,"losses":15,"wins":20},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":18},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":34},"gpt-5.5":{"draws":13,"losses":10,"wins":21},"gpt-5.6-luna":{"draws":13,"losses":7,"wins":28},"gpt-5.6-sol":{"draws":6,"losses":20,"wins":22},"gpt-5.6-terra":{"draws":9,"losses":12,"wins":25},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"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":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":7,"losses":8,"wins":17},"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":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":12,"losses":4,"wins":26},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":27},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":17},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":27},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":5,"losses":16,"wins":21},"mistralai/mistral-large-4-0":{"draws":11,"losses":5,"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":11,"losses":9,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":34,"wins":12},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":12},"o3":{"draws":12,"losses":15,"wins":39},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":23},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":20},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":12,"wins":26},"qwen/qwen3.8-27b":{"draws":10,"losses":5,"wins":19},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":12,"losses":11,"wins":25},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":10,"wins":23},"stealth/ox-alpha":{"draws":31,"losses":29,"wins":98},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"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":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":5,"losses":7,"wins":18},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":10,"losses":6,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"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":4,"losses":14,"wins":30},"x-ai/grok-4.6":{"draws":17,"losses":16,"wins":15},"x-ai/grok-4.7":{"draws":4,"losses":24,"wins":14},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":20,"losses":7,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.2":{"draws":14,"losses":16,"wins":66},"z-ai/glm-5.3":{"draws":7,"losses":25,"wins":14},"z-ai/glm-5.3-flash":{"draws":10,"losses":18,"wins":20},"z-ai/glm-5.3-flashx":{"draws":12,"losses":10,"wins":26}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":36,"wins":20},"claude-fable-5":{"draws":11,"losses":68,"wins":5},"claude-fable-5-1":{"draws":0,"losses":94,"wins":0},"claude-haiku-5-5":{"draws":28,"losses":43,"wins":9},"claude-opus-4-5":{"draws":42,"losses":75,"wins":19},"claude-opus-4-8":{"draws":17,"losses":48,"wins":11},"claude-opus-5":{"draws":21,"losses":120,"wins":9},"claude-opus-5-5":{"draws":7,"losses":85,"wins":0},"claude-sonnet-5":{"draws":27,"losses":44,"wins":13},"claude-sonnet-5-5":{"draws":19,"losses":47,"wins":18},"cohere/north-mini-code":{"draws":7,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":36,"losses":38,"wins":54},"deepseek/deepseek-v4-pro":{"draws":24,"losses":40,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":34,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":21,"losses":50,"wins":13},"elorian/glimpse":{"draws":9,"losses":25,"wins":12},"fireworks/ember-1":{"draws":25,"losses":46,"wins":13},"gemini-3.1-pro-preview":{"draws":30,"losses":34,"wins":20},"gemini-4-argon":{"draws":8,"losses":73,"wins":3},"google/gemini-3.1-flash-lite":{"draws":16,"losses":8,"wins":30},"google/gemini-3.5-flash":{"draws":24,"losses":54,"wins":26},"google/gemini-3.5-flash-lite":{"draws":41,"losses":52,"wins":51},"google/gemini-3.6-flash":{"draws":43,"losses":86,"wins":31},"google/gemini-3.8-flash":{"draws":26,"losses":48,"wins":10},"google/gemma-4-31b-it":{"draws":17,"losses":12,"wins":19},"gpt-4.1":{"draws":7,"losses":11,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":17,"losses":38,"wins":21},"gpt-5.4":{"draws":21,"losses":44,"wins":15},"gpt-5.4-mini":{"draws":21,"losses":19,"wins":16},"gpt-5.4-nano":{"draws":24,"losses":28,"wins":34},"gpt-5.5":{"draws":24,"losses":42,"wins":12},"gpt-5.6-luna":{"draws":26,"losses":37,"wins":21},"gpt-5.6-sol":{"draws":13,"losses":62,"wins":9},"gpt-5.6-terra":{"draws":23,"losses":39,"wins":18},"gpt-6-astra":{"draws":6,"losses":77,"wins":1},"gpt-6-luna":{"draws":23,"losses":40,"wins":21},"gpt-6-sol":{"draws":8,"losses":67,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":74,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":25,"losses":12,"wins":19},"inception/mercury-3":{"draws":20,"losses":21,"wins":17},"inclusionai/ling-3.0-flash":{"draws":21,"losses":14,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":22,"losses":28,"wins":40},"meta/muse-glimmer-30b":{"draws":22,"losses":27,"wins":27},"meta/muse-spark-1.2":{"draws":21,"losses":50,"wins":11},"meta/muse-spark-1.3":{"draws":14,"losses":61,"wins":9},"meta/muse-spark-open":{"draws":17,"losses":55,"wins":8},"meta/muse-wonder":{"draws":24,"losses":52,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":15,"wins":21},"minimax/minimax-m3.1-flash":{"draws":14,"losses":30,"wins":28},"mistralai/mistral-large-4-0":{"draws":19,"losses":25,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":11,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":24,"losses":41,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":72,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":14,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":9,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":24,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":18,"wins":10},"o3":{"draws":24,"losses":60,"wins":32},"openai/gpt-oss-120b":{"draws":21,"losses":21,"wins":34},"poolside/laguna-s-2.1":{"draws":23,"losses":37,"wins":26},"qwen/qwen3.7-max":{"draws":12,"losses":28,"wins":10},"qwen/qwen3.7-plus":{"draws":13,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":48,"wins":8},"qwen/qwen3.8-27b":{"draws":19,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":20,"losses":25,"wins":11},"qwen/qwen3.8-max":{"draws":24,"losses":43,"wins":17},"qwen/qwen3.8-max-0902":{"draws":26,"losses":44,"wins":14},"recursive/flint-v1.0":{"draws":8,"losses":5,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":24,"losses":36,"wins":18},"stealth/ox-alpha":{"draws":67,"losses":159,"wins":56},"stealth/space-bunny-alpha":{"draws":19,"losses":24,"wins":23},"stepfun/step-3.7-flash":{"draws":18,"losses":17,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":15,"losses":19,"wins":12},"tencent/hy4-preview":{"draws":15,"losses":47,"wins":18},"thinkingmachines/inkling":{"draws":25,"losses":29,"wins":32},"thinkingmachines/inkling-small":{"draws":32,"losses":14,"wins":38},"unbiased/pareto-26.10":{"draws":0,"losses":28,"wins":0},"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":27,"losses":47,"wins":10},"x-ai/grok-4.6":{"draws":25,"losses":52,"wins":7},"x-ai/grok-4.7":{"draws":13,"losses":58,"wins":5},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":9},"xiaomi/mimo-v2.5":{"draws":39,"losses":45,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":20,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":25,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":40,"wins":7},"z-ai/glm-5.2":{"draws":37,"losses":80,"wins":51},"z-ai/glm-5.3":{"draws":16,"losses":53,"wins":11},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":14},"z-ai/glm-5.3-flashx":{"draws":20,"losses":52,"wins":12}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":19,"wins":11},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":30,"wins":5},"claude-opus-4-5":{"draws":26,"losses":34,"wins":18},"claude-opus-4-8":{"draws":11,"losses":26,"wins":7},"claude-opus-5":{"draws":14,"losses":66,"wins":2},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":11,"losses":27,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":28,"wins":9},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":23,"losses":27,"wins":22},"deepseek/deepseek-v4-pro":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":21,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":27,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":37,"wins":4},"elorian/glimpse":{"draws":7,"losses":16,"wins":3},"fireworks/ember-1":{"draws":14,"losses":24,"wins":10},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"gemini-4-argon":{"draws":4,"losses":44,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":30,"wins":14},"google/gemini-3.5-flash-lite":{"draws":21,"losses":26,"wins":37},"google/gemini-3.6-flash":{"draws":30,"losses":46,"wins":16},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":3,"losses":6,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":19,"wins":9},"gpt-5.4":{"draws":10,"losses":30,"wins":6},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":16,"losses":14,"wins":18},"gpt-5.5":{"draws":18,"losses":20,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":16,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":24,"wins":12},"gpt-6-astra":{"draws":4,"losses":44,"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":13,"losses":9,"wins":12},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":15,"wins":21},"meta/muse-glimmer-30b":{"draws":14,"losses":16,"wins":12},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":12,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":10,"losses":28,"wins":8},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":11,"losses":15,"wins":16},"mistralai/mistral-large-4-0":{"draws":9,"losses":16,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":3},"o3":{"draws":14,"losses":33,"wins":19},"openai/gpt-oss-120b":{"draws":14,"losses":11,"wins":17},"poolside/laguna-s-2.1":{"draws":16,"losses":20,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":14,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":18,"wins":8},"qwen/qwen3.8-27b":{"draws":12,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":12,"losses":29,"wins":7},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":17,"wins":10},"stealth/ox-alpha":{"draws":38,"losses":97,"wins":23},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":10},"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":14,"losses":25,"wins":7},"thinkingmachines/inkling":{"draws":20,"losses":17,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":29,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":25,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":30,"losses":23,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":22,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":30,"losses":40,"wins":26},"z-ai/glm-5.3":{"draws":6,"losses":37,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":31,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":17,"wins":1},"elorian/glimpse":{"draws":0,"losses":6,"wins":2},"fireworks/ember-1":{"draws":0,"losses":11,"wins":7},"gemini-3.1-pro-preview":{"draws":0,"losses":8,"wins":10},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"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},"inception/mercury-3":{"draws":0,"losses":7,"wins":3},"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-spark-open":{"draws":0,"losses":15,"wins":3},"meta/muse-wonder":{"draws":0,"losses":17,"wins":1},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"minimax/minimax-m3.1-flash":{"draws":0,"losses":14,"wins":4},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":6,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":6,"wins":2},"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":10,"wins":6},"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":{"draws":0,"losses":6,"wins":0},"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":10,"losses":2,"wins":32},"claude-fable-5":{"draws":6,"losses":18,"wins":24},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":13,"wins":23},"claude-opus-4-5":{"draws":17,"losses":22,"wins":39},"claude-opus-4-8":{"draws":11,"losses":14,"wins":19},"claude-opus-5":{"draws":10,"losses":51,"wins":21},"claude-opus-5-5":{"draws":9,"losses":39,"wins":4},"claude-sonnet-5":{"draws":8,"losses":11,"wins":29},"claude-sonnet-5-5":{"draws":7,"losses":21,"wins":20},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":55},"deepseek/deepseek-v4-pro":{"draws":13,"losses":8,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":12,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":16,"wins":26},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":25},"elorian/glimpse":{"draws":4,"losses":8,"wins":14},"fireworks/ember-1":{"draws":5,"losses":12,"wins":31},"gemini-3.1-pro-preview":{"draws":8,"losses":14,"wins":26},"gemini-4-argon":{"draws":1,"losses":37,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":8,"losses":17,"wins":35},"google/gemini-3.5-flash-lite":{"draws":13,"losses":18,"wins":53},"google/gemini-3.6-flash":{"draws":14,"losses":32,"wins":46},"google/gemini-3.8-flash":{"draws":4,"losses":17,"wins":27},"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":9,"losses":9,"wins":24},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":21},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":29},"gpt-5.5":{"draws":11,"losses":13,"wins":20},"gpt-5.6-luna":{"draws":7,"losses":13,"wins":28},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":10,"losses":7,"wins":29},"gpt-6-astra":{"draws":0,"losses":43,"wins":5},"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":36,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":25},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-1.2":{"draws":8,"losses":12,"wins":26},"meta/muse-spark-1.3":{"draws":6,"losses":19,"wins":23},"meta/muse-spark-open":{"draws":8,"losses":13,"wins":25},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":9,"losses":10,"wins":23},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":11},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":2,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":16},"o3":{"draws":7,"losses":12,"wins":47},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":31},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"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":9,"losses":15,"wins":24},"qwen/qwen3.8-27b":{"draws":9,"losses":5,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":8,"losses":16,"wins":24},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":8,"wins":25},"stealth/ox-alpha":{"draws":29,"losses":51,"wins":78},"stealth/space-bunny-alpha":{"draws":8,"losses":7,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":8,"losses":18,"wins":20},"thinkingmachines/inkling":{"draws":15,"losses":7,"wins":42},"thinkingmachines/inkling-small":{"draws":5,"losses":7,"wins":36},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":10,"wins":12},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":23},"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":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":10,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":19,"losses":15,"wins":62},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":14},"z-ai/glm-5.3-flash":{"draws":5,"losses":21,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":20,"wins":24}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":7,"wins":30},"claude-fable-5":{"draws":11,"losses":17,"wins":20},"claude-fable-5-1":{"draws":3,"losses":36,"wins":15},"claude-haiku-5-5":{"draws":13,"losses":15,"wins":18},"claude-opus-4-5":{"draws":14,"losses":17,"wins":47},"claude-opus-4-8":{"draws":11,"losses":12,"wins":21},"claude-opus-5":{"draws":9,"losses":52,"wins":21},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":9,"losses":8,"wins":31},"claude-sonnet-5-5":{"draws":2,"losses":19,"wins":27},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":52},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":13,"wins":27},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":19},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":11,"losses":13,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"gemini-4-argon":{"draws":9,"losses":29,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":10,"losses":12,"wins":38},"google/gemini-3.5-flash-lite":{"draws":17,"losses":10,"wins":57},"google/gemini-3.6-flash":{"draws":14,"losses":26,"wins":52},"google/gemini-3.8-flash":{"draws":12,"losses":13,"wins":23},"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":10,"losses":3,"wins":29},"gpt-5.4":{"draws":12,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":20},"gpt-5.4-nano":{"draws":7,"losses":7,"wins":34},"gpt-5.5":{"draws":9,"losses":7,"wins":28},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":33},"gpt-5.6-sol":{"draws":8,"losses":15,"wins":25},"gpt-5.6-terra":{"draws":8,"losses":3,"wins":35},"gpt-6-astra":{"draws":5,"losses":36,"wins":7},"gpt-6-luna":{"draws":9,"losses":12,"wins":27},"gpt-6-sol":{"draws":3,"losses":36,"wins":9},"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":7,"losses":1,"wins":26},"inception/mercury-3":{"draws":9,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":10,"losses":1,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":18},"meta/muse-spark-open":{"draws":7,"losses":13,"wins":26},"meta/muse-wonder":{"draws":11,"losses":20,"wins":17},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":9,"losses":7,"wins":26},"mistralai/mistral-large-4-0":{"draws":11,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":31,"wins":16},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":17},"o3":{"draws":12,"losses":17,"wins":37},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":7,"wins":31},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":7,"losses":0,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":20,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":10,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":6,"losses":15,"wins":27},"qwen/qwen3.8-max-0902":{"draws":11,"losses":13,"wins":24},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":39,"losses":46,"wins":73},"stealth/space-bunny-alpha":{"draws":7,"losses":7,"wins":24},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":18},"tencent/hy4-preview":{"draws":14,"losses":8,"wins":24},"thinkingmachines/inkling":{"draws":19,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":2},"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":13,"losses":14,"wins":21},"x-ai/grok-4.6":{"draws":12,"losses":5,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":22,"losses":2,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":10,"wins":13},"z-ai/glm-5.2":{"draws":17,"losses":16,"wins":63},"z-ai/glm-5.3":{"draws":8,"losses":17,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":25},"z-ai/glm-5.3-flashx":{"draws":8,"losses":14,"wins":26}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":37},"claude-fable-5":{"draws":0,"losses":12,"wins":30},"claude-fable-5-1":{"draws":1,"losses":31,"wins":14},"claude-haiku-5-5":{"draws":0,"losses":4,"wins":36},"claude-opus-4-5":{"draws":1,"losses":6,"wins":61},"claude-opus-4-8":{"draws":3,"losses":8,"wins":27},"claude-opus-5":{"draws":3,"losses":31,"wins":36},"claude-opus-5-5":{"draws":1,"losses":33,"wins":12},"claude-sonnet-5":{"draws":0,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":0,"losses":15,"wins":27},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":65},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":8,"wins":27},"elorian/glimpse":{"draws":2,"losses":5,"wins":15},"fireworks/ember-1":{"draws":3,"losses":9,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":5,"wins":35},"gemini-4-argon":{"draws":5,"losses":19,"wins":18},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":48},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":71},"google/gemini-3.6-flash":{"draws":2,"losses":11,"wins":67},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":33},"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":1,"wins":44},"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":3,"losses":3,"wins":34},"gpt-6-astra":{"draws":3,"losses":31,"wins":8},"gpt-6-luna":{"draws":0,"losses":6,"wins":36},"gpt-6-sol":{"draws":1,"losses":13,"wins":28},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":16},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":27},"inception/mercury-3":{"draws":2,"losses":1,"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":3,"losses":6,"wins":33},"meta/muse-spark-open":{"draws":0,"losses":6,"wins":34},"meta/muse-wonder":{"draws":5,"losses":10,"wins":27},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":4,"losses":4,"wins":28},"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":2,"losses":4,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":17,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":16},"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":5,"wins":20},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":7,"wins":35},"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":5,"wins":36},"qwen/qwen3.8-max-0902":{"draws":4,"losses":8,"wins":30},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":1,"wins":37},"stealth/ox-alpha":{"draws":5,"losses":16,"wins":119},"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":1,"wins":18},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":31},"thinkingmachines/inkling":{"draws":6,"losses":1,"wins":49},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":39},"unbiased/pareto-26.10":{"draws":1,"losses":8,"wins":5},"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":11,"wins":13},"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":6,"wins":22},"z-ai/glm-5.2":{"draws":4,"losses":9,"wins":71},"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":13,"losses":9,"wins":6},"claude-fable-5":{"draws":9,"losses":21,"wins":0},"claude-fable-5-1":{"draws":1,"losses":30,"wins":1},"claude-haiku-5-5":{"draws":11,"losses":18,"wins":1},"claude-opus-4-5":{"draws":24,"losses":22,"wins":4},"claude-opus-4-8":{"draws":13,"losses":15,"wins":2},"claude-opus-5":{"draws":11,"losses":37,"wins":2},"claude-opus-5-5":{"draws":2,"losses":32,"wins":0},"claude-sonnet-5":{"draws":15,"losses":10,"wins":5},"claude-sonnet-5-5":{"draws":11,"losses":17,"wins":2},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":10},"deepseek/deepseek-v4-pro":{"draws":13,"losses":9,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":11,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":13,"wins":1},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":19,"wins":1},"elorian/glimpse":{"draws":5,"losses":9,"wins":2},"fireworks/ember-1":{"draws":14,"losses":11,"wins":5},"gemini-3.1-pro-preview":{"draws":13,"losses":11,"wins":6},"gemini-4-argon":{"draws":3,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":15,"losses":20,"wins":3},"google/gemini-3.5-flash-lite":{"draws":23,"losses":21,"wins":8},"google/gemini-3.6-flash":{"draws":22,"losses":27,"wins":7},"google/gemini-3.8-flash":{"draws":9,"losses":19,"wins":2},"google/gemma-4-31b-it":{"draws":13,"losses":2,"wins":3},"gpt-4.1":{"draws":6,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":12,"wins":2},"gpt-5.4":{"draws":8,"losses":17,"wins":3},"gpt-5.4-mini":{"draws":8,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":19,"wins":5},"gpt-5.5":{"draws":14,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":18,"losses":9,"wins":3},"gpt-5.6-sol":{"draws":8,"losses":20,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":13,"wins":2},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":18,"losses":10,"wins":2},"gpt-6-sol":{"draws":5,"losses":23,"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":15,"losses":0,"wins":9},"inception/mercury-3":{"draws":12,"losses":9,"wins":1},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":6},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":2},"meta/muse-spark-1.2":{"draws":11,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":9,"losses":20,"wins":1},"meta/muse-spark-open":{"draws":11,"losses":15,"wins":2},"meta/muse-wonder":{"draws":9,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":3},"minimax/minimax-m3.1-flash":{"draws":6,"losses":10,"wins":8},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":0},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":10,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":26,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":5},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":1},"o3":{"draws":9,"losses":21,"wins":8},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":3},"poolside/laguna-s-2.1":{"draws":8,"losses":15,"wins":3},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":3},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":12,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":4},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":1},"qwen/qwen3.8-max":{"draws":14,"losses":10,"wins":6},"qwen/qwen3.8-max-0902":{"draws":15,"losses":11,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":10,"wins":3},"stealth/ox-alpha":{"draws":29,"losses":42,"wins":11},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":3},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":13,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":8,"wins":7},"thinkingmachines/inkling-small":{"draws":17,"losses":6,"wins":7},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"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":14,"losses":14,"wins":2},"x-ai/grok-4.6":{"draws":13,"losses":15,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":20,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":13,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":26,"losses":26,"wins":8},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":20,"wins":4},"z-ai/glm-5.3-flashx":{"draws":15,"losses":14,"wins":1}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":13,"wins":16},"claude-fable-5":{"draws":11,"losses":29,"wins":8},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":15,"losses":36,"wins":27},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":19,"losses":60,"wins":3},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":6,"losses":20,"wins":22},"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":21,"losses":23,"wins":28},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":18,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":22,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":24,"wins":13},"elorian/glimpse":{"draws":3,"losses":13,"wins":10},"fireworks/ember-1":{"draws":9,"losses":19,"wins":20},"gemini-3.1-pro-preview":{"draws":9,"losses":15,"wins":24},"gemini-4-argon":{"draws":7,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":28},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":18},"google/gemini-3.5-flash-lite":{"draws":26,"losses":18,"wins":40},"google/gemini-3.6-flash":{"draws":19,"losses":45,"wins":28},"google/gemini-3.8-flash":{"draws":14,"losses":25,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":15,"losses":14,"wins":13},"gpt-5.4":{"draws":14,"losses":26,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":5,"wins":17},"gpt-5.4-nano":{"draws":9,"losses":17,"wins":22},"gpt-5.5":{"draws":12,"losses":21,"wins":11},"gpt-5.6-luna":{"draws":10,"losses":14,"wins":24},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":20,"losses":17,"wins":9},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":16,"losses":22,"wins":10},"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":8,"losses":7,"wins":19},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"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":10,"losses":17,"wins":25},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":24},"meta/muse-spark-1.2":{"draws":9,"losses":24,"wins":13},"meta/muse-spark-1.3":{"draws":5,"losses":31,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":24,"wins":11},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":16,"wins":19},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":19,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":15,"losses":30,"wins":21},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-max-0902":{"draws":13,"losses":28,"wins":7},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":20,"wins":15},"stealth/ox-alpha":{"draws":43,"losses":78,"wins":37},"stealth/space-bunny-alpha":{"draws":13,"losses":10,"wins":15},"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":7,"losses":9,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":18,"wins":30},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":8,"losses":27,"wins":13},"x-ai/grok-4.6":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":7,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":4},"z-ai/glm-5.2":{"draws":25,"losses":26,"wins":29},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":27,"wins":11}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":34},"claude-fable-5":{"draws":5,"losses":7,"wins":30},"claude-fable-5-1":{"draws":2,"losses":35,"wins":11},"claude-haiku-5-5":{"draws":3,"losses":5,"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":5,"losses":27,"wins":38},"claude-opus-5-5":{"draws":3,"losses":31,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":2,"wins":31},"elorian/glimpse":{"draws":2,"losses":1,"wins":19},"fireworks/ember-1":{"draws":3,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":32},"gemini-4-argon":{"draws":8,"losses":8,"wins":26},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":44},"google/gemini-3.5-flash-lite":{"draws":5,"losses":1,"wins":68},"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},"inception/mercury-3":{"draws":5,"losses":3,"wins":20},"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":7,"losses":3,"wins":30},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":29},"meta/muse-spark-open":{"draws":3,"losses":3,"wins":34},"meta/muse-wonder":{"draws":5,"losses":8,"wins":29},"minimax/minimax-m3":{"draws":5,"losses":0,"wins":17},"minimax/minimax-m3.1-flash":{"draws":2,"losses":2,"wins":32},"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":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":17,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":19},"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":38},"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":{"draws":2,"losses":10,"wins":2},"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":2,"wins":71},"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":3,"losses":15,"wins":26},"claude-fable-5":{"draws":4,"losses":23,"wins":21},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":6,"losses":18,"wins":22},"claude-opus-4-5":{"draws":11,"losses":18,"wins":49},"claude-opus-4-8":{"draws":5,"losses":17,"wins":22},"claude-opus-5":{"draws":12,"losses":52,"wins":18},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":3,"losses":14,"wins":31},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":5,"losses":21,"wins":46},"deepseek/deepseek-v4-pro":{"draws":2,"losses":15,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":10,"wins":30},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":22,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":18},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":7,"losses":17,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":26},"gemini-4-argon":{"draws":3,"losses":37,"wins":8},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":22},"google/gemini-3.5-flash":{"draws":4,"losses":21,"wins":35},"google/gemini-3.5-flash-lite":{"draws":10,"losses":19,"wins":55},"google/gemini-3.6-flash":{"draws":6,"losses":33,"wins":53},"google/gemini-3.8-flash":{"draws":3,"losses":22,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":0,"losses":5,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"gpt-5":{"draws":3,"losses":10,"wins":29},"gpt-5.4":{"draws":2,"losses":20,"wins":24},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":20},"gpt-5.4-nano":{"draws":2,"losses":15,"wins":31},"gpt-5.5":{"draws":3,"losses":18,"wins":23},"gpt-5.6-luna":{"draws":7,"losses":9,"wins":32},"gpt-5.6-sol":{"draws":6,"losses":24,"wins":18},"gpt-5.6-terra":{"draws":5,"losses":16,"wins":25},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":10,"losses":11,"wins":27},"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":4,"losses":7,"wins":23},"inception/mercury-3":{"draws":5,"losses":11,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":9,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":12,"wins":35},"meta/muse-glimmer-30b":{"draws":3,"losses":7,"wins":32},"meta/muse-spark-1.2":{"draws":3,"losses":20,"wins":23},"meta/muse-spark-1.3":{"draws":7,"losses":14,"wins":27},"meta/muse-spark-open":{"draws":4,"losses":20,"wins":22},"meta/muse-wonder":{"draws":7,"losses":24,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":17},"minimax/minimax-m3.1-flash":{"draws":4,"losses":12,"wins":26},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":6,"losses":14,"wins":26},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":14,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":6,"wins":15},"o3":{"draws":5,"losses":31,"wins":30},"openai/gpt-oss-120b":{"draws":3,"losses":8,"wins":31},"poolside/laguna-s-2.1":{"draws":3,"losses":13,"wins":30},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":18},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":16,"wins":28},"qwen/qwen3.8-27b":{"draws":3,"losses":12,"wins":19},"qwen/qwen3.8-flash":{"draws":2,"losses":11,"wins":19},"qwen/qwen3.8-max":{"draws":7,"losses":21,"wins":20},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":14,"wins":26},"stealth/ox-alpha":{"draws":17,"losses":57,"wins":84},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":22},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":23},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":28},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":46},"thinkingmachines/inkling-small":{"draws":6,"losses":9,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"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":5,"losses":19,"wins":24},"x-ai/grok-4.6":{"draws":7,"losses":23,"wins":18},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":15},"x-ai/grok-build-0.1":{"draws":1,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":21,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":14,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":11,"losses":26,"wins":59},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"z-ai/glm-5.3-flash":{"draws":5,"losses":15,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":15,"wins":25}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":7,"wins":33},"claude-fable-5":{"draws":6,"losses":18,"wins":24},"claude-fable-5-1":{"draws":3,"losses":44,"wins":7},"claude-haiku-5-5":{"draws":8,"losses":10,"wins":28},"claude-opus-4-5":{"draws":9,"losses":11,"wins":58},"claude-opus-4-8":{"draws":2,"losses":16,"wins":26},"claude-opus-5":{"draws":9,"losses":52,"wins":21},"claude-opus-5-5":{"draws":7,"losses":39,"wins":6},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":6,"losses":20,"wins":22},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":10,"losses":9,"wins":53},"deepseek/deepseek-v4-pro":{"draws":6,"losses":9,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":8,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":9,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":18,"wins":25},"elorian/glimpse":{"draws":2,"losses":8,"wins":16},"fireworks/ember-1":{"draws":4,"losses":8,"wins":36},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":31},"gemini-4-argon":{"draws":2,"losses":35,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":3,"losses":10,"wins":47},"google/gemini-3.5-flash-lite":{"draws":16,"losses":8,"wins":60},"google/gemini-3.6-flash":{"draws":17,"losses":24,"wins":51},"google/gemini-3.8-flash":{"draws":3,"losses":16,"wins":29},"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":7,"losses":6,"wins":29},"gpt-5.4":{"draws":5,"losses":11,"wins":30},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":34},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":37},"gpt-5.6-sol":{"draws":5,"losses":18,"wins":25},"gpt-5.6-terra":{"draws":7,"losses":8,"wins":31},"gpt-6-astra":{"draws":3,"losses":40,"wins":5},"gpt-6-luna":{"draws":8,"losses":9,"wins":31},"gpt-6-sol":{"draws":4,"losses":24,"wins":20},"gpt-6.1-sol":{"draws":7,"losses":35,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":2,"wins":29},"inception/mercury-3":{"draws":4,"losses":8,"wins":20},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":46},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":31},"meta/muse-spark-1.2":{"draws":7,"losses":10,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":29},"meta/muse-spark-open":{"draws":7,"losses":11,"wins":28},"meta/muse-wonder":{"draws":11,"losses":19,"wins":18},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":17},"minimax/minimax-m3.1-flash":{"draws":6,"losses":8,"wins":28},"mistralai/mistral-large-4-0":{"draws":10,"losses":4,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":8},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":8},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":5,"losses":13,"wins":48},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":33},"poolside/laguna-s-2.1":{"draws":11,"losses":3,"wins":32},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":19},"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":3,"losses":7,"wins":24},"qwen/qwen3.8-flash":{"draws":5,"losses":10,"wins":17},"qwen/qwen3.8-max":{"draws":8,"losses":15,"wins":25},"qwen/qwen3.8-max-0902":{"draws":7,"losses":10,"wins":31},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":9,"wins":31},"stealth/ox-alpha":{"draws":18,"losses":33,"wins":107},"stealth/space-bunny-alpha":{"draws":3,"losses":6,"wins":29},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":30},"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":13,"wins":27},"thinkingmachines/inkling":{"draws":7,"losses":10,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":6,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"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":5,"losses":15,"wins":28},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":59},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":13,"wins":14},"z-ai/glm-5.2":{"draws":15,"losses":14,"wins":67},"z-ai/glm-5.3":{"draws":4,"losses":23,"wins":19},"z-ai/glm-5.3-flash":{"draws":9,"losses":13,"wins":26},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":20}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":13},"claude-fable-5":{"draws":6,"losses":25,"wins":11},"claude-fable-5-1":{"draws":3,"losses":41,"wins":2},"claude-haiku-5-5":{"draws":6,"losses":17,"wins":17},"claude-opus-4-5":{"draws":21,"losses":22,"wins":25},"claude-opus-4-8":{"draws":8,"losses":16,"wins":14},"claude-opus-5":{"draws":10,"losses":52,"wins":12},"claude-opus-5-5":{"draws":2,"losses":39,"wins":5},"claude-sonnet-5":{"draws":14,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":25,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":6},"fireworks/ember-1":{"draws":10,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":9,"losses":18,"wins":15},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":14},"google/gemini-3.5-flash":{"draws":12,"losses":20,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":17,"losses":40,"wins":23},"google/gemini-3.8-flash":{"draws":9,"losses":23,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":4,"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":9,"losses":19,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":12},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":22},"gpt-5.5":{"draws":12,"losses":17,"wins":9},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":29,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":18,"wins":10},"gpt-6-astra":{"draws":2,"losses":37,"wins":3},"gpt-6-luna":{"draws":12,"losses":14,"wins":16},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"gpt-6.1-sol":{"draws":4,"losses":32,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":9,"wins":10},"inception/mercury-3":{"draws":7,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":16},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":13,"wins":22},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":11},"meta/muse-spark-open":{"draws":8,"losses":20,"wins":12},"meta/muse-wonder":{"draws":13,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":15},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":8,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":6},"o3":{"draws":9,"losses":23,"wins":22},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":13,"wins":17},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":5,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":8,"losses":25,"wins":9},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":12},"stealth/ox-alpha":{"draws":33,"losses":72,"wins":35},"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":8,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":6},"thinkingmachines/inkling":{"draws":18,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":12,"losses":10,"wins":20},"unbiased/pareto-26.10":{"draws":2,"losses":12,"wins":0},"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":11,"losses":25,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":22,"wins":7},"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":23,"losses":14,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":11},"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":24,"losses":29,"wins":31},"z-ai/glm-5.3":{"draws":6,"losses":22,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":10}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":8,"wins":29},"claude-fable-5":{"draws":7,"losses":11,"wins":14},"claude-fable-5-1":{"draws":2,"losses":46,"wins":6},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":16,"losses":12,"wins":50},"claude-opus-4-8":{"draws":10,"losses":8,"wins":26},"claude-opus-5":{"draws":10,"losses":47,"wins":25},"claude-opus-5-5":{"draws":5,"losses":38,"wins":9},"claude-sonnet-5":{"draws":8,"losses":10,"wins":30},"claude-sonnet-5-5":{"draws":11,"losses":16,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":18,"wins":20},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":12,"losses":7,"wins":29},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":12,"losses":13,"wins":35},"google/gemini-3.5-flash-lite":{"draws":15,"losses":12,"wins":57},"google/gemini-3.6-flash":{"draws":15,"losses":31,"wins":46},"google/gemini-3.8-flash":{"draws":7,"losses":15,"wins":26},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":18},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":6,"losses":8,"wins":28},"gpt-5.4":{"draws":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":38},"gpt-5.5":{"draws":11,"losses":11,"wins":22},"gpt-5.6-luna":{"draws":11,"losses":7,"wins":30},"gpt-5.6-sol":{"draws":3,"losses":22,"wins":23},"gpt-5.6-terra":{"draws":12,"losses":6,"wins":28},"gpt-6-astra":{"draws":2,"losses":37,"wins":9},"gpt-6-luna":{"draws":11,"losses":8,"wins":29},"gpt-6-sol":{"draws":7,"losses":26,"wins":15},"gpt-6.1-sol":{"draws":5,"losses":30,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":22},"inception/mercury-3":{"draws":8,"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":5,"losses":6,"wins":41},"meta/muse-glimmer-30b":{"draws":7,"losses":5,"wins":30},"meta/muse-spark-1.2":{"draws":6,"losses":10,"wins":30},"meta/muse-spark-1.3":{"draws":11,"losses":16,"wins":21},"meta/muse-spark-open":{"draws":7,"losses":10,"wins":29},"meta/muse-wonder":{"draws":9,"losses":20,"wins":19},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"wins":27},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":7,"losses":10,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":29,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":3,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":14},"o3":{"draws":6,"losses":8,"wins":52},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":25},"poolside/laguna-s-2.1":{"draws":5,"losses":10,"wins":31},"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":15,"losses":11,"wins":22},"qwen/qwen3.8-27b":{"draws":7,"losses":5,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":8,"wins":18},"qwen/qwen3.8-max":{"draws":8,"losses":14,"wins":26},"qwen/qwen3.8-max-0902":{"draws":11,"losses":12,"wins":25},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":8,"wins":24},"stealth/ox-alpha":{"draws":30,"losses":46,"wins":82},"stealth/space-bunny-alpha":{"draws":11,"losses":6,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":9,"losses":8,"wins":29},"thinkingmachines/inkling":{"draws":15,"losses":4,"wins":45},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":10,"losses":16,"wins":22},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":16},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":2,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":8,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":21,"losses":14,"wins":61},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":24},"z-ai/glm-5.3-flashx":{"draws":10,"losses":14,"wins":24}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":1,"wins":41},"claude-fable-5":{"draws":3,"losses":9,"wins":36},"claude-fable-5-1":{"draws":3,"losses":24,"wins":11},"claude-haiku-5-5":{"draws":1,"losses":3,"wins":42},"claude-opus-4-5":{"draws":5,"losses":6,"wins":67},"claude-opus-4-8":{"draws":4,"losses":3,"wins":37},"claude-opus-5":{"draws":4,"losses":36,"wins":42},"claude-opus-5-5":{"draws":2,"losses":36,"wins":14},"claude-sonnet-5":{"draws":3,"losses":3,"wins":42},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":34},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":68},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":8,"wins":35},"elorian/glimpse":{"draws":2,"losses":3,"wins":21},"fireworks/ember-1":{"draws":1,"losses":8,"wins":39},"gemini-3.1-pro-preview":{"draws":2,"losses":2,"wins":44},"gemini-4-argon":{"draws":4,"losses":21,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":52},"google/gemini-3.5-flash-lite":{"draws":6,"losses":0,"wins":78},"google/gemini-3.6-flash":{"draws":8,"losses":11,"wins":73},"google/gemini-3.8-flash":{"draws":1,"losses":8,"wins":39},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":0,"wins":39},"gpt-5.4":{"draws":4,"losses":5,"wins":37},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":46},"gpt-5.5":{"draws":3,"losses":9,"wins":32},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":40},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":36},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":37},"gpt-6-astra":{"draws":5,"losses":33,"wins":10},"gpt-6-luna":{"draws":6,"losses":3,"wins":39},"gpt-6-sol":{"draws":6,"losses":14,"wins":28},"gpt-6.1-sol":{"draws":3,"losses":30,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inception/mercury-3":{"draws":2,"losses":0,"wins":30},"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":2,"losses":2,"wins":48},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":36},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":38},"meta/muse-spark-1.3":{"draws":3,"losses":7,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":8,"wins":34},"meta/muse-wonder":{"draws":3,"losses":14,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":6,"losses":3,"wins":33},"mistralai/mistral-large-4-0":{"draws":3,"losses":2,"wins":25},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":16,"wins":24},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":0,"wins":21},"o3":{"draws":2,"losses":5,"wins":59},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":41},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":43},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":39},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":26},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":42},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":37},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":1,"wins":42},"stealth/ox-alpha":{"draws":9,"losses":13,"wins":136},"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":2,"losses":6,"wins":38},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":58},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":1,"losses":7,"wins":8},"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":6,"wins":39},"x-ai/grok-4.6":{"draws":3,"losses":10,"wins":35},"x-ai/grok-4.7":{"draws":2,"losses":15,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":24},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":2,"wins":25},"z-ai/glm-5.2":{"draws":7,"losses":4,"wins":85},"z-ai/glm-5.3":{"draws":5,"losses":7,"wins":34},"z-ai/glm-5.3-flash":{"draws":3,"losses":8,"wins":37},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":38}},"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":5,"losses":14,"wins":11},"claude-opus-4-5":{"draws":22,"losses":19,"wins":37},"claude-opus-4-8":{"draws":6,"losses":20,"wins":18},"claude-opus-5":{"draws":16,"losses":56,"wins":10},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":20,"wins":20},"elorian/glimpse":{"draws":3,"losses":9,"wins":14},"fireworks/ember-1":{"draws":14,"losses":11,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":24,"wins":22},"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":14,"losses":11,"wins":23},"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":28,"wins":12},"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},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":22},"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-spark-open":{"draws":4,"losses":19,"wins":23},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":3,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":24},"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},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":37,"wins":9},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":12},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":12,"wins":26},"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":{"draws":0,"losses":15,"wins":1},"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":14,"losses":9,"wins":21},"claude-fable-5":{"draws":7,"losses":33,"wins":8},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":20,"wins":15},"claude-opus-4-5":{"draws":20,"losses":14,"wins":28},"claude-opus-4-8":{"draws":13,"losses":16,"wins":15},"claude-opus-5":{"draws":13,"losses":61,"wins":8},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":13,"losses":11,"wins":24},"claude-sonnet-5-5":{"draws":10,"losses":21,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":13,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":25,"wins":14},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":16,"losses":19,"wins":13},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":1,"losses":44,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":23,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":14,"wins":44},"google/gemini-3.6-flash":{"draws":25,"losses":39,"wins":28},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":13},"google/gemma-4-31b-it":{"draws":8,"losses":1,"wins":19},"gpt-4.1":{"draws":5,"losses":4,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":14,"wins":17},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":27},"gpt-5.5":{"draws":18,"losses":17,"wins":9},"gpt-5.6-luna":{"draws":18,"losses":10,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":33,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":15,"losses":12,"wins":21},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"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":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":9,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":34},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":26,"wins":15},"meta/muse-spark-open":{"draws":13,"losses":19,"wins":14},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":10,"losses":13,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":15,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":19,"wins":38},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":12,"losses":8,"wins":12},"qwen/qwen3.8-max":{"draws":12,"losses":21,"wins":15},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":14,"wins":13},"stealth/ox-alpha":{"draws":47,"losses":61,"wins":50},"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":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":15},"thinkingmachines/inkling":{"draws":16,"losses":12,"wins":36},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"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":13,"losses":21,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":11},"x-ai/grok-4.7":{"draws":1,"losses":31,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":30,"wins":39},"z-ai/glm-5.3":{"draws":12,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":10,"losses":24,"wins":14}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":21},"claude-fable-5":{"draws":13,"losses":27,"wins":8},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-5":{"draws":24,"losses":26,"wins":28},"claude-opus-4-8":{"draws":5,"losses":15,"wins":8},"claude-opus-5":{"draws":10,"losses":66,"wins":6},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":13,"losses":22,"wins":13},"claude-sonnet-5-5":{"draws":10,"losses":28,"wins":10},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":23,"losses":17,"wins":32},"deepseek/deepseek-v4-pro":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":24,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":9},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":17},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":24},"google/gemini-3.5-flash-lite":{"draws":25,"losses":12,"wins":47},"google/gemini-3.6-flash":{"draws":21,"losses":44,"wins":27},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":11},"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":4,"losses":0,"wins":2},"gpt-5":{"draws":15,"losses":12,"wins":15},"gpt-5.4":{"draws":16,"losses":20,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":17,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":19,"wins":14},"gpt-6-astra":{"draws":1,"losses":45,"wins":2},"gpt-6-luna":{"draws":15,"losses":16,"wins":17},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":1,"losses":46,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inception/mercury-3":{"draws":11,"losses":12,"wins":9},"inclusionai/ling-3.0-flash":{"draws":17,"losses":0,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":14,"wins":25},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":13},"meta/muse-spark-1.3":{"draws":9,"losses":23,"wins":16},"meta/muse-spark-open":{"draws":13,"losses":20,"wins":13},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":15,"losses":16,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":43,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":2,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":10,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":8},"o3":{"draws":14,"losses":20,"wins":32},"openai/gpt-oss-120b":{"draws":14,"losses":8,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":17,"losses":6,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":15,"wins":15},"stealth/ox-alpha":{"draws":37,"losses":75,"wins":46},"stealth/space-bunny-alpha":{"draws":9,"losses":14,"wins":15},"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":9,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":19,"losses":4,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":14,"losses":19,"wins":15},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":25,"losses":13,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":18,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":36,"losses":24,"wins":36},"z-ai/glm-5.3":{"draws":6,"losses":35,"wins":5},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":8,"losses":25,"wins":15}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":4,"wins":59},"claude-fable-5":{"draws":12,"losses":22,"wins":50},"claude-fable-5-1":{"draws":7,"losses":69,"wins":20},"claude-haiku-5-5":{"draws":14,"losses":14,"wins":52},"claude-opus-4-5":{"draws":26,"losses":7,"wins":103},"claude-opus-4-8":{"draws":13,"losses":10,"wins":53},"claude-opus-5":{"draws":18,"losses":59,"wins":55},"claude-opus-5-5":{"draws":8,"losses":60,"wins":24},"claude-sonnet-5":{"draws":13,"losses":9,"wins":62},"claude-sonnet-5-5":{"draws":8,"losses":30,"wins":46},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":28},"deepseek/deepseek-v4-flash":{"draws":18,"losses":1,"wins":105},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":12,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":16,"wins":54},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":53},"elorian/glimpse":{"draws":8,"losses":9,"wins":31},"fireworks/ember-1":{"draws":10,"losses":12,"wins":62},"gemini-3.1-pro-preview":{"draws":11,"losses":10,"wins":63},"gemini-4-argon":{"draws":11,"losses":46,"wins":27},"google/gemini-3.1-flash-lite":{"draws":11,"losses":1,"wins":40},"google/gemini-3.5-flash":{"draws":14,"losses":7,"wins":83},"google/gemini-3.5-flash-lite":{"draws":22,"losses":11,"wins":111},"google/gemini-3.6-flash":{"draws":20,"losses":28,"wins":112},"google/gemini-3.8-flash":{"draws":7,"losses":19,"wins":58},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":35},"gpt-4.1":{"draws":4,"losses":1,"wins":23},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":10,"losses":5,"wins":61},"gpt-5.4":{"draws":9,"losses":14,"wins":57},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":39},"gpt-5.4-nano":{"draws":8,"losses":3,"wins":69},"gpt-5.5":{"draws":11,"losses":22,"wins":47},"gpt-5.6-luna":{"draws":10,"losses":11,"wins":63},"gpt-5.6-sol":{"draws":16,"losses":22,"wins":46},"gpt-5.6-terra":{"draws":11,"losses":8,"wins":61},"gpt-6-astra":{"draws":6,"losses":58,"wins":20},"gpt-6-luna":{"draws":15,"losses":8,"wins":61},"gpt-6-sol":{"draws":13,"losses":29,"wins":42},"gpt-6.1-sol":{"draws":7,"losses":54,"wins":23},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":39},"inception/mercury-3":{"draws":5,"losses":6,"wins":45},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":48},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":7,"wins":72},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":66},"meta/muse-spark-1.2":{"draws":13,"losses":14,"wins":57},"meta/muse-spark-1.3":{"draws":14,"losses":17,"wins":53},"meta/muse-spark-open":{"draws":11,"losses":13,"wins":56},"meta/muse-wonder":{"draws":9,"losses":32,"wins":43},"minimax/minimax-m3":{"draws":5,"losses":4,"wins":39},"minimax/minimax-m3.1-flash":{"draws":11,"losses":7,"wins":54},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":39},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":22},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":62},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":34,"wins":42},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":38},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":64},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":26},"o3":{"draws":8,"losses":10,"wins":90},"openai/gpt-oss-120b":{"draws":7,"losses":2,"wins":67},"poolside/laguna-s-2.1":{"draws":5,"losses":3,"wins":76},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":37},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":9,"wins":58},"qwen/qwen3.8-27b":{"draws":12,"losses":6,"wins":38},"qwen/qwen3.8-flash":{"draws":8,"losses":3,"wins":45},"qwen/qwen3.8-max":{"draws":14,"losses":5,"wins":65},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":59},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":21},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":5,"wins":62},"stealth/ox-alpha":{"draws":45,"losses":28,"wins":211},"stealth/space-bunny-alpha":{"draws":14,"losses":5,"wins":49},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":51},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":34},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":63},"thinkingmachines/inkling":{"draws":20,"losses":5,"wins":91},"thinkingmachines/inkling-small":{"draws":15,"losses":2,"wins":67},"unbiased/pareto-26.10":{"draws":1,"losses":19,"wins":8},"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":13,"losses":17,"wins":54},"x-ai/grok-4.6":{"draws":16,"losses":15,"wins":53},"x-ai/grok-4.7":{"draws":7,"losses":40,"wins":29},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":20},"xiaomi/mimo-v2.5":{"draws":28,"losses":6,"wins":94},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":1,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":40},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":16,"wins":31},"z-ai/glm-5.2":{"draws":23,"losses":11,"wins":134},"z-ai/glm-5.3":{"draws":9,"losses":23,"wins":48},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":56},"z-ai/glm-5.3-flashx":{"draws":13,"losses":13,"wins":58}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":50},"claude-fable-5":{"draws":3,"losses":2,"wins":49},"claude-fable-5-1":{"draws":6,"losses":23,"wins":31},"claude-haiku-5-5":{"draws":2,"losses":1,"wins":49},"claude-opus-4-5":{"draws":4,"losses":1,"wins":83},"claude-opus-4-8":{"draws":1,"losses":1,"wins":48},"claude-opus-5":{"draws":3,"losses":19,"wins":72},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":0,"wins":54},"claude-sonnet-5-5":{"draws":4,"losses":10,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":81},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":51},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":0,"wins":51},"elorian/glimpse":{"draws":1,"losses":0,"wins":29},"fireworks/ember-1":{"draws":0,"losses":0,"wins":54},"gemini-3.1-pro-preview":{"draws":1,"losses":3,"wins":50},"gemini-4-argon":{"draws":2,"losses":16,"wins":36},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":35},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":68},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":94},"google/gemini-3.6-flash":{"draws":2,"losses":10,"wins":90},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":49},"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":0,"wins":48},"gpt-5.4":{"draws":1,"losses":4,"wins":47},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":35},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":55},"gpt-5.5":{"draws":2,"losses":0,"wins":48},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":51},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":48},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":51},"gpt-6-astra":{"draws":3,"losses":24,"wins":27},"gpt-6-luna":{"draws":0,"losses":1,"wins":53},"gpt-6-sol":{"draws":4,"losses":14,"wins":36},"gpt-6.1-sol":{"draws":2,"losses":21,"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},"inception/mercury-3":{"draws":3,"losses":0,"wins":35},"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":1,"losses":2,"wins":49},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":53},"meta/muse-spark-open":{"draws":0,"losses":0,"wins":52},"meta/muse-wonder":{"draws":2,"losses":7,"wins":45},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":30},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":41},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":30},"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},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":15,"wins":33},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":27},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":1,"wins":25},"o3":{"draws":2,"losses":1,"wins":73},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":47},"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":1,"losses":0,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":54},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":35},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":33},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":52},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":48},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":48},"stealth/ox-alpha":{"draws":6,"losses":2,"wins":166},"stealth/space-bunny-alpha":{"draws":1,"losses":1,"wins":40},"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":3,"wins":48},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":68},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":52},"unbiased/pareto-26.10":{"draws":1,"losses":6,"wins":11},"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":1,"wins":50},"x-ai/grok-4.6":{"draws":1,"losses":2,"wins":51},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":41},"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":0,"losses":0,"wins":34},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":33},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":107},"z-ai/glm-5.3":{"draws":4,"losses":5,"wins":43},"z-ai/glm-5.3-flash":{"draws":4,"losses":3,"wins":47},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":51}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":7,"wins":25},"claude-fable-5":{"draws":7,"losses":36,"wins":5},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":25,"losses":28,"wins":25},"claude-opus-4-8":{"draws":12,"losses":20,"wins":12},"claude-opus-5":{"draws":9,"losses":60,"wins":13},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":9,"losses":15,"wins":8},"claude-sonnet-5-5":{"draws":9,"losses":30,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":18,"wins":34},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":32,"wins":5},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":4,"losses":42,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":17,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":25,"losses":22,"wins":37},"google/gemini-3.6-flash":{"draws":28,"losses":47,"wins":17},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"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":12,"losses":11,"wins":19},"gpt-5.4":{"draws":11,"losses":27,"wins":8},"gpt-5.4-mini":{"draws":16,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":11,"losses":16,"wins":21},"gpt-5.5":{"draws":20,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":12,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":20,"losses":15,"wins":11},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":13,"losses":17,"wins":18},"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":13,"losses":4,"wins":17},"inception/mercury-3":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":14,"losses":3,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":24},"meta/muse-glimmer-30b":{"draws":17,"losses":5,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":13,"losses":25,"wins":10},"meta/muse-spark-open":{"draws":9,"losses":28,"wins":9},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":12,"losses":11,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":3,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":22,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":10,"losses":32,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":7,"wins":23},"poolside/laguna-s-2.1":{"draws":18,"losses":10,"wins":18},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":22,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":15,"wins":10},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-max-0902":{"draws":13,"losses":23,"wins":12},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":17,"wins":16},"stealth/ox-alpha":{"draws":35,"losses":93,"wins":30},"stealth/space-bunny-alpha":{"draws":8,"losses":15,"wins":15},"stepfun/step-3.7-flash":{"draws":7,"losses":10,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":7},"thinkingmachines/inkling":{"draws":22,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":19,"losses":7,"wins":22},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":12,"losses":25,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":24,"wins":11},"x-ai/grok-4.7":{"draws":3,"losses":36,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":17,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":31,"losses":33,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":36,"wins":2},"z-ai/glm-5.3-flash":{"draws":11,"losses":28,"wins":9},"z-ai/glm-5.3-flashx":{"draws":12,"losses":28,"wins":8}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":12,"losses":28,"wins":8},"claude-fable-5-1":{"draws":2,"losses":48,"wins":4},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":22,"losses":24,"wins":32},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":8,"losses":61,"wins":13},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":12,"losses":17,"wins":19},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":11,"wins":41},"deepseek/deepseek-v4-pro":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":14,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":9,"losses":8,"wins":9},"fireworks/ember-1":{"draws":12,"losses":22,"wins":14},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":20},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":13,"losses":19,"wins":28},"google/gemini-3.5-flash-lite":{"draws":24,"losses":16,"wins":44},"google/gemini-3.6-flash":{"draws":21,"losses":39,"wins":32},"google/gemini-3.8-flash":{"draws":6,"losses":25,"wins":17},"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":13,"losses":18,"wins":15},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":11,"losses":21,"wins":12},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":5,"losses":34,"wins":9},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":1,"losses":42,"wins":5},"gpt-6-luna":{"draws":13,"losses":16,"wins":19},"gpt-6-sol":{"draws":3,"losses":34,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":43,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inception/mercury-3":{"draws":9,"losses":11,"wins":12},"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":9,"losses":12,"wins":31},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":14,"wins":18},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":16},"meta/muse-spark-open":{"draws":10,"losses":23,"wins":13},"meta/muse-wonder":{"draws":11,"losses":21,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":23},"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":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":4,"wins":10},"o3":{"draws":7,"losses":15,"wins":44},"openai/gpt-oss-120b":{"draws":14,"losses":7,"wins":21},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"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":17,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":13,"wins":16},"stealth/ox-alpha":{"draws":31,"losses":69,"wins":58},"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":{"draws":1,"losses":14,"wins":1},"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":12,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":29,"wins":9},"x-ai/grok-4.7":{"draws":8,"losses":25,"wins":9},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":11,"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":23,"wins":44},"z-ai/glm-5.3":{"draws":9,"losses":26,"wins":11},"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":9,"losses":13,"wins":12},"claude-fable-5":{"draws":6,"losses":28,"wins":2},"claude-fable-5-1":{"draws":1,"losses":40,"wins":1},"claude-haiku-5-5":{"draws":7,"losses":20,"wins":7},"claude-opus-4-5":{"draws":6,"losses":44,"wins":8},"claude-opus-4-8":{"draws":8,"losses":22,"wins":2},"claude-opus-5":{"draws":6,"losses":48,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":5,"losses":23,"wins":8},"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":12,"losses":20,"wins":20},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":21,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":1},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":7,"losses":22,"wins":7},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":12},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":12},"google/gemini-3.5-flash":{"draws":8,"losses":29,"wins":9},"google/gemini-3.5-flash-lite":{"draws":22,"losses":24,"wins":20},"google/gemini-3.6-flash":{"draws":14,"losses":48,"wins":8},"google/gemini-3.8-flash":{"draws":4,"losses":26,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":11,"wins":5},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":22,"wins":6},"gpt-5.4":{"draws":5,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":10,"wins":8},"gpt-5.4-nano":{"draws":3,"losses":20,"wins":11},"gpt-5.5":{"draws":8,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":17,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":29,"wins":5},"gpt-5.6-terra":{"draws":7,"losses":21,"wins":6},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":21,"wins":7},"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":9,"wins":11},"inception/mercury-3":{"draws":2,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":6,"losses":9,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":4,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":3,"losses":31,"wins":2},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":7},"meta/muse-wonder":{"draws":3,"losses":29,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":8,"losses":15,"wins":9},"mistralai/mistral-large-4-0":{"draws":6,"losses":11,"wins":5},"mistralai/mistral-medium-3-5":{"draws":5,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":10,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":13,"wins":2},"o3":{"draws":5,"losses":36,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":12,"wins":11},"poolside/laguna-s-2.1":{"draws":5,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":29,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":16,"wins":6},"qwen/qwen3.8-flash":{"draws":3,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":5,"losses":28,"wins":3},"qwen/qwen3.8-max-0902":{"draws":4,"losses":27,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":21,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":86,"wins":21},"stealth/space-bunny-alpha":{"draws":7,"losses":16,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":15,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":4},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":13},"thinkingmachines/inkling-small":{"draws":9,"losses":13,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":26,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":13,"losses":18,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":35,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":5,"losses":27,"wins":4}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":51,"wins":37},"claude-fable-5":{"draws":20,"losses":104,"wins":8},"claude-fable-5-1":{"draws":3,"losses":142,"wins":1},"claude-haiku-5-5":{"draws":34,"losses":75,"wins":19},"claude-opus-4-5":{"draws":58,"losses":117,"wins":41},"claude-opus-4-8":{"draws":31,"losses":78,"wins":15},"claude-opus-5":{"draws":24,"losses":187,"wins":11},"claude-opus-5-5":{"draws":6,"losses":135,"wins":3},"claude-sonnet-5":{"draws":36,"losses":71,"wins":25},"claude-sonnet-5-5":{"draws":27,"losses":88,"wins":17},"cohere/north-mini-code":{"draws":10,"losses":21,"wins":19},"deepseek/deepseek-v4-flash":{"draws":49,"losses":57,"wins":52},"deepseek/deepseek-v4-pro":{"draws":30,"losses":67,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":33,"losses":64,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":32,"losses":80,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":93,"wins":15},"elorian/glimpse":{"draws":15,"losses":39,"wins":16},"fireworks/ember-1":{"draws":36,"losses":73,"wins":23},"gemini-3.1-pro-preview":{"draws":33,"losses":67,"wins":32},"gemini-4-argon":{"draws":5,"losses":123,"wins":4},"google/gemini-3.1-flash-lite":{"draws":25,"losses":21,"wins":46},"google/gemini-3.5-flash":{"draws":33,"losses":97,"wins":36},"google/gemini-3.5-flash-lite":{"draws":59,"losses":84,"wins":87},"google/gemini-3.6-flash":{"draws":54,"losses":154,"wins":44},"google/gemini-3.8-flash":{"draws":24,"losses":96,"wins":12},"google/gemma-4-31b-it":{"draws":34,"losses":17,"wins":27},"gpt-4.1":{"draws":12,"losses":24,"wins":8},"gpt-4.1-nano":{"draws":10,"losses":3,"wins":3},"gpt-5":{"draws":32,"losses":56,"wins":28},"gpt-5.4":{"draws":30,"losses":78,"wins":18},"gpt-5.4-mini":{"draws":29,"losses":34,"wins":25},"gpt-5.4-nano":{"draws":24,"losses":64,"wins":52},"gpt-5.5":{"draws":37,"losses":70,"wins":13},"gpt-5.6-luna":{"draws":47,"losses":56,"wins":29},"gpt-5.6-sol":{"draws":17,"losses":110,"wins":5},"gpt-5.6-terra":{"draws":33,"losses":75,"wins":18},"gpt-6-astra":{"draws":3,"losses":125,"wins":4},"gpt-6-luna":{"draws":33,"losses":72,"wins":27},"gpt-6-sol":{"draws":18,"losses":106,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":122,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":36,"losses":22,"wins":36},"inception/mercury-3":{"draws":23,"losses":46,"wins":21},"inclusionai/ling-3.0-flash":{"draws":32,"losses":26,"wins":36},"inclusionai/ling-3.1-flash":{"draws":5,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":34,"losses":52,"wins":58},"meta/muse-glimmer-30b":{"draws":36,"losses":30,"wins":48},"meta/muse-spark-1.2":{"draws":34,"losses":74,"wins":18},"meta/muse-spark-1.3":{"draws":24,"losses":91,"wins":17},"meta/muse-spark-open":{"draws":24,"losses":86,"wins":16},"meta/muse-wonder":{"draws":23,"losses":93,"wins":16},"minimax/minimax-m3":{"draws":17,"losses":28,"wins":29},"minimax/minimax-m3.1-flash":{"draws":27,"losses":56,"wins":31},"mistralai/mistral-large-4-0":{"draws":26,"losses":45,"wins":11},"mistralai/mistral-medium-3-5":{"draws":27,"losses":21,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":17,"wins":8},"moonshotai/kimi-k3":{"draws":38,"losses":68,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":118,"wins":5},"nex-agi/nex-n2-pro":{"draws":13,"losses":23,"wins":30},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":14,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":30,"losses":41,"wins":49},"nvidia/nemotron-3.5-super-vl":{"draws":17,"losses":26,"wins":17},"o3":{"draws":22,"losses":125,"wins":43},"openai/gpt-oss-120b":{"draws":36,"losses":39,"wins":41},"poolside/laguna-s-2.1":{"draws":33,"losses":46,"wins":49},"qwen/qwen3.7-max":{"draws":21,"losses":32,"wins":27},"qwen/qwen3.7-plus":{"draws":17,"losses":27,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":36,"losses":80,"wins":16},"qwen/qwen3.8-27b":{"draws":22,"losses":52,"wins":20},"qwen/qwen3.8-flash":{"draws":23,"losses":42,"wins":23},"qwen/qwen3.8-max":{"draws":35,"losses":73,"wins":24},"qwen/qwen3.8-max-0902":{"draws":36,"losses":77,"wins":19},"recursive/flint-v1.0":{"draws":9,"losses":11,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":73,"wins":21},"stealth/ox-alpha":{"draws":95,"losses":251,"wins":70},"stealth/space-bunny-alpha":{"draws":31,"losses":51,"wins":22},"stepfun/step-3.7-flash":{"draws":21,"losses":35,"wins":40},"stepfun/step-5-preview":{"draws":3,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":26,"losses":26,"wins":20},"tencent/hy4-preview":{"draws":27,"losses":77,"wins":22},"thinkingmachines/inkling":{"draws":47,"losses":67,"wins":60},"thinkingmachines/inkling-small":{"draws":45,"losses":33,"wins":54},"unbiased/pareto-26.10":{"draws":3,"losses":41,"wins":0},"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":21,"losses":95,"wins":16},"x-ai/grok-4.6":{"draws":29,"losses":92,"wins":11},"x-ai/grok-4.7":{"draws":11,"losses":98,"wins":9},"x-ai/grok-build-0.1":{"draws":13,"losses":12,"wins":19},"xiaomi/mimo-v2.5":{"draws":60,"losses":73,"wins":75},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":32,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":56,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":63,"wins":13},"z-ai/glm-5.2":{"draws":76,"losses":121,"wins":67},"z-ai/glm-5.3":{"draws":26,"losses":91,"wins":9},"z-ai/glm-5.3-flash":{"draws":24,"losses":78,"wins":30},"z-ai/glm-5.3-flashx":{"draws":29,"losses":77,"wins":26}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":6,"wins":28},"claude-fable-5":{"draws":8,"losses":27,"wins":13},"claude-fable-5-1":{"draws":3,"losses":47,"wins":4},"claude-haiku-5-5":{"draws":8,"losses":20,"wins":18},"claude-opus-4-5":{"draws":22,"losses":18,"wins":38},"claude-opus-4-8":{"draws":9,"losses":19,"wins":16},"claude-opus-5":{"draws":8,"losses":58,"wins":16},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":16,"wins":40},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":28,"wins":10},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":23},"google/gemini-3.5-flash-lite":{"draws":13,"losses":24,"wins":47},"google/gemini-3.6-flash":{"draws":20,"losses":31,"wins":41},"google/gemini-3.8-flash":{"draws":6,"losses":27,"wins":15},"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":13,"wins":23},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":11,"wins":28},"gpt-5.5":{"draws":9,"losses":20,"wins":15},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":13},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":20},"gpt-6-astra":{"draws":4,"losses":38,"wins":6},"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":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":9,"losses":10,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":39},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":26},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":22},"meta/muse-spark-1.3":{"draws":7,"losses":24,"wins":17},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":11},"meta/muse-wonder":{"draws":7,"losses":29,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":9,"losses":11,"wins":22},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":12},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":20,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":39,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":6,"losses":23,"wins":37},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":26},"poolside/laguna-s-2.1":{"draws":7,"losses":10,"wins":29},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":19,"wins":16},"qwen/qwen3.8-27b":{"draws":9,"losses":7,"wins":18},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":20,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":39,"losses":62,"wins":57},"stealth/space-bunny-alpha":{"draws":10,"losses":9,"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":4,"wins":14},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":16},"thinkingmachines/inkling":{"draws":20,"losses":6,"wins":38},"thinkingmachines/inkling-small":{"draws":15,"losses":6,"wins":27},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":9,"losses":26,"wins":13},"x-ai/grok-4.6":{"draws":7,"losses":26,"wins":15},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":7,"wins":46},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":16},"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":26,"losses":23,"wins":47},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":15},"z-ai/glm-5.3-flash":{"draws":8,"losses":22,"wins":18},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":17}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"claude-fable-5":{"draws":5,"losses":33,"wins":10},"claude-fable-5-1":{"draws":1,"losses":51,"wins":2},"claude-haiku-5-5":{"draws":10,"losses":24,"wins":12},"claude-opus-4-5":{"draws":21,"losses":30,"wins":27},"claude-opus-4-8":{"draws":11,"losses":16,"wins":17},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":16,"losses":14,"wins":18},"claude-sonnet-5-5":{"draws":9,"losses":28,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":15},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":12},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":11,"losses":26,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":19,"wins":18},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":23},"google/gemini-3.5-flash":{"draws":14,"losses":28,"wins":18},"google/gemini-3.5-flash-lite":{"draws":24,"losses":17,"wins":43},"google/gemini-3.6-flash":{"draws":19,"losses":47,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":11},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":17,"wins":14},"gpt-5.4":{"draws":7,"losses":28,"wins":11},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":25},"gpt-5.5":{"draws":11,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":14,"losses":18,"wins":16},"gpt-5.6-sol":{"draws":5,"losses":34,"wins":9},"gpt-5.6-terra":{"draws":9,"losses":21,"wins":16},"gpt-6-astra":{"draws":1,"losses":47,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"wins":15},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":4,"losses":43,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":17},"inception/mercury-3":{"draws":11,"losses":10,"wins":11},"inclusionai/ling-3.0-flash":{"draws":15,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":12,"losses":6,"wins":24},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":24,"wins":13},"meta/muse-spark-open":{"draws":8,"losses":28,"wins":10},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":7,"losses":16,"wins":19},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":19,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":37,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":10,"losses":22,"wins":34},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":19},"poolside/laguna-s-2.1":{"draws":10,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":18,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":16,"wins":8},"qwen/qwen3.8-flash":{"draws":8,"losses":16,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":21,"wins":10},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":38,"losses":68,"wins":52},"stealth/space-bunny-alpha":{"draws":11,"losses":10,"wins":17},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":9,"losses":22,"wins":15},"thinkingmachines/inkling":{"draws":23,"losses":14,"wins":27},"thinkingmachines/inkling-small":{"draws":11,"losses":9,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":9,"losses":28,"wins":11},"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":24,"losses":14,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":13,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":15,"wins":9},"z-ai/glm-5.2":{"draws":30,"losses":31,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":5,"losses":30,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":24},"claude-fable-5":{"draws":13,"losses":23,"wins":12},"claude-fable-5-1":{"draws":6,"losses":43,"wins":5},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":18,"losses":22,"wins":38},"claude-opus-4-8":{"draws":9,"losses":12,"wins":23},"claude-opus-5":{"draws":17,"losses":52,"wins":13},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":11,"losses":15,"wins":22},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":20,"losses":12,"wins":40},"deepseek/deepseek-v4-pro":{"draws":13,"losses":14,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":13,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":25,"wins":11},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":15,"losses":16,"wins":17},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":25},"gemini-4-argon":{"draws":8,"losses":35,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":18,"wins":27},"google/gemini-3.5-flash-lite":{"draws":31,"losses":7,"wins":46},"google/gemini-3.6-flash":{"draws":32,"losses":32,"wins":28},"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":14,"losses":10,"wins":18},"gpt-5.4":{"draws":14,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":18,"losses":9,"wins":21},"gpt-5.5":{"draws":14,"losses":17,"wins":13},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":23,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":12,"wins":17},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":15,"losses":11,"wins":22},"gpt-6-sol":{"draws":7,"losses":30,"wins":11},"gpt-6.1-sol":{"draws":6,"losses":36,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":4,"wins":15},"inception/mercury-3":{"draws":11,"losses":6,"wins":15},"inclusionai/ling-3.0-flash":{"draws":19,"losses":3,"wins":12},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":13,"wins":30},"meta/muse-glimmer-30b":{"draws":16,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":15,"losses":13,"wins":18},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":18},"meta/muse-spark-open":{"draws":13,"losses":13,"wins":20},"meta/muse-wonder":{"draws":16,"losses":19,"wins":13},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":13,"losses":7,"wins":22},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":5,"wins":10},"o3":{"draws":15,"losses":16,"wins":35},"openai/gpt-oss-120b":{"draws":15,"losses":4,"wins":23},"poolside/laguna-s-2.1":{"draws":20,"losses":6,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":12},"qwen/qwen3.7-plus":{"draws":11,"losses":1,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":24},"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":12,"losses":17,"wins":19},"qwen/qwen3.8-max-0902":{"draws":18,"losses":15,"wins":15},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":10,"wins":23},"stealth/ox-alpha":{"draws":34,"losses":63,"wins":61},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"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":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":17,"losses":5,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":17,"losses":18,"wins":13},"x-ai/grok-4.7":{"draws":8,"losses":24,"wins":10},"x-ai/grok-build-0.1":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":29,"losses":7,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":39,"losses":18,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":27,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":18,"wins":23},"z-ai/glm-5.3-flashx":{"draws":7,"losses":23,"wins":18}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":7,"losses":20,"wins":21},"claude-fable-5-1":{"draws":3,"losses":45,"wins":6},"claude-haiku-5-5":{"draws":5,"losses":19,"wins":22},"claude-opus-4-5":{"draws":11,"losses":15,"wins":52},"claude-opus-4-8":{"draws":6,"losses":11,"wins":27},"claude-opus-5":{"draws":11,"losses":56,"wins":15},"claude-opus-5-5":{"draws":4,"losses":43,"wins":5},"claude-sonnet-5":{"draws":10,"losses":9,"wins":29},"claude-sonnet-5-5":{"draws":9,"losses":18,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":12,"losses":10,"wins":50},"deepseek/deepseek-v4-pro":{"draws":9,"losses":6,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":11,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":14,"wins":16},"elorian/glimpse":{"draws":5,"losses":7,"wins":14},"fireworks/ember-1":{"draws":10,"losses":9,"wins":29},"gemini-3.1-pro-preview":{"draws":10,"losses":14,"wins":24},"gemini-4-argon":{"draws":5,"losses":37,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":14,"wins":37},"google/gemini-3.5-flash-lite":{"draws":9,"losses":10,"wins":65},"google/gemini-3.6-flash":{"draws":16,"losses":33,"wins":43},"google/gemini-3.8-flash":{"draws":7,"losses":13,"wins":28},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":21},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":6,"wins":28},"gpt-5.4":{"draws":10,"losses":14,"wins":22},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":33},"gpt-5.5":{"draws":11,"losses":14,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":6,"wins":32},"gpt-5.6-sol":{"draws":7,"losses":21,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":29},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":10,"losses":10,"wins":28},"gpt-6-sol":{"draws":6,"losses":31,"wins":11},"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":8,"losses":4,"wins":22},"inception/mercury-3":{"draws":5,"losses":5,"wins":22},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":3,"wins":33},"meta/muse-spark-1.2":{"draws":8,"losses":13,"wins":25},"meta/muse-spark-1.3":{"draws":7,"losses":16,"wins":25},"meta/muse-spark-open":{"draws":8,"losses":14,"wins":24},"meta/muse-wonder":{"draws":9,"losses":17,"wins":22},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":7,"wins":30},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":11},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":3,"wins":16},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":8,"losses":6,"wins":28},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":31},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":25},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":23},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":9,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":12,"losses":13,"wins":23},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":9,"wins":27},"stealth/ox-alpha":{"draws":21,"losses":54,"wins":83},"stealth/space-bunny-alpha":{"draws":5,"losses":3,"wins":30},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":14,"wins":23},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":47},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":38},"unbiased/pareto-26.10":{"draws":3,"losses":12,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":13,"wins":3},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.6":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":14},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":12,"losses":4,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":5,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":17,"losses":11,"wins":68},"z-ai/glm-5.3":{"draws":6,"losses":27,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":8,"wins":30}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":7,"wins":28},"claude-fable-5":{"draws":7,"losses":16,"wins":25},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":9,"losses":12,"wins":25},"claude-opus-4-5":{"draws":23,"losses":9,"wins":46},"claude-opus-4-8":{"draws":9,"losses":7,"wins":28},"claude-opus-5":{"draws":10,"losses":49,"wins":23},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":9,"losses":11,"wins":28},"claude-sonnet-5-5":{"draws":12,"losses":18,"wins":18},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":18,"losses":8,"wins":46},"deepseek/deepseek-v4-pro":{"draws":11,"losses":6,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":10,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":16,"wins":19},"elorian/glimpse":{"draws":1,"losses":2,"wins":7},"fireworks/ember-1":{"draws":13,"losses":10,"wins":25},"gemini-3.1-pro-preview":{"draws":13,"losses":10,"wins":25},"gemini-4-argon":{"draws":7,"losses":30,"wins":11},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":35},"google/gemini-3.5-flash-lite":{"draws":23,"losses":4,"wins":57},"google/gemini-3.6-flash":{"draws":19,"losses":25,"wins":48},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":26},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":3,"losses":1,"wins":12},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":8,"wins":27},"gpt-5.4":{"draws":13,"losses":17,"wins":16},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":19},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":12,"losses":11,"wins":21},"gpt-5.6-luna":{"draws":14,"losses":5,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":26},"gpt-6-astra":{"draws":4,"losses":37,"wins":7},"gpt-6-luna":{"draws":9,"losses":10,"wins":29},"gpt-6-sol":{"draws":8,"losses":26,"wins":14},"gpt-6.1-sol":{"draws":3,"losses":35,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":23},"inception/mercury-3":{"draws":8,"losses":5,"wins":19},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":11,"wins":24},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":23},"meta/muse-spark-open":{"draws":9,"losses":7,"wins":30},"meta/muse-wonder":{"draws":12,"losses":18,"wins":18},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":4,"wins":25},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":15,"losses":7,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":28,"wins":13},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":1,"wins":14},"o3":{"draws":7,"losses":8,"wins":51},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":13,"losses":5,"wins":28},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":18},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":8,"wins":26},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":9,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":5,"wins":27},"stealth/ox-alpha":{"draws":47,"losses":40,"wins":71},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":27},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":27},"thinkingmachines/inkling":{"draws":21,"losses":3,"wins":40},"thinkingmachines/inkling-small":{"draws":13,"losses":0,"wins":35},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":2},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":25},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":22},"x-ai/grok-4.7":{"draws":5,"losses":22,"wins":15},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":0,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":18},"z-ai/glm-5.2":{"draws":27,"losses":14,"wins":55},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":15,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":12,"wins":24}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":5,"wins":26},"claude-fable-5":{"draws":13,"losses":30,"wins":5},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":15,"losses":24,"wins":7},"claude-opus-4-5":{"draws":29,"losses":21,"wins":28},"claude-opus-4-8":{"draws":16,"losses":15,"wins":13},"claude-opus-5":{"draws":10,"losses":59,"wins":13},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":13,"losses":18,"wins":17},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":22,"losses":13,"wins":37},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":27,"wins":7},"elorian/glimpse":{"draws":7,"losses":7,"wins":12},"fireworks/ember-1":{"draws":8,"losses":8,"wins":16},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":25},"google/gemini-3.5-flash-lite":{"draws":31,"losses":8,"wins":45},"google/gemini-3.6-flash":{"draws":27,"losses":29,"wins":36},"google/gemini-3.8-flash":{"draws":8,"losses":21,"wins":19},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":9,"wins":23},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":14,"losses":10,"wins":24},"gpt-5.5":{"draws":17,"losses":14,"wins":13},"gpt-5.6-luna":{"draws":17,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":14,"losses":11,"wins":23},"gpt-6-sol":{"draws":7,"losses":34,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":3,"wins":20},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":32},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":18,"losses":17,"wins":13},"meta/muse-spark-open":{"draws":10,"losses":18,"wins":18},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":21},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":12,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"o3":{"draws":12,"losses":16,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":13},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":12},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":20,"wins":11},"stealth/ox-alpha":{"draws":45,"losses":52,"wins":61},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"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":11,"losses":21,"wins":14},"thinkingmachines/inkling":{"draws":22,"losses":4,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":21,"wins":17},"x-ai/grok-4.6":{"draws":15,"losses":20,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":25,"losses":11,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":18,"wins":6},"z-ai/glm-5.2":{"draws":28,"losses":22,"wins":46},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":17}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":12,"wins":18},"claude-fable-5":{"draws":11,"losses":27,"wins":10},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":19,"wins":13},"claude-opus-4-5":{"draws":23,"losses":37,"wins":18},"claude-opus-4-8":{"draws":14,"losses":23,"wins":7},"claude-opus-5":{"draws":9,"losses":67,"wins":6},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":16,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":13,"losses":25,"wins":10},"gemini-3.1-pro-preview":{"draws":8,"losses":13,"wins":11},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":20},"google/gemini-3.5-flash":{"draws":13,"losses":33,"wins":14},"google/gemini-3.5-flash-lite":{"draws":34,"losses":22,"wins":28},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":25},"google/gemini-3.8-flash":{"draws":10,"losses":32,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":5,"wins":9},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":13,"wins":15},"gpt-5.4":{"draws":12,"losses":22,"wins":12},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":10,"losses":24,"wins":10},"gpt-5.6-luna":{"draws":13,"losses":19,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":16,"losses":17,"wins":15},"gpt-6-sol":{"draws":4,"losses":39,"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":17,"losses":7,"wins":10},"inception/mercury-3":{"draws":11,"losses":16,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":17,"wins":22},"meta/muse-glimmer-30b":{"draws":19,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":19,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":27,"wins":10},"meta/muse-spark-open":{"draws":11,"losses":25,"wins":10},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":11},"minimax/minimax-m3.1-flash":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-large-4-0":{"draws":7,"losses":14,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":26,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":11,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"o3":{"draws":15,"losses":29,"wins":22},"openai/gpt-oss-120b":{"draws":13,"losses":10,"wins":19},"poolside/laguna-s-2.1":{"draws":18,"losses":12,"wins":16},"qwen/qwen3.7-max":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":24,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":25,"wins":13},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":13},"stealth/ox-alpha":{"draws":42,"losses":77,"wins":39},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":13},"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":9,"losses":10,"wins":7},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":30,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":32,"losses":18,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":20,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":40,"wins":31},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":12,"losses":28,"wins":8}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":38},"claude-fable-5":{"draws":3,"losses":15,"wins":30},"claude-fable-5-1":{"draws":5,"losses":40,"wins":9},"claude-haiku-5-5":{"draws":7,"losses":9,"wins":30},"claude-opus-4-5":{"draws":5,"losses":7,"wins":66},"claude-opus-4-8":{"draws":5,"losses":8,"wins":31},"claude-opus-5":{"draws":12,"losses":43,"wins":27},"claude-opus-5-5":{"draws":1,"losses":38,"wins":13},"claude-sonnet-5":{"draws":7,"losses":4,"wins":37},"claude-sonnet-5-5":{"draws":5,"losses":17,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":2,"wins":63},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":2,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":34},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":10,"wins":29},"elorian/glimpse":{"draws":6,"losses":3,"wins":17},"fireworks/ember-1":{"draws":7,"losses":4,"wins":37},"gemini-3.1-pro-preview":{"draws":5,"losses":5,"wins":38},"gemini-4-argon":{"draws":7,"losses":16,"wins":9},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":7,"losses":4,"wins":73},"google/gemini-3.6-flash":{"draws":11,"losses":13,"wins":68},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":35},"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":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":2,"wins":38},"gpt-5.4":{"draws":8,"losses":13,"wins":25},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":25},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":44},"gpt-5.5":{"draws":5,"losses":8,"wins":31},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":29},"gpt-5.6-terra":{"draws":7,"losses":3,"wins":36},"gpt-6-astra":{"draws":4,"losses":35,"wins":9},"gpt-6-luna":{"draws":6,"losses":5,"wins":37},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":5,"losses":34,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":6,"losses":4,"wins":22},"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":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":36},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":34},"meta/muse-spark-1.3":{"draws":7,"losses":7,"wins":34},"meta/muse-spark-open":{"draws":4,"losses":10,"wins":32},"meta/muse-wonder":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":10,"losses":4,"wins":28},"mistralai/mistral-large-4-0":{"draws":2,"losses":4,"wins":24},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":9},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":24,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"o3":{"draws":1,"losses":4,"wins":61},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":42},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":9,"wins":35},"qwen/qwen3.8-27b":{"draws":5,"losses":2,"wins":27},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":20},"qwen/qwen3.8-max":{"draws":7,"losses":6,"wins":35},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":37},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":6,"wins":34},"stealth/ox-alpha":{"draws":18,"losses":22,"wins":118},"stealth/space-bunny-alpha":{"draws":4,"losses":1,"wins":33},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":32},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":8,"losses":4,"wins":34},"thinkingmachines/inkling":{"draws":8,"losses":3,"wins":53},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":4},"unbiased/pareto-26.10-preview":{"draws":0,"losses":11,"wins":5},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":9,"losses":9,"wins":30},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":26},"x-ai/grok-4.7":{"draws":8,"losses":16,"wins":18},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5":{"draws":8,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":16},"z-ai/glm-5.2":{"draws":14,"losses":4,"wins":78},"z-ai/glm-5.3":{"draws":5,"losses":19,"wins":22},"z-ai/glm-5.3-flash":{"draws":8,"losses":4,"wins":36},"z-ai/glm-5.3-flashx":{"draws":5,"losses":11,"wins":32}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":15,"wins":10},"claude-fable-5":{"draws":5,"losses":31,"wins":0},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":23,"wins":4},"claude-opus-4-5":{"draws":13,"losses":46,"wins":1},"claude-opus-4-8":{"draws":12,"losses":21,"wins":3},"claude-opus-5":{"draws":8,"losses":48,"wins":2},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":14,"losses":21,"wins":1},"claude-sonnet-5-5":{"draws":8,"losses":21,"wins":7},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":14,"losses":31,"wins":9},"deepseek/deepseek-v4-pro":{"draws":9,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":11,"wins":2},"fireworks/ember-1":{"draws":6,"losses":26,"wins":4},"gemini-3.1-pro-preview":{"draws":9,"losses":17,"wins":10},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":8,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":10},"google/gemini-3.5-flash-lite":{"draws":19,"losses":24,"wins":23},"google/gemini-3.6-flash":{"draws":15,"losses":46,"wins":9},"google/gemini-3.8-flash":{"draws":10,"losses":26,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":11,"wins":7},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":20,"wins":4},"gpt-5.4":{"draws":6,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":9,"losses":22,"wins":9},"gpt-5.5":{"draws":8,"losses":24,"wins":2},"gpt-5.6-luna":{"draws":6,"losses":23,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":32,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":2},"gpt-6-astra":{"draws":0,"losses":36,"wins":0},"gpt-6-luna":{"draws":10,"losses":22,"wins":4},"gpt-6-sol":{"draws":7,"losses":27,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":35,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":10,"losses":9,"wins":7},"inception/mercury-3":{"draws":3,"losses":12,"wins":7},"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":7,"losses":21,"wins":14},"meta/muse-glimmer-30b":{"draws":12,"losses":11,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":22,"wins":4},"meta/muse-spark-1.3":{"draws":5,"losses":30,"wins":1},"meta/muse-spark-open":{"draws":7,"losses":29,"wins":0},"meta/muse-wonder":{"draws":5,"losses":30,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":6},"minimax/minimax-m3.1-flash":{"draws":8,"losses":20,"wins":4},"mistralai/mistral-large-4-0":{"draws":7,"losses":15,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":9,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":22,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":9,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":13,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":12,"wins":2},"o3":{"draws":11,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":10,"losses":14,"wins":6},"poolside/laguna-s-2.1":{"draws":8,"losses":12,"wins":12},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":11,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":26,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":3},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":27,"wins":0},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":0},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":26,"wins":0},"stealth/ox-alpha":{"draws":20,"losses":70,"wins":12},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":5},"stepfun/step-3.7-flash":{"draws":6,"losses":18,"wins":4},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":3},"thinkingmachines/inkling":{"draws":13,"losses":22,"wins":13},"thinkingmachines/inkling-small":{"draws":11,"losses":11,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":7,"losses":28,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":24,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":16,"losses":24,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":17,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":16,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":20,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":46,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":32,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":25,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":22,"wins":4}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":28},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":7,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":17,"wins":19},"claude-opus-4-5":{"draws":21,"losses":16,"wins":41},"claude-opus-4-8":{"draws":9,"losses":15,"wins":20},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":5,"losses":45,"wins":2},"claude-sonnet-5":{"draws":9,"losses":12,"wins":27},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":21},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":14},"deepseek/deepseek-v4-flash":{"draws":21,"losses":10,"wins":41},"deepseek/deepseek-v4-pro":{"draws":10,"losses":10,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":8,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":9,"losses":15,"wins":24},"gemini-3.1-pro-preview":{"draws":7,"losses":13,"wins":28},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":25},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":8,"wins":59},"google/gemini-3.6-flash":{"draws":18,"losses":37,"wins":37},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":15},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":16},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":10,"wins":26},"gpt-5.4":{"draws":7,"losses":24,"wins":15},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":8,"wins":33},"gpt-5.5":{"draws":12,"losses":19,"wins":13},"gpt-5.6-luna":{"draws":18,"losses":8,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":12},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":23},"gpt-6-astra":{"draws":0,"losses":46,"wins":2},"gpt-6-luna":{"draws":12,"losses":15,"wins":21},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":23},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":32},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":29},"meta/muse-spark-1.2":{"draws":9,"losses":18,"wins":19},"meta/muse-spark-1.3":{"draws":9,"losses":24,"wins":15},"meta/muse-spark-open":{"draws":10,"losses":15,"wins":21},"meta/muse-wonder":{"draws":11,"losses":27,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":10,"losses":8,"wins":24},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":6,"losses":17,"wins":43},"openai/gpt-oss-120b":{"draws":8,"losses":8,"wins":26},"poolside/laguna-s-2.1":{"draws":9,"losses":3,"wins":34},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":21},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":17,"wins":18},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":24,"losses":57,"wins":77},"stealth/space-bunny-alpha":{"draws":9,"losses":5,"wins":24},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"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":7,"losses":20,"wins":19},"thinkingmachines/inkling":{"draws":17,"losses":6,"wins":41},"thinkingmachines/inkling-small":{"draws":12,"losses":8,"wins":28},"unbiased/pareto-26.10":{"draws":3,"losses":12,"wins":1},"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":9,"losses":16,"wins":23},"x-ai/grok-4.6":{"draws":12,"losses":25,"wins":11},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":22,"wins":53},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":16},"z-ai/glm-5.3-flash":{"draws":7,"losses":24,"wins":17},"z-ai/glm-5.3-flashx":{"draws":13,"losses":16,"wins":19}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":26,"losses":34,"wins":20},"claude-fable-5":{"draws":13,"losses":66,"wins":5},"claude-fable-5-1":{"draws":6,"losses":87,"wins":1},"claude-haiku-5-5":{"draws":20,"losses":48,"wins":12},"claude-opus-4-5":{"draws":47,"losses":75,"wins":14},"claude-opus-4-8":{"draws":24,"losses":50,"wins":2},"claude-opus-5":{"draws":20,"losses":114,"wins":10},"claude-opus-5-5":{"draws":6,"losses":86,"wins":0},"claude-sonnet-5":{"draws":23,"losses":48,"wins":13},"claude-sonnet-5-5":{"draws":15,"losses":58,"wins":11},"cohere/north-mini-code":{"draws":11,"losses":14,"wins":7},"deepseek/deepseek-v4-flash":{"draws":36,"losses":57,"wins":31},"deepseek/deepseek-v4-pro":{"draws":20,"losses":38,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":45,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":49,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":12,"losses":28,"wins":6},"fireworks/ember-1":{"draws":31,"losses":44,"wins":9},"gemini-3.1-pro-preview":{"draws":29,"losses":41,"wins":14},"gemini-4-argon":{"draws":7,"losses":77,"wins":0},"google/gemini-3.1-flash-lite":{"draws":17,"losses":15,"wins":24},"google/gemini-3.5-flash":{"draws":23,"losses":61,"wins":22},"google/gemini-3.5-flash-lite":{"draws":35,"losses":50,"wins":37},"google/gemini-3.6-flash":{"draws":43,"losses":97,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":63,"wins":4},"google/gemma-4-31b-it":{"draws":20,"losses":14,"wins":14},"gpt-4.1":{"draws":9,"losses":16,"wins":3},"gpt-4.1-nano":{"draws":6,"losses":3,"wins":1},"gpt-5":{"draws":21,"losses":34,"wins":19},"gpt-5.4":{"draws":22,"losses":50,"wins":10},"gpt-5.4-mini":{"draws":20,"losses":26,"wins":10},"gpt-5.4-nano":{"draws":20,"losses":35,"wins":29},"gpt-5.5":{"draws":29,"losses":42,"wins":7},"gpt-5.6-luna":{"draws":25,"losses":43,"wins":16},"gpt-5.6-sol":{"draws":12,"losses":69,"wins":3},"gpt-5.6-terra":{"draws":22,"losses":52,"wins":6},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":24,"losses":40,"wins":20},"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":19,"losses":24,"wins":15},"inception/mercury-3":{"draws":17,"losses":28,"wins":9},"inclusionai/ling-3.0-flash":{"draws":21,"losses":20,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":42,"wins":24},"meta/muse-glimmer-30b":{"draws":27,"losses":23,"wins":24},"meta/muse-spark-1.2":{"draws":18,"losses":50,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":63,"wins":8},"meta/muse-spark-open":{"draws":13,"losses":62,"wins":7},"meta/muse-wonder":{"draws":15,"losses":63,"wins":6},"minimax/minimax-m3":{"draws":11,"losses":15,"wins":18},"minimax/minimax-m3.1-flash":{"draws":19,"losses":36,"wins":19},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":19,"losses":16,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":31,"losses":41,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":68,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":19,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":6,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":31,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":24,"wins":4},"o3":{"draws":18,"losses":86,"wins":14},"openai/gpt-oss-120b":{"draws":21,"losses":32,"wins":19},"poolside/laguna-s-2.1":{"draws":24,"losses":43,"wins":15},"qwen/qwen3.7-max":{"draws":12,"losses":26,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":50,"wins":6},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":29,"wins":5},"qwen/qwen3.8-max":{"draws":26,"losses":47,"wins":11},"qwen/qwen3.8-max-0902":{"draws":21,"losses":56,"wins":7},"recursive/flint-v1.0":{"draws":6,"losses":5,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":48,"wins":6},"stealth/ox-alpha":{"draws":65,"losses":180,"wins":37},"stealth/space-bunny-alpha":{"draws":17,"losses":38,"wins":11},"stepfun/step-3.7-flash":{"draws":17,"losses":30,"wins":13},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":24,"wins":7},"tencent/hy4-preview":{"draws":24,"losses":43,"wins":15},"thinkingmachines/inkling":{"draws":28,"losses":50,"wins":36},"thinkingmachines/inkling-small":{"draws":24,"losses":26,"wins":34},"unbiased/pareto-26.10":{"draws":1,"losses":27,"wins":0},"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":21,"losses":55,"wins":8},"x-ai/grok-4.6":{"draws":21,"losses":56,"wins":7},"x-ai/grok-4.7":{"draws":7,"losses":58,"wins":7},"x-ai/grok-build-0.1":{"draws":13,"losses":12,"wins":3},"xiaomi/mimo-v2.5":{"draws":36,"losses":61,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":41,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":44,"wins":6},"z-ai/glm-5.2":{"draws":56,"losses":78,"wins":34},"z-ai/glm-5.3":{"draws":17,"losses":61,"wins":2},"z-ai/glm-5.3-flash":{"draws":19,"losses":51,"wins":14},"z-ai/glm-5.3-flashx":{"draws":17,"losses":55,"wins":12}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":12,"wins":49},"claude-fable-5":{"draws":12,"losses":43,"wins":29},"claude-fable-5-1":{"draws":4,"losses":82,"wins":10},"claude-haiku-5-5":{"draws":13,"losses":31,"wins":36},"claude-opus-4-5":{"draws":34,"losses":31,"wins":71},"claude-opus-4-8":{"draws":16,"losses":26,"wins":34},"claude-opus-5":{"draws":14,"losses":89,"wins":37},"claude-opus-5-5":{"draws":5,"losses":70,"wins":13},"claude-sonnet-5":{"draws":21,"losses":23,"wins":40},"claude-sonnet-5-5":{"draws":12,"losses":34,"wins":38},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":26},"deepseek/deepseek-v4-flash":{"draws":24,"losses":18,"wins":82},"deepseek/deepseek-v4-pro":{"draws":18,"losses":27,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":18,"wins":47},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":25,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":35,"wins":36},"elorian/glimpse":{"draws":9,"losses":14,"wins":23},"fireworks/ember-1":{"draws":17,"losses":34,"wins":33},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":46},"gemini-4-argon":{"draws":5,"losses":61,"wins":18},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":46},"google/gemini-3.5-flash":{"draws":21,"losses":32,"wins":53},"google/gemini-3.5-flash-lite":{"draws":37,"losses":25,"wins":88},"google/gemini-3.6-flash":{"draws":29,"losses":45,"wins":62},"google/gemini-3.8-flash":{"draws":15,"losses":39,"wins":30},"google/gemma-4-31b-it":{"draws":13,"losses":7,"wins":28},"gpt-4.1":{"draws":7,"losses":4,"wins":17},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":14,"losses":15,"wins":45},"gpt-5.4":{"draws":16,"losses":30,"wins":36},"gpt-5.4-mini":{"draws":17,"losses":8,"wins":31},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":58},"gpt-5.5":{"draws":17,"losses":31,"wins":30},"gpt-5.6-luna":{"draws":24,"losses":11,"wins":49},"gpt-5.6-sol":{"draws":10,"losses":50,"wins":24},"gpt-5.6-terra":{"draws":19,"losses":15,"wins":46},"gpt-6-astra":{"draws":6,"losses":71,"wins":7},"gpt-6-luna":{"draws":19,"losses":25,"wins":40},"gpt-6-sol":{"draws":8,"losses":51,"wins":25},"gpt-6.1-sol":{"draws":4,"losses":69,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":17,"losses":5,"wins":36},"inception/mercury-3":{"draws":14,"losses":11,"wins":27},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":40},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":20,"losses":7,"wins":65},"meta/muse-glimmer-30b":{"draws":18,"losses":11,"wins":45},"meta/muse-spark-1.2":{"draws":15,"losses":28,"wins":37},"meta/muse-spark-1.3":{"draws":7,"losses":40,"wins":37},"meta/muse-spark-open":{"draws":19,"losses":28,"wins":35},"meta/muse-wonder":{"draws":14,"losses":42,"wins":28},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":31},"minimax/minimax-m3.1-flash":{"draws":18,"losses":14,"wins":46},"mistralai/mistral-large-4-0":{"draws":10,"losses":19,"wins":23},"mistralai/mistral-medium-3-5":{"draws":12,"losses":6,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":10},"moonshotai/kimi-k3":{"draws":21,"losses":24,"wins":35},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":60,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":31},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":43},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":5,"wins":22},"o3":{"draws":15,"losses":26,"wins":79},"openai/gpt-oss-120b":{"draws":19,"losses":10,"wins":43},"poolside/laguna-s-2.1":{"draws":16,"losses":13,"wins":49},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":30},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":24,"wins":40},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":33},"qwen/qwen3.8-flash":{"draws":14,"losses":14,"wins":28},"qwen/qwen3.8-max":{"draws":17,"losses":28,"wins":39},"qwen/qwen3.8-max-0902":{"draws":15,"losses":32,"wins":37},"recursive/flint-v1.0":{"draws":8,"losses":0,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":23,"wins":35},"stealth/ox-alpha":{"draws":51,"losses":105,"wins":128},"stealth/space-bunny-alpha":{"draws":18,"losses":9,"wins":41},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":44},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":24},"tencent/hy4-preview":{"draws":19,"losses":26,"wins":37},"thinkingmachines/inkling":{"draws":29,"losses":15,"wins":72},"thinkingmachines/inkling-small":{"draws":19,"losses":12,"wins":53},"unbiased/pareto-26.10":{"draws":2,"losses":24,"wins":2},"unbiased/pareto-26.10-preview":{"draws":1,"losses":24,"wins":3},"upstage/solar-mini4":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":18,"losses":29,"wins":37},"x-ai/grok-4.6":{"draws":21,"losses":35,"wins":28},"x-ai/grok-4.7":{"draws":4,"losses":46,"wins":22},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":19},"xiaomi/mimo-v2.5":{"draws":35,"losses":10,"wins":83},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":19,"wins":25},"z-ai/glm-5.2":{"draws":36,"losses":47,"wins":85},"z-ai/glm-5.3":{"draws":14,"losses":44,"wins":22},"z-ai/glm-5.3-flash":{"draws":8,"losses":44,"wins":32},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":40}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":27},"claude-fable-5":{"draws":6,"losses":17,"wins":25},"claude-fable-5-1":{"draws":2,"losses":48,"wins":4},"claude-haiku-5-5":{"draws":11,"losses":13,"wins":22},"claude-opus-4-5":{"draws":28,"losses":12,"wins":38},"claude-opus-4-8":{"draws":13,"losses":11,"wins":20},"claude-opus-5":{"draws":11,"losses":51,"wins":20},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":6,"wins":49},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":12,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":23,"wins":14},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":15,"losses":12,"wins":21},"gemini-3.1-pro-preview":{"draws":13,"losses":8,"wins":27},"gemini-4-argon":{"draws":12,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":10,"losses":14,"wins":36},"google/gemini-3.5-flash-lite":{"draws":20,"losses":4,"wins":60},"google/gemini-3.6-flash":{"draws":23,"losses":25,"wins":44},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":14},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":13,"wins":20},"gpt-5.4":{"draws":10,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":9,"losses":4,"wins":19},"gpt-5.4-nano":{"draws":9,"losses":8,"wins":31},"gpt-5.5":{"draws":21,"losses":13,"wins":10},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":14},"gpt-5.6-terra":{"draws":11,"losses":13,"wins":22},"gpt-6-astra":{"draws":4,"losses":41,"wins":3},"gpt-6-luna":{"draws":14,"losses":14,"wins":20},"gpt-6-sol":{"draws":8,"losses":30,"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":14,"losses":0,"wins":20},"inception/mercury-3":{"draws":9,"losses":9,"wins":14},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":26},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":35},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":26},"meta/muse-spark-1.2":{"draws":10,"losses":24,"wins":12},"meta/muse-spark-1.3":{"draws":15,"losses":14,"wins":19},"meta/muse-spark-open":{"draws":9,"losses":19,"wins":18},"meta/muse-wonder":{"draws":12,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":19},"minimax/minimax-m3.1-flash":{"draws":7,"losses":8,"wins":27},"mistralai/mistral-large-4-0":{"draws":11,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":11,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":32,"wins":11},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":0,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":7,"wins":13},"o3":{"draws":8,"losses":20,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":22},"qwen/qwen3.8-flash":{"draws":6,"losses":9,"wins":17},"qwen/qwen3.8-max":{"draws":12,"losses":15,"wins":21},"qwen/qwen3.8-max-0902":{"draws":18,"losses":11,"wins":19},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":12,"wins":22},"stealth/ox-alpha":{"draws":34,"losses":44,"wins":80},"stealth/space-bunny-alpha":{"draws":7,"losses":8,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":22},"thinkingmachines/inkling":{"draws":21,"losses":5,"wins":38},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":31},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"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":10,"losses":22,"wins":16},"x-ai/grok-4.6":{"draws":21,"losses":16,"wins":11},"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":23,"losses":3,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":5,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":10,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":25,"losses":16,"wins":55},"z-ai/glm-5.3":{"draws":8,"losses":22,"wins":16},"z-ai/glm-5.3-flash":{"draws":5,"losses":16,"wins":27},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":32,"wins":6},"elorian/glimpse":{"draws":6,"losses":13,"wins":7},"fireworks/ember-1":{"draws":19,"losses":21,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":15,"losses":28,"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},"inception/mercury-3":{"draws":13,"losses":13,"wins":6},"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":13,"losses":18,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":30,"wins":6},"meta/muse-spark-open":{"draws":12,"losses":30,"wins":4},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":11,"losses":7,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":17,"wins":15},"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},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":8,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"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},"recursive/flint-v1.0":{"draws":3,"losses":5,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":21,"wins":10},"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":{"draws":1,"losses":15,"wins":0},"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":9,"losses":30,"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":33,"losses":19,"wins":22},"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":8,"losses":16,"wins":16},"claude-fable-5":{"draws":5,"losses":29,"wins":8},"claude-fable-5-1":{"draws":2,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":22,"wins":6},"claude-opus-4-5":{"draws":13,"losses":32,"wins":23},"claude-opus-4-8":{"draws":7,"losses":22,"wins":9},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":12,"losses":15,"wins":15},"claude-sonnet-5-5":{"draws":6,"losses":27,"wins":9},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":18,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":24,"wins":8},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":8,"losses":22,"wins":12},"gemini-3.1-pro-preview":{"draws":11,"losses":17,"wins":14},"gemini-4-argon":{"draws":3,"losses":33,"wins":6},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":14,"losses":26,"wins":36},"google/gemini-3.6-flash":{"draws":8,"losses":42,"wins":32},"google/gemini-3.8-flash":{"draws":5,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":11},"gpt-4.1":{"draws":3,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":6},"gpt-5.4":{"draws":7,"losses":25,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":10,"wins":12},"gpt-5.4-nano":{"draws":2,"losses":21,"wins":19},"gpt-5.5":{"draws":9,"losses":18,"wins":13},"gpt-5.6-luna":{"draws":11,"losses":15,"wins":16},"gpt-5.6-sol":{"draws":3,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":18,"wins":13},"gpt-6-astra":{"draws":3,"losses":38,"wins":1},"gpt-6-luna":{"draws":11,"losses":19,"wins":12},"gpt-6-sol":{"draws":2,"losses":35,"wins":5},"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},"inception/mercury-3":{"draws":1,"losses":20,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":13},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":29},"meta/muse-glimmer-30b":{"draws":9,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":8,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":9},"meta/muse-spark-open":{"draws":6,"losses":28,"wins":8},"meta/muse-wonder":{"draws":7,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":11,"wins":17},"mistralai/mistral-large-4-0":{"draws":8,"losses":15,"wins":3},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":18,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":9,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":11,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":8,"losses":23,"wins":33},"openai/gpt-oss-120b":{"draws":8,"losses":9,"wins":19},"poolside/laguna-s-2.1":{"draws":4,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":3,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":21,"wins":10},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":3,"losses":31,"wins":8},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":8},"recursive/flint-v1.0":{"draws":1,"losses":5,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":29,"losses":63,"wins":50},"stealth/space-bunny-alpha":{"draws":5,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":6},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":11,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":9,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":9,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":27,"wins":7},"x-ai/grok-build-0.1":{"draws":1,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":18,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":21,"losses":27,"wins":36},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":8},"z-ai/glm-5.3-flash":{"draws":4,"losses":26,"wins":12},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":8}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":25},"claude-fable-5":{"draws":10,"losses":25,"wins":13},"claude-fable-5-1":{"draws":4,"losses":45,"wins":5},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":15},"claude-opus-4-5":{"draws":25,"losses":14,"wins":39},"claude-opus-4-8":{"draws":13,"losses":15,"wins":16},"claude-opus-5":{"draws":7,"losses":62,"wins":13},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":17,"losses":10,"wins":21},"claude-sonnet-5-5":{"draws":15,"losses":22,"wins":11},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":8},"deepseek/deepseek-v4-flash":{"draws":21,"losses":13,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":17,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":23,"wins":15},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":15,"losses":15,"wins":18},"gemini-3.1-pro-preview":{"draws":15,"losses":13,"wins":20},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":8,"losses":23,"wins":29},"google/gemini-3.5-flash-lite":{"draws":21,"losses":17,"wins":46},"google/gemini-3.6-flash":{"draws":21,"losses":41,"wins":30},"google/gemini-3.8-flash":{"draws":11,"losses":20,"wins":17},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":16,"wins":19},"gpt-5.4":{"draws":8,"losses":10,"wins":12},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":20},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":29},"gpt-5.5":{"draws":9,"losses":19,"wins":16},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":14},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"gpt-6-astra":{"draws":3,"losses":37,"wins":8},"gpt-6-luna":{"draws":13,"losses":14,"wins":21},"gpt-6-sol":{"draws":4,"losses":38,"wins":6},"gpt-6.1-sol":{"draws":4,"losses":38,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":8,"losses":9,"wins":15},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":10,"wins":30},"meta/muse-glimmer-30b":{"draws":15,"losses":4,"wins":23},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":18,"wins":15},"meta/muse-spark-open":{"draws":8,"losses":24,"wins":14},"meta/muse-wonder":{"draws":15,"losses":20,"wins":13},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":16},"minimax/minimax-m3.1-flash":{"draws":13,"losses":6,"wins":23},"mistralai/mistral-large-4-0":{"draws":12,"losses":5,"wins":13},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":9,"losses":13,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":8,"losses":13,"wins":45},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":19},"poolside/laguna-s-2.1":{"draws":11,"losses":9,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":22,"wins":18},"qwen/qwen3.8-27b":{"draws":6,"losses":6,"wins":22},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.8-max":{"draws":11,"losses":19,"wins":18},"qwen/qwen3.8-max-0902":{"draws":14,"losses":16,"wins":18},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":43,"losses":54,"wins":61},"stealth/space-bunny-alpha":{"draws":11,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":20},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":16,"wins":18},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":15,"losses":5,"wins":28},"unbiased/pareto-26.10":{"draws":3,"losses":11,"wins":2},"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":13,"losses":16,"wins":19},"x-ai/grok-4.6":{"draws":17,"losses":17,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":10},"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":8,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":14,"wins":14},"z-ai/glm-5.2":{"draws":30,"losses":20,"wins":46},"z-ai/glm-5.3":{"draws":11,"losses":24,"wins":11},"z-ai/glm-5.3-flash":{"draws":7,"losses":22,"wins":19},"z-ai/glm-5.3-flashx":{"draws":9,"losses":21,"wins":18}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":11,"wins":21},"claude-fable-5":{"draws":9,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":23,"wins":10},"claude-opus-4-5":{"draws":20,"losses":33,"wins":25},"claude-opus-4-8":{"draws":10,"losses":13,"wins":21},"claude-opus-5":{"draws":10,"losses":63,"wins":9},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":17,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":7,"losses":29,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":37},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":19,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":32,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":13,"losses":24,"wins":11},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"gemini-4-argon":{"draws":6,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":4,"wins":23},"google/gemini-3.5-flash":{"draws":16,"losses":17,"wins":27},"google/gemini-3.5-flash-lite":{"draws":24,"losses":15,"wins":45},"google/gemini-3.6-flash":{"draws":20,"losses":45,"wins":27},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":11},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":17},"gpt-4.1":{"draws":5,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":10,"wins":24},"gpt-5.4":{"draws":12,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":19,"wins":22},"gpt-5.5":{"draws":20,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":17},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":11},"gpt-5.6-terra":{"draws":17,"losses":14,"wins":15},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":16,"wins":11},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":42,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":16},"inception/mercury-3":{"draws":8,"losses":18,"wins":6},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":31},"meta/muse-glimmer-30b":{"draws":17,"losses":0,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":15},"meta/muse-spark-1.3":{"draws":9,"losses":29,"wins":10},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":12},"meta/muse-wonder":{"draws":10,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":13,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":9,"wins":8},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":15,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":9,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":6},"o3":{"draws":9,"losses":29,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":29},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":24,"wins":11},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-max":{"draws":11,"losses":23,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":19,"wins":15},"stealth/ox-alpha":{"draws":32,"losses":79,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":16},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":17},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":12,"losses":24,"wins":12},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":10},"x-ai/grok-4.7":{"draws":6,"losses":31,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":13,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":9,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":19,"wins":8},"z-ai/glm-5.2":{"draws":29,"losses":33,"wins":34},"z-ai/glm-5.3":{"draws":5,"losses":34,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":26,"wins":11}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":28,"wins":26},"claude-fable-5":{"draws":6,"losses":55,"wins":11},"claude-fable-5-1":{"draws":2,"losses":76,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":38,"wins":24},"claude-opus-4-5":{"draws":30,"losses":50,"wins":40},"claude-opus-4-8":{"draws":11,"losses":42,"wins":19},"claude-opus-5":{"draws":11,"losses":93,"wins":12},"claude-opus-5-5":{"draws":2,"losses":77,"wins":1},"claude-sonnet-5":{"draws":10,"losses":37,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":52,"wins":12},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":20},"deepseek/deepseek-v4-flash":{"draws":20,"losses":37,"wins":55},"deepseek/deepseek-v4-pro":{"draws":6,"losses":36,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":31,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":36,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":46,"wins":16},"elorian/glimpse":{"draws":5,"losses":18,"wins":15},"fireworks/ember-1":{"draws":15,"losses":34,"wins":23},"gemini-3.1-pro-preview":{"draws":13,"losses":34,"wins":25},"gemini-4-argon":{"draws":2,"losses":66,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":9,"wins":39},"google/gemini-3.5-flash":{"draws":11,"losses":49,"wins":34},"google/gemini-3.5-flash-lite":{"draws":17,"losses":55,"wins":56},"google/gemini-3.6-flash":{"draws":20,"losses":82,"wins":36},"google/gemini-3.8-flash":{"draws":8,"losses":48,"wins":16},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":26},"gpt-4.1":{"draws":3,"losses":11,"wins":10},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":7,"losses":30,"wins":27},"gpt-5.4":{"draws":7,"losses":44,"wins":19},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":28},"gpt-5.4-nano":{"draws":4,"losses":26,"wins":30},"gpt-5.5":{"draws":12,"losses":35,"wins":19},"gpt-5.6-luna":{"draws":13,"losses":30,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":55,"wins":11},"gpt-5.6-terra":{"draws":8,"losses":36,"wins":24},"gpt-6-astra":{"draws":0,"losses":70,"wins":2},"gpt-6-luna":{"draws":12,"losses":31,"wins":29},"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":5,"wins":33},"inception/mercury-3":{"draws":11,"losses":21,"wins":16},"inclusionai/ling-3.0-flash":{"draws":11,"losses":18,"wins":23},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":22,"wins":52},"meta/muse-glimmer-30b":{"draws":11,"losses":21,"wins":30},"meta/muse-spark-1.2":{"draws":11,"losses":32,"wins":25},"meta/muse-spark-1.3":{"draws":11,"losses":40,"wins":21},"meta/muse-spark-open":{"draws":11,"losses":42,"wins":17},"meta/muse-wonder":{"draws":7,"losses":55,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":27,"wins":27},"mistralai/mistral-large-4-0":{"draws":8,"losses":23,"wins":13},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":15,"losses":32,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":11,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":8,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":24,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":14,"wins":15},"o3":{"draws":7,"losses":46,"wins":65},"openai/gpt-oss-120b":{"draws":11,"losses":23,"wins":28},"poolside/laguna-s-2.1":{"draws":6,"losses":24,"wins":38},"qwen/qwen3.7-max":{"draws":6,"losses":19,"wins":21},"qwen/qwen3.7-plus":{"draws":7,"losses":16,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":40,"wins":15},"qwen/qwen3.8-27b":{"draws":6,"losses":25,"wins":21},"qwen/qwen3.8-flash":{"draws":7,"losses":23,"wins":18},"qwen/qwen3.8-max":{"draws":17,"losses":37,"wins":18},"qwen/qwen3.8-max-0902":{"draws":14,"losses":38,"wins":20},"recursive/flint-v1.0":{"draws":3,"losses":10,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":30,"wins":24},"stealth/ox-alpha":{"draws":28,"losses":103,"wins":71},"stealth/space-bunny-alpha":{"draws":13,"losses":20,"wins":25},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":34},"stepfun/step-5-preview":{"draws":1,"losses":5,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":16},"tencent/hy4-preview":{"draws":8,"losses":41,"wins":21},"thinkingmachines/inkling":{"draws":17,"losses":29,"wins":48},"thinkingmachines/inkling-small":{"draws":18,"losses":18,"wins":36},"unbiased/pareto-26.10":{"draws":2,"losses":20,"wins":2},"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":14,"losses":38,"wins":20},"x-ai/grok-4.6":{"draws":8,"losses":51,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":54,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":15},"xiaomi/mimo-v2.5":{"draws":24,"losses":35,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":17,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":25,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":31,"wins":11},"z-ai/glm-5.2":{"draws":24,"losses":59,"wins":61},"z-ai/glm-5.3":{"draws":7,"losses":47,"wins":14},"z-ai/glm-5.3-flash":{"draws":9,"losses":38,"wins":25},"z-ai/glm-5.3-flashx":{"draws":10,"losses":41,"wins":21}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":9,"wins":18},"claude-fable-5":{"draws":11,"losses":22,"wins":15},"claude-fable-5-1":{"draws":2,"losses":48,"wins":4},"claude-haiku-5-5":{"draws":20,"losses":19,"wins":7},"claude-opus-4-5":{"draws":34,"losses":17,"wins":27},"claude-opus-4-8":{"draws":12,"losses":13,"wins":19},"claude-opus-5":{"draws":12,"losses":54,"wins":16},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":19,"losses":9,"wins":20},"claude-sonnet-5-5":{"draws":11,"losses":22,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":12,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":19,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":20,"wins":13},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":17,"losses":16,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":23},"gemini-4-argon":{"draws":2,"losses":41,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":24},"google/gemini-3.5-flash":{"draws":17,"losses":19,"wins":24},"google/gemini-3.5-flash-lite":{"draws":30,"losses":18,"wins":36},"google/gemini-3.6-flash":{"draws":22,"losses":36,"wins":34},"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":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":10,"wins":20},"gpt-5.4":{"draws":12,"losses":18,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":10,"losses":18,"wins":20},"gpt-5.5":{"draws":9,"losses":9,"wins":10},"gpt-5.6-luna":{"draws":19,"losses":7,"wins":22},"gpt-5.6-sol":{"draws":10,"losses":22,"wins":16},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":19},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":20,"losses":10,"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},"inception/mercury-3":{"draws":10,"losses":8,"wins":14},"inclusionai/ling-3.0-flash":{"draws":13,"losses":5,"wins":16},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":17,"losses":7,"wins":18},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":13,"losses":17,"wins":18},"meta/muse-spark-open":{"draws":11,"losses":20,"wins":15},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":11,"losses":11,"wins":20},"mistralai/mistral-large-4-0":{"draws":11,"losses":7,"wins":12},"mistralai/mistral-medium-3-5":{"draws":8,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":9,"losses":16,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":9},"o3":{"draws":13,"losses":20,"wins":33},"openai/gpt-oss-120b":{"draws":18,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":15,"losses":13,"wins":18},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":16,"wins":17},"qwen/qwen3.8-max-0902":{"draws":19,"losses":14,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":8,"wins":24},"stealth/ox-alpha":{"draws":39,"losses":69,"wins":50},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":2,"wins":13},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":15,"wins":29},"thinkingmachines/inkling-small":{"draws":17,"losses":9,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":3},"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":8,"losses":23,"wins":17},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":14},"x-ai/grok-4.7":{"draws":2,"losses":26,"wins":14},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":29,"losses":13,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":7,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":12},"z-ai/glm-5.2":{"draws":35,"losses":19,"wins":42},"z-ai/glm-5.3":{"draws":13,"losses":26,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":16}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":17},"claude-fable-5":{"draws":11,"losses":34,"wins":3},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":28,"losses":31,"wins":19},"claude-opus-4-8":{"draws":10,"losses":25,"wins":9},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":6,"losses":46,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":13},"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":23,"losses":20,"wins":29},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":23,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":31,"wins":6},"elorian/glimpse":{"draws":8,"losses":13,"wins":5},"fireworks/ember-1":{"draws":15,"losses":19,"wins":14},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":19},"gemini-4-argon":{"draws":5,"losses":41,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":16},"google/gemini-3.5-flash-lite":{"draws":22,"losses":20,"wins":42},"google/gemini-3.6-flash":{"draws":28,"losses":44,"wins":20},"google/gemini-3.8-flash":{"draws":12,"losses":31,"wins":5},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":3,"losses":8,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":18,"wins":11},"gpt-5.4":{"draws":14,"losses":25,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":13,"losses":13,"wins":22},"gpt-5.5":{"draws":16,"losses":19,"wins":9},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":14},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":10,"losses":23,"wins":13},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":16,"losses":18,"wins":14},"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":15,"losses":3,"wins":16},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"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":13,"losses":12,"wins":27},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":23},"meta/muse-spark-1.2":{"draws":13,"losses":22,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":26,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":26,"wins":11},"meta/muse-wonder":{"draws":9,"losses":34,"wins":5},"minimax/minimax-m3":{"draws":10,"losses":2,"wins":14},"minimax/minimax-m3.1-flash":{"draws":9,"losses":18,"wins":15},"mistralai/mistral-large-4-0":{"draws":13,"losses":15,"wins":2},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":23,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":8,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":9,"wins":6},"o3":{"draws":15,"losses":23,"wins":28},"openai/gpt-oss-120b":{"draws":15,"losses":8,"wins":19},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":24,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":9,"losses":11,"wins":12},"qwen/qwen3.8-max":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.8-max-0902":{"draws":15,"losses":21,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":21,"wins":9},"stealth/ox-alpha":{"draws":48,"losses":75,"wins":35},"stealth/space-bunny-alpha":{"draws":8,"losses":16,"wins":14},"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":6,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":25,"wins":10},"thinkingmachines/inkling":{"draws":17,"losses":14,"wins":33},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":26,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":31,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":29,"losses":9,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":16,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":21,"wins":6},"z-ai/glm-5.2":{"draws":28,"losses":35,"wins":33},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":7},"z-ai/glm-5.3-flash":{"draws":12,"losses":28,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":22,"wins":14}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":32},"claude-fable-5":{"draws":7,"losses":20,"wins":21},"claude-fable-5-1":{"draws":4,"losses":49,"wins":1},"claude-haiku-5-5":{"draws":9,"losses":15,"wins":22},"claude-opus-4-5":{"draws":17,"losses":11,"wins":50},"claude-opus-4-8":{"draws":5,"losses":13,"wins":26},"claude-opus-5":{"draws":15,"losses":49,"wins":18},"claude-opus-5-5":{"draws":3,"losses":44,"wins":5},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"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":12,"losses":6,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":9,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":18,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":16,"wins":25},"elorian/glimpse":{"draws":2,"losses":7,"wins":17},"fireworks/ember-1":{"draws":6,"losses":11,"wins":31},"gemini-3.1-pro-preview":{"draws":4,"losses":17,"wins":27},"gemini-4-argon":{"draws":6,"losses":30,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":29},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":41},"google/gemini-3.5-flash-lite":{"draws":10,"losses":10,"wins":64},"google/gemini-3.6-flash":{"draws":8,"losses":27,"wins":57},"google/gemini-3.8-flash":{"draws":5,"losses":17,"wins":26},"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":9,"losses":14,"wins":23},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":25},"gpt-5.4-nano":{"draws":3,"losses":8,"wins":37},"gpt-5.5":{"draws":8,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":4,"losses":9,"wins":35},"gpt-5.6-sol":{"draws":4,"losses":21,"wins":7},"gpt-5.6-terra":{"draws":10,"losses":6,"wins":30},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":8,"losses":10,"wins":30},"gpt-6-sol":{"draws":4,"losses":31,"wins":13},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":5,"losses":7,"wins":20},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":6,"wins":39},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":35},"meta/muse-spark-1.2":{"draws":6,"losses":15,"wins":25},"meta/muse-spark-1.3":{"draws":9,"losses":16,"wins":23},"meta/muse-spark-open":{"draws":8,"losses":17,"wins":21},"meta/muse-wonder":{"draws":10,"losses":22,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":22},"minimax/minimax-m3.1-flash":{"draws":5,"losses":9,"wins":28},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":16},"mistralai/mistral-medium-3-5":{"draws":1,"losses":3,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":10},"moonshotai/kimi-k3":{"draws":12,"losses":10,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":30,"wins":10},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":33},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":15},"o3":{"draws":4,"losses":11,"wins":51},"openai/gpt-oss-120b":{"draws":1,"losses":4,"wins":37},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":11,"wins":31},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":24},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":21},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":6,"losses":11,"wins":31},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":35},"stealth/ox-alpha":{"draws":21,"losses":35,"wins":102},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"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":2,"wins":17},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":26},"thinkingmachines/inkling":{"draws":8,"losses":8,"wins":48},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":6,"losses":15,"wins":27},"x-ai/grok-4.6":{"draws":9,"losses":22,"wins":17},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":5,"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":11,"losses":15,"wins":70},"z-ai/glm-5.3":{"draws":9,"losses":15,"wins":22},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":21},"z-ai/glm-5.3-flashx":{"draws":8,"losses":15,"wins":25}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":22},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":23,"losses":25,"wins":30},"claude-opus-4-8":{"draws":8,"losses":21,"wins":15},"claude-opus-5":{"draws":8,"losses":69,"wins":5},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":14,"losses":14,"wins":20},"claude-sonnet-5-5":{"draws":8,"losses":29,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":20,"losses":14,"wins":38},"deepseek/deepseek-v4-pro":{"draws":16,"losses":13,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":24,"wins":13},"elorian/glimpse":{"draws":6,"losses":10,"wins":10},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":14,"losses":14,"wins":20},"gemini-4-argon":{"draws":7,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":11,"losses":19,"wins":30},"google/gemini-3.5-flash-lite":{"draws":21,"losses":15,"wins":48},"google/gemini-3.6-flash":{"draws":20,"losses":46,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":18,"wins":16},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":14},"gpt-4.1":{"draws":8,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":9,"wins":25},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":9,"losses":15,"wins":24},"gpt-5.5":{"draws":15,"losses":17,"wins":12},"gpt-5.6-luna":{"draws":12,"losses":16,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":10,"losses":11,"wins":9},"gpt-6-astra":{"draws":4,"losses":42,"wins":2},"gpt-6-luna":{"draws":9,"losses":23,"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":12,"losses":2,"wins":20},"inception/mercury-3":{"draws":9,"losses":11,"wins":12},"inclusionai/ling-3.0-flash":{"draws":12,"losses":1,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":13,"wins":28},"meta/muse-glimmer-30b":{"draws":13,"losses":5,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":25,"wins":14},"meta/muse-spark-open":{"draws":10,"losses":20,"wins":16},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":14,"losses":14,"wins":14},"mistralai/mistral-large-4-0":{"draws":10,"losses":11,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":21,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":7,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":8},"o3":{"draws":11,"losses":24,"wins":31},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":4,"wins":28},"qwen/qwen3.7-max":{"draws":7,"losses":9,"wins":12},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":21,"wins":11},"qwen/qwen3.8-27b":{"draws":9,"losses":9,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-max-0902":{"draws":16,"losses":17,"wins":15},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":16},"stealth/ox-alpha":{"draws":41,"losses":67,"wins":50},"stealth/space-bunny-alpha":{"draws":9,"losses":11,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":19},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":11,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":13,"losses":10,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":21,"losses":5,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":33,"losses":25,"wins":38},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":18}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":42},"claude-fable-5":{"draws":4,"losses":5,"wins":39},"claude-fable-5-1":{"draws":5,"losses":19,"wins":30},"claude-haiku-5-5":{"draws":3,"losses":2,"wins":41},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":1,"losses":3,"wins":40},"claude-opus-5":{"draws":8,"losses":23,"wins":51},"claude-opus-5-5":{"draws":4,"losses":25,"wins":23},"claude-sonnet-5":{"draws":0,"losses":0,"wins":48},"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":3,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":3,"wins":42},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":1,"wins":24},"fireworks/ember-1":{"draws":1,"losses":3,"wins":44},"gemini-3.1-pro-preview":{"draws":3,"losses":1,"wins":44},"gemini-4-argon":{"draws":3,"losses":14,"wins":31},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":32},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":54},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":80},"google/gemini-3.6-flash":{"draws":4,"losses":7,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":1,"wins":43},"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":1,"losses":6,"wins":39},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":46},"gpt-5.5":{"draws":1,"losses":3,"wins":40},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":42},"gpt-5.6-sol":{"draws":4,"losses":8,"wins":36},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":19,"wins":9},"gpt-6-luna":{"draws":4,"losses":5,"wins":39},"gpt-6-sol":{"draws":6,"losses":7,"wins":35},"gpt-6.1-sol":{"draws":7,"losses":20,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":31},"inception/mercury-3":{"draws":3,"losses":1,"wins":28},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":33},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":49},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":42},"meta/muse-spark-1.3":{"draws":7,"losses":4,"wins":37},"meta/muse-spark-open":{"draws":1,"losses":1,"wins":44},"meta/muse-wonder":{"draws":3,"losses":6,"wins":39},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":0,"wins":41},"mistralai/mistral-large-4-0":{"draws":3,"losses":0,"wins":27},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":6,"losses":4,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":12,"wins":32},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"o3":{"draws":3,"losses":1,"wins":62},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":38},"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":2,"losses":0,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":45},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":33},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":28},"qwen/qwen3.8-max":{"draws":5,"losses":0,"wins":43},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":46},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":0,"wins":41},"stealth/ox-alpha":{"draws":10,"losses":9,"wins":139},"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":2,"losses":1,"wins":43},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":60},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"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":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":5,"losses":6,"wins":37},"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":71},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":24},"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":5,"losses":3,"wins":88},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":38},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":44},"z-ai/glm-5.3-flashx":{"draws":4,"losses":3,"wins":41}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":14,"wins":13},"claude-fable-5":{"draws":8,"losses":30,"wins":10},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":23,"wins":9},"claude-opus-4-5":{"draws":27,"losses":34,"wins":17},"claude-opus-4-8":{"draws":7,"losses":26,"wins":11},"claude-opus-5":{"draws":18,"losses":59,"wins":5},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":24,"wins":12},"claude-sonnet-5-5":{"draws":14,"losses":21,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":26,"losses":19,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":23,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":11},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":15,"losses":21,"wins":12},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":16},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":17,"losses":25,"wins":18},"google/gemini-3.5-flash-lite":{"draws":24,"losses":27,"wins":33},"google/gemini-3.6-flash":{"draws":25,"losses":51,"wins":16},"google/gemini-3.8-flash":{"draws":19,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":6,"wins":10},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":14,"wins":11},"gpt-5.4":{"draws":13,"losses":24,"wins":9},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":16,"wins":20},"gpt-5.5":{"draws":19,"losses":19,"wins":6},"gpt-5.6-luna":{"draws":18,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":7,"losses":36,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":20},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":9,"losses":13,"wins":10},"gpt-6-sol":{"draws":8,"losses":36,"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":15,"losses":6,"wins":13},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":18},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":28},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":18},"meta/muse-spark-1.2":{"draws":14,"losses":23,"wins":9},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":11},"meta/muse-wonder":{"draws":12,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":17,"wins":16},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":12,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":8},"o3":{"draws":14,"losses":21,"wins":31},"openai/gpt-oss-120b":{"draws":11,"losses":14,"wins":17},"poolside/laguna-s-2.1":{"draws":15,"losses":15,"wins":16},"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":9,"losses":17,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":13},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":36,"losses":78,"wins":44},"stealth/space-bunny-alpha":{"draws":11,"losses":12,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":10},"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":{"draws":1,"losses":15,"wins":0},"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":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":13,"losses":32,"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":25,"losses":14,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":42,"losses":24,"wins":30},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":27,"wins":6},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":14}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":2,"wins":34},"claude-fable-5":{"draws":7,"losses":11,"wins":30},"claude-fable-5-1":{"draws":6,"losses":37,"wins":11},"claude-haiku-5-5":{"draws":11,"losses":7,"wins":28},"claude-opus-4-5":{"draws":17,"losses":5,"wins":56},"claude-opus-4-8":{"draws":8,"losses":9,"wins":27},"claude-opus-5":{"draws":12,"losses":36,"wins":34},"claude-opus-5-5":{"draws":6,"losses":34,"wins":12},"claude-sonnet-5":{"draws":10,"losses":6,"wins":32},"claude-sonnet-5-5":{"draws":4,"losses":17,"wins":27},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":15,"losses":3,"wins":54},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":37},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":6,"wins":31},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":11,"wins":33},"elorian/glimpse":{"draws":5,"losses":4,"wins":17},"fireworks/ember-1":{"draws":7,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":2,"losses":8,"wins":38},"gemini-4-argon":{"draws":5,"losses":22,"wins":21},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":4,"wins":47},"google/gemini-3.5-flash-lite":{"draws":19,"losses":5,"wins":60},"google/gemini-3.6-flash":{"draws":13,"losses":16,"wins":63},"google/gemini-3.8-flash":{"draws":9,"losses":8,"wins":31},"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":7,"losses":3,"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":11,"losses":5,"wins":32},"gpt-5.5":{"draws":6,"losses":10,"wins":28},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":34},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":28},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":32},"gpt-6-astra":{"draws":8,"losses":28,"wins":12},"gpt-6-luna":{"draws":7,"losses":8,"wins":33},"gpt-6-sol":{"draws":5,"losses":13,"wins":14},"gpt-6.1-sol":{"draws":8,"losses":29,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":28},"inception/mercury-3":{"draws":4,"losses":4,"wins":24},"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":5,"losses":9,"wins":32},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":31},"meta/muse-spark-open":{"draws":3,"losses":7,"wins":36},"meta/muse-wonder":{"draws":4,"losses":16,"wins":28},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":22},"minimax/minimax-m3.1-flash":{"draws":6,"losses":0,"wins":36},"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},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":29,"wins":15},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":1,"wins":34},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":2,"wins":18},"o3":{"draws":6,"losses":4,"wins":56},"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":8,"losses":4,"wins":22},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":24},"qwen/qwen3.8-max":{"draws":5,"losses":7,"wins":36},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":34},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":4,"wins":34},"stealth/ox-alpha":{"draws":24,"losses":19,"wins":115},"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":{"draws":0,"losses":16,"wins":0},"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":8,"losses":7,"wins":33},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":16},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":7,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":10,"wins":14},"z-ai/glm-5.2":{"draws":16,"losses":6,"wins":74},"z-ai/glm-5.3":{"draws":7,"losses":13,"wins":26},"z-ai/glm-5.3-flash":{"draws":8,"losses":8,"wins":32},"z-ai/glm-5.3-flashx":{"draws":6,"losses":11,"wins":31}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":5,"wins":38},"claude-fable-5":{"draws":3,"losses":9,"wins":36},"claude-fable-5-1":{"draws":2,"losses":23,"wins":29},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":2,"losses":4,"wins":72},"claude-opus-4-8":{"draws":1,"losses":6,"wins":37},"claude-opus-5":{"draws":13,"losses":26,"wins":43},"claude-opus-5-5":{"draws":4,"losses":25,"wins":23},"claude-sonnet-5":{"draws":1,"losses":2,"wins":45},"claude-sonnet-5-5":{"draws":1,"losses":10,"wins":37},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":65},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":5,"wins":39},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":10,"wins":33},"elorian/glimpse":{"draws":1,"losses":4,"wins":21},"fireworks/ember-1":{"draws":0,"losses":8,"wins":40},"gemini-3.1-pro-preview":{"draws":1,"losses":5,"wins":42},"gemini-4-argon":{"draws":7,"losses":16,"wins":25},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":3,"wins":83},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":39},"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":1,"losses":4,"wins":41},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":29},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":46},"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":6,"wins":39},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":41},"gpt-6-astra":{"draws":7,"losses":24,"wins":17},"gpt-6-luna":{"draws":1,"losses":1,"wins":46},"gpt-6-sol":{"draws":5,"losses":11,"wins":32},"gpt-6.1-sol":{"draws":1,"losses":14,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":32},"inception/mercury-3":{"draws":0,"losses":1,"wins":31},"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":3,"losses":6,"wins":37},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":38},"meta/muse-spark-open":{"draws":0,"losses":5,"wins":41},"meta/muse-wonder":{"draws":7,"losses":11,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":1,"losses":0,"wins":41},"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":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":3,"losses":4,"wins":39},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":16,"wins":29},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":42},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":22},"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":2,"losses":1,"wins":25},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":39},"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":4,"losses":2,"wins":42},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":45},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":4,"wins":39},"stealth/ox-alpha":{"draws":13,"losses":9,"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":1,"losses":2,"wins":43},"thinkingmachines/inkling":{"draws":2,"losses":1,"wins":61},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"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":4,"wins":41},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":28},"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":7,"losses":7,"wins":32},"z-ai/glm-5.3-flash":{"draws":4,"losses":5,"wins":39},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":40}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":1,"wins":0},"elorian/glimpse":{"draws":3,"losses":1,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":1,"losses":5,"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},"inception/mercury-3":{"draws":2,"losses":0,"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-spark-open":{"draws":4,"losses":2,"wins":0},"meta/muse-wonder":{"draws":4,"losses":1,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":5,"losses":0,"wins":1},"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},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":5,"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},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":3,"wins":0},"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":{"draws":1,"losses":1,"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":11,"losses":13,"wins":8},"claude-fable-5":{"draws":8,"losses":28,"wins":0},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":25,"wins":1},"claude-opus-4-5":{"draws":19,"losses":40,"wins":1},"claude-opus-4-8":{"draws":9,"losses":26,"wins":1},"claude-opus-5":{"draws":6,"losses":49,"wins":3},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":11,"losses":22,"wins":3},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":19,"losses":27,"wins":8},"deepseek/deepseek-v4-pro":{"draws":11,"losses":20,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":16,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":21,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":13,"wins":1},"fireworks/ember-1":{"draws":14,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":4},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":11,"wins":11},"google/gemini-3.5-flash":{"draws":14,"losses":26,"wins":6},"google/gemini-3.5-flash-lite":{"draws":22,"losses":31,"wins":11},"google/gemini-3.6-flash":{"draws":20,"losses":44,"wins":4},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":2},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":18,"wins":2},"gpt-5.4":{"draws":14,"losses":19,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":25,"wins":4},"gpt-5.5":{"draws":12,"losses":18,"wins":2},"gpt-5.6-luna":{"draws":12,"losses":17,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":21,"wins":2},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":21,"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":8,"losses":4,"wins":6},"inception/mercury-3":{"draws":8,"losses":14,"wins":2},"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":11,"losses":18,"wins":13},"meta/muse-glimmer-30b":{"draws":10,"losses":13,"wins":7},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":2},"meta/muse-spark-open":{"draws":9,"losses":23,"wins":2},"meta/muse-wonder":{"draws":10,"losses":25,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3.1-flash":{"draws":9,"losses":19,"wins":2},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":1},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":16,"losses":18,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":32,"wins":0},"nex-agi/nex-n2-pro":{"draws":5,"losses":9,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":13,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":10,"wins":2},"o3":{"draws":14,"losses":35,"wins":3},"openai/gpt-oss-120b":{"draws":11,"losses":16,"wins":5},"poolside/laguna-s-2.1":{"draws":14,"losses":11,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":21,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":24,"wins":1},"qwen/qwen3.8-max-0902":{"draws":12,"losses":20,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":21,"wins":2},"stealth/ox-alpha":{"draws":29,"losses":70,"wins":3},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":0},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":14,"losses":21,"wins":9},"thinkingmachines/inkling-small":{"draws":15,"losses":12,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":11,"losses":24,"wins":1},"x-ai/grok-4.6":{"draws":5,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":44,"wins":7},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":25,"wins":3},"z-ai/glm-5.3-flashx":{"draws":7,"losses":27,"wins":2}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":6},"claude-fable-5":{"draws":4,"losses":8,"wins":6},"claude-fable-5-1":{"draws":0,"losses":19,"wins":1},"claude-haiku-5-5":{"draws":3,"losses":7,"wins":8},"claude-opus-4-5":{"draws":9,"losses":9,"wins":12},"claude-opus-4-8":{"draws":4,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":24,"wins":3},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":5,"losses":5,"wins":8},"claude-sonnet-5-5":{"draws":3,"losses":11,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":8,"wins":5},"elorian/glimpse":{"draws":2,"losses":3,"wins":5},"fireworks/ember-1":{"draws":5,"losses":5,"wins":8},"gemini-3.1-pro-preview":{"draws":6,"losses":4,"wins":8},"gemini-4-argon":{"draws":1,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":13},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":17},"google/gemini-3.6-flash":{"draws":4,"losses":11,"wins":17},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":9},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":0,"losses":1,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":3,"wins":10},"gpt-5.4":{"draws":2,"losses":5,"wins":9},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":5,"wins":10},"gpt-5.5":{"draws":3,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":11},"gpt-5.6-sol":{"draws":3,"losses":10,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":11},"gpt-6-astra":{"draws":2,"losses":16,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":8},"gpt-6-sol":{"draws":3,"losses":12,"wins":3},"gpt-6.1-sol":{"draws":0,"losses":18,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":8},"inception/mercury-3":{"draws":3,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":10},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":13},"meta/muse-glimmer-30b":{"draws":4,"losses":1,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":6,"wins":7},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":7},"meta/muse-spark-open":{"draws":1,"losses":9,"wins":6},"meta/muse-wonder":{"draws":6,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":9},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":9},"mistralai/mistral-large-4-0":{"draws":3,"losses":4,"wins":5},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":12,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":1,"wins":7},"o3":{"draws":1,"losses":7,"wins":16},"openai/gpt-oss-120b":{"draws":6,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":7},"qwen/qwen3.8-max":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":10},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":4,"wins":10},"stealth/ox-alpha":{"draws":11,"losses":16,"wins":23},"stealth/space-bunny-alpha":{"draws":4,"losses":0,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":6},"tencent/hy4-preview":{"draws":1,"losses":7,"wins":8},"thinkingmachines/inkling":{"draws":5,"losses":2,"wins":13},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":9},"unbiased/pareto-26.10":{"draws":0,"losses":5,"wins":1},"unbiased/pareto-26.10-preview":{"draws":0,"losses":5,"wins":1},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":6,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":12,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":12,"losses":3,"wins":21},"z-ai/glm-5.3":{"draws":5,"losses":7,"wins":6},"z-ai/glm-5.3-flash":{"draws":3,"losses":4,"wins":11},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"wins":13}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":12,"wins":6},"claude-fable-5":{"draws":5,"losses":30,"wins":1},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":27,"wins":1},"claude-opus-4-5":{"draws":24,"losses":25,"wins":11},"claude-opus-4-8":{"draws":11,"losses":25,"wins":0},"claude-opus-5":{"draws":9,"losses":44,"wins":1},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":18,"losses":20,"wins":18},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":28,"wins":1},"elorian/glimpse":{"draws":7,"losses":9,"wins":4},"fireworks/ember-1":{"draws":13,"losses":19,"wins":4},"gemini-3.1-pro-preview":{"draws":11,"losses":20,"wins":5},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":8,"wins":15},"google/gemini-3.5-flash":{"draws":10,"losses":29,"wins":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":30,"wins":15},"google/gemini-3.6-flash":{"draws":23,"losses":40,"wins":7},"google/gemini-3.8-flash":{"draws":8,"losses":27,"wins":1},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":16,"wins":4},"gpt-5.4":{"draws":8,"losses":20,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":14},"gpt-5.5":{"draws":10,"losses":18,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":4},"gpt-6-astra":{"draws":2,"losses":34,"wins":0},"gpt-6-luna":{"draws":8,"losses":22,"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":12,"losses":4,"wins":12},"inception/mercury-3":{"draws":10,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":4,"losses":7,"wins":5},"meituan/longcat-2.0":{"draws":12,"losses":14,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":10,"wins":6},"meta/muse-spark-1.2":{"draws":12,"losses":15,"wins":7},"meta/muse-spark-1.3":{"draws":1,"losses":30,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":25,"wins":3},"meta/muse-wonder":{"draws":7,"losses":29,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":7},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":6},"mistralai/mistral-large-4-0":{"draws":7,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":31,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":5,"losses":36,"wins":11},"openai/gpt-oss-120b":{"draws":8,"losses":16,"wins":6},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":4},"qwen/qwen3.7-max":{"draws":5,"losses":15,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":9,"wins":12},"stealth/ox-alpha":{"draws":22,"losses":64,"wins":16},"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":8,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":8,"losses":22,"wins":4},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":9},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":9,"losses":24,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":25,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":26,"losses":20,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":2},"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":22,"losses":35,"wins":15},"z-ai/glm-5.3":{"draws":5,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":23,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":26,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":28,"wins":22},"claude-fable-5":{"draws":6,"losses":55,"wins":11},"claude-fable-5-1":{"draws":3,"losses":75,"wins":4},"claude-haiku-5-5":{"draws":14,"losses":45,"wins":11},"claude-opus-4-5":{"draws":28,"losses":69,"wins":21},"claude-opus-4-8":{"draws":14,"losses":41,"wins":13},"claude-opus-5":{"draws":9,"losses":95,"wins":12},"claude-opus-5-5":{"draws":6,"losses":70,"wins":4},"claude-sonnet-5":{"draws":15,"losses":42,"wins":15},"claude-sonnet-5-5":{"draws":8,"losses":47,"wins":17},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":29,"losses":43,"wins":34},"deepseek/deepseek-v4-pro":{"draws":13,"losses":40,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":35,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":44,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":48,"wins":13},"elorian/glimpse":{"draws":11,"losses":17,"wins":10},"fireworks/ember-1":{"draws":13,"losses":39,"wins":20},"gemini-3.1-pro-preview":{"draws":14,"losses":31,"wins":27},"gemini-4-argon":{"draws":5,"losses":61,"wins":6},"google/gemini-3.1-flash-lite":{"draws":7,"losses":15,"wins":32},"google/gemini-3.5-flash":{"draws":18,"losses":54,"wins":20},"google/gemini-3.5-flash-lite":{"draws":33,"losses":42,"wins":55},"google/gemini-3.6-flash":{"draws":28,"losses":84,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":46,"wins":12},"google/gemma-4-31b-it":{"draws":13,"losses":15,"wins":18},"gpt-4.1":{"draws":8,"losses":11,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":19,"losses":32,"wins":11},"gpt-5.4":{"draws":13,"losses":42,"wins":15},"gpt-5.4-mini":{"draws":13,"losses":18,"wins":17},"gpt-5.4-nano":{"draws":11,"losses":39,"wins":22},"gpt-5.5":{"draws":11,"losses":41,"wins":14},"gpt-5.6-luna":{"draws":18,"losses":30,"wins":24},"gpt-5.6-sol":{"draws":11,"losses":53,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":32,"wins":18},"gpt-6-astra":{"draws":2,"losses":67,"wins":3},"gpt-6-luna":{"draws":13,"losses":41,"wins":18},"gpt-6-sol":{"draws":4,"losses":63,"wins":5},"gpt-6.1-sol":{"draws":5,"losses":62,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":18,"losses":12,"wins":26},"inception/mercury-3":{"draws":10,"losses":22,"wins":14},"inclusionai/ling-3.0-flash":{"draws":22,"losses":7,"wins":19},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":18,"wins":27},"meta/muse-glimmer-30b":{"draws":17,"losses":17,"wins":28},"meta/muse-spark-1.2":{"draws":13,"losses":39,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":46,"wins":14},"meta/muse-spark-open":{"draws":12,"losses":49,"wins":9},"meta/muse-wonder":{"draws":11,"losses":51,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":12,"wins":19},"minimax/minimax-m3.1-flash":{"draws":17,"losses":30,"wins":15},"mistralai/mistral-large-4-0":{"draws":16,"losses":19,"wins":9},"mistralai/mistral-medium-3-5":{"draws":15,"losses":8,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":9,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":40,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":63,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":15,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":18,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":13,"wins":11},"o3":{"draws":13,"losses":62,"wins":31},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":36},"poolside/laguna-s-2.1":{"draws":17,"losses":19,"wins":30},"qwen/qwen3.7-max":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.7-plus":{"draws":8,"losses":13,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":42,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":32,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":19,"losses":44,"wins":9},"qwen/qwen3.8-max-0902":{"draws":9,"losses":52,"wins":11},"recursive/flint-v1.0":{"draws":6,"losses":4,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":36,"wins":16},"stealth/ox-alpha":{"draws":48,"losses":142,"wins":38},"stealth/space-bunny-alpha":{"draws":15,"losses":24,"wins":21},"stepfun/step-3.7-flash":{"draws":10,"losses":27,"wins":13},"stepfun/step-5-preview":{"draws":3,"losses":4,"wins":1},"tencent/hy3-preview":{"draws":15,"losses":13,"wins":10},"tencent/hy4-preview":{"draws":20,"losses":39,"wins":11},"thinkingmachines/inkling":{"draws":24,"losses":35,"wins":33},"thinkingmachines/inkling-small":{"draws":18,"losses":21,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":15,"losses":48,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":45,"wins":14},"x-ai/grok-4.7":{"draws":3,"losses":57,"wins":2},"x-ai/grok-build-0.1":{"draws":9,"losses":8,"wins":7},"xiaomi/mimo-v2.5":{"draws":37,"losses":37,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":14,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":24,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":37,"wins":6},"z-ai/glm-5.2":{"draws":35,"losses":72,"wins":37},"z-ai/glm-5.3":{"draws":12,"losses":52,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":47,"wins":14},"z-ai/glm-5.3-flashx":{"draws":13,"losses":49,"wins":10}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":18,"wins":13},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":28,"wins":4},"claude-opus-4-5":{"draws":25,"losses":43,"wins":10},"claude-opus-4-8":{"draws":9,"losses":29,"wins":6},"claude-opus-5":{"draws":3,"losses":71,"wins":8},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":28,"losses":32,"wins":12},"deepseek/deepseek-v4-pro":{"draws":14,"losses":23,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":27,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":31,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":33,"wins":5},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":13,"losses":29,"wins":6},"gemini-3.1-pro-preview":{"draws":20,"losses":23,"wins":5},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"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":36,"losses":32,"wins":16},"google/gemini-3.6-flash":{"draws":26,"losses":58,"wins":8},"google/gemini-3.8-flash":{"draws":10,"losses":34,"wins":4},"google/gemma-4-31b-it":{"draws":15,"losses":8,"wins":5},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":21,"wins":9},"gpt-5.4":{"draws":11,"losses":29,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":8,"losses":23,"wins":17},"gpt-5.5":{"draws":10,"losses":24,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":24,"wins":9},"gpt-5.6-sol":{"draws":8,"losses":38,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":27,"wins":7},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":14,"losses":27,"wins":7},"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":15,"losses":10,"wins":9},"inception/mercury-3":{"draws":9,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":20,"losses":6,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":19,"wins":17},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":6},"meta/muse-spark-1.2":{"draws":13,"losses":25,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":11,"losses":33,"wins":2},"meta/muse-wonder":{"draws":8,"losses":34,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":11,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":24,"wins":8},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":11,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":29,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":40,"wins":1},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":17,"wins":10},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":11,"wins":3},"o3":{"draws":15,"losses":45,"wins":6},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":8,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":34,"wins":2},"qwen/qwen3.8-27b":{"draws":11,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":11,"losses":29,"wins":8},"qwen/qwen3.8-max-0902":{"draws":17,"losses":28,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":27,"wins":4},"stealth/ox-alpha":{"draws":34,"losses":108,"wins":16},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":16,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":33,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":24,"wins":19},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":10,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":13,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":38,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":5},"xiaomi/mimo-v2.5":{"draws":29,"losses":25,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":14,"wins":8},"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":33,"losses":45,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":35,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":15,"losses":29,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":21},"claude-fable-5":{"draws":6,"losses":25,"wins":11},"claude-fable-5-1":{"draws":2,"losses":39,"wins":7},"claude-haiku-5-5":{"draws":8,"losses":16,"wins":16},"claude-opus-4-5":{"draws":21,"losses":10,"wins":37},"claude-opus-4-8":{"draws":10,"losses":11,"wins":17},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":11,"losses":11,"wins":20},"claude-sonnet-5-5":{"draws":14,"losses":16,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":4,"wins":40},"deepseek/deepseek-v4-pro":{"draws":6,"losses":15,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":8,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":11,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":19,"wins":16},"elorian/glimpse":{"draws":5,"losses":7,"wins":12},"fireworks/ember-1":{"draws":12,"losses":14,"wins":16},"gemini-3.1-pro-preview":{"draws":10,"losses":12,"wins":20},"gemini-4-argon":{"draws":4,"losses":32,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":10,"losses":11,"wins":31},"google/gemini-3.5-flash-lite":{"draws":21,"losses":8,"wins":43},"google/gemini-3.6-flash":{"draws":13,"losses":25,"wins":42},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":23},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":12},"gpt-4.1":{"draws":4,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":10,"losses":8,"wins":20},"gpt-5.4":{"draws":8,"losses":16,"wins":16},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":24},"gpt-5.5":{"draws":7,"losses":16,"wins":17},"gpt-5.6-luna":{"draws":15,"losses":5,"wins":22},"gpt-5.6-sol":{"draws":4,"losses":23,"wins":15},"gpt-5.6-terra":{"draws":13,"losses":9,"wins":18},"gpt-6-astra":{"draws":4,"losses":37,"wins":1},"gpt-6-luna":{"draws":12,"losses":7,"wins":23},"gpt-6-sol":{"draws":4,"losses":28,"wins":10},"gpt-6.1-sol":{"draws":6,"losses":29,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":2,"wins":14},"inception/mercury-3":{"draws":9,"losses":5,"wins":14},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":27},"meta/muse-spark-1.2":{"draws":8,"losses":8,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":21},"meta/muse-spark-open":{"draws":10,"losses":14,"wins":16},"meta/muse-wonder":{"draws":8,"losses":18,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":20},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":16},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":9,"losses":14,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":32,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":11},"o3":{"draws":9,"losses":14,"wins":31},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":26},"poolside/laguna-s-2.1":{"draws":10,"losses":7,"wins":25},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":17},"qwen/qwen3.8-27b":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":13,"wins":16},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":11,"wins":20},"stealth/ox-alpha":{"draws":40,"losses":57,"wins":45},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":19},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":20},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":15,"losses":6,"wins":37},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":25},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":10,"losses":19,"wins":13},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":14},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":14,"losses":5,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":20,"wins":7},"z-ai/glm-5.2":{"draws":15,"losses":17,"wins":52},"z-ai/glm-5.3":{"draws":7,"losses":21,"wins":12},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":20},"z-ai/glm-5.3-flashx":{"draws":9,"losses":16,"wins":17}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":6,"wins":31},"claude-fable-5":{"draws":7,"losses":22,"wins":19},"claude-fable-5-1":{"draws":3,"losses":43,"wins":8},"claude-haiku-5-5":{"draws":5,"losses":18,"wins":23},"claude-opus-4-5":{"draws":13,"losses":13,"wins":52},"claude-opus-4-8":{"draws":5,"losses":16,"wins":23},"claude-opus-5":{"draws":8,"losses":50,"wins":24},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":12,"losses":8,"wins":28},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":56},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":28},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":17,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":16,"wins":27},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":11,"losses":14,"wins":23},"gemini-3.1-pro-preview":{"draws":5,"losses":10,"wins":33},"gemini-4-argon":{"draws":8,"losses":33,"wins":7},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":45},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":62},"google/gemini-3.6-flash":{"draws":18,"losses":24,"wins":50},"google/gemini-3.8-flash":{"draws":10,"losses":14,"wins":24},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":19},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":7,"losses":5,"wins":30},"gpt-5.4":{"draws":9,"losses":15,"wins":22},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":36},"gpt-5.5":{"draws":9,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":10,"losses":5,"wins":33},"gpt-5.6-sol":{"draws":9,"losses":20,"wins":19},"gpt-5.6-terra":{"draws":12,"losses":8,"wins":26},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":5,"losses":10,"wins":33},"gpt-6-sol":{"draws":7,"losses":33,"wins":8},"gpt-6.1-sol":{"draws":5,"losses":35,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":5,"losses":7,"wins":20},"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":5,"losses":4,"wins":43},"meta/muse-glimmer-30b":{"draws":9,"losses":1,"wins":32},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":21},"meta/muse-spark-1.3":{"draws":6,"losses":12,"wins":14},"meta/muse-spark-open":{"draws":7,"losses":12,"wins":27},"meta/muse-wonder":{"draws":10,"losses":21,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":26},"mistralai/mistral-large-4-0":{"draws":5,"losses":4,"wins":21},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":9,"wins":30},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":5,"wins":15},"o3":{"draws":5,"losses":11,"wins":50},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":30},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":4,"losses":6,"wins":18},"qwen/qwen3.7-plus":{"draws":1,"losses":7,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.8-flash":{"draws":8,"losses":6,"wins":18},"qwen/qwen3.8-max":{"draws":8,"losses":12,"wins":28},"qwen/qwen3.8-max-0902":{"draws":9,"losses":14,"wins":25},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":7,"wins":30},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":82},"stealth/space-bunny-alpha":{"draws":6,"losses":6,"wins":26},"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":2,"losses":5,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":27},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":52},"thinkingmachines/inkling-small":{"draws":8,"losses":4,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":10,"losses":18,"wins":20},"x-ai/grok-4.7":{"draws":2,"losses":28,"wins":12},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":13,"losses":1,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":20},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":15,"wins":11},"z-ai/glm-5.2":{"draws":18,"losses":15,"wins":63},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":21},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":22},"claude-fable-5":{"draws":11,"losses":26,"wins":11},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":19,"wins":18},"claude-opus-4-5":{"draws":29,"losses":23,"wins":26},"claude-opus-4-8":{"draws":13,"losses":16,"wins":15},"claude-opus-5":{"draws":10,"losses":64,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":17,"losses":9,"wins":22},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":18,"losses":10,"wins":44},"deepseek/deepseek-v4-pro":{"draws":11,"losses":13,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":14,"losses":21,"wins":13},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":20,"losses":11,"wins":53},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":34},"google/gemini-3.8-flash":{"draws":11,"losses":22,"wins":15},"google/gemma-4-31b-it":{"draws":11,"losses":2,"wins":15},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":7,"wins":23},"gpt-5.4":{"draws":13,"losses":15,"wins":18},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":32},"gpt-5.5":{"draws":10,"losses":19,"wins":15},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":20},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":16,"losses":14,"wins":18},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"gpt-6.1-sol":{"draws":3,"losses":43,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"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":12,"losses":4,"wins":36},"meta/muse-glimmer-30b":{"draws":11,"losses":7,"wins":24},"meta/muse-spark-1.2":{"draws":12,"losses":16,"wins":18},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":15},"meta/muse-spark-open":{"draws":6,"losses":16,"wins":8},"meta/muse-wonder":{"draws":8,"losses":26,"wins":14},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":24},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":2,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":10},"o3":{"draws":10,"losses":15,"wins":41},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":26},"poolside/laguna-s-2.1":{"draws":11,"losses":11,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":1,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":19,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":6,"losses":12,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":15,"wins":20},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":18},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":12,"wins":19},"stealth/ox-alpha":{"draws":40,"losses":61,"wins":57},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"stepfun/step-3.7-flash":{"draws":9,"losses":4,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":12},"tencent/hy4-preview":{"draws":10,"losses":16,"wins":20},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":16,"wins":0},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":14},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":2,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":2,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":10,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":13,"wins":10},"z-ai/glm-5.2":{"draws":33,"losses":17,"wins":46},"z-ai/glm-5.3":{"draws":11,"losses":25,"wins":10},"z-ai/glm-5.3-flash":{"draws":12,"losses":19,"wins":17},"z-ai/glm-5.3-flashx":{"draws":12,"losses":20,"wins":16}},"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":8,"losses":52,"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":9,"losses":12,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":23,"wins":19},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":8,"losses":15,"wins":25},"gemini-3.1-pro-preview":{"draws":6,"losses":6,"wins":36},"gemini-4-argon":{"draws":7,"losses":34,"wins":7},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":26},"google/gemini-3.5-flash":{"draws":9,"losses":10,"wins":41},"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":11,"wins":27},"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":5,"losses":9,"wins":34},"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},"inception/mercury-3":{"draws":5,"losses":10,"wins":17},"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":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":15,"wins":24},"meta/muse-spark-open":{"draws":7,"losses":17,"wins":22},"meta/muse-wonder":{"draws":5,"losses":13,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":18},"minimax/minimax-m3.1-flash":{"draws":9,"losses":9,"wins":24},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":13},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":5,"wins":14},"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":11,"wins":26},"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":{"draws":2,"losses":11,"wins":3},"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":16,"wins":57},"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":14,"losses":19,"wins":5},"claude-fable-5":{"draws":9,"losses":32,"wins":1},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":6,"losses":31,"wins":5},"claude-opus-4-5":{"draws":20,"losses":47,"wins":3},"claude-opus-4-8":{"draws":13,"losses":27,"wins":2},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":13,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":7,"losses":33,"wins":2},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":7},"deepseek/deepseek-v4-flash":{"draws":21,"losses":25,"wins":18},"deepseek/deepseek-v4-pro":{"draws":7,"losses":28,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":27,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":2},"elorian/glimpse":{"draws":6,"losses":12,"wins":4},"fireworks/ember-1":{"draws":9,"losses":30,"wins":3},"gemini-3.1-pro-preview":{"draws":11,"losses":24,"wins":7},"gemini-4-argon":{"draws":1,"losses":40,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":15,"wins":8},"google/gemini-3.5-flash":{"draws":13,"losses":32,"wins":9},"google/gemini-3.5-flash-lite":{"draws":20,"losses":37,"wins":17},"google/gemini-3.6-flash":{"draws":18,"losses":50,"wins":12},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":12,"losses":7,"wins":7},"gpt-4.1":{"draws":6,"losses":7,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":22,"wins":6},"gpt-5.4":{"draws":10,"losses":27,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":12,"wins":9},"gpt-5.4-nano":{"draws":8,"losses":28,"wins":10},"gpt-5.5":{"draws":14,"losses":21,"wins":3},"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":10,"losses":27,"wins":3},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":13,"losses":23,"wins":6},"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":14,"losses":10,"wins":8},"inception/mercury-3":{"draws":7,"losses":21,"wins":0},"inclusionai/ling-3.0-flash":{"draws":11,"losses":12,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":26,"wins":14},"meta/muse-glimmer-30b":{"draws":12,"losses":16,"wins":8},"meta/muse-spark-1.2":{"draws":10,"losses":26,"wins":4},"meta/muse-spark-1.3":{"draws":6,"losses":34,"wins":2},"meta/muse-spark-open":{"draws":9,"losses":29,"wins":2},"meta/muse-wonder":{"draws":8,"losses":30,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"minimax/minimax-m3.1-flash":{"draws":10,"losses":23,"wins":3},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":8,"losses":9,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":26,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":38,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":10,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":22,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":3},"o3":{"draws":7,"losses":43,"wins":12},"openai/gpt-oss-120b":{"draws":12,"losses":16,"wins":8},"poolside/laguna-s-2.1":{"draws":8,"losses":21,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":13,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":29,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":21,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":7,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":26,"wins":5},"stealth/ox-alpha":{"draws":21,"losses":85,"wins":12},"stealth/space-bunny-alpha":{"draws":8,"losses":22,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":12},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":12,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":29,"wins":2},"thinkingmachines/inkling":{"draws":14,"losses":31,"wins":9},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":31,"wins":2},"x-ai/grok-4.6":{"draws":9,"losses":31,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":32,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":8,"wins":3},"xiaomi/mimo-v2.5":{"draws":21,"losses":34,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":14,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":21,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":1},"z-ai/glm-5.2":{"draws":24,"losses":50,"wins":10},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":29,"wins":6},"z-ai/glm-5.3-flashx":{"draws":12,"losses":28,"wins":2}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":15,"wins":18},"claude-fable-5":{"draws":3,"losses":30,"wins":9},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":20,"wins":14},"claude-opus-4-5":{"draws":11,"losses":29,"wins":28},"claude-opus-4-8":{"draws":5,"losses":20,"wins":13},"claude-opus-5":{"draws":2,"losses":60,"wins":8},"claude-opus-5-5":{"draws":2,"losses":42,"wins":2},"claude-sonnet-5":{"draws":6,"losses":20,"wins":16},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":6,"losses":24,"wins":32},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":27,"wins":8},"elorian/glimpse":{"draws":3,"losses":15,"wins":6},"fireworks/ember-1":{"draws":10,"losses":16,"wins":16},"gemini-3.1-pro-preview":{"draws":8,"losses":17,"wins":17},"gemini-4-argon":{"draws":4,"losses":34,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":25,"wins":24},"google/gemini-3.5-flash-lite":{"draws":12,"losses":24,"wins":40},"google/gemini-3.6-flash":{"draws":15,"losses":36,"wins":31},"google/gemini-3.8-flash":{"draws":7,"losses":21,"wins":14},"google/gemma-4-31b-it":{"draws":4,"losses":5,"wins":15},"gpt-4.1":{"draws":0,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":19,"wins":14},"gpt-5.4":{"draws":5,"losses":28,"wins":9},"gpt-5.4-mini":{"draws":6,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":2,"losses":16,"wins":24},"gpt-5.5":{"draws":11,"losses":19,"wins":10},"gpt-5.6-luna":{"draws":6,"losses":13,"wins":23},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":10},"gpt-5.6-terra":{"draws":9,"losses":18,"wins":13},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":8,"losses":16,"wins":18},"gpt-6-sol":{"draws":3,"losses":35,"wins":4},"gpt-6.1-sol":{"draws":6,"losses":35,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":4,"wins":19},"inception/mercury-3":{"draws":5,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":5,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":12,"wins":27},"meta/muse-glimmer-30b":{"draws":5,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":5,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":5,"losses":22,"wins":15},"meta/muse-spark-open":{"draws":5,"losses":22,"wins":15},"meta/muse-wonder":{"draws":4,"losses":30,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":1,"losses":8,"wins":15},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":11},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":31,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":13,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":9},"o3":{"draws":5,"losses":26,"wins":33},"openai/gpt-oss-120b":{"draws":5,"losses":7,"wins":24},"poolside/laguna-s-2.1":{"draws":4,"losses":13,"wins":23},"qwen/qwen3.7-max":{"draws":1,"losses":9,"wins":14},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":4,"losses":9,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":7,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":5,"losses":24,"wins":13},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":16,"wins":14},"stealth/ox-alpha":{"draws":20,"losses":74,"wins":48},"stealth/space-bunny-alpha":{"draws":5,"losses":14,"wins":15},"stepfun/step-3.7-flash":{"draws":1,"losses":5,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":12,"wins":9},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":8,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"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":7,"losses":22,"wins":13},"x-ai/grok-4.6":{"draws":11,"losses":19,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":23,"wins":11},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":8,"losses":20,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":14,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":14,"losses":31,"wins":39},"z-ai/glm-5.3":{"draws":4,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":2,"losses":17,"wins":23},"z-ai/glm-5.3-flashx":{"draws":5,"losses":22,"wins":15}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":15},"claude-fable-5":{"draws":5,"losses":27,"wins":4},"claude-fable-5-1":{"draws":2,"losses":37,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":15,"wins":15},"claude-opus-4-5":{"draws":17,"losses":30,"wins":13},"claude-opus-4-8":{"draws":8,"losses":21,"wins":7},"claude-opus-5":{"draws":8,"losses":57,"wins":3},"claude-opus-5-5":{"draws":2,"losses":36,"wins":2},"claude-sonnet-5":{"draws":11,"losses":9,"wins":16},"claude-sonnet-5-5":{"draws":9,"losses":20,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":12,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":26,"wins":2},"elorian/glimpse":{"draws":4,"losses":9,"wins":7},"fireworks/ember-1":{"draws":11,"losses":14,"wins":11},"gemini-3.1-pro-preview":{"draws":7,"losses":18,"wins":11},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":18,"wins":16},"google/gemini-3.5-flash-lite":{"draws":16,"losses":14,"wins":32},"google/gemini-3.6-flash":{"draws":19,"losses":32,"wins":17},"google/gemini-3.8-flash":{"draws":4,"losses":15,"wins":17},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":11},"gpt-4.1":{"draws":4,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":11,"wins":15},"gpt-5.4":{"draws":5,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":13},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":18},"gpt-5.5":{"draws":9,"losses":12,"wins":13},"gpt-5.6-luna":{"draws":10,"losses":8,"wins":18},"gpt-5.6-sol":{"draws":4,"losses":25,"wins":7},"gpt-5.6-terra":{"draws":9,"losses":13,"wins":12},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":11,"losses":13,"wins":12},"gpt-6-sol":{"draws":5,"losses":28,"wins":3},"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":10,"losses":2,"wins":14},"inception/mercury-3":{"draws":6,"losses":10,"wins":8},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":8,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":16,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":13,"wins":16},"meta/muse-spark-open":{"draws":7,"losses":21,"wins":6},"meta/muse-wonder":{"draws":7,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":14},"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":11,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":32,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":8},"o3":{"draws":5,"losses":22,"wins":23},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":7,"losses":12,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":16,"wins":8},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":9,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":9},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":11,"wins":13},"stealth/ox-alpha":{"draws":21,"losses":54,"wins":27},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":14},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":15},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":17,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":11,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":7,"losses":25,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":19,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":12,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":3},"z-ai/glm-5.2":{"draws":17,"losses":24,"wins":31},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":5},"z-ai/glm-5.3-flash":{"draws":6,"losses":17,"wins":13},"z-ai/glm-5.3-flashx":{"draws":8,"losses":13,"wins":15}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":21},"claude-fable-5":{"draws":13,"losses":32,"wins":3},"claude-fable-5-1":{"draws":5,"losses":48,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":23,"wins":11},"claude-opus-4-5":{"draws":27,"losses":27,"wins":24},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":14,"losses":60,"wins":8},"claude-opus-5-5":{"draws":1,"losses":47,"wins":4},"claude-sonnet-5":{"draws":14,"losses":16,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":23,"wins":14},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":9},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":16,"losses":20,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":24},"google/gemini-3.5-flash-lite":{"draws":25,"losses":16,"wins":43},"google/gemini-3.6-flash":{"draws":25,"losses":41,"wins":26},"google/gemini-3.8-flash":{"draws":12,"losses":29,"wins":7},"google/gemma-4-31b-it":{"draws":12,"losses":3,"wins":13},"gpt-4.1":{"draws":6,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":9,"losses":17,"wins":16},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":17},"gpt-5.4-nano":{"draws":8,"losses":14,"wins":26},"gpt-5.5":{"draws":15,"losses":18,"wins":11},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":16,"losses":15,"wins":15},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":16,"losses":16,"wins":16},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"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":16,"losses":2,"wins":16},"inception/mercury-3":{"draws":12,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":25},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":7,"wins":26},"meta/muse-spark-1.2":{"draws":11,"losses":20,"wins":15},"meta/muse-spark-1.3":{"draws":11,"losses":25,"wins":12},"meta/muse-spark-open":{"draws":10,"losses":23,"wins":13},"meta/muse-wonder":{"draws":12,"losses":29,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":18},"minimax/minimax-m3.1-flash":{"draws":12,"losses":16,"wins":14},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":7,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":25},"poolside/laguna-s-2.1":{"draws":9,"losses":7,"wins":30},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":22,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":7,"wins":17},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":15},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":14,"losses":23,"wins":11},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":19,"wins":13},"stealth/ox-alpha":{"draws":33,"losses":69,"wins":56},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":14},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":32},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":26,"wins":12},"x-ai/grok-4.6":{"draws":17,"losses":23,"wins":8},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":8,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":32,"wins":37},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":16},"z-ai/glm-5.3-flashx":{"draws":9,"losses":27,"wins":12}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":27},"claude-fable-5":{"draws":5,"losses":14,"wins":29},"claude-fable-5-1":{"draws":5,"losses":36,"wins":13},"claude-haiku-5-5":{"draws":6,"losses":10,"wins":30},"claude-opus-4-5":{"draws":14,"losses":10,"wins":54},"claude-opus-4-8":{"draws":5,"losses":7,"wins":32},"claude-opus-5":{"draws":10,"losses":47,"wins":25},"claude-opus-5-5":{"draws":2,"losses":37,"wins":13},"claude-sonnet-5":{"draws":6,"losses":7,"wins":35},"claude-sonnet-5-5":{"draws":5,"losses":16,"wins":27},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":17},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":58},"deepseek/deepseek-v4-pro":{"draws":4,"losses":8,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":9,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":15,"wins":24},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":13,"wins":30},"elorian/glimpse":{"draws":1,"losses":7,"wins":18},"fireworks/ember-1":{"draws":6,"losses":8,"wins":34},"gemini-3.1-pro-preview":{"draws":4,"losses":9,"wins":35},"gemini-4-argon":{"draws":4,"losses":29,"wins":15},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":46},"google/gemini-3.5-flash-lite":{"draws":10,"losses":9,"wins":65},"google/gemini-3.6-flash":{"draws":12,"losses":23,"wins":57},"google/gemini-3.8-flash":{"draws":4,"losses":13,"wins":31},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":22},"gpt-4.1":{"draws":1,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":1,"losses":2,"wins":3},"gpt-5":{"draws":6,"losses":7,"wins":29},"gpt-5.4":{"draws":6,"losses":12,"wins":28},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":24},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":40},"gpt-5.5":{"draws":4,"losses":12,"wins":28},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":39},"gpt-5.6-sol":{"draws":5,"losses":15,"wins":28},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":36},"gpt-6-astra":{"draws":2,"losses":36,"wins":10},"gpt-6-luna":{"draws":5,"losses":7,"wins":36},"gpt-6-sol":{"draws":4,"losses":17,"wins":27},"gpt-6.1-sol":{"draws":2,"losses":31,"wins":15},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":24},"inception/mercury-3":{"draws":5,"losses":4,"wins":23},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":24},"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":8,"losses":5,"wins":29},"meta/muse-spark-1.2":{"draws":6,"losses":9,"wins":31},"meta/muse-spark-1.3":{"draws":4,"losses":6,"wins":38},"meta/muse-spark-open":{"draws":4,"losses":9,"wins":33},"meta/muse-wonder":{"draws":5,"losses":19,"wins":24},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":4,"losses":5,"wins":33},"mistralai/mistral-large-4-0":{"draws":3,"losses":7,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":32},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":20,"wins":9},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":4,"wins":16},"o3":{"draws":5,"losses":6,"wins":55},"openai/gpt-oss-120b":{"draws":5,"losses":5,"wins":32},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":31},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":22},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":7,"wins":35},"qwen/qwen3.8-27b":{"draws":5,"losses":4,"wins":25},"qwen/qwen3.8-flash":{"draws":1,"losses":4,"wins":27},"qwen/qwen3.8-max":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-max-0902":{"draws":7,"losses":8,"wins":33},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":22,"losses":41,"wins":95},"stealth/space-bunny-alpha":{"draws":5,"losses":5,"wins":28},"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":7,"losses":2,"wins":17},"tencent/hy4-preview":{"draws":3,"losses":8,"wins":35},"thinkingmachines/inkling":{"draws":9,"losses":8,"wins":47},"thinkingmachines/inkling-small":{"draws":5,"losses":4,"wins":39},"unbiased/pareto-26.10":{"draws":2,"losses":9,"wins":5},"unbiased/pareto-26.10-preview":{"draws":1,"losses":11,"wins":4},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":9,"losses":10,"wins":29},"x-ai/grok-4.6":{"draws":6,"losses":12,"wins":30},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":24},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":13,"losses":16,"wins":67},"z-ai/glm-5.3":{"draws":5,"losses":15,"wins":26},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":32},"z-ai/glm-5.3-flashx":{"draws":5,"losses":9,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":20,"wins":5},"claude-fable-5":{"draws":4,"losses":26,"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":3,"losses":42,"wins":3},"claude-opus-4-8":{"draws":3,"losses":23,"wins":0},"claude-opus-5":{"draws":0,"losses":46,"wins":0},"claude-opus-5-5":{"draws":3,"losses":31,"wins":0},"claude-sonnet-5":{"draws":5,"losses":21,"wins":4},"claude-sonnet-5-5":{"draws":3,"losses":25,"wins":2},"cohere/north-mini-code":{"draws":1,"losses":9,"wins":6},"deepseek/deepseek-v4-flash":{"draws":5,"losses":26,"wins":15},"deepseek/deepseek-v4-pro":{"draws":2,"losses":24,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":21,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":26,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":24,"wins":4},"elorian/glimpse":{"draws":0,"losses":11,"wins":5},"fireworks/ember-1":{"draws":2,"losses":26,"wins":2},"gemini-3.1-pro-preview":{"draws":3,"losses":22,"wins":5},"gemini-4-argon":{"draws":0,"losses":29,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":9,"wins":13},"google/gemini-3.5-flash":{"draws":3,"losses":32,"wins":3},"google/gemini-3.5-flash-lite":{"draws":4,"losses":37,"wins":13},"google/gemini-3.6-flash":{"draws":2,"losses":52,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":30,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":10,"wins":4},"gpt-4.1":{"draws":0,"losses":10,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":21,"wins":6},"gpt-5.4":{"draws":4,"losses":21,"wins":5},"gpt-5.4-mini":{"draws":3,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":1,"losses":19,"wins":12},"gpt-5.5":{"draws":0,"losses":26,"wins":2},"gpt-5.6-luna":{"draws":4,"losses":21,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":29,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":24,"wins":3},"gpt-6-astra":{"draws":0,"losses":30,"wins":0},"gpt-6-luna":{"draws":2,"losses":23,"wins":5},"gpt-6-sol":{"draws":0,"losses":30,"wins":0},"gpt-6.1-sol":{"draws":0,"losses":30,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":10,"wins":8},"inception/mercury-3":{"draws":0,"losses":19,"wins":1},"inclusionai/ling-3.0-flash":{"draws":1,"losses":10,"wins":9},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":27,"wins":10},"meta/muse-glimmer-30b":{"draws":4,"losses":17,"wins":5},"meta/muse-spark-1.2":{"draws":1,"losses":25,"wins":2},"meta/muse-spark-1.3":{"draws":0,"losses":30,"wins":0},"meta/muse-spark-open":{"draws":3,"losses":26,"wins":1},"meta/muse-wonder":{"draws":1,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":9,"wins":5},"minimax/minimax-m3.1-flash":{"draws":3,"losses":19,"wins":4},"mistralai/mistral-large-4-0":{"draws":1,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":0,"losses":14,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":24,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":7,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":18,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":3},"o3":{"draws":1,"losses":45,"wins":4},"openai/gpt-oss-120b":{"draws":4,"losses":14,"wins":10},"poolside/laguna-s-2.1":{"draws":6,"losses":21,"wins":5},"qwen/qwen3.7-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":24,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":17,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":22,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":24,"wins":2},"recursive/flint-v1.0":{"draws":0,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":22,"wins":3},"stealth/ox-alpha":{"draws":14,"losses":85,"wins":9},"stealth/space-bunny-alpha":{"draws":2,"losses":18,"wins":4},"stepfun/step-3.7-flash":{"draws":2,"losses":13,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":0,"losses":27,"wins":3},"thinkingmachines/inkling":{"draws":6,"losses":24,"wins":10},"thinkingmachines/inkling-small":{"draws":3,"losses":20,"wins":7},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"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":1,"losses":25,"wins":4},"x-ai/grok-4.6":{"draws":3,"losses":26,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":25,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":2,"losses":29,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":3},"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":12,"losses":43,"wins":5},"z-ai/glm-5.3":{"draws":2,"losses":28,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":27,"wins":1},"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":8,"losses":10,"wins":8},"claude-fable-5":{"draws":4,"losses":23,"wins":3},"claude-fable-5-1":{"draws":0,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":16,"wins":7},"claude-opus-4-5":{"draws":18,"losses":23,"wins":9},"claude-opus-4-8":{"draws":6,"losses":23,"wins":1},"claude-opus-5":{"draws":4,"losses":41,"wins":1},"claude-opus-5-5":{"draws":0,"losses":34,"wins":0},"claude-sonnet-5":{"draws":9,"losses":12,"wins":9},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":14,"losses":18,"wins":18},"deepseek/deepseek-v4-pro":{"draws":4,"losses":16,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":21,"wins":5},"elorian/glimpse":{"draws":2,"losses":11,"wins":3},"fireworks/ember-1":{"draws":10,"losses":14,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":12,"wins":6},"gemini-4-argon":{"draws":1,"losses":27,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":13},"google/gemini-3.5-flash":{"draws":7,"losses":25,"wins":6},"google/gemini-3.5-flash-lite":{"draws":11,"losses":20,"wins":19},"google/gemini-3.6-flash":{"draws":10,"losses":33,"wins":13},"google/gemini-3.8-flash":{"draws":6,"losses":22,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":15,"wins":6},"gpt-5.4":{"draws":5,"losses":17,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":14},"gpt-5.5":{"draws":5,"losses":15,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":7},"gpt-5.6-sol":{"draws":4,"losses":22,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":15,"wins":9},"gpt-6-astra":{"draws":3,"losses":26,"wins":1},"gpt-6-luna":{"draws":13,"losses":12,"wins":5},"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":2,"wins":10},"inception/mercury-3":{"draws":9,"losses":10,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":10,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":10,"wins":14},"meta/muse-glimmer-30b":{"draws":8,"losses":7,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":16,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":8},"meta/muse-spark-open":{"draws":6,"losses":17,"wins":5},"meta/muse-wonder":{"draws":7,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":5},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":8},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":9,"losses":9,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":25,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":5,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":2},"o3":{"draws":6,"losses":29,"wins":11},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":4},"poolside/laguna-s-2.1":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":16,"wins":5},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":6,"losses":14,"wins":10},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":3},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":17,"wins":4},"stealth/ox-alpha":{"draws":15,"losses":44,"wins":23},"stealth/space-bunny-alpha":{"draws":9,"losses":6,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":13,"wins":6},"thinkingmachines/inkling":{"draws":8,"losses":15,"wins":13},"thinkingmachines/inkling-small":{"draws":9,"losses":7,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"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":5,"losses":18,"wins":7},"x-ai/grok-4.6":{"draws":6,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":18,"losses":14,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":18,"losses":25,"wins":17},"z-ai/glm-5.3":{"draws":4,"losses":19,"wins":5},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":13},"z-ai/glm-5.3-flashx":{"draws":5,"losses":16,"wins":9}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":9,"losses":35,"wins":4},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":8,"losses":22,"wins":16},"claude-opus-4-5":{"draws":27,"losses":21,"wins":30},"claude-opus-4-8":{"draws":10,"losses":23,"wins":11},"claude-opus-5":{"draws":14,"losses":56,"wins":12},"claude-opus-5-5":{"draws":3,"losses":45,"wins":4},"claude-sonnet-5":{"draws":12,"losses":20,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":26,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":18,"losses":16,"wins":38},"deepseek/deepseek-v4-pro":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":14,"losses":19,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":14,"wins":22},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":25},"google/gemini-3.5-flash-lite":{"draws":24,"losses":11,"wins":49},"google/gemini-3.6-flash":{"draws":23,"losses":42,"wins":27},"google/gemini-3.8-flash":{"draws":8,"losses":26,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":12,"wins":21},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":25},"gpt-5.5":{"draws":17,"losses":18,"wins":9},"gpt-5.6-luna":{"draws":16,"losses":11,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":19,"losses":12,"wins":15},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"gpt-6-luna":{"draws":13,"losses":22,"wins":13},"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":11,"losses":1,"wins":22},"inception/mercury-3":{"draws":11,"losses":13,"wins":8},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":5,"wins":31},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":26},"meta/muse-spark-1.2":{"draws":13,"losses":20,"wins":13},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":18},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":11},"meta/muse-wonder":{"draws":9,"losses":31,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":10,"losses":15,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":8},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":20,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":40,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":4,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":4},"o3":{"draws":7,"losses":13,"wins":46},"openai/gpt-oss-120b":{"draws":11,"losses":5,"wins":26},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":27},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":12},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":12},"qwen/qwen3.8-flash":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":14,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":23,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":16,"wins":15},"stealth/ox-alpha":{"draws":41,"losses":70,"wins":47},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":5,"wins":22},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":12,"losses":23,"wins":11},"thinkingmachines/inkling":{"draws":17,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"unbiased/pareto-26.10-preview":{"draws":3,"losses":13,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":2,"wins":8},"x-ai/grok-4.5":{"draws":14,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":9},"x-ai/grok-4.7":{"draws":3,"losses":28,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":13,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":10,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":12},"z-ai/glm-5.2":{"draws":31,"losses":26,"wins":39},"z-ai/glm-5.3":{"draws":7,"losses":35,"wins":4},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":16},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":17},"claude-fable-5":{"draws":4,"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":16,"losses":27,"wins":17},"claude-opus-4-8":{"draws":6,"losses":19,"wins":11},"claude-opus-5":{"draws":7,"losses":45,"wins":6},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":6,"losses":17,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":22,"wins":9},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":13,"wins":35},"deepseek/deepseek-v4-pro":{"draws":5,"losses":18,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":15,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":6},"elorian/glimpse":{"draws":4,"losses":11,"wins":5},"fireworks/ember-1":{"draws":13,"losses":16,"wins":7},"gemini-3.1-pro-preview":{"draws":7,"losses":12,"wins":17},"gemini-4-argon":{"draws":1,"losses":32,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":8,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":16,"losses":13,"wins":37},"google/gemini-3.6-flash":{"draws":16,"losses":31,"wins":23},"google/gemini-3.8-flash":{"draws":2,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":13},"gpt-4.1":{"draws":2,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":15,"wins":13},"gpt-5.4":{"draws":6,"losses":21,"wins":9},"gpt-5.4-mini":{"draws":5,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":21},"gpt-5.5":{"draws":10,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":12,"wins":17},"gpt-5.6-sol":{"draws":2,"losses":28,"wins":6},"gpt-5.6-terra":{"draws":6,"losses":20,"wins":8},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":6,"losses":16,"wins":14},"gpt-6-sol":{"draws":6,"losses":27,"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":8,"losses":1,"wins":17},"inception/mercury-3":{"draws":4,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":25},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":20},"meta/muse-spark-1.2":{"draws":5,"losses":19,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":24,"wins":7},"meta/muse-spark-open":{"draws":6,"losses":26,"wins":4},"meta/muse-wonder":{"draws":2,"losses":29,"wins":5},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":16},"minimax/minimax-m3.1-flash":{"draws":6,"losses":15,"wins":11},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":32,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":5},"o3":{"draws":6,"losses":22,"wins":20},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":25},"poolside/laguna-s-2.1":{"draws":3,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":9},"qwen/qwen3.8-27b":{"draws":3,"losses":15,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":13},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":7},"recursive/flint-v1.0":{"draws":1,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":15,"losses":60,"wins":27},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":5,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":10},"thinkingmachines/inkling":{"draws":10,"losses":9,"wins":29},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":24},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":6,"losses":21,"wins":9},"x-ai/grok-4.6":{"draws":7,"losses":22,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":22,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":17,"losses":9,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":15,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":27,"wins":29},"z-ai/glm-5.3":{"draws":4,"losses":27,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":3,"losses":23,"wins":10}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":14},"claude-fable-5":{"draws":10,"losses":37,"wins":1},"claude-fable-5-1":{"draws":0,"losses":54,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":32,"wins":3},"claude-opus-4-5":{"draws":25,"losses":44,"wins":9},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":11,"losses":66,"wins":5},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":12,"losses":30,"wins":6},"claude-sonnet-5-5":{"draws":11,"losses":32,"wins":5},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":24,"losses":27,"wins":21},"deepseek/deepseek-v4-pro":{"draws":13,"losses":23,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":33,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":35,"wins":4},"elorian/glimpse":{"draws":4,"losses":15,"wins":7},"fireworks/ember-1":{"draws":17,"losses":25,"wins":6},"gemini-3.1-pro-preview":{"draws":12,"losses":23,"wins":13},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":15,"losses":35,"wins":10},"google/gemini-3.5-flash-lite":{"draws":25,"losses":31,"wins":28},"google/gemini-3.6-flash":{"draws":24,"losses":54,"wins":14},"google/gemini-3.8-flash":{"draws":11,"losses":36,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":5,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":23,"wins":6},"gpt-5.4":{"draws":14,"losses":30,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":17,"wins":18},"gpt-5.5":{"draws":17,"losses":24,"wins":3},"gpt-5.6-luna":{"draws":16,"losses":24,"wins":8},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":29,"wins":3},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":15,"losses":24,"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":13,"losses":10,"wins":11},"inception/mercury-3":{"draws":11,"losses":14,"wins":7},"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":13,"losses":27,"wins":12},"meta/muse-glimmer-30b":{"draws":13,"losses":14,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":28,"wins":4},"meta/muse-spark-1.3":{"draws":11,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":11,"losses":32,"wins":3},"meta/muse-wonder":{"draws":10,"losses":36,"wins":2},"minimax/minimax-m3":{"draws":10,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":10,"losses":22,"wins":10},"mistralai/mistral-large-4-0":{"draws":10,"losses":18,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":26,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":42,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":12,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":16,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":2},"o3":{"draws":11,"losses":50,"wins":5},"openai/gpt-oss-120b":{"draws":7,"losses":14,"wins":5},"poolside/laguna-s-2.1":{"draws":16,"losses":20,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":31,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":18,"losses":28,"wins":2},"qwen/qwen3.8-max-0902":{"draws":12,"losses":34,"wins":2},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":26,"wins":5},"stealth/ox-alpha":{"draws":40,"losses":103,"wins":15},"stealth/space-bunny-alpha":{"draws":11,"losses":20,"wins":7},"stepfun/step-3.7-flash":{"draws":11,"losses":15,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":13,"wins":5},"tencent/hy4-preview":{"draws":15,"losses":23,"wins":8},"thinkingmachines/inkling":{"draws":18,"losses":24,"wins":22},"thinkingmachines/inkling-small":{"draws":17,"losses":15,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":30,"wins":2},"x-ai/grok-4.7":{"draws":5,"losses":36,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":2},"xiaomi/mimo-v2.5":{"draws":22,"losses":31,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":25,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":24,"wins":2},"z-ai/glm-5.2":{"draws":31,"losses":47,"wins":18},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":35,"wins":5},"z-ai/glm-5.3-flashx":{"draws":7,"losses":34,"wins":7}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":25,"wins":15},"claude-fable-5":{"draws":14,"losses":45,"wins":7},"claude-fable-5-1":{"draws":5,"losses":66,"wins":1},"claude-haiku-5-5":{"draws":19,"losses":31,"wins":12},"claude-opus-4-5":{"draws":40,"losses":55,"wins":11},"claude-opus-4-8":{"draws":23,"losses":30,"wins":5},"claude-opus-5":{"draws":16,"losses":100,"wins":6},"claude-opus-5-5":{"draws":5,"losses":69,"wins":0},"claude-sonnet-5":{"draws":23,"losses":36,"wins":7},"claude-sonnet-5-5":{"draws":16,"losses":39,"wins":11},"cohere/north-mini-code":{"draws":8,"losses":11,"wins":5},"deepseek/deepseek-v4-flash":{"draws":40,"losses":34,"wins":24},"deepseek/deepseek-v4-pro":{"draws":19,"losses":22,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":29,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":28,"losses":27,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":43,"wins":7},"elorian/glimpse":{"draws":11,"losses":18,"wins":5},"fireworks/ember-1":{"draws":29,"losses":28,"wins":9},"gemini-3.1-pro-preview":{"draws":23,"losses":29,"wins":14},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":21,"losses":47,"wins":12},"google/gemini-3.5-flash-lite":{"draws":41,"losses":34,"wins":39},"google/gemini-3.6-flash":{"draws":36,"losses":72,"wins":16},"google/gemini-3.8-flash":{"draws":12,"losses":48,"wins":6},"google/gemma-4-31b-it":{"draws":20,"losses":10,"wins":8},"gpt-4.1":{"draws":9,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":1},"gpt-5":{"draws":19,"losses":28,"wins":11},"gpt-5.4":{"draws":16,"losses":37,"wins":9},"gpt-5.4-mini":{"draws":15,"losses":18,"wins":11},"gpt-5.4-nano":{"draws":17,"losses":27,"wins":22},"gpt-5.5":{"draws":22,"losses":27,"wins":11},"gpt-5.6-luna":{"draws":30,"losses":23,"wins":13},"gpt-5.6-sol":{"draws":11,"losses":54,"wins":1},"gpt-5.6-terra":{"draws":23,"losses":34,"wins":5},"gpt-6-astra":{"draws":5,"losses":61,"wins":0},"gpt-6-luna":{"draws":24,"losses":33,"wins":9},"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":24,"losses":12,"wins":10},"inception/mercury-3":{"draws":19,"losses":22,"wins":5},"inclusionai/ling-3.0-flash":{"draws":19,"losses":13,"wins":12},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":26,"wins":22},"meta/muse-glimmer-30b":{"draws":25,"losses":13,"wins":20},"meta/muse-spark-1.2":{"draws":18,"losses":43,"wins":3},"meta/muse-spark-1.3":{"draws":19,"losses":40,"wins":7},"meta/muse-spark-open":{"draws":17,"losses":39,"wins":6},"meta/muse-wonder":{"draws":12,"losses":48,"wins":6},"minimax/minimax-m3":{"draws":13,"losses":11,"wins":12},"minimax/minimax-m3.1-flash":{"draws":16,"losses":23,"wins":15},"mistralai/mistral-large-4-0":{"draws":19,"losses":19,"wins":4},"mistralai/mistral-medium-3-5":{"draws":18,"losses":7,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":23,"losses":37,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":52,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":13,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":21,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":4},"o3":{"draws":15,"losses":45,"wins":22},"openai/gpt-oss-120b":{"draws":30,"losses":22,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":21,"wins":15},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":10},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":40,"wins":5},"qwen/qwen3.8-27b":{"draws":14,"losses":24,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":21,"wins":9},"qwen/qwen3.8-max":{"draws":21,"losses":36,"wins":9},"qwen/qwen3.8-max-0902":{"draws":22,"losses":38,"wins":6},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":20,"losses":34,"wins":8},"stealth/ox-alpha":{"draws":63,"losses":139,"wins":28},"stealth/space-bunny-alpha":{"draws":20,"losses":20,"wins":10},"stepfun/step-3.7-flash":{"draws":16,"losses":15,"wins":11},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":13,"wins":8},"tencent/hy4-preview":{"draws":16,"losses":33,"wins":13},"thinkingmachines/inkling":{"draws":34,"losses":26,"wins":28},"thinkingmachines/inkling-small":{"draws":25,"losses":12,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":21,"wins":0},"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":21,"losses":39,"wins":6},"x-ai/grok-4.6":{"draws":15,"losses":44,"wins":7},"x-ai/grok-4.7":{"draws":8,"losses":46,"wins":4},"x-ai/grok-build-0.1":{"draws":10,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":39,"losses":27,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":29,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":31,"wins":5},"z-ai/glm-5.2":{"draws":51,"losses":50,"wins":31},"z-ai/glm-5.3":{"draws":18,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":37,"wins":14},"z-ai/glm-5.3-flashx":{"draws":23,"losses":32,"wins":11}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":19},"claude-fable-5":{"draws":6,"losses":28,"wins":8},"claude-fable-5-1":{"draws":2,"losses":43,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":15,"wins":12},"claude-opus-4-5":{"draws":18,"losses":30,"wins":22},"claude-opus-4-8":{"draws":12,"losses":17,"wins":13},"claude-opus-5":{"draws":8,"losses":53,"wins":9},"claude-opus-5-5":{"draws":1,"losses":45,"wins":0},"claude-sonnet-5":{"draws":10,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":11},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":25,"losses":13,"wins":26},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":12,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":29,"wins":5},"elorian/glimpse":{"draws":3,"losses":11,"wins":8},"fireworks/ember-1":{"draws":10,"losses":18,"wins":14},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"gemini-4-argon":{"draws":4,"losses":33,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":17,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":19,"wins":34},"google/gemini-3.6-flash":{"draws":20,"losses":34,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":21,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":10},"gpt-4.1":{"draws":6,"losses":3,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":14,"wins":10},"gpt-5.4":{"draws":7,"losses":23,"wins":10},"gpt-5.4-mini":{"draws":6,"losses":8,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":22},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":14,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":9,"losses":19,"wins":12},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":10,"losses":20,"wins":12},"gpt-6-sol":{"draws":7,"losses":30,"wins":5},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":5,"wins":14},"inception/mercury-3":{"draws":9,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":11,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":22,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":21,"wins":13},"meta/muse-spark-open":{"draws":7,"losses":21,"wins":12},"meta/muse-wonder":{"draws":6,"losses":33,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":8,"losses":11,"wins":17},"mistralai/mistral-large-4-0":{"draws":9,"losses":14,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":19,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":10,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":5,"wins":10},"o3":{"draws":13,"losses":23,"wins":26},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":18},"poolside/laguna-s-2.1":{"draws":10,"losses":8,"wins":20},"qwen/qwen3.7-max":{"draws":1,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-27b":{"draws":8,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":17,"wins":17},"qwen/qwen3.8-max-0902":{"draws":15,"losses":19,"wins":8},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":19,"wins":10},"stealth/ox-alpha":{"draws":29,"losses":56,"wins":33},"stealth/space-bunny-alpha":{"draws":7,"losses":9,"wins":18},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":4,"losses":23,"wins":13},"thinkingmachines/inkling":{"draws":15,"losses":6,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":7,"wins":21},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":10,"losses":21,"wins":11},"x-ai/grok-4.6":{"draws":8,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":24,"wins":11},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":24,"losses":14,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":18,"losses":34,"wins":32},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":10},"z-ai/glm-5.3-flash":{"draws":13,"losses":17,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":19,"wins":12}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":12,"wins":14},"claude-fable-5":{"draws":3,"losses":28,"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":13,"losses":26,"wins":21},"claude-opus-4-8":{"draws":8,"losses":20,"wins":8},"claude-opus-5":{"draws":9,"losses":48,"wins":1},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":9,"losses":15,"wins":12},"claude-sonnet-5-5":{"draws":7,"losses":20,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":14,"losses":18,"wins":26},"deepseek/deepseek-v4-pro":{"draws":4,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":10,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":18,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":6},"elorian/glimpse":{"draws":2,"losses":13,"wins":3},"fireworks/ember-1":{"draws":8,"losses":17,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":13,"wins":12},"gemini-4-argon":{"draws":2,"losses":33,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":6,"losses":25,"wins":15},"google/gemini-3.5-flash-lite":{"draws":13,"losses":19,"wins":30},"google/gemini-3.6-flash":{"draws":12,"losses":36,"wins":20},"google/gemini-3.8-flash":{"draws":6,"losses":26,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":4,"wins":9},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":18,"wins":8},"gpt-5.4":{"draws":4,"losses":23,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":26},"gpt-5.5":{"draws":11,"losses":17,"wins":4},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":6,"losses":25,"wins":5},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":8},"gpt-6-astra":{"draws":2,"losses":34,"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":1,"wins":15},"inception/mercury-3":{"draws":7,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":15},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":23},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":6,"losses":23,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":18,"wins":9},"meta/muse-spark-open":{"draws":7,"losses":20,"wins":7},"meta/muse-wonder":{"draws":11,"losses":25,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":15,"wins":12},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":1},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":6,"wins":8},"o3":{"draws":5,"losses":29,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":3,"wins":17},"poolside/laguna-s-2.1":{"draws":8,"losses":18,"wins":10},"qwen/qwen3.7-max":{"draws":3,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":16,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":11},"stealth/ox-alpha":{"draws":15,"losses":65,"wins":20},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":3,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":31},"thinkingmachines/inkling-small":{"draws":9,"losses":8,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":6,"losses":23,"wins":7},"x-ai/grok-4.6":{"draws":12,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":9,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":16,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":18,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":32,"wins":26},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":18,"wins":11},"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":16,"losses":14,"wins":14},"claude-fable-5":{"draws":11,"losses":33,"wins":4},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":23,"wins":8},"claude-opus-4-5":{"draws":31,"losses":30,"wins":17},"claude-opus-4-8":{"draws":16,"losses":20,"wins":8},"claude-opus-5":{"draws":13,"losses":59,"wins":10},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":18,"losses":21,"wins":9},"claude-sonnet-5-5":{"draws":14,"losses":24,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":28,"losses":15,"wins":29},"deepseek/deepseek-v4-pro":{"draws":11,"losses":19,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":29,"wins":10},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":24,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":16},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":17},"google/gemini-3.5-flash-lite":{"draws":31,"losses":19,"wins":34},"google/gemini-3.6-flash":{"draws":23,"losses":49,"wins":20},"google/gemini-3.8-flash":{"draws":8,"losses":31,"wins":9},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":7,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":16,"losses":16,"wins":10},"gpt-5.4":{"draws":10,"losses":27,"wins":9},"gpt-5.4-mini":{"draws":11,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":19},"gpt-5.5":{"draws":16,"losses":19,"wins":9},"gpt-5.6-luna":{"draws":25,"losses":10,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":36,"wins":6},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":7,"losses":35,"wins":6},"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":16,"losses":3,"wins":15},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":16,"losses":2,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":24},"meta/muse-glimmer-30b":{"draws":21,"losses":2,"wins":19},"meta/muse-spark-1.2":{"draws":13,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":14,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":12,"losses":25,"wins":9},"meta/muse-wonder":{"draws":9,"losses":33,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":16,"losses":12,"wins":14},"mistralai/mistral-large-4-0":{"draws":14,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":3,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":23,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":8,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":8,"wins":6},"o3":{"draws":12,"losses":29,"wins":25},"openai/gpt-oss-120b":{"draws":20,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":13,"losses":6,"wins":27},"qwen/qwen3.7-max":{"draws":12,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":13,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-max":{"draws":18,"losses":17,"wins":13},"qwen/qwen3.8-max-0902":{"draws":18,"losses":26,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":18,"wins":14},"stealth/ox-alpha":{"draws":50,"losses":73,"wins":35},"stealth/space-bunny-alpha":{"draws":17,"losses":12,"wins":9},"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":13,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling":{"draws":20,"losses":11,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":25},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":11,"losses":30,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":27,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":9,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":34,"losses":16,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":6,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":17,"wins":6},"z-ai/glm-5.2":{"draws":40,"losses":31,"wins":25},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":36,"wins":5},"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":2,"losses":46,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":23,"wins":13},"elorian/glimpse":{"draws":7,"losses":8,"wins":7},"fireworks/ember-1":{"draws":14,"losses":13,"wins":15},"gemini-3.1-pro-preview":{"draws":11,"losses":14,"wins":17},"gemini-4-argon":{"draws":3,"losses":36,"wins":3},"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":21,"losses":16,"wins":37},"google/gemini-3.6-flash":{"draws":23,"losses":38,"wins":21},"google/gemini-3.8-flash":{"draws":7,"losses":28,"wins":7},"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":7,"losses":7,"wins":14},"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":32,"wins":4},"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},"inception/mercury-3":{"draws":11,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"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-spark-open":{"draws":15,"losses":16,"wins":9},"meta/muse-wonder":{"draws":10,"losses":27,"wins":5},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"minimax/minimax-m3.1-flash":{"draws":13,"losses":11,"wins":16},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":4,"wins":7},"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},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":14,"wins":11},"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":{"draws":1,"losses":13,"wins":0},"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":25,"losses":9,"wins":30},"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":12,"losses":5,"wins":27},"claude-fable-5":{"draws":10,"losses":18,"wins":20},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":15,"losses":15,"wins":16},"claude-opus-4-5":{"draws":24,"losses":13,"wins":41},"claude-opus-4-8":{"draws":17,"losses":11,"wins":16},"claude-opus-5":{"draws":13,"losses":59,"wins":10},"claude-opus-5-5":{"draws":7,"losses":43,"wins":2},"claude-sonnet-5":{"draws":12,"losses":9,"wins":27},"claude-sonnet-5-5":{"draws":4,"losses":20,"wins":24},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":6,"wins":45},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":19,"wins":16},"elorian/glimpse":{"draws":6,"losses":7,"wins":13},"fireworks/ember-1":{"draws":15,"losses":9,"wins":24},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":20},"gemini-4-argon":{"draws":10,"losses":27,"wins":11},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":15,"losses":12,"wins":33},"google/gemini-3.5-flash-lite":{"draws":28,"losses":3,"wins":53},"google/gemini-3.6-flash":{"draws":21,"losses":29,"wins":42},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":28},"google/gemma-4-31b-it":{"draws":14,"losses":1,"wins":13},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":11,"losses":4,"wins":27},"gpt-5.4":{"draws":10,"losses":17,"wins":19},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":20},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":32},"gpt-5.5":{"draws":13,"losses":16,"wins":15},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":11,"losses":24,"wins":13},"gpt-5.6-terra":{"draws":16,"losses":9,"wins":21},"gpt-6-astra":{"draws":6,"losses":39,"wins":3},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":6,"losses":28,"wins":14},"gpt-6.1-sol":{"draws":5,"losses":36,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":21},"inception/mercury-3":{"draws":11,"losses":4,"wins":17},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":32},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":23},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":15,"wins":22},"meta/muse-spark-open":{"draws":10,"losses":10,"wins":26},"meta/muse-wonder":{"draws":13,"losses":25,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":11,"losses":9,"wins":22},"mistralai/mistral-large-4-0":{"draws":11,"losses":3,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":10,"losses":8,"wins":28},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":12},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":3,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":0,"wins":15},"o3":{"draws":7,"losses":12,"wins":47},"openai/gpt-oss-120b":{"draws":15,"losses":6,"wins":21},"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":5,"losses":5,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":12,"wins":27},"qwen/qwen3.8-27b":{"draws":9,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":7,"losses":0,"wins":9},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-max-0902":{"draws":15,"losses":10,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":9,"wins":26},"stealth/ox-alpha":{"draws":40,"losses":41,"wins":77},"stealth/space-bunny-alpha":{"draws":13,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":0,"wins":27},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":4,"wins":16},"tencent/hy4-preview":{"draws":13,"losses":11,"wins":22},"thinkingmachines/inkling":{"draws":20,"losses":7,"wins":37},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":26},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":14,"losses":17,"wins":17},"x-ai/grok-4.6":{"draws":18,"losses":17,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":26,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":4,"wins":19},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":13,"wins":11},"z-ai/glm-5.2":{"draws":29,"losses":12,"wins":55},"z-ai/glm-5.3":{"draws":12,"losses":23,"wins":11},"z-ai/glm-5.3-flash":{"draws":6,"losses":14,"wins":28},"z-ai/glm-5.3-flashx":{"draws":11,"losses":16,"wins":21}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":10,"wins":20},"claude-fable-5":{"draws":5,"losses":31,"wins":12},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":27,"wins":12},"claude-opus-4-5":{"draws":24,"losses":17,"wins":37},"claude-opus-4-8":{"draws":10,"losses":22,"wins":12},"claude-opus-5":{"draws":15,"losses":59,"wins":8},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":15,"losses":12,"wins":21},"claude-sonnet-5-5":{"draws":9,"losses":27,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":15},"deepseek/deepseek-v4-flash":{"draws":19,"losses":12,"wins":41},"deepseek/deepseek-v4-pro":{"draws":14,"losses":13,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":13,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":7},"elorian/glimpse":{"draws":7,"losses":10,"wins":9},"fireworks/ember-1":{"draws":16,"losses":20,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":17,"wins":19},"gemini-4-argon":{"draws":0,"losses":46,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":15,"losses":21,"wins":24},"google/gemini-3.5-flash-lite":{"draws":26,"losses":18,"wins":40},"google/gemini-3.6-flash":{"draws":26,"losses":44,"wins":22},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":17},"google/gemma-4-31b-it":{"draws":10,"losses":1,"wins":17},"gpt-4.1":{"draws":6,"losses":5,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":12,"losses":8,"wins":22},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":11,"losses":11,"wins":26},"gpt-5.5":{"draws":15,"losses":18,"wins":11},"gpt-5.6-luna":{"draws":16,"losses":9,"wins":23},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":16,"wins":13},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":14,"losses":13,"wins":21},"gpt-6-sol":{"draws":6,"losses":35,"wins":7},"gpt-6.1-sol":{"draws":6,"losses":41,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":17},"inception/mercury-3":{"draws":13,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":15,"wins":25},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":13,"losses":12,"wins":21},"meta/muse-spark-1.3":{"draws":10,"losses":30,"wins":8},"meta/muse-spark-open":{"draws":13,"losses":20,"wins":13},"meta/muse-wonder":{"draws":11,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":7,"losses":1,"wins":18},"minimax/minimax-m3.1-flash":{"draws":10,"losses":15,"wins":17},"mistralai/mistral-large-4-0":{"draws":10,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":15,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":41,"wins":4},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":23},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":12,"losses":20,"wins":34},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":25},"poolside/laguna-s-2.1":{"draws":13,"losses":11,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":13,"wins":19},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":8,"wins":16},"qwen/qwen3.8-max-0902":{"draws":16,"losses":19,"wins":13},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":10,"wins":25},"stealth/ox-alpha":{"draws":35,"losses":64,"wins":59},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":14},"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":11,"losses":20,"wins":15},"thinkingmachines/inkling":{"draws":18,"losses":10,"wins":36},"thinkingmachines/inkling-small":{"draws":11,"losses":15,"wins":22},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":11,"losses":26,"wins":11},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":24,"losses":15,"wins":35},"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":28,"losses":26,"wins":42},"z-ai/glm-5.3":{"draws":12,"losses":24,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":22,"wins":16},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":15}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":13,"wins":23},"claude-fable-5":{"draws":8,"losses":35,"wins":5},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":11},"claude-opus-4-5":{"draws":22,"losses":41,"wins":15},"claude-opus-4-8":{"draws":11,"losses":24,"wins":9},"claude-opus-5":{"draws":15,"losses":58,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":10,"losses":17,"wins":21},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":32},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":20,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":28,"wins":9},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":10,"losses":23,"wins":15},"gemini-3.1-pro-preview":{"draws":9,"losses":20,"wins":19},"gemini-4-argon":{"draws":2,"losses":42,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":20},"google/gemini-3.5-flash-lite":{"draws":26,"losses":24,"wins":34},"google/gemini-3.6-flash":{"draws":17,"losses":49,"wins":26},"google/gemini-3.8-flash":{"draws":13,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":12},"gpt-4.1":{"draws":3,"losses":7,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":17,"wins":16},"gpt-5.4":{"draws":7,"losses":26,"wins":13},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":19,"wins":16},"gpt-5.5":{"draws":9,"losses":22,"wins":13},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":35,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":14,"wins":16},"gpt-6-astra":{"draws":4,"losses":44,"wins":0},"gpt-6-luna":{"draws":12,"losses":25,"wins":11},"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":14,"losses":3,"wins":17},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":16,"wins":31},"meta/muse-glimmer-30b":{"draws":13,"losses":8,"wins":21},"meta/muse-spark-1.2":{"draws":14,"losses":24,"wins":8},"meta/muse-spark-1.3":{"draws":13,"losses":25,"wins":10},"meta/muse-spark-open":{"draws":13,"losses":27,"wins":6},"meta/muse-wonder":{"draws":7,"losses":30,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"minimax/minimax-m3.1-flash":{"draws":11,"losses":15,"wins":16},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"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":9,"losses":17,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":43,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":10,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":10,"wins":4},"o3":{"draws":11,"losses":29,"wins":26},"openai/gpt-oss-120b":{"draws":10,"losses":9,"wins":23},"poolside/laguna-s-2.1":{"draws":16,"losses":14,"wins":16},"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":11,"losses":16,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":5},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":33,"losses":80,"wins":45},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"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":10,"losses":5,"wins":11},"tencent/hy4-preview":{"draws":9,"losses":25,"wins":12},"thinkingmachines/inkling":{"draws":22,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":12,"losses":11,"wins":25},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":11,"losses":26,"wins":11},"x-ai/grok-4.7":{"draws":9,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":25,"losses":19,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":10,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":6},"z-ai/glm-5.2":{"draws":32,"losses":30,"wins":34},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":22,"wins":12},"z-ai/glm-5.3-flashx":{"draws":11,"losses":25,"wins":12}},"recursive/flint-v1.0":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":21,"wins":9},"claude-fable-5":{"draws":3,"losses":39,"wins":0},"claude-fable-5-1":{"draws":2,"losses":44,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":25,"wins":8},"claude-opus-4-5":{"draws":18,"losses":47,"wins":5},"claude-opus-4-8":{"draws":11,"losses":29,"wins":2},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":12,"losses":27,"wins":3},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":12,"losses":36,"wins":16},"deepseek/deepseek-v4-pro":{"draws":8,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":27,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":1},"elorian/glimpse":{"draws":5,"losses":13,"wins":4},"fireworks/ember-1":{"draws":10,"losses":27,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":27,"wins":4},"gemini-4-argon":{"draws":3,"losses":39,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":12,"wins":12},"google/gemini-3.5-flash":{"draws":10,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":20,"losses":42,"wins":12},"google/gemini-3.6-flash":{"draws":26,"losses":45,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":7,"losses":12,"wins":7},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":5,"losses":21,"wins":10},"gpt-5.4":{"draws":6,"losses":30,"wins":4},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":17},"gpt-5.5":{"draws":11,"losses":25,"wins":2},"gpt-5.6-luna":{"draws":9,"losses":23,"wins":10},"gpt-5.6-sol":{"draws":3,"losses":38,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":28,"wins":2},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":11,"losses":26,"wins":5},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"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":12,"losses":8,"wins":12},"inception/mercury-3":{"draws":8,"losses":14,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":11,"losses":22,"wins":13},"meta/muse-glimmer-30b":{"draws":11,"losses":17,"wins":8},"meta/muse-spark-1.2":{"draws":7,"losses":30,"wins":3},"meta/muse-spark-1.3":{"draws":4,"losses":34,"wins":4},"meta/muse-spark-open":{"draws":5,"losses":32,"wins":3},"meta/muse-wonder":{"draws":6,"losses":36,"wins":0},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":10,"losses":19,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":17,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":35,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":17,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":1},"o3":{"draws":4,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":8,"losses":19,"wins":9},"poolside/laguna-s-2.1":{"draws":7,"losses":24,"wins":7},"qwen/qwen3.7-max":{"draws":5,"losses":13,"wins":8},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":18,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":17,"wins":3},"qwen/qwen3.8-max":{"draws":10,"losses":26,"wins":6},"qwen/qwen3.8-max-0902":{"draws":9,"losses":27,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":29,"wins":1},"stealth/ox-alpha":{"draws":23,"losses":85,"wins":10},"stealth/space-bunny-alpha":{"draws":9,"losses":15,"wins":10},"stepfun/step-3.7-flash":{"draws":3,"losses":16,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":27,"wins":4},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":14},"thinkingmachines/inkling-small":{"draws":12,"losses":14,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":30,"wins":0},"x-ai/grok-4.6":{"draws":7,"losses":30,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":35,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":11,"wins":0},"xiaomi/mimo-v2.5":{"draws":20,"losses":31,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":14,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":20,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":20,"wins":2},"z-ai/glm-5.2":{"draws":17,"losses":49,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":31,"wins":2},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":9},"z-ai/glm-5.3-flashx":{"draws":10,"losses":29,"wins":3}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":17},"claude-fable-5":{"draws":8,"losses":29,"wins":5},"claude-fable-5-1":{"draws":1,"losses":47,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":24,"wins":9},"claude-opus-4-5":{"draws":21,"losses":30,"wins":17},"claude-opus-4-8":{"draws":6,"losses":25,"wins":7},"claude-opus-5":{"draws":8,"losses":59,"wins":3},"claude-opus-5-5":{"draws":2,"losses":44,"wins":0},"claude-sonnet-5":{"draws":10,"losses":21,"wins":11},"claude-sonnet-5-5":{"draws":10,"losses":22,"wins":10},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":15,"losses":15,"wins":32},"deepseek/deepseek-v4-pro":{"draws":8,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":17,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":22,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":28,"wins":6},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":12,"losses":18,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":15,"wins":17},"gemini-4-argon":{"draws":3,"losses":36,"wins":3},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":14,"losses":19,"wins":19},"google/gemini-3.5-flash-lite":{"draws":22,"losses":14,"wins":38},"google/gemini-3.6-flash":{"draws":17,"losses":42,"wins":21},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":19},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":13,"wins":14},"gpt-5.4":{"draws":12,"losses":19,"wins":9},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":7,"losses":16,"wins":17},"gpt-5.5":{"draws":7,"losses":21,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":30,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":11,"wins":15},"gpt-6-astra":{"draws":2,"losses":39,"wins":1},"gpt-6-luna":{"draws":7,"losses":24,"wins":11},"gpt-6-sol":{"draws":5,"losses":35,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":39,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":18},"inception/mercury-3":{"draws":5,"losses":17,"wins":6},"inclusionai/ling-3.0-flash":{"draws":7,"losses":6,"wins":15},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":31},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":10,"losses":23,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":25,"wins":8},"meta/muse-spark-open":{"draws":7,"losses":31,"wins":2},"meta/muse-wonder":{"draws":6,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":9,"losses":16,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":7,"wins":6},"o3":{"draws":6,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":22},"poolside/laguna-s-2.1":{"draws":7,"losses":13,"wins":20},"qwen/qwen3.7-max":{"draws":7,"losses":8,"wins":9},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":25,"wins":8},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":33,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":26,"wins":8},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":10,"wins":9},"stealth/ox-alpha":{"draws":30,"losses":77,"wins":35},"stealth/space-bunny-alpha":{"draws":9,"losses":12,"wins":13},"stepfun/step-3.7-flash":{"draws":7,"losses":15,"wins":6},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":5,"losses":5,"wins":12},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":8},"thinkingmachines/inkling":{"draws":14,"losses":14,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":14,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":13,"losses":21,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":34,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":19,"losses":12,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":17,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":31,"wins":21},"z-ai/glm-5.3":{"draws":4,"losses":35,"wins":3},"z-ai/glm-5.3-flash":{"draws":5,"losses":25,"wins":12},"z-ai/glm-5.3-flashx":{"draws":8,"losses":26,"wins":8}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":33,"wins":81},"claude-fable-5":{"draws":27,"losses":92,"wins":37},"claude-fable-5-1":{"draws":6,"losses":168,"wins":8},"claude-haiku-5-5":{"draws":32,"losses":59,"wins":51},"claude-opus-4-5":{"draws":67,"losses":77,"wins":102},"claude-opus-4-8":{"draws":28,"losses":51,"wins":49},"claude-opus-5":{"draws":49,"losses":187,"wins":44},"claude-opus-5-5":{"draws":20,"losses":142,"wins":6},"claude-sonnet-5":{"draws":36,"losses":43,"wins":77},"claude-sonnet-5-5":{"draws":32,"losses":76,"wins":48},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":47},"deepseek/deepseek-v4-flash":{"draws":51,"losses":49,"wins":128},"deepseek/deepseek-v4-pro":{"draws":32,"losses":45,"wins":69},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":50,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":35,"losses":64,"wins":57},"deepseek/deepseek-v4.1-flash-1017":{"draws":26,"losses":83,"wins":47},"elorian/glimpse":{"draws":20,"losses":30,"wins":38},"fireworks/ember-1":{"draws":35,"losses":64,"wins":57},"gemini-3.1-pro-preview":{"draws":35,"losses":49,"wins":72},"gemini-4-argon":{"draws":16,"losses":125,"wins":15},"google/gemini-3.1-flash-lite":{"draws":19,"losses":13,"wins":54},"google/gemini-3.5-flash":{"draws":37,"losses":63,"wins":88},"google/gemini-3.5-flash-lite":{"draws":57,"losses":58,"wins":155},"google/gemini-3.6-flash":{"draws":72,"losses":126,"wins":102},"google/gemini-3.8-flash":{"draws":36,"losses":73,"wins":47},"google/gemma-4-31b-it":{"draws":18,"losses":17,"wins":51},"gpt-4.1":{"draws":10,"losses":9,"wins":33},"gpt-4.1-nano":{"draws":13,"losses":1,"wins":10},"gpt-5":{"draws":28,"losses":45,"wins":67},"gpt-5.4":{"draws":38,"losses":59,"wins":53},"gpt-5.4-mini":{"draws":28,"losses":17,"wins":59},"gpt-5.4-nano":{"draws":25,"losses":35,"wins":76},"gpt-5.5":{"draws":36,"losses":56,"wins":54},"gpt-5.6-luna":{"draws":49,"losses":31,"wins":76},"gpt-5.6-sol":{"draws":23,"losses":103,"wins":30},"gpt-5.6-terra":{"draws":37,"losses":39,"wins":74},"gpt-6-astra":{"draws":9,"losses":141,"wins":6},"gpt-6-luna":{"draws":37,"losses":57,"wins":62},"gpt-6-sol":{"draws":23,"losses":115,"wins":18},"gpt-6.1-sol":{"draws":15,"losses":131,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":33,"losses":11,"wins":58},"inception/mercury-3":{"draws":29,"losses":32,"wins":43},"inclusionai/ling-3.0-flash":{"draws":26,"losses":9,"wins":71},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":30,"losses":26,"wins":112},"meta/muse-glimmer-30b":{"draws":27,"losses":21,"wins":94},"meta/muse-spark-1.2":{"draws":36,"losses":55,"wins":61},"meta/muse-spark-1.3":{"draws":35,"losses":69,"wins":52},"meta/muse-spark-open":{"draws":31,"losses":76,"wins":43},"meta/muse-wonder":{"draws":37,"losses":76,"wins":43},"minimax/minimax-m3":{"draws":18,"losses":16,"wins":46},"minimax/minimax-m3.1-flash":{"draws":27,"losses":42,"wins":69},"mistralai/mistral-large-4-0":{"draws":33,"losses":24,"wins":43},"mistralai/mistral-medium-3-5":{"draws":17,"losses":20,"wins":57},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":9,"wins":19},"moonshotai/kimi-k3":{"draws":39,"losses":63,"wins":50},"moonshotai/kimi-k3.1-pro":{"draws":19,"losses":116,"wins":21},"nex-agi/nex-n2-pro":{"draws":15,"losses":14,"wins":55},"nex-agi/nex-n2.5-pro":{"draws":8,"losses":9,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":18,"wins":75},"nvidia/nemotron-3.5-super-vl":{"draws":19,"losses":19,"wins":32},"o3":{"draws":27,"losses":71,"wins":94},"openai/gpt-oss-120b":{"draws":28,"losses":25,"wins":89},"poolside/laguna-s-2.1":{"draws":32,"losses":31,"wins":97},"qwen/qwen3.7-max":{"draws":22,"losses":22,"wins":40},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":40},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":64,"wins":50},"qwen/qwen3.8-27b":{"draws":22,"losses":40,"wins":44},"qwen/qwen3.8-flash":{"draws":27,"losses":36,"wins":41},"qwen/qwen3.8-max":{"draws":45,"losses":52,"wins":59},"qwen/qwen3.8-max-0902":{"draws":28,"losses":71,"wins":57},"recursive/flint-v1.0":{"draws":8,"losses":4,"wins":26},"reflection/beam-1.0-501b-a23b":{"draws":28,"losses":50,"wins":70},"stealth/ox-alpha":{"draws":93,"losses":249,"wins":208},"stealth/space-bunny-alpha":{"draws":31,"losses":30,"wins":61},"stepfun/step-3.7-flash":{"draws":14,"losses":22,"wins":70},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":24,"losses":12,"wins":44},"tencent/hy4-preview":{"draws":31,"losses":67,"wins":52},"thinkingmachines/inkling":{"draws":53,"losses":46,"wins":117},"thinkingmachines/inkling-small":{"draws":38,"losses":37,"wins":81},"unbiased/pareto-26.10":{"draws":5,"losses":45,"wins":2},"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":36,"losses":72,"wins":48},"x-ai/grok-4.6":{"draws":40,"losses":64,"wins":52},"x-ai/grok-4.7":{"draws":16,"losses":98,"wins":18},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":35},"xiaomi/mimo-v2.5":{"draws":55,"losses":32,"wins":121},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":18,"wins":48},"xiaomi/mimo-v2.6-flash":{"draws":18,"losses":35,"wins":45},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":50,"wins":37},"z-ai/glm-5.2":{"draws":77,"losses":83,"wins":152},"z-ai/glm-5.3":{"draws":30,"losses":88,"wins":34},"z-ai/glm-5.3-flash":{"draws":28,"losses":76,"wins":52},"z-ai/glm-5.3-flashx":{"draws":25,"losses":78,"wins":53}},"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":0,"losses":48,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":20,"wins":8},"claude-opus-4-5":{"draws":21,"losses":23,"wins":24},"claude-opus-4-8":{"draws":10,"losses":23,"wins":5},"claude-opus-5":{"draws":9,"losses":56,"wins":5},"claude-opus-5-5":{"draws":1,"losses":40,"wins":1},"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":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":24,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":6},"elorian/glimpse":{"draws":5,"losses":10,"wins":7},"fireworks/ember-1":{"draws":14,"losses":20,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":19,"wins":11},"gemini-4-argon":{"draws":5,"losses":37,"wins":0},"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":17,"losses":28,"wins":29},"google/gemini-3.6-flash":{"draws":22,"losses":44,"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":12,"losses":22,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":6,"wins":12},"gpt-5.4-nano":{"draws":6,"losses":18,"wins":16},"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":21,"wins":4},"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":4,"wins":16},"inception/mercury-3":{"draws":9,"losses":10,"wins":7},"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":12,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":6,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":10,"losses":19,"wins":11},"meta/muse-wonder":{"draws":14,"losses":21,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":12},"minimax/minimax-m3.1-flash":{"draws":9,"losses":14,"wins":17},"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},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":3},"o3":{"draws":6,"losses":26,"wins":24},"openai/gpt-oss-120b":{"draws":11,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":9,"losses":14,"wins":15},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":15,"wins":8},"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":15,"losses":15,"wins":12},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":6},"stealth/ox-alpha":{"draws":31,"losses":76,"wins":35},"stealth/space-bunny-alpha":{"draws":7,"losses":11,"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":19,"wins":20},"thinkingmachines/inkling-small":{"draws":12,"losses":13,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":19,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":5},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":23,"losses":17,"wins":24},"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":32,"losses":28,"wins":24},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":30,"wins":5},"elorian/glimpse":{"draws":0,"losses":16,"wins":4},"fireworks/ember-1":{"draws":5,"losses":22,"wins":9},"gemini-3.1-pro-preview":{"draws":4,"losses":19,"wins":13},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"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":7,"losses":8,"wins":9},"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},"inception/mercury-3":{"draws":4,"losses":12,"wins":8},"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-spark-open":{"draws":1,"losses":29,"wins":6},"meta/muse-wonder":{"draws":1,"losses":32,"wins":3},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":8},"minimax/minimax-m3.1-flash":{"draws":1,"losses":18,"wins":13},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":13,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":11,"wins":4},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":16,"wins":14},"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":{"draws":0,"losses":12,"wins":0},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":2,"wins":4},"elorian/glimpse":{"draws":0,"losses":2,"wins":2},"fireworks/ember-1":{"draws":0,"losses":2,"wins":4},"gemini-3.1-pro-preview":{"draws":0,"losses":2,"wins":4},"gemini-4-argon":{"draws":0,"losses":4,"wins":2},"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},"inception/mercury-3":{"draws":0,"losses":0,"wins":6},"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-spark-open":{"draws":0,"losses":1,"wins":5},"meta/muse-wonder":{"draws":0,"losses":0,"wins":6},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"minimax/minimax-m3.1-flash":{"draws":0,"losses":0,"wins":2},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":0,"wins":4},"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":0,"wins":6},"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":{"draws":0,"losses":2,"wins":0},"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":9,"losses":6,"wins":25},"claude-fable-5":{"draws":3,"losses":30,"wins":9},"claude-fable-5-1":{"draws":0,"losses":44,"wins":4},"claude-haiku-5-5":{"draws":5,"losses":13,"wins":22},"claude-opus-4-5":{"draws":13,"losses":15,"wins":40},"claude-opus-4-8":{"draws":7,"losses":14,"wins":17},"claude-opus-5":{"draws":2,"losses":55,"wins":13},"claude-opus-5-5":{"draws":3,"losses":35,"wins":8},"claude-sonnet-5":{"draws":11,"losses":13,"wins":18},"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":11,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":8,"losses":9,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":19,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":23,"wins":12},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":8,"losses":16,"wins":18},"gemini-3.1-pro-preview":{"draws":7,"losses":10,"wins":25},"gemini-4-argon":{"draws":9,"losses":23,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":7,"losses":16,"wins":31},"google/gemini-3.5-flash-lite":{"draws":14,"losses":14,"wins":48},"google/gemini-3.6-flash":{"draws":8,"losses":40,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":19},"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":6,"losses":13,"wins":19},"gpt-5.4":{"draws":4,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":8,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":33},"gpt-5.5":{"draws":9,"losses":14,"wins":17},"gpt-5.6-luna":{"draws":7,"losses":11,"wins":24},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":20},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":20},"gpt-6-astra":{"draws":2,"losses":37,"wins":3},"gpt-6-luna":{"draws":8,"losses":10,"wins":24},"gpt-6-sol":{"draws":2,"losses":32,"wins":8},"gpt-6.1-sol":{"draws":0,"losses":38,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":3,"wins":18},"inception/mercury-3":{"draws":5,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":27},"meta/muse-spark-1.2":{"draws":7,"losses":13,"wins":20},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":22},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":12},"meta/muse-wonder":{"draws":6,"losses":19,"wins":17},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":2,"losses":12,"wins":12},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":6,"losses":18,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":3,"wins":12},"o3":{"draws":5,"losses":14,"wins":45},"openai/gpt-oss-120b":{"draws":7,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":24},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":0,"losses":7,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":15,"wins":18},"qwen/qwen3.8-27b":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.8-flash":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.8-max":{"draws":6,"losses":19,"wins":17},"qwen/qwen3.8-max-0902":{"draws":6,"losses":17,"wins":19},"recursive/flint-v1.0":{"draws":1,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":22},"stealth/ox-alpha":{"draws":31,"losses":55,"wins":56},"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":6,"losses":11,"wins":11},"thinkingmachines/inkling":{"draws":13,"losses":6,"wins":39},"thinkingmachines/inkling-small":{"draws":10,"losses":3,"wins":29},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":9,"losses":17,"wins":16},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":18,"wins":14},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":9,"losses":8,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":17},"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":18,"losses":20,"wins":46},"z-ai/glm-5.3":{"draws":4,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":2,"losses":21,"wins":19},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":26,"wins":1},"elorian/glimpse":{"draws":5,"losses":10,"wins":5},"fireworks/ember-1":{"draws":8,"losses":27,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":21,"wins":7},"gemini-4-argon":{"draws":4,"losses":29,"wins":3},"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},"inception/mercury-3":{"draws":7,"losses":12,"wins":1},"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":8,"losses":22,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":31,"wins":1},"meta/muse-spark-open":{"draws":8,"losses":27,"wins":1},"meta/muse-wonder":{"draws":8,"losses":27,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":8},"minimax/minimax-m3.1-flash":{"draws":12,"losses":20,"wins":4},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":30,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":4},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":16,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":1},"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},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":19,"wins":3},"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":{"draws":0,"losses":12,"wins":0},"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":12,"losses":20,"wins":12},"claude-fable-5":{"draws":10,"losses":34,"wins":4},"claude-fable-5-1":{"draws":5,"losses":49,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":33,"wins":3},"claude-opus-4-5":{"draws":21,"losses":50,"wins":7},"claude-opus-4-8":{"draws":12,"losses":28,"wins":4},"claude-opus-5":{"draws":15,"losses":61,"wins":6},"claude-opus-5-5":{"draws":4,"losses":48,"wins":0},"claude-sonnet-5":{"draws":16,"losses":25,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":29,"losses":29,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":29,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":24,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":33,"wins":7},"elorian/glimpse":{"draws":5,"losses":17,"wins":4},"fireworks/ember-1":{"draws":14,"losses":28,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":29,"wins":6},"gemini-4-argon":{"draws":4,"losses":41,"wins":3},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":11,"losses":36,"wins":13},"google/gemini-3.5-flash-lite":{"draws":26,"losses":42,"wins":16},"google/gemini-3.6-flash":{"draws":22,"losses":57,"wins":13},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":8},"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":11,"losses":23,"wins":8},"gpt-5.4":{"draws":14,"losses":27,"wins":5},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":29,"wins":9},"gpt-5.5":{"draws":12,"losses":22,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":18,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":25,"wins":9},"gpt-6-astra":{"draws":3,"losses":45,"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":14,"losses":10,"wins":10},"inception/mercury-3":{"draws":8,"losses":20,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":24,"wins":16},"meta/muse-glimmer-30b":{"draws":14,"losses":20,"wins":8},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":8},"meta/muse-spark-1.3":{"draws":8,"losses":35,"wins":5},"meta/muse-spark-open":{"draws":8,"losses":33,"wins":5},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":16,"wins":4},"minimax/minimax-m3.1-flash":{"draws":9,"losses":21,"wins":12},"mistralai/mistral-large-4-0":{"draws":10,"losses":15,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":9,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":43,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":23,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":10,"losses":45,"wins":11},"openai/gpt-oss-120b":{"draws":14,"losses":20,"wins":8},"poolside/laguna-s-2.1":{"draws":10,"losses":30,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":32,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":22,"wins":4},"qwen/qwen3.8-flash":{"draws":8,"losses":18,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":28,"wins":8},"qwen/qwen3.8-max-0902":{"draws":14,"losses":28,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":22,"wins":8},"stealth/ox-alpha":{"draws":41,"losses":94,"wins":23},"stealth/space-bunny-alpha":{"draws":12,"losses":17,"wins":9},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":13,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":31,"wins":5},"thinkingmachines/inkling":{"draws":20,"losses":32,"wins":12},"thinkingmachines/inkling-small":{"draws":10,"losses":14,"wins":8},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":32,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":39,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":8,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":28,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":5},"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":28,"losses":51,"wins":17},"z-ai/glm-5.3":{"draws":7,"losses":34,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":34,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":32,"wins":6}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":12,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":2},"fireworks/ember-1":{"draws":0,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":3},"gemini-4-argon":{"draws":0,"losses":12,"wins":0},"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},"inception/mercury-3":{"draws":0,"losses":8,"wins":0},"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-spark-open":{"draws":0,"losses":12,"wins":0},"meta/muse-wonder":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":10,"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":12,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":7,"wins":3},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":4,"wins":0},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":7,"wins":1},"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":{"draws":0,"losses":4,"wins":0},"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":31},"claude-fable-5":{"draws":9,"losses":24,"wins":15},"claude-fable-5-1":{"draws":5,"losses":46,"wins":3},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":21},"claude-opus-4-5":{"draws":19,"losses":18,"wins":41},"claude-opus-4-8":{"draws":8,"losses":15,"wins":21},"claude-opus-5":{"draws":13,"losses":52,"wins":17},"claude-opus-5-5":{"draws":5,"losses":40,"wins":7},"claude-sonnet-5":{"draws":12,"losses":10,"wins":26},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":13,"losses":8,"wins":51},"deepseek/deepseek-v4-pro":{"draws":8,"losses":11,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":20,"wins":17},"elorian/glimpse":{"draws":5,"losses":9,"wins":12},"fireworks/ember-1":{"draws":11,"losses":15,"wins":22},"gemini-3.1-pro-preview":{"draws":9,"losses":13,"wins":26},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":10,"losses":21,"wins":29},"google/gemini-3.5-flash-lite":{"draws":17,"losses":14,"wins":53},"google/gemini-3.6-flash":{"draws":22,"losses":29,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":16,"wins":24},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":18},"gpt-4.1":{"draws":5,"losses":3,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":7,"wins":27},"gpt-5.4":{"draws":14,"losses":17,"wins":15},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":18},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":27},"gpt-5.5":{"draws":13,"losses":9,"wins":22},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":13},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":23},"gpt-6-astra":{"draws":5,"losses":38,"wins":5},"gpt-6-luna":{"draws":10,"losses":15,"wins":23},"gpt-6-sol":{"draws":7,"losses":33,"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":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":10,"losses":6,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":28},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":36},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":30},"meta/muse-spark-1.2":{"draws":10,"losses":10,"wins":26},"meta/muse-spark-1.3":{"draws":10,"losses":16,"wins":22},"meta/muse-spark-open":{"draws":8,"losses":16,"wins":22},"meta/muse-wonder":{"draws":9,"losses":25,"wins":14},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"minimax/minimax-m3.1-flash":{"draws":11,"losses":8,"wins":23},"mistralai/mistral-large-4-0":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":30,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":12},"o3":{"draws":7,"losses":17,"wins":42},"openai/gpt-oss-120b":{"draws":11,"losses":3,"wins":28},"poolside/laguna-s-2.1":{"draws":10,"losses":6,"wins":30},"qwen/qwen3.7-max":{"draws":8,"losses":7,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":4,"losses":7,"wins":23},"qwen/qwen3.8-flash":{"draws":12,"losses":6,"wins":14},"qwen/qwen3.8-max":{"draws":8,"losses":14,"wins":26},"qwen/qwen3.8-max-0902":{"draws":10,"losses":15,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":5,"wins":26},"stealth/ox-alpha":{"draws":30,"losses":45,"wins":83},"stealth/space-bunny-alpha":{"draws":8,"losses":5,"wins":25},"stepfun/step-3.7-flash":{"draws":3,"losses":7,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":2,"wins":18},"tencent/hy4-preview":{"draws":9,"losses":14,"wins":23},"thinkingmachines/inkling":{"draws":19,"losses":5,"wins":40},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":8,"losses":8,"wins":16},"x-ai/grok-4.6":{"draws":16,"losses":16,"wins":16},"x-ai/grok-4.7":{"draws":6,"losses":24,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":20,"losses":5,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":4,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":24,"losses":15,"wins":57},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":8,"losses":15,"wins":25},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":22}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":36},"claude-fable-5":{"draws":7,"losses":17,"wins":24},"claude-fable-5-1":{"draws":4,"losses":42,"wins":8},"claude-haiku-5-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-5":{"draws":15,"losses":15,"wins":48},"claude-opus-4-8":{"draws":10,"losses":11,"wins":23},"claude-opus-5":{"draws":11,"losses":50,"wins":21},"claude-opus-5-5":{"draws":7,"losses":37,"wins":8},"claude-sonnet-5":{"draws":10,"losses":8,"wins":30},"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":11,"losses":5,"wins":56},"deepseek/deepseek-v4-pro":{"draws":8,"losses":5,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":4,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":13,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":12,"wins":22},"elorian/glimpse":{"draws":7,"losses":6,"wins":13},"fireworks/ember-1":{"draws":8,"losses":7,"wins":33},"gemini-3.1-pro-preview":{"draws":11,"losses":7,"wins":30},"gemini-4-argon":{"draws":5,"losses":34,"wins":9},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":40},"google/gemini-3.5-flash-lite":{"draws":12,"losses":6,"wins":66},"google/gemini-3.6-flash":{"draws":18,"losses":20,"wins":54},"google/gemini-3.8-flash":{"draws":11,"losses":16,"wins":21},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":5,"losses":0,"wins":11},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":4,"wins":29},"gpt-5.4":{"draws":10,"losses":11,"wins":25},"gpt-5.4-mini":{"draws":8,"losses":1,"wins":23},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":42},"gpt-5.5":{"draws":8,"losses":15,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":36},"gpt-5.6-sol":{"draws":10,"losses":13,"wins":25},"gpt-5.6-terra":{"draws":13,"losses":6,"wins":27},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":7,"losses":2,"wins":39},"gpt-6-sol":{"draws":8,"losses":28,"wins":12},"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":7,"losses":1,"wins":26},"inception/mercury-3":{"draws":8,"losses":6,"wins":18},"inclusionai/ling-3.0-flash":{"draws":7,"losses":0,"wins":27},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":6,"wins":38},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":35},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":32},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":26},"meta/muse-spark-open":{"draws":9,"losses":7,"wins":30},"meta/muse-wonder":{"draws":10,"losses":16,"wins":22},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":19},"minimax/minimax-m3.1-flash":{"draws":12,"losses":5,"wins":25},"mistralai/mistral-large-4-0":{"draws":6,"losses":6,"wins":18},"mistralai/mistral-medium-3-5":{"draws":7,"losses":1,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":33,"wins":10},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":0,"wins":17},"o3":{"draws":9,"losses":3,"wins":54},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":40},"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":10,"losses":10,"wins":28},"qwen/qwen3.8-27b":{"draws":7,"losses":3,"wins":24},"qwen/qwen3.8-flash":{"draws":9,"losses":4,"wins":19},"qwen/qwen3.8-max":{"draws":12,"losses":10,"wins":26},"qwen/qwen3.8-max-0902":{"draws":11,"losses":9,"wins":28},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":7,"wins":27},"stealth/ox-alpha":{"draws":30,"losses":29,"wins":99},"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":7,"losses":1,"wins":18},"tencent/hy4-preview":{"draws":8,"losses":7,"wins":31},"thinkingmachines/inkling":{"draws":19,"losses":3,"wins":42},"thinkingmachines/inkling-small":{"draws":9,"losses":2,"wins":37},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":14,"losses":9,"wins":25},"x-ai/grok-4.6":{"draws":12,"losses":7,"wins":13},"x-ai/grok-4.7":{"draws":5,"losses":19,"wins":18},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":20,"losses":2,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":8,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":10,"wins":15},"z-ai/glm-5.2":{"draws":20,"losses":9,"wins":67},"z-ai/glm-5.3":{"draws":8,"losses":21,"wins":17},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":25},"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":29,"wins":17},"claude-haiku-5-5":{"draws":0,"losses":2,"wins":38},"claude-opus-4-5":{"draws":2,"losses":3,"wins":63},"claude-opus-4-8":{"draws":2,"losses":5,"wins":31},"claude-opus-5":{"draws":11,"losses":24,"wins":45},"claude-opus-5-5":{"draws":5,"losses":29,"wins":12},"claude-sonnet-5":{"draws":3,"losses":5,"wins":34},"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":2,"losses":4,"wins":56},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":3,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":6,"wins":30},"elorian/glimpse":{"draws":1,"losses":0,"wins":23},"fireworks/ember-1":{"draws":1,"losses":6,"wins":35},"gemini-3.1-pro-preview":{"draws":3,"losses":5,"wins":34},"gemini-4-argon":{"draws":3,"losses":22,"wins":17},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":43},"google/gemini-3.5-flash-lite":{"draws":5,"losses":8,"wins":59},"google/gemini-3.6-flash":{"draws":2,"losses":8,"wins":70},"google/gemini-3.8-flash":{"draws":0,"losses":5,"wins":37},"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":3,"losses":0,"wins":37},"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":6,"losses":27,"wins":9},"gpt-6-luna":{"draws":3,"losses":1,"wins":38},"gpt-6-sol":{"draws":3,"losses":15,"wins":24},"gpt-6.1-sol":{"draws":2,"losses":26,"wins":14},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":25},"inception/mercury-3":{"draws":2,"losses":2,"wins":24},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":3,"wins":41},"meta/muse-glimmer-30b":{"draws":0,"losses":1,"wins":39},"meta/muse-spark-1.2":{"draws":0,"losses":5,"wins":37},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":33},"meta/muse-spark-open":{"draws":2,"losses":4,"wins":34},"meta/muse-wonder":{"draws":1,"losses":10,"wins":31},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":23},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":34},"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":7,"wins":34},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":17,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":35},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":17},"o3":{"draws":3,"losses":2,"wins":49},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":35},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"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":5,"wins":34},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":3,"wins":33},"stealth/ox-alpha":{"draws":12,"losses":15,"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":9,"wins":30},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":51},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":4},"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":6,"wins":17},"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":6,"wins":20},"z-ai/glm-5.2":{"draws":3,"losses":6,"wins":75},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":28},"z-ai/glm-5.3-flash":{"draws":4,"losses":10,"wins":28},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":33}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":21,"wins":11},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":12,"losses":30,"wins":4},"claude-opus-4-5":{"draws":24,"losses":41,"wins":13},"claude-opus-4-8":{"draws":9,"losses":28,"wins":7},"claude-opus-5":{"draws":15,"losses":64,"wins":3},"claude-opus-5-5":{"draws":1,"losses":51,"wins":0},"claude-sonnet-5":{"draws":17,"losses":27,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":33,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":31,"wins":19},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":26,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":35,"wins":7},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":16,"losses":24,"wins":8},"gemini-3.1-pro-preview":{"draws":12,"losses":22,"wins":14},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":14,"losses":37,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":27,"wins":27},"google/gemini-3.6-flash":{"draws":27,"losses":58,"wins":7},"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":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":21,"wins":8},"gpt-5.4":{"draws":11,"losses":28,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":14,"wins":9},"gpt-5.4-nano":{"draws":7,"losses":26,"wins":15},"gpt-5.5":{"draws":19,"losses":17,"wins":8},"gpt-5.6-luna":{"draws":15,"losses":22,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":26,"wins":6},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"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":16,"losses":8,"wins":10},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":10,"losses":5,"wins":19},"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":14,"losses":12,"wins":16},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":8},"meta/muse-spark-open":{"draws":10,"losses":29,"wins":7},"meta/muse-wonder":{"draws":10,"losses":33,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":11},"minimax/minimax-m3.1-flash":{"draws":13,"losses":18,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":25,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":37,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":12,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":14,"wins":5},"o3":{"draws":12,"losses":38,"wins":16},"openai/gpt-oss-120b":{"draws":15,"losses":10,"wins":17},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":12,"losses":21,"wins":1},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":26,"wins":7},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":33,"losses":105,"wins":20},"stealth/space-bunny-alpha":{"draws":9,"losses":19,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":15,"wins":9},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":12,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":20,"losses":16,"wins":28},"thinkingmachines/inkling-small":{"draws":16,"losses":15,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":13,"losses":30,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"xiaomi/mimo-v2.5":{"draws":30,"losses":18,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":13,"wins":4},"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":36,"losses":38,"wins":22},"z-ai/glm-5.3":{"draws":10,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":30,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":30,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":36,"wins":13},"claude-fable-5":{"draws":16,"losses":70,"wins":4},"claude-fable-5-1":{"draws":5,"losses":92,"wins":3},"claude-haiku-5-5":{"draws":29,"losses":51,"wins":10},"claude-opus-4-5":{"draws":57,"losses":73,"wins":20},"claude-opus-4-8":{"draws":33,"losses":49,"wins":8},"claude-opus-5":{"draws":23,"losses":124,"wins":15},"claude-opus-5-5":{"draws":5,"losses":89,"wins":4},"claude-sonnet-5":{"draws":34,"losses":40,"wins":16},"claude-sonnet-5-5":{"draws":23,"losses":55,"wins":12},"cohere/north-mini-code":{"draws":9,"losses":13,"wins":10},"deepseek/deepseek-v4-flash":{"draws":52,"losses":40,"wins":42},"deepseek/deepseek-v4-pro":{"draws":30,"losses":40,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":41,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":30,"losses":49,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":24,"losses":61,"wins":5},"elorian/glimpse":{"draws":16,"losses":22,"wins":10},"fireworks/ember-1":{"draws":32,"losses":49,"wins":9},"gemini-3.1-pro-preview":{"draws":35,"losses":35,"wins":20},"gemini-4-argon":{"draws":6,"losses":83,"wins":1},"google/gemini-3.1-flash-lite":{"draws":22,"losses":13,"wins":29},"google/gemini-3.5-flash":{"draws":36,"losses":59,"wins":19},"google/gemini-3.5-flash-lite":{"draws":54,"losses":45,"wins":57},"google/gemini-3.6-flash":{"draws":58,"losses":98,"wins":14},"google/gemini-3.8-flash":{"draws":25,"losses":58,"wins":7},"google/gemma-4-31b-it":{"draws":28,"losses":15,"wins":13},"gpt-4.1":{"draws":12,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":24,"losses":35,"wins":17},"gpt-5.4":{"draws":26,"losses":48,"wins":10},"gpt-5.4-mini":{"draws":23,"losses":25,"wins":12},"gpt-5.4-nano":{"draws":24,"losses":38,"wins":30},"gpt-5.5":{"draws":30,"losses":46,"wins":6},"gpt-5.6-luna":{"draws":35,"losses":36,"wins":19},"gpt-5.6-sol":{"draws":17,"losses":72,"wins":1},"gpt-5.6-terra":{"draws":31,"losses":49,"wins":6},"gpt-6-astra":{"draws":5,"losses":84,"wins":1},"gpt-6-luna":{"draws":34,"losses":43,"wins":13},"gpt-6-sol":{"draws":16,"losses":69,"wins":5},"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":33,"losses":13,"wins":24},"inception/mercury-3":{"draws":23,"losses":27,"wins":10},"inclusionai/ling-3.0-flash":{"draws":29,"losses":13,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":28,"losses":31,"wins":35},"meta/muse-glimmer-30b":{"draws":30,"losses":25,"wins":25},"meta/muse-spark-1.2":{"draws":28,"losses":51,"wins":9},"meta/muse-spark-1.3":{"draws":23,"losses":58,"wins":9},"meta/muse-spark-open":{"draws":25,"losses":54,"wins":5},"meta/muse-wonder":{"draws":26,"losses":60,"wins":4},"minimax/minimax-m3":{"draws":21,"losses":16,"wins":15},"minimax/minimax-m3.1-flash":{"draws":24,"losses":32,"wins":20},"mistralai/mistral-large-4-0":{"draws":24,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":24,"losses":10,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":43,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":78,"wins":1},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":7,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":29,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":16,"losses":18,"wins":10},"o3":{"draws":22,"losses":80,"wins":16},"openai/gpt-oss-120b":{"draws":28,"losses":26,"wins":24},"poolside/laguna-s-2.1":{"draws":23,"losses":30,"wins":27},"qwen/qwen3.7-max":{"draws":19,"losses":26,"wins":9},"qwen/qwen3.7-plus":{"draws":21,"losses":17,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":44,"wins":7},"qwen/qwen3.8-27b":{"draws":21,"losses":34,"wins":7},"qwen/qwen3.8-flash":{"draws":24,"losses":22,"wins":14},"qwen/qwen3.8-max":{"draws":35,"losses":45,"wins":10},"qwen/qwen3.8-max-0902":{"draws":31,"losses":46,"wins":13},"recursive/flint-v1.0":{"draws":12,"losses":6,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":31,"losses":42,"wins":11},"stealth/ox-alpha":{"draws":73,"losses":146,"wins":35},"stealth/space-bunny-alpha":{"draws":30,"losses":31,"wins":13},"stepfun/step-3.7-flash":{"draws":17,"losses":22,"wins":19},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":24,"losses":16,"wins":14},"tencent/hy4-preview":{"draws":24,"losses":48,"wins":12},"thinkingmachines/inkling":{"draws":41,"losses":33,"wins":42},"thinkingmachines/inkling-small":{"draws":36,"losses":28,"wins":26},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"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":27,"losses":59,"wins":4},"x-ai/grok-4.6":{"draws":24,"losses":59,"wins":7},"x-ai/grok-4.7":{"draws":10,"losses":66,"wins":6},"x-ai/grok-build-0.1":{"draws":14,"losses":10,"wins":6},"xiaomi/mimo-v2.5":{"draws":54,"losses":38,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":22,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":37,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":38,"wins":4},"z-ai/glm-5.2":{"draws":65,"losses":79,"wins":36},"z-ai/glm-5.3":{"draws":22,"losses":63,"wins":1},"z-ai/glm-5.3-flash":{"draws":26,"losses":53,"wins":11},"z-ai/glm-5.3-flashx":{"draws":29,"losses":55,"wins":6}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":17},"claude-fable-5":{"draws":2,"losses":32,"wins":2},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":19,"wins":10},"claude-opus-4-5":{"draws":9,"losses":28,"wins":23},"claude-opus-4-8":{"draws":4,"losses":22,"wins":10},"claude-opus-5":{"draws":8,"losses":46,"wins":4},"claude-opus-5-5":{"draws":2,"losses":38,"wins":0},"claude-sonnet-5":{"draws":1,"losses":20,"wins":15},"claude-sonnet-5-5":{"draws":6,"losses":24,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":8,"losses":20,"wins":26},"deepseek/deepseek-v4-pro":{"draws":6,"losses":16,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":23,"wins":10},"elorian/glimpse":{"draws":3,"losses":9,"wins":8},"fireworks/ember-1":{"draws":10,"losses":14,"wins":12},"gemini-3.1-pro-preview":{"draws":2,"losses":16,"wins":18},"gemini-4-argon":{"draws":0,"losses":33,"wins":3},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":8,"losses":24,"wins":16},"google/gemini-3.5-flash-lite":{"draws":13,"losses":20,"wins":33},"google/gemini-3.6-flash":{"draws":12,"losses":39,"wins":19},"google/gemini-3.8-flash":{"draws":5,"losses":24,"wins":7},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":12},"gpt-4.1":{"draws":1,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":14,"wins":11},"gpt-5.4":{"draws":5,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":16},"gpt-5.4-nano":{"draws":3,"losses":14,"wins":23},"gpt-5.5":{"draws":6,"losses":21,"wins":7},"gpt-5.6-luna":{"draws":1,"losses":18,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":10},"gpt-6-astra":{"draws":1,"losses":34,"wins":1},"gpt-6-luna":{"draws":6,"losses":18,"wins":12},"gpt-6-sol":{"draws":4,"losses":29,"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":5,"losses":6,"wins":15},"inception/mercury-3":{"draws":3,"losses":13,"wins":6},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":15},"inclusionai/ling-3.1-flash":{"draws":1,"losses":1,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":10,"wins":25},"meta/muse-glimmer-30b":{"draws":5,"losses":9,"wins":18},"meta/muse-spark-1.2":{"draws":3,"losses":17,"wins":14},"meta/muse-spark-1.3":{"draws":4,"losses":21,"wins":11},"meta/muse-spark-open":{"draws":7,"losses":22,"wins":7},"meta/muse-wonder":{"draws":3,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":15},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":30,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":9,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":8,"wins":7},"o3":{"draws":7,"losses":22,"wins":31},"openai/gpt-oss-120b":{"draws":3,"losses":8,"wins":19},"poolside/laguna-s-2.1":{"draws":7,"losses":8,"wins":17},"qwen/qwen3.7-max":{"draws":3,"losses":11,"wins":8},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":17,"wins":12},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":14},"qwen/qwen3.8-flash":{"draws":3,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":3,"losses":21,"wins":12},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":14,"wins":12},"stealth/ox-alpha":{"draws":13,"losses":52,"wins":37},"stealth/space-bunny-alpha":{"draws":9,"losses":8,"wins":13},"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":5,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":3,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":6,"losses":12,"wins":30},"thinkingmachines/inkling-small":{"draws":8,"losses":10,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"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":5,"losses":15,"wins":16},"x-ai/grok-4.6":{"draws":6,"losses":21,"wins":9},"x-ai/grok-4.7":{"draws":0,"losses":26,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":9},"xiaomi/mimo-v2.5":{"draws":9,"losses":9,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":12,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":12,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":29,"wins":30},"z-ai/glm-5.3":{"draws":4,"losses":26,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":23,"wins":10},"z-ai/glm-5.3-flashx":{"draws":6,"losses":17,"wins":13}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":9,"wins":34},"claude-fable-5":{"draws":5,"losses":26,"wins":17},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":17},"claude-opus-4-5":{"draws":9,"losses":18,"wins":51},"claude-opus-4-8":{"draws":5,"losses":11,"wins":28},"claude-opus-5":{"draws":7,"losses":64,"wins":11},"claude-opus-5-5":{"draws":3,"losses":47,"wins":2},"claude-sonnet-5":{"draws":4,"losses":12,"wins":32},"claude-sonnet-5-5":{"draws":2,"losses":24,"wins":22},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":5,"losses":12,"wins":55},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":22,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":21,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":26,"wins":16},"elorian/glimpse":{"draws":2,"losses":9,"wins":15},"fireworks/ember-1":{"draws":2,"losses":19,"wins":27},"gemini-3.1-pro-preview":{"draws":5,"losses":13,"wins":30},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":27},"google/gemini-3.5-flash":{"draws":6,"losses":17,"wins":37},"google/gemini-3.5-flash-lite":{"draws":13,"losses":8,"wins":63},"google/gemini-3.6-flash":{"draws":7,"losses":33,"wins":52},"google/gemini-3.8-flash":{"draws":6,"losses":20,"wins":22},"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":1,"losses":0,"wins":5},"gpt-5":{"draws":2,"losses":10,"wins":30},"gpt-5.4":{"draws":9,"losses":19,"wins":18},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":24},"gpt-5.4-nano":{"draws":7,"losses":11,"wins":30},"gpt-5.5":{"draws":4,"losses":21,"wins":19},"gpt-5.6-luna":{"draws":5,"losses":15,"wins":28},"gpt-5.6-sol":{"draws":2,"losses":31,"wins":15},"gpt-5.6-terra":{"draws":5,"losses":14,"wins":27},"gpt-6-astra":{"draws":2,"losses":43,"wins":3},"gpt-6-luna":{"draws":6,"losses":13,"wins":29},"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":3,"losses":4,"wins":27},"inception/mercury-3":{"draws":3,"losses":12,"wins":17},"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":6,"losses":13,"wins":33},"meta/muse-glimmer-30b":{"draws":5,"losses":7,"wins":30},"meta/muse-spark-1.2":{"draws":5,"losses":20,"wins":21},"meta/muse-spark-1.3":{"draws":6,"losses":20,"wins":22},"meta/muse-spark-open":{"draws":4,"losses":24,"wins":18},"meta/muse-wonder":{"draws":1,"losses":31,"wins":16},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":1,"losses":9,"wins":32},"mistralai/mistral-large-4-0":{"draws":9,"losses":7,"wins":14},"mistralai/mistral-medium-3-5":{"draws":3,"losses":5,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":14,"wins":25},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":34,"wins":7},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":6,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":6,"wins":13},"o3":{"draws":7,"losses":15,"wins":44},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":33},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"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":6,"losses":17,"wins":25},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":20},"qwen/qwen3.8-flash":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.8-max":{"draws":5,"losses":20,"wins":23},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":27},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":17,"wins":25},"stealth/ox-alpha":{"draws":20,"losses":63,"wins":75},"stealth/space-bunny-alpha":{"draws":4,"losses":7,"wins":27},"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":1,"losses":7,"wins":18},"tencent/hy4-preview":{"draws":7,"losses":19,"wins":20},"thinkingmachines/inkling":{"draws":13,"losses":9,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":1,"wins":36},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":6,"losses":19,"wins":23},"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":6,"losses":14,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":8,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":8,"losses":23,"wins":65},"z-ai/glm-5.3":{"draws":5,"losses":28,"wins":13},"z-ai/glm-5.3-flash":{"draws":5,"losses":18,"wins":25},"z-ai/glm-5.3-flashx":{"draws":2,"losses":21,"wins":25}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":15,"wins":27},"elorian/glimpse":{"draws":4,"losses":9,"wins":13},"fireworks/ember-1":{"draws":7,"losses":11,"wins":30},"gemini-3.1-pro-preview":{"draws":2,"losses":9,"wins":37},"gemini-4-argon":{"draws":5,"losses":25,"wins":18},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":30},"google/gemini-3.5-flash":{"draws":8,"losses":11,"wins":41},"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":7,"wins":34},"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},"inception/mercury-3":{"draws":6,"losses":5,"wins":21},"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-spark-open":{"draws":3,"losses":15,"wins":28},"meta/muse-wonder":{"draws":9,"losses":15,"wins":24},"minimax/minimax-m3":{"draws":1,"losses":3,"wins":22},"minimax/minimax-m3.1-flash":{"draws":3,"losses":8,"wins":31},"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},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":19,"wins":19},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":6,"wins":16},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":7,"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":{"draws":0,"losses":16,"wins":0},"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":25,"losses":18,"wins":45},"claude-fable-5":{"draws":23,"losses":58,"wins":15},"claude-fable-5-1":{"draws":6,"losses":100,"wins":2},"claude-haiku-5-5":{"draws":23,"losses":39,"wins":30},"claude-opus-4-5":{"draws":52,"losses":48,"wins":56},"claude-opus-4-8":{"draws":24,"losses":40,"wins":24},"claude-opus-5":{"draws":24,"losses":131,"wins":9},"claude-opus-5-5":{"draws":5,"losses":94,"wins":5},"claude-sonnet-5":{"draws":25,"losses":35,"wins":36},"claude-sonnet-5-5":{"draws":19,"losses":53,"wins":24},"cohere/north-mini-code":{"draws":10,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":50,"losses":33,"wins":61},"deepseek/deepseek-v4-pro":{"draws":27,"losses":30,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":36,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":37,"losses":37,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":22,"losses":54,"wins":20},"elorian/glimpse":{"draws":13,"losses":23,"wins":16},"fireworks/ember-1":{"draws":28,"losses":41,"wins":27},"gemini-3.1-pro-preview":{"draws":26,"losses":34,"wins":36},"gemini-4-argon":{"draws":9,"losses":83,"wins":4},"google/gemini-3.1-flash-lite":{"draws":19,"losses":5,"wins":40},"google/gemini-3.5-flash":{"draws":30,"losses":40,"wins":50},"google/gemini-3.5-flash-lite":{"draws":55,"losses":39,"wins":74},"google/gemini-3.6-flash":{"draws":39,"losses":82,"wins":63},"google/gemini-3.8-flash":{"draws":21,"losses":50,"wins":25},"google/gemma-4-31b-it":{"draws":25,"losses":8,"wins":23},"gpt-4.1":{"draws":13,"losses":5,"wins":14},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":4},"gpt-5":{"draws":27,"losses":29,"wins":28},"gpt-5.4":{"draws":27,"losses":39,"wins":26},"gpt-5.4-mini":{"draws":26,"losses":10,"wins":28},"gpt-5.4-nano":{"draws":22,"losses":28,"wins":46},"gpt-5.5":{"draws":34,"losses":40,"wins":14},"gpt-5.6-luna":{"draws":39,"losses":20,"wins":37},"gpt-5.6-sol":{"draws":12,"losses":60,"wins":24},"gpt-5.6-terra":{"draws":34,"losses":31,"wins":27},"gpt-6-astra":{"draws":9,"losses":82,"wins":5},"gpt-6-luna":{"draws":31,"losses":35,"wins":30},"gpt-6-sol":{"draws":12,"losses":72,"wins":12},"gpt-6.1-sol":{"draws":15,"losses":78,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":34},"inception/mercury-3":{"draws":22,"losses":24,"wins":18},"inclusionai/ling-3.0-flash":{"draws":29,"losses":13,"wins":26},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":30,"losses":23,"wins":51},"meta/muse-glimmer-30b":{"draws":32,"losses":18,"wins":34},"meta/muse-spark-1.2":{"draws":24,"losses":46,"wins":22},"meta/muse-spark-1.3":{"draws":24,"losses":45,"wins":27},"meta/muse-spark-open":{"draws":22,"losses":46,"wins":24},"meta/muse-wonder":{"draws":24,"losses":52,"wins":20},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":29},"minimax/minimax-m3.1-flash":{"draws":24,"losses":26,"wins":34},"mistralai/mistral-large-4-0":{"draws":29,"losses":19,"wins":12},"mistralai/mistral-medium-3-5":{"draws":20,"losses":7,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":12},"moonshotai/kimi-k3":{"draws":33,"losses":30,"wins":29},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":73,"wins":12},"nex-agi/nex-n2-pro":{"draws":14,"losses":6,"wins":28},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":7,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":20,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":15,"losses":13,"wins":16},"o3":{"draws":21,"losses":53,"wins":58},"openai/gpt-oss-120b":{"draws":39,"losses":10,"wins":35},"poolside/laguna-s-2.1":{"draws":32,"losses":24,"wins":36},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":26},"qwen/qwen3.7-plus":{"draws":12,"losses":11,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":43,"wins":26},"qwen/qwen3.8-27b":{"draws":21,"losses":20,"wins":27},"qwen/qwen3.8-flash":{"draws":15,"losses":27,"wins":22},"qwen/qwen3.8-max":{"draws":24,"losses":41,"wins":31},"qwen/qwen3.8-max-0902":{"draws":30,"losses":44,"wins":22},"recursive/flint-v1.0":{"draws":5,"losses":6,"wins":17},"reflection/beam-1.0-501b-a23b":{"draws":29,"losses":35,"wins":24},"stealth/ox-alpha":{"draws":78,"losses":145,"wins":93},"stealth/space-bunny-alpha":{"draws":28,"losses":23,"wins":25},"stepfun/step-3.7-flash":{"draws":18,"losses":7,"wins":43},"stepfun/step-5-preview":{"draws":2,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":17,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":17,"losses":47,"wins":28},"thinkingmachines/inkling":{"draws":38,"losses":30,"wins":60},"thinkingmachines/inkling-small":{"draws":30,"losses":12,"wins":54},"unbiased/pareto-26.10":{"draws":1,"losses":30,"wins":1},"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":28,"losses":41,"wins":27},"x-ai/grok-4.6":{"draws":25,"losses":52,"wins":19},"x-ai/grok-4.7":{"draws":9,"losses":60,"wins":15},"x-ai/grok-build-0.1":{"draws":14,"losses":4,"wins":14},"xiaomi/mimo-v2.5":{"draws":54,"losses":18,"wins":76},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":10,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":25,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":17,"losses":32,"wins":15},"z-ai/glm-5.2":{"draws":54,"losses":46,"wins":60},"z-ai/glm-5.3":{"draws":18,"losses":58,"wins":16},"z-ai/glm-5.3-flash":{"draws":21,"losses":44,"wins":31},"z-ai/glm-5.3-flashx":{"draws":29,"losses":42,"wins":25}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":8,"losses":18,"wins":22},"claude-fable-5-1":{"draws":5,"losses":42,"wins":7},"claude-haiku-5-5":{"draws":9,"losses":9,"wins":28},"claude-opus-4-5":{"draws":15,"losses":5,"wins":58},"claude-opus-4-8":{"draws":5,"losses":11,"wins":28},"claude-opus-5":{"draws":13,"losses":51,"wins":18},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":15,"wins":28},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":17},"deepseek/deepseek-v4-flash":{"draws":13,"losses":3,"wins":56},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":8,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":14,"wins":29},"elorian/glimpse":{"draws":4,"losses":5,"wins":17},"fireworks/ember-1":{"draws":5,"losses":11,"wins":32},"gemini-3.1-pro-preview":{"draws":7,"losses":9,"wins":32},"gemini-4-argon":{"draws":5,"losses":32,"wins":11},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":43},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":70},"google/gemini-3.6-flash":{"draws":18,"losses":18,"wins":56},"google/gemini-3.8-flash":{"draws":9,"losses":11,"wins":28},"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":3,"losses":8,"wins":31},"gpt-5.4":{"draws":5,"losses":12,"wins":29},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":24},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":37},"gpt-5.5":{"draws":10,"losses":10,"wins":24},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":40},"gpt-5.6-sol":{"draws":8,"losses":23,"wins":17},"gpt-5.6-terra":{"draws":11,"losses":4,"wins":31},"gpt-6-astra":{"draws":6,"losses":40,"wins":2},"gpt-6-luna":{"draws":9,"losses":9,"wins":30},"gpt-6-sol":{"draws":5,"losses":26,"wins":17},"gpt-6.1-sol":{"draws":11,"losses":30,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":0,"wins":25},"inception/mercury-3":{"draws":7,"losses":7,"wins":18},"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":8,"losses":2,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":34},"meta/muse-spark-1.2":{"draws":6,"losses":13,"wins":27},"meta/muse-spark-1.3":{"draws":8,"losses":13,"wins":27},"meta/muse-spark-open":{"draws":5,"losses":12,"wins":29},"meta/muse-wonder":{"draws":4,"losses":23,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":27},"mistralai/mistral-large-4-0":{"draws":4,"losses":6,"wins":20},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":5,"losses":17,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":28,"wins":17},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"o3":{"draws":5,"losses":8,"wins":53},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":32},"poolside/laguna-s-2.1":{"draws":7,"losses":5,"wins":34},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":12,"wins":30},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":23},"qwen/qwen3.8-max":{"draws":9,"losses":8,"wins":31},"qwen/qwen3.8-max-0902":{"draws":7,"losses":7,"wins":34},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":4,"wins":34},"stealth/ox-alpha":{"draws":22,"losses":38,"wins":98},"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":3,"losses":12,"wins":31},"thinkingmachines/inkling":{"draws":12,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":5,"losses":15,"wins":28},"x-ai/grok-4.6":{"draws":9,"losses":15,"wins":24},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":15,"losses":1,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":21},"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":16,"losses":14,"wins":66},"z-ai/glm-5.3":{"draws":9,"losses":8,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":9,"wins":28},"z-ai/glm-5.3-flashx":{"draws":6,"losses":10,"wins":32}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":7,"wins":27},"claude-fable-5":{"draws":8,"losses":23,"wins":17},"claude-fable-5-1":{"draws":5,"losses":45,"wins":4},"claude-haiku-5-5":{"draws":9,"losses":13,"wins":24},"claude-opus-4-5":{"draws":19,"losses":13,"wins":46},"claude-opus-4-8":{"draws":8,"losses":12,"wins":24},"claude-opus-5":{"draws":9,"losses":54,"wins":19},"claude-opus-5-5":{"draws":3,"losses":43,"wins":6},"claude-sonnet-5":{"draws":9,"losses":7,"wins":32},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":16,"losses":8,"wins":48},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":20,"wins":19},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":7,"losses":13,"wins":28},"gemini-3.1-pro-preview":{"draws":9,"losses":11,"wins":28},"gemini-4-argon":{"draws":6,"losses":35,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":7,"losses":11,"wins":42},"google/gemini-3.5-flash-lite":{"draws":13,"losses":7,"wins":64},"google/gemini-3.6-flash":{"draws":12,"losses":25,"wins":55},"google/gemini-3.8-flash":{"draws":8,"losses":23,"wins":17},"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":6,"losses":11,"wins":25},"gpt-5.4":{"draws":8,"losses":20,"wins":18},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":24},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":32},"gpt-5.5":{"draws":10,"losses":14,"wins":20},"gpt-5.6-luna":{"draws":12,"losses":7,"wins":29},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":11,"wins":24},"gpt-6-astra":{"draws":6,"losses":37,"wins":5},"gpt-6-luna":{"draws":14,"losses":10,"wins":24},"gpt-6-sol":{"draws":7,"losses":27,"wins":14},"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":10,"losses":0,"wins":24},"inception/mercury-3":{"draws":4,"losses":10,"wins":18},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":37},"meta/muse-glimmer-30b":{"draws":8,"losses":4,"wins":30},"meta/muse-spark-1.2":{"draws":6,"losses":18,"wins":22},"meta/muse-spark-1.3":{"draws":11,"losses":14,"wins":23},"meta/muse-spark-open":{"draws":9,"losses":13,"wins":24},"meta/muse-wonder":{"draws":7,"losses":23,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":5,"wins":17},"minimax/minimax-m3.1-flash":{"draws":6,"losses":12,"wins":24},"mistralai/mistral-large-4-0":{"draws":8,"losses":7,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":24},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":31,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":8,"losses":18,"wins":40},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":29},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":15},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":14,"wins":23},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":20},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":15},"qwen/qwen3.8-max":{"draws":7,"losses":16,"wins":25},"qwen/qwen3.8-max-0902":{"draws":16,"losses":14,"wins":18},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":9,"wins":28},"stealth/ox-alpha":{"draws":23,"losses":53,"wins":82},"stealth/space-bunny-alpha":{"draws":7,"losses":3,"wins":28},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":28},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":16},"tencent/hy4-preview":{"draws":3,"losses":18,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":5,"wins":48},"thinkingmachines/inkling-small":{"draws":9,"losses":4,"wins":35},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":2},"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":6,"losses":19,"wins":23},"x-ai/grok-4.6":{"draws":9,"losses":17,"wins":22},"x-ai/grok-4.7":{"draws":7,"losses":22,"wins":13},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":12},"xiaomi/mimo-v2.5":{"draws":16,"losses":5,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":1,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":13,"wins":15},"z-ai/glm-5.2":{"draws":16,"losses":15,"wins":65},"z-ai/glm-5.3":{"draws":9,"losses":22,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":22},"z-ai/glm-5.3-flashx":{"draws":10,"losses":16,"wins":22}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":11,"wins":27},"claude-fable-5":{"draws":10,"losses":28,"wins":10},"claude-fable-5-1":{"draws":5,"losses":43,"wins":6},"claude-haiku-5-5":{"draws":7,"losses":26,"wins":13},"claude-opus-4-5":{"draws":21,"losses":18,"wins":39},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":4,"losses":46,"wins":2},"claude-sonnet-5":{"draws":9,"losses":15,"wins":24},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":19},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":17,"losses":15,"wins":40},"deepseek/deepseek-v4-pro":{"draws":9,"losses":20,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":16,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":22,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":12},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":10,"losses":21,"wins":17},"gemini-3.1-pro-preview":{"draws":8,"losses":16,"wins":24},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":21},"google/gemini-3.5-flash":{"draws":13,"losses":23,"wins":24},"google/gemini-3.5-flash-lite":{"draws":14,"losses":25,"wins":45},"google/gemini-3.6-flash":{"draws":18,"losses":40,"wins":34},"google/gemini-3.8-flash":{"draws":10,"losses":25,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":6,"wins":12},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":7,"losses":18,"wins":17},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":23},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":8,"losses":21,"wins":15},"gpt-5.6-luna":{"draws":11,"losses":14,"wins":23},"gpt-5.6-sol":{"draws":9,"losses":30,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":14,"wins":18},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"gpt-6-luna":{"draws":10,"losses":19,"wins":19},"gpt-6-sol":{"draws":4,"losses":33,"wins":11},"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":8,"losses":3,"wins":23},"inception/mercury-3":{"draws":7,"losses":11,"wins":14},"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":10,"losses":6,"wins":36},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":20,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":24,"wins":15},"meta/muse-spark-open":{"draws":10,"losses":22,"wins":14},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":8,"losses":13,"wins":21},"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":4,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":6},"nex-agi/nex-n2-pro":{"draws":1,"losses":4,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":11,"wins":26},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":4,"losses":31,"wins":31},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":7,"losses":15,"wins":24},"qwen/qwen3.7-max":{"draws":5,"losses":8,"wins":15},"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":9,"losses":6,"wins":17},"qwen/qwen3.8-max":{"draws":9,"losses":21,"wins":18},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":17,"wins":19},"stealth/ox-alpha":{"draws":32,"losses":64,"wins":62},"stealth/space-bunny-alpha":{"draws":10,"losses":10,"wins":18},"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":3,"wins":18},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":12},"thinkingmachines/inkling":{"draws":16,"losses":8,"wins":40},"thinkingmachines/inkling-small":{"draws":9,"losses":11,"wins":28},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"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":22,"wins":18},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":13},"x-ai/grok-4.7":{"draws":6,"losses":27,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":10,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":17,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":24,"losses":27,"wins":45},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":11},"z-ai/glm-5.3-flash":{"draws":9,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":8}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":5},"claude-fable-5":{"draws":3,"losses":36,"wins":3},"claude-fable-5-1":{"draws":1,"losses":45,"wins":2},"claude-haiku-5-5":{"draws":8,"losses":29,"wins":3},"claude-opus-4-5":{"draws":17,"losses":40,"wins":11},"claude-opus-4-8":{"draws":7,"losses":30,"wins":1},"claude-opus-5":{"draws":7,"losses":62,"wins":1},"claude-opus-5-5":{"draws":0,"losses":46,"wins":0},"claude-sonnet-5":{"draws":7,"losses":31,"wins":4},"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":14,"losses":32,"wins":16},"deepseek/deepseek-v4-pro":{"draws":10,"losses":26,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":28,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":33,"wins":5},"elorian/glimpse":{"draws":4,"losses":14,"wins":6},"fireworks/ember-1":{"draws":9,"losses":27,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":27,"wins":9},"gemini-4-argon":{"draws":0,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":10,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":33,"wins":13},"google/gemini-3.5-flash-lite":{"draws":15,"losses":39,"wins":22},"google/gemini-3.6-flash":{"draws":16,"losses":54,"wins":12},"google/gemini-3.8-flash":{"draws":7,"losses":31,"wins":4},"google/gemma-4-31b-it":{"draws":9,"losses":8,"wins":7},"gpt-4.1":{"draws":3,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":2},"gpt-5":{"draws":9,"losses":18,"wins":11},"gpt-5.4":{"draws":10,"losses":25,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":14,"wins":8},"gpt-5.4-nano":{"draws":5,"losses":20,"wins":17},"gpt-5.5":{"draws":11,"losses":26,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":24,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":30,"wins":4},"gpt-6-astra":{"draws":1,"losses":40,"wins":1},"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":6,"losses":10,"wins":12},"inception/mercury-3":{"draws":3,"losses":19,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":7,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":21,"wins":15},"meta/muse-glimmer-30b":{"draws":10,"losses":19,"wins":9},"meta/muse-spark-1.2":{"draws":8,"losses":27,"wins":5},"meta/muse-spark-1.3":{"draws":3,"losses":35,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":30,"wins":4},"meta/muse-wonder":{"draws":5,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":7,"losses":19,"wins":12},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":1},"nex-agi/nex-n2-pro":{"draws":4,"losses":10,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":17,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":3},"o3":{"draws":15,"losses":38,"wins":11},"openai/gpt-oss-120b":{"draws":7,"losses":17,"wins":12},"poolside/laguna-s-2.1":{"draws":11,"losses":20,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":14,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":12,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":28,"wins":3},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":6},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":24,"wins":5},"qwen/qwen3.8-max-0902":{"draws":8,"losses":29,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":23,"losses":100,"wins":19},"stealth/space-bunny-alpha":{"draws":8,"losses":21,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":11,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":29,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":24,"wins":20},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":5,"losses":32,"wins":5},"x-ai/grok-4.6":{"draws":8,"losses":29,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":33,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":17,"losses":27,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":12,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":20,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":22,"wins":2},"z-ai/glm-5.2":{"draws":29,"losses":41,"wins":14},"z-ai/glm-5.3":{"draws":7,"losses":32,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":26,"wins":6},"z-ai/glm-5.3-flashx":{"draws":3,"losses":32,"wins":7}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":5,"wins":31},"claude-fable-5":{"draws":5,"losses":18,"wins":9},"claude-fable-5-1":{"draws":3,"losses":48,"wins":3},"claude-haiku-5-5":{"draws":8,"losses":14,"wins":24},"claude-opus-4-5":{"draws":19,"losses":16,"wins":43},"claude-opus-4-8":{"draws":11,"losses":17,"wins":16},"claude-opus-5":{"draws":13,"losses":55,"wins":14},"claude-opus-5-5":{"draws":1,"losses":46,"wins":5},"claude-sonnet-5":{"draws":12,"losses":12,"wins":24},"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":16,"losses":7,"wins":49},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":20,"wins":18},"elorian/glimpse":{"draws":5,"losses":12,"wins":9},"fireworks/ember-1":{"draws":14,"losses":10,"wins":24},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":1,"losses":41,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":26},"google/gemini-3.5-flash":{"draws":14,"losses":16,"wins":30},"google/gemini-3.5-flash-lite":{"draws":21,"losses":12,"wins":51},"google/gemini-3.6-flash":{"draws":20,"losses":31,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":23,"wins":17},"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":13,"losses":4,"wins":25},"gpt-5.4":{"draws":14,"losses":13,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":20},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":34},"gpt-5.5":{"draws":16,"losses":10,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":6,"wins":28},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":15},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":24},"gpt-6-astra":{"draws":4,"losses":38,"wins":6},"gpt-6-luna":{"draws":12,"losses":9,"wins":27},"gpt-6-sol":{"draws":7,"losses":30,"wins":11},"gpt-6.1-sol":{"draws":3,"losses":38,"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},"inception/mercury-3":{"draws":13,"losses":4,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":35},"meta/muse-glimmer-30b":{"draws":12,"losses":1,"wins":29},"meta/muse-spark-1.2":{"draws":11,"losses":13,"wins":22},"meta/muse-spark-1.3":{"draws":8,"losses":19,"wins":21},"meta/muse-spark-open":{"draws":13,"losses":10,"wins":23},"meta/muse-wonder":{"draws":11,"losses":22,"wins":15},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":18},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":21},"mistralai/mistral-large-4-0":{"draws":8,"losses":8,"wins":14},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":7},"moonshotai/kimi-k3":{"draws":14,"losses":10,"wins":22},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":40,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":5,"wins":29},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":0,"wins":14},"o3":{"draws":7,"losses":11,"wins":48},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":14,"losses":7,"wins":25},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":19},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":14,"wins":19},"qwen/qwen3.8-27b":{"draws":11,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":15},"qwen/qwen3.8-max":{"draws":12,"losses":13,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":12,"wins":23},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":10,"wins":24},"stealth/ox-alpha":{"draws":34,"losses":53,"wins":71},"stealth/space-bunny-alpha":{"draws":12,"losses":7,"wins":19},"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":12,"losses":4,"wins":10},"tencent/hy4-preview":{"draws":7,"losses":16,"wins":23},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":43},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":11,"losses":21,"wins":16},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":21},"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":16,"losses":3,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":3,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":9,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":19,"wins":12},"z-ai/glm-5.2":{"draws":29,"losses":18,"wins":49},"z-ai/glm-5.3":{"draws":9,"losses":27,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":9,"losses":18,"wins":21}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":38},"claude-fable-5":{"draws":7,"losses":5,"wins":36},"claude-fable-5-1":{"draws":2,"losses":28,"wins":8},"claude-haiku-5-5":{"draws":3,"losses":6,"wins":37},"claude-opus-4-5":{"draws":7,"losses":2,"wins":69},"claude-opus-4-8":{"draws":4,"losses":5,"wins":35},"claude-opus-5":{"draws":12,"losses":24,"wins":46},"claude-opus-5-5":{"draws":5,"losses":25,"wins":22},"claude-sonnet-5":{"draws":4,"losses":2,"wins":42},"claude-sonnet-5-5":{"draws":4,"losses":14,"wins":30},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":70},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":3,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":7,"wins":38},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":3,"losses":1,"wins":44},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":42},"gemini-4-argon":{"draws":7,"losses":19,"wins":22},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":51},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":3,"wins":83},"google/gemini-3.8-flash":{"draws":5,"losses":5,"wins":38},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":25},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":40},"gpt-5.4":{"draws":5,"losses":7,"wins":34},"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":5,"wins":36},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":41},"gpt-5.6-sol":{"draws":5,"losses":8,"wins":35},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":42},"gpt-6-astra":{"draws":4,"losses":30,"wins":14},"gpt-6-luna":{"draws":5,"losses":1,"wins":42},"gpt-6-sol":{"draws":6,"losses":14,"wins":28},"gpt-6.1-sol":{"draws":2,"losses":26,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"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":2,"losses":1,"wins":49},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":4,"losses":1,"wins":41},"meta/muse-spark-1.3":{"draws":5,"losses":6,"wins":37},"meta/muse-spark-open":{"draws":0,"losses":4,"wins":42},"meta/muse-wonder":{"draws":6,"losses":10,"wins":32},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":24},"minimax/minimax-m3.1-flash":{"draws":2,"losses":1,"wins":39},"mistralai/mistral-large-4-0":{"draws":2,"losses":2,"wins":26},"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":3,"losses":5,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":19,"wins":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":38},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":1,"wins":18},"o3":{"draws":1,"losses":3,"wins":62},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":40},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":44},"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":4,"losses":2,"wins":42},"qwen/qwen3.8-27b":{"draws":4,"losses":1,"wins":29},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":27},"qwen/qwen3.8-max":{"draws":5,"losses":1,"wins":42},"qwen/qwen3.8-max-0902":{"draws":4,"losses":5,"wins":39},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":0,"wins":38},"stealth/ox-alpha":{"draws":12,"losses":7,"wins":139},"stealth/space-bunny-alpha":{"draws":2,"losses":0,"wins":36},"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":5,"losses":6,"wins":35},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":62},"thinkingmachines/inkling-small":{"draws":7,"losses":0,"wins":41},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":3},"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":8,"losses":3,"wins":37},"x-ai/grok-4.6":{"draws":3,"losses":8,"wins":37},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":24},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":23},"z-ai/glm-5.2":{"draws":9,"losses":1,"wins":86},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":32},"z-ai/glm-5.3-flash":{"draws":4,"losses":2,"wins":42},"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":6,"losses":17,"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":11,"losses":65,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":31,"wins":9},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":17,"losses":19,"wins":12},"gemini-3.1-pro-preview":{"draws":15,"losses":23,"wins":10},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":27,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":29,"losses":49,"wins":14},"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":34,"wins":7},"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},"inception/mercury-3":{"draws":9,"losses":17,"wins":6},"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":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":12,"losses":28,"wins":6},"meta/muse-wonder":{"draws":11,"losses":36,"wins":1},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":12},"minimax/minimax-m3.1-flash":{"draws":14,"losses":16,"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},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":11,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"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},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":16,"losses":19,"wins":9},"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":{"draws":1,"losses":15,"wins":0},"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":13,"losses":17,"wins":14},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":15,"losses":19,"wins":12},"claude-opus-4-5":{"draws":21,"losses":20,"wins":21},"claude-opus-4-8":{"draws":11,"losses":24,"wins":9},"claude-opus-5":{"draws":15,"losses":60,"wins":7},"claude-opus-5-5":{"draws":6,"losses":42,"wins":4},"claude-sonnet-5":{"draws":16,"losses":23,"wins":9},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":13},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":31},"deepseek/deepseek-v4-pro":{"draws":14,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":22,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":18,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":12,"losses":19,"wins":17},"gemini-4-argon":{"draws":3,"losses":43,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":20},"google/gemini-3.5-flash-lite":{"draws":28,"losses":18,"wins":38},"google/gemini-3.6-flash":{"draws":27,"losses":41,"wins":24},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":13},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":14,"wins":14},"gpt-5.4":{"draws":12,"losses":21,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":11},"gpt-5.4-nano":{"draws":13,"losses":12,"wins":23},"gpt-5.5":{"draws":22,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":19,"losses":10,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":34,"wins":5},"gpt-5.6-terra":{"draws":20,"losses":15,"wins":11},"gpt-6-astra":{"draws":2,"losses":42,"wins":4},"gpt-6-luna":{"draws":14,"losses":20,"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":15,"losses":1,"wins":18},"inception/mercury-3":{"draws":9,"losses":13,"wins":10},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":14},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":19,"losses":5,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":7,"wins":19},"meta/muse-spark-1.2":{"draws":12,"losses":18,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":28,"wins":9},"meta/muse-spark-open":{"draws":15,"losses":18,"wins":13},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":13,"losses":12,"wins":17},"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":2,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":18,"losses":15,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":10,"losses":34,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":7,"wins":6},"o3":{"draws":9,"losses":17,"wins":40},"openai/gpt-oss-120b":{"draws":15,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":18,"losses":7,"wins":21},"qwen/qwen3.7-max":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-27b":{"draws":13,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-max-0902":{"draws":10,"losses":17,"wins":21},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":13,"wins":17},"stealth/ox-alpha":{"draws":43,"losses":76,"wins":39},"stealth/space-bunny-alpha":{"draws":13,"losses":11,"wins":14},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":14},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":25,"losses":9,"wins":30},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":13,"losses":20,"wins":15},"x-ai/grok-4.6":{"draws":10,"losses":24,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":23,"losses":10,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":9},"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":32,"losses":26,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":27,"wins":7},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"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":8,"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":8,"losses":19,"wins":15},"claude-opus-4-5":{"draws":23,"losses":19,"wins":28},"claude-opus-4-8":{"draws":7,"losses":16,"wins":5},"claude-opus-5":{"draws":10,"losses":52,"wins":8},"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":23,"wins":12},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":18,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":24,"wins":8},"elorian/glimpse":{"draws":5,"losses":11,"wins":6},"fireworks/ember-1":{"draws":15,"losses":15,"wins":12},"gemini-3.1-pro-preview":{"draws":12,"losses":11,"wins":19},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":22},"google/gemini-3.5-flash":{"draws":11,"losses":22,"wins":21},"google/gemini-3.5-flash-lite":{"draws":24,"losses":9,"wins":41},"google/gemini-3.6-flash":{"draws":18,"losses":41,"wins":21},"google/gemini-3.8-flash":{"draws":8,"losses":24,"wins":10},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":9},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":14,"wins":12},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":12},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":23},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":31,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":15,"wins":13},"gpt-6-astra":{"draws":2,"losses":37,"wins":3},"gpt-6-luna":{"draws":9,"losses":17,"wins":16},"gpt-6-sol":{"draws":5,"losses":27,"wins":10},"gpt-6.1-sol":{"draws":1,"losses":36,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":16},"inception/mercury-3":{"draws":9,"losses":6,"wins":13},"inclusionai/ling-3.0-flash":{"draws":11,"losses":0,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":6,"wins":29},"meta/muse-glimmer-30b":{"draws":10,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":12},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":12},"meta/muse-spark-open":{"draws":9,"losses":22,"wins":9},"meta/muse-wonder":{"draws":8,"losses":22,"wins":12},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":12,"wins":16},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":9},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":7,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":4,"wins":10},"o3":{"draws":7,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":14,"losses":3,"wins":19},"poolside/laguna-s-2.1":{"draws":12,"losses":7,"wins":19},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":18,"wins":12},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.8-max":{"draws":10,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":9,"losses":18,"wins":15},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":12,"wins":17},"stealth/ox-alpha":{"draws":18,"losses":64,"wins":36},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":7,"wins":18},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":13},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":10},"thinkingmachines/inkling":{"draws":13,"losses":8,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":23},"unbiased/pareto-26.10":{"draws":0,"losses":13,"wins":1},"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":11,"losses":24,"wins":7},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":27,"wins":8},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":20,"losses":13,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":10,"wins":11},"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":23,"losses":29,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":27,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":22,"wins":14}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":10,"wins":56},"claude-fable-5":{"draws":16,"losses":28,"wins":40},"claude-fable-5-1":{"draws":8,"losses":67,"wins":19},"claude-haiku-5-5":{"draws":19,"losses":14,"wins":47},"claude-opus-4-5":{"draws":34,"losses":19,"wins":83},"claude-opus-4-8":{"draws":17,"losses":12,"wins":47},"claude-opus-5":{"draws":21,"losses":69,"wins":36},"claude-opus-5-5":{"draws":11,"losses":66,"wins":15},"claude-sonnet-5":{"draws":17,"losses":18,"wins":49},"claude-sonnet-5-5":{"draws":16,"losses":33,"wins":35},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4-flash":{"draws":24,"losses":12,"wins":88},"deepseek/deepseek-v4-pro":{"draws":13,"losses":16,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"wins":56},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":13,"wins":53},"deepseek/deepseek-v4.1-flash-1017":{"draws":18,"losses":21,"wins":45},"elorian/glimpse":{"draws":8,"losses":11,"wins":27},"fireworks/ember-1":{"draws":15,"losses":16,"wins":53},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":56},"gemini-4-argon":{"draws":13,"losses":45,"wins":26},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":45},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":69},"google/gemini-3.5-flash-lite":{"draws":27,"losses":18,"wins":101},"google/gemini-3.6-flash":{"draws":32,"losses":40,"wins":88},"google/gemini-3.8-flash":{"draws":15,"losses":23,"wins":46},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":34},"gpt-4.1":{"draws":7,"losses":2,"wins":19},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":6},"gpt-5":{"draws":15,"losses":9,"wins":50},"gpt-5.4":{"draws":17,"losses":13,"wins":50},"gpt-5.4-mini":{"draws":16,"losses":6,"wins":34},"gpt-5.4-nano":{"draws":11,"losses":6,"wins":65},"gpt-5.5":{"draws":14,"losses":18,"wins":46},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":60},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":50},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":60},"gpt-6-astra":{"draws":10,"losses":58,"wins":16},"gpt-6-luna":{"draws":20,"losses":11,"wins":53},"gpt-6-sol":{"draws":14,"losses":38,"wins":32},"gpt-6.1-sol":{"draws":12,"losses":52,"wins":20},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":42},"inception/mercury-3":{"draws":10,"losses":10,"wins":36},"inclusionai/ling-3.0-flash":{"draws":17,"losses":2,"wins":39},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":68},"meta/muse-glimmer-30b":{"draws":7,"losses":11,"wins":58},"meta/muse-spark-1.2":{"draws":17,"losses":16,"wins":49},"meta/muse-spark-1.3":{"draws":16,"losses":23,"wins":45},"meta/muse-spark-open":{"draws":11,"losses":21,"wins":48},"meta/muse-wonder":{"draws":15,"losses":27,"wins":42},"minimax/minimax-m3":{"draws":11,"losses":0,"wins":35},"minimax/minimax-m3.1-flash":{"draws":13,"losses":9,"wins":50},"mistralai/mistral-large-4-0":{"draws":12,"losses":7,"wins":35},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":15},"moonshotai/kimi-k3":{"draws":18,"losses":23,"wins":41},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":52,"wins":24},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":35},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":1,"wins":57},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":3,"wins":25},"o3":{"draws":15,"losses":7,"wins":86},"openai/gpt-oss-120b":{"draws":17,"losses":5,"wins":52},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":62},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":36},"qwen/qwen3.7-plus":{"draws":10,"losses":3,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":24,"wins":49},"qwen/qwen3.8-27b":{"draws":15,"losses":4,"wins":39},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":34},"qwen/qwen3.8-max":{"draws":21,"losses":21,"wins":42},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":47},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":20},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":15,"wins":50},"stealth/ox-alpha":{"draws":67,"losses":69,"wins":146},"stealth/space-bunny-alpha":{"draws":12,"losses":8,"wins":46},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":44},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":33},"tencent/hy4-preview":{"draws":15,"losses":15,"wins":50},"thinkingmachines/inkling":{"draws":22,"losses":18,"wins":74},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":63},"unbiased/pareto-26.10":{"draws":3,"losses":19,"wins":6},"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":15,"losses":22,"wins":47},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":46},"x-ai/grok-4.7":{"draws":8,"losses":39,"wins":27},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":19},"xiaomi/mimo-v2.5":{"draws":24,"losses":10,"wins":96},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":1,"wins":36},"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":42,"losses":13,"wins":113},"z-ai/glm-5.3":{"draws":14,"losses":34,"wins":32},"z-ai/glm-5.3-flash":{"draws":18,"losses":20,"wins":46},"z-ai/glm-5.3-flashx":{"draws":17,"losses":23,"wins":44}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":6,"wins":38},"claude-fable-5":{"draws":8,"losses":17,"wins":29},"claude-fable-5-1":{"draws":4,"losses":40,"wins":16},"claude-haiku-5-5":{"draws":12,"losses":6,"wins":34},"claude-opus-4-5":{"draws":15,"losses":13,"wins":60},"claude-opus-4-8":{"draws":9,"losses":14,"wins":27},"claude-opus-5":{"draws":17,"losses":50,"wins":27},"claude-opus-5-5":{"draws":2,"losses":31,"wins":11},"claude-sonnet-5":{"draws":10,"losses":9,"wins":35},"claude-sonnet-5-5":{"draws":7,"losses":18,"wins":29},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":6,"wins":65},"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":9,"losses":9,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":14,"wins":33},"elorian/glimpse":{"draws":6,"losses":5,"wins":19},"fireworks/ember-1":{"draws":8,"losses":10,"wins":36},"gemini-3.1-pro-preview":{"draws":8,"losses":6,"wins":40},"gemini-4-argon":{"draws":6,"losses":26,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":10,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":17,"losses":11,"wins":74},"google/gemini-3.8-flash":{"draws":9,"losses":16,"wins":29},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":27},"gpt-4.1":{"draws":3,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":8,"losses":2,"wins":38},"gpt-5.4":{"draws":8,"losses":4,"wins":40},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":31},"gpt-5.4-nano":{"draws":6,"losses":1,"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":9,"losses":13,"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":12,"losses":2,"wins":40},"gpt-6-sol":{"draws":7,"losses":24,"wins":23},"gpt-6.1-sol":{"draws":8,"losses":35,"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},"inception/mercury-3":{"draws":2,"losses":1,"wins":35},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":32},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":46},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":41},"meta/muse-spark-1.2":{"draws":10,"losses":5,"wins":37},"meta/muse-spark-1.3":{"draws":8,"losses":11,"wins":35},"meta/muse-spark-open":{"draws":10,"losses":12,"wins":30},"meta/muse-wonder":{"draws":6,"losses":20,"wins":28},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":27},"minimax/minimax-m3.1-flash":{"draws":5,"losses":1,"wins":38},"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":4,"losses":6,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":29,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":45},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":1,"wins":21},"o3":{"draws":8,"losses":1,"wins":67},"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":12,"wins":32},"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":12,"losses":11,"wins":31},"qwen/qwen3.8-max-0902":{"draws":9,"losses":5,"wins":40},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":3,"wins":36},"stealth/ox-alpha":{"draws":38,"losses":25,"wins":111},"stealth/space-bunny-alpha":{"draws":5,"losses":1,"wins":36},"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":9,"losses":10,"wins":33},"thinkingmachines/inkling":{"draws":15,"losses":0,"wins":55},"thinkingmachines/inkling-small":{"draws":8,"losses":0,"wins":46},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":6},"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":12,"losses":14,"wins":28},"x-ai/grok-4.6":{"draws":12,"losses":11,"wins":31},"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":7,"losses":2,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":16,"losses":10,"wins":82},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":28},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":41},"z-ai/glm-5.3-flashx":{"draws":11,"losses":5,"wins":38}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":14,"wins":17},"claude-fable-5":{"draws":8,"losses":33,"wins":7},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":21,"wins":10},"claude-opus-4-5":{"draws":26,"losses":31,"wins":21},"claude-opus-4-8":{"draws":12,"losses":23,"wins":9},"claude-opus-5":{"draws":13,"losses":60,"wins":9},"claude-opus-5-5":{"draws":3,"losses":46,"wins":3},"claude-sonnet-5":{"draws":7,"losses":16,"wins":9},"claude-sonnet-5-5":{"draws":9,"losses":31,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":20,"losses":19,"wins":33},"deepseek/deepseek-v4-pro":{"draws":13,"losses":19,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":15,"losses":23,"wins":10},"gemini-3.1-pro-preview":{"draws":12,"losses":21,"wins":15},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":14,"losses":31,"wins":15},"google/gemini-3.5-flash-lite":{"draws":20,"losses":23,"wins":41},"google/gemini-3.6-flash":{"draws":24,"losses":42,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":28,"wins":10},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":15},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":12,"losses":19,"wins":11},"gpt-5.4":{"draws":13,"losses":25,"wins":8},"gpt-5.4-mini":{"draws":14,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":13,"losses":14,"wins":21},"gpt-5.5":{"draws":15,"losses":21,"wins":8},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":24},"gpt-5.6-sol":{"draws":7,"losses":37,"wins":4},"gpt-5.6-terra":{"draws":15,"losses":21,"wins":10},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":13,"losses":19,"wins":16},"gpt-6-sol":{"draws":7,"losses":36,"wins":5},"gpt-6.1-sol":{"draws":0,"losses":46,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":18},"inception/mercury-3":{"draws":10,"losses":13,"wins":9},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":21},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":15,"wins":24},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":20},"meta/muse-spark-1.2":{"draws":11,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":13,"losses":27,"wins":8},"meta/muse-spark-open":{"draws":13,"losses":26,"wins":7},"meta/muse-wonder":{"draws":10,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":9,"losses":7,"wins":10},"minimax/minimax-m3.1-flash":{"draws":10,"losses":12,"wins":20},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":11,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":6,"wins":11},"o3":{"draws":11,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":14,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":15},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":7,"losses":15,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":13,"wins":11},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":27,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":19,"wins":10},"stealth/ox-alpha":{"draws":35,"losses":84,"wins":39},"stealth/space-bunny-alpha":{"draws":9,"losses":16,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":15},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":11},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":11},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":36},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":11,"losses":28,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":27,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":25,"losses":19,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":20,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":19,"wins":10},"z-ai/glm-5.2":{"draws":24,"losses":35,"wins":37},"z-ai/glm-5.3":{"draws":8,"losses":32,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":27,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":31,"wins":8}},"claude-sonnet-5-5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":17,"wins":19},"claude-fable-5":{"draws":9,"losses":30,"wins":9},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":21,"wins":15},"claude-opus-4-5":{"draws":17,"losses":35,"wins":26},"claude-opus-4-8":{"draws":12,"losses":23,"wins":9},"claude-opus-5":{"draws":11,"losses":64,"wins":7},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":11,"losses":20,"wins":17},"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":21,"losses":20,"wins":31},"deepseek/deepseek-v4-pro":{"draws":15,"losses":19,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":33,"wins":7},"elorian/glimpse":{"draws":6,"losses":11,"wins":9},"fireworks/ember-1":{"draws":11,"losses":22,"wins":15},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":17},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":10,"wins":15},"google/gemini-3.5-flash":{"draws":15,"losses":25,"wins":20},"google/gemini-3.5-flash-lite":{"draws":20,"losses":21,"wins":43},"google/gemini-3.6-flash":{"draws":22,"losses":51,"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":12,"losses":17,"wins":17},"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},"inception/mercury-3":{"draws":8,"losses":11,"wins":13},"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":8,"losses":18,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":28,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":31,"wins":8},"meta/muse-spark-open":{"draws":10,"losses":28,"wins":8},"meta/muse-wonder":{"draws":5,"losses":32,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":16,"wins":16},"mistralai/mistral-large-4-0":{"draws":11,"losses":15,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":27,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":44,"wins":1},"nex-agi/nex-n2-pro":{"draws":8,"losses":7,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":14,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":7,"wins":10},"o3":{"draws":8,"losses":30,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":10,"wins":22},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":24},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":29,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":15,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":9,"losses":25,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":29,"wins":9},"recursive/flint-v1.0":{"draws":3,"losses":2,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":21,"wins":11},"stealth/ox-alpha":{"draws":37,"losses":90,"wins":31},"stealth/space-bunny-alpha":{"draws":8,"losses":15,"wins":15},"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":8,"losses":29,"wins":9},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":25},"thinkingmachines/inkling-small":{"draws":13,"losses":16,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":7,"losses":32,"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":20,"losses":18,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":18,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":19,"wins":9},"z-ai/glm-5.2":{"draws":20,"losses":42,"wins":34},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":7},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":18,"wins":0},"elorian/glimpse":{"draws":0,"losses":9,"wins":1},"fireworks/ember-1":{"draws":3,"losses":13,"wins":2},"gemini-3.1-pro-preview":{"draws":4,"losses":10,"wins":4},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"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},"inception/mercury-3":{"draws":0,"losses":10,"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-spark-open":{"draws":0,"losses":18,"wins":0},"meta/muse-wonder":{"draws":0,"losses":18,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":2},"minimax/minimax-m3.1-flash":{"draws":0,"losses":12,"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":9,"wins":1},"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},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":18,"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":{"draws":0,"losses":6,"wins":0},"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":8,"losses":13,"wins":17},"claude-fable-5":{"draws":7,"losses":35,"wins":0},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":4},"claude-opus-4-5":{"draws":19,"losses":37,"wins":12},"claude-opus-4-8":{"draws":6,"losses":26,"wins":6},"claude-opus-5":{"draws":7,"losses":61,"wins":2},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":9,"losses":24,"wins":9},"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":16,"losses":17,"wins":19},"deepseek/deepseek-v4-pro":{"draws":8,"losses":18,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":32,"wins":4},"elorian/glimpse":{"draws":4,"losses":12,"wins":6},"fireworks/ember-1":{"draws":14,"losses":16,"wins":12},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":14},"gemini-4-argon":{"draws":0,"losses":42,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":25,"wins":32},"google/gemini-3.6-flash":{"draws":14,"losses":57,"wins":9},"google/gemini-3.8-flash":{"draws":6,"losses":32,"wins":4},"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":24,"wins":8},"gpt-5.4":{"draws":7,"losses":28,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":18},"gpt-5.5":{"draws":7,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":9,"losses":17,"wins":16},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":26,"wins":6},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":9,"losses":21,"wins":12},"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":6,"losses":3,"wins":19},"inception/mercury-3":{"draws":9,"losses":14,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":17,"wins":20},"meta/muse-glimmer-30b":{"draws":10,"losses":12,"wins":14},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":5,"losses":28,"wins":7},"meta/muse-wonder":{"draws":6,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":18,"wins":13},"mistralai/mistral-large-4-0":{"draws":6,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":21,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":36,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":10,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":11,"wins":6},"o3":{"draws":8,"losses":36,"wins":18},"openai/gpt-oss-120b":{"draws":11,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":14},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":6},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":25,"wins":5},"qwen/qwen3.8-27b":{"draws":8,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":11,"losses":24,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":30,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":22,"wins":10},"stealth/ox-alpha":{"draws":28,"losses":81,"wins":31},"stealth/space-bunny-alpha":{"draws":4,"losses":12,"wins":16},"stepfun/step-3.7-flash":{"draws":5,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":8,"wins":10},"tencent/hy4-preview":{"draws":9,"losses":23,"wins":8},"thinkingmachines/inkling":{"draws":12,"losses":21,"wins":23},"thinkingmachines/inkling-small":{"draws":17,"losses":8,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":7,"losses":28,"wins":7},"x-ai/grok-4.6":{"draws":8,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":4,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"losses":21,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":20,"wins":3},"z-ai/glm-5.2":{"draws":25,"losses":37,"wins":22},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":13,"losses":22,"wins":7},"z-ai/glm-5.3-flashx":{"draws":5,"losses":30,"wins":7}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":15,"wins":9},"claude-fable-5":{"draws":7,"losses":25,"wins":4},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":15,"wins":7},"claude-opus-4-5":{"draws":18,"losses":33,"wins":7},"claude-opus-4-8":{"draws":9,"losses":17,"wins":6},"claude-opus-5":{"draws":9,"losses":51,"wins":8},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":13,"losses":13,"wins":10},"claude-sonnet-5-5":{"draws":7,"losses":22,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":12,"wins":24},"deepseek/deepseek-v4-pro":{"draws":5,"losses":14,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":5},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":6,"losses":22,"wins":8},"gemini-4-argon":{"draws":3,"losses":32,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":25,"wins":13},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":21},"google/gemini-3.6-flash":{"draws":20,"losses":38,"wins":12},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":8},"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":11,"losses":15,"wins":8},"gpt-5.4":{"draws":6,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":9},"gpt-5.4-nano":{"draws":1,"losses":22,"wins":11},"gpt-5.5":{"draws":12,"losses":18,"wins":6},"gpt-5.6-luna":{"draws":12,"losses":15,"wins":9},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":7},"gpt-6-astra":{"draws":2,"losses":34,"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":8,"losses":6,"wins":8},"inception/mercury-3":{"draws":5,"losses":11,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":6},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":11},"meta/muse-spark-1.2":{"draws":4,"losses":22,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":7},"meta/muse-wonder":{"draws":2,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":10,"losses":12,"wins":10},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":11,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":5},"o3":{"draws":6,"losses":26,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":10,"wins":11},"poolside/laguna-s-2.1":{"draws":10,"losses":20,"wins":6},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":7,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":17,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":29,"losses":66,"wins":31},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":10},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":14,"wins":19},"thinkingmachines/inkling-small":{"draws":13,"losses":11,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":12,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":14,"losses":20,"wins":2},"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":21,"losses":13,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":13,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":13,"wins":5},"z-ai/glm-5.2":{"draws":22,"losses":32,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":4},"z-ai/glm-5.3-flash":{"draws":3,"losses":26,"wins":7},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":9},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":18,"wins":3},"claude-opus-4-5":{"draws":20,"losses":29,"wins":9},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":12,"losses":16,"wins":8},"claude-sonnet-5-5":{"draws":5,"losses":26,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":18},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":14,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":23,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":24,"wins":4},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":10},"gemini-4-argon":{"draws":7,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":3,"wins":11},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":8},"google/gemini-3.5-flash-lite":{"draws":25,"losses":23,"wins":16},"google/gemini-3.6-flash":{"draws":15,"losses":41,"wins":14},"google/gemini-3.8-flash":{"draws":7,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":9},"gpt-4.1":{"draws":2,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":19,"wins":6},"gpt-5.4":{"draws":8,"losses":21,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":5,"losses":16,"wins":13},"gpt-5.5":{"draws":10,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":12,"losses":12,"wins":12},"gpt-5.6-sol":{"draws":5,"losses":25,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":20,"wins":5},"gpt-6-astra":{"draws":2,"losses":33,"wins":1},"gpt-6-luna":{"draws":9,"losses":16,"wins":11},"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":10,"losses":4,"wins":10},"inception/mercury-3":{"draws":5,"losses":14,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":12,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":12,"wins":13},"meta/muse-glimmer-30b":{"draws":10,"losses":10,"wins":12},"meta/muse-spark-1.2":{"draws":6,"losses":22,"wins":6},"meta/muse-spark-1.3":{"draws":4,"losses":26,"wins":6},"meta/muse-spark-open":{"draws":6,"losses":25,"wins":5},"meta/muse-wonder":{"draws":7,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":8,"losses":14,"wins":10},"mistralai/mistral-large-4-0":{"draws":9,"losses":8,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":13,"wins":10},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":29,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":10,"wins":4},"o3":{"draws":8,"losses":23,"wins":21},"openai/gpt-oss-120b":{"draws":13,"losses":9,"wins":8},"poolside/laguna-s-2.1":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":9,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":22,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":22,"wins":7},"qwen/qwen3.8-max-0902":{"draws":9,"losses":20,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":14,"wins":7},"stealth/ox-alpha":{"draws":34,"losses":65,"wins":25},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":8},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":11,"losses":18,"wins":7},"thinkingmachines/inkling":{"draws":22,"losses":16,"wins":10},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":14},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":9,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":16,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":30,"losses":20,"wins":22},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":25,"wins":6}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":20,"wins":10},"claude-fable-5":{"draws":10,"losses":33,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":27,"wins":5},"claude-opus-4-5":{"draws":28,"losses":37,"wins":13},"claude-opus-4-8":{"draws":12,"losses":25,"wins":7},"claude-opus-5":{"draws":14,"losses":63,"wins":5},"claude-opus-5-5":{"draws":1,"losses":50,"wins":1},"claude-sonnet-5":{"draws":16,"losses":28,"wins":4},"claude-sonnet-5-5":{"draws":12,"losses":33,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":23,"losses":23,"wins":26},"deepseek/deepseek-v4-pro":{"draws":16,"losses":20,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":18,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":31,"wins":5},"elorian/glimpse":{"draws":7,"losses":13,"wins":6},"fireworks/ember-1":{"draws":15,"losses":28,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":26,"wins":11},"gemini-4-argon":{"draws":0,"losses":47,"wins":1},"google/gemini-3.1-flash-lite":{"draws":13,"losses":8,"wins":11},"google/gemini-3.5-flash":{"draws":15,"losses":33,"wins":12},"google/gemini-3.5-flash-lite":{"draws":28,"losses":40,"wins":16},"google/gemini-3.6-flash":{"draws":27,"losses":53,"wins":12},"google/gemini-3.8-flash":{"draws":11,"losses":34,"wins":3},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":4,"losses":9,"wins":3},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":10,"losses":16,"wins":16},"gpt-5.4":{"draws":17,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":13,"losses":14,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":22,"wins":15},"gpt-5.5":{"draws":18,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":16,"losses":21,"wins":11},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":10},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":15,"losses":24,"wins":9},"gpt-6-sol":{"draws":9,"losses":33,"wins":6},"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":13,"losses":7,"wins":14},"inception/mercury-3":{"draws":11,"losses":17,"wins":4},"inclusionai/ling-3.0-flash":{"draws":19,"losses":6,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":21,"wins":21},"meta/muse-glimmer-30b":{"draws":18,"losses":11,"wins":13},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":8},"meta/muse-spark-1.3":{"draws":7,"losses":32,"wins":9},"meta/muse-spark-open":{"draws":10,"losses":29,"wins":7},"meta/muse-wonder":{"draws":9,"losses":35,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":11,"wins":10},"minimax/minimax-m3.1-flash":{"draws":13,"losses":14,"wins":15},"mistralai/mistral-large-4-0":{"draws":10,"losses":13,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":23,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":38,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":8,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":11,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":11,"wins":4},"o3":{"draws":15,"losses":36,"wins":15},"openai/gpt-oss-120b":{"draws":13,"losses":19,"wins":10},"poolside/laguna-s-2.1":{"draws":21,"losses":15,"wins":10},"qwen/qwen3.7-max":{"draws":11,"losses":9,"wins":8},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":27,"wins":7},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":8},"qwen/qwen3.8-flash":{"draws":13,"losses":14,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":26,"wins":9},"qwen/qwen3.8-max-0902":{"draws":14,"losses":26,"wins":8},"recursive/flint-v1.0":{"draws":5,"losses":2,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":17,"losses":18,"wins":9},"stealth/ox-alpha":{"draws":42,"losses":82,"wins":34},"stealth/space-bunny-alpha":{"draws":11,"losses":16,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":8,"wins":17},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":8,"losses":12,"wins":6},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":23,"losses":14,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":17,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":31,"wins":6},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5":{"draws":24,"losses":24,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":13,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":19,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":20,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":39,"wins":21},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":30,"wins":7},"z-ai/glm-5.3-flashx":{"draws":9,"losses":32,"wins":7}},"deepseek/deepseek-v4.1-flash-1017":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":6,"wins":26},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":1,"losses":48,"wins":5},"claude-haiku-5-5":{"draws":10,"losses":23,"wins":13},"claude-opus-4-5":{"draws":22,"losses":26,"wins":30},"claude-opus-4-8":{"draws":9,"losses":22,"wins":13},"claude-opus-5":{"draws":14,"losses":52,"wins":16},"claude-opus-5-5":{"draws":2,"losses":47,"wins":3},"claude-sonnet-5":{"draws":14,"losses":14,"wins":20},"claude-sonnet-5-5":{"draws":12,"losses":21,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":40},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":21,"wins":4},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":15,"losses":15,"wins":18},"gemini-3.1-pro-preview":{"draws":12,"losses":16,"wins":20},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":12,"losses":24,"wins":24},"google/gemini-3.5-flash-lite":{"draws":22,"losses":15,"wins":47},"google/gemini-3.6-flash":{"draws":18,"losses":45,"wins":29},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":14,"wins":16},"gpt-5.4":{"draws":10,"losses":24,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":23},"gpt-5.5":{"draws":18,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":15,"losses":13,"wins":20},"gpt-5.6-sol":{"draws":10,"losses":25,"wins":13},"gpt-5.6-terra":{"draws":16,"losses":16,"wins":14},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":15,"losses":16,"wins":17},"gpt-6-sol":{"draws":4,"losses":32,"wins":12},"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":13,"losses":0,"wins":21},"inception/mercury-3":{"draws":12,"losses":8,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":22},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":12,"wins":28},"meta/muse-glimmer-30b":{"draws":14,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":19},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":11},"meta/muse-spark-open":{"draws":11,"losses":16,"wins":19},"meta/muse-wonder":{"draws":11,"losses":26,"wins":11},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"minimax/minimax-m3.1-flash":{"draws":12,"losses":15,"wins":15},"mistralai/mistral-large-4-0":{"draws":5,"losses":10,"wins":15},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":8,"losses":17,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":37,"wins":5},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":27},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":4,"wins":11},"o3":{"draws":6,"losses":30,"wins":30},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":26},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-27b":{"draws":6,"losses":13,"wins":15},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max-0902":{"draws":13,"losses":18,"wins":17},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":14,"wins":17},"stealth/ox-alpha":{"draws":38,"losses":66,"wins":54},"stealth/space-bunny-alpha":{"draws":10,"losses":8,"wins":20},"stepfun/step-3.7-flash":{"draws":5,"losses":10,"wins":19},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":13},"tencent/hy4-preview":{"draws":9,"losses":21,"wins":16},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":26},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":14,"losses":26,"wins":8},"x-ai/grok-4.6":{"draws":19,"losses":20,"wins":9},"x-ai/grok-4.7":{"draws":7,"losses":25,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":18,"wins":10},"z-ai/glm-5.2":{"draws":31,"losses":26,"wins":39},"z-ai/glm-5.3":{"draws":8,"losses":29,"wins":9},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":9,"losses":27,"wins":12}},"elorian/glimpse":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":15,"wins":6},"claude-fable-5":{"draws":4,"losses":23,"wins":3},"claude-fable-5-1":{"draws":2,"losses":34,"wins":0},"claude-haiku-5-5":{"draws":2,"losses":22,"wins":4},"claude-opus-4-5":{"draws":6,"losses":32,"wins":10},"claude-opus-4-8":{"draws":5,"losses":20,"wins":1},"claude-opus-5":{"draws":9,"losses":42,"wins":5},"claude-opus-5-5":{"draws":5,"losses":29,"wins":0},"claude-sonnet-5":{"draws":9,"losses":18,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":25,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":5,"wins":5},"deepseek/deepseek-v4-flash":{"draws":7,"losses":22,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":18,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":17,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":19,"wins":7},"elorian/glimpse":{"draws":1,"losses":7,"wins":2},"fireworks/ember-1":{"draws":5,"losses":21,"wins":4},"gemini-3.1-pro-preview":{"draws":2,"losses":21,"wins":7},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":22,"wins":10},"google/gemini-3.5-flash-lite":{"draws":15,"losses":23,"wins":14},"google/gemini-3.6-flash":{"draws":11,"losses":37,"wins":10},"google/gemini-3.8-flash":{"draws":3,"losses":23,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":6,"wins":7},"gpt-4.1":{"draws":3,"losses":7,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":14,"wins":7},"gpt-5.4":{"draws":5,"losses":15,"wins":10},"gpt-5.4-mini":{"draws":4,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":18,"wins":5},"gpt-5.5":{"draws":5,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":15,"wins":7},"gpt-5.6-sol":{"draws":1,"losses":26,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":6},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":5,"losses":17,"wins":8},"gpt-6-sol":{"draws":2,"losses":27,"wins":1},"gpt-6.1-sol":{"draws":1,"losses":29,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":5,"wins":9},"inception/mercury-3":{"draws":0,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":8,"wins":9},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":6,"losses":16,"wins":10},"meta/muse-glimmer-30b":{"draws":9,"losses":13,"wins":8},"meta/muse-spark-1.2":{"draws":5,"losses":24,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":23,"wins":2},"meta/muse-spark-open":{"draws":4,"losses":21,"wins":5},"meta/muse-wonder":{"draws":3,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":11,"wins":10},"mistralai/mistral-large-4-0":{"draws":4,"losses":13,"wins":3},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":4,"losses":19,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":28,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":8,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":9,"wins":3},"o3":{"draws":7,"losses":28,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":5,"losses":11,"wins":12},"qwen/qwen3.7-max":{"draws":2,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":21,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":5,"losses":20,"wins":5},"qwen/qwen3.8-max-0902":{"draws":4,"losses":21,"wins":5},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":16,"wins":6},"stealth/ox-alpha":{"draws":18,"losses":67,"wins":23},"stealth/space-bunny-alpha":{"draws":5,"losses":13,"wins":6},"stepfun/step-3.7-flash":{"draws":1,"losses":10,"wins":11},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":8,"wins":5},"tencent/hy4-preview":{"draws":4,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":6,"losses":23,"wins":13},"thinkingmachines/inkling-small":{"draws":5,"losses":12,"wins":13},"unbiased/pareto-26.10":{"draws":0,"losses":10,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":10,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":22,"wins":3},"x-ai/grok-4.6":{"draws":6,"losses":21,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":22,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":13,"losses":20,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":4},"z-ai/glm-5.2":{"draws":8,"losses":35,"wins":17},"z-ai/glm-5.3":{"draws":2,"losses":23,"wins":3},"z-ai/glm-5.3-flash":{"draws":2,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":5,"losses":20,"wins":5}},"fireworks/ember-1":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":17,"wins":13},"claude-fable-5":{"draws":13,"losses":34,"wins":1},"claude-fable-5-1":{"draws":1,"losses":52,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":30,"losses":31,"wins":17},"claude-opus-4-8":{"draws":16,"losses":26,"wins":2},"claude-opus-5":{"draws":9,"losses":69,"wins":4},"claude-opus-5-5":{"draws":2,"losses":50,"wins":0},"claude-sonnet-5":{"draws":15,"losses":20,"wins":13},"claude-sonnet-5-5":{"draws":11,"losses":30,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":25,"wins":21},"deepseek/deepseek-v4-pro":{"draws":16,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":31,"wins":4},"elorian/glimpse":{"draws":6,"losses":14,"wins":6},"fireworks/ember-1":{"draws":10,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":14,"losses":21,"wins":13},"gemini-4-argon":{"draws":3,"losses":45,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":19,"losses":32,"wins":9},"google/gemini-3.5-flash-lite":{"draws":31,"losses":30,"wins":23},"google/gemini-3.6-flash":{"draws":32,"losses":42,"wins":18},"google/gemini-3.8-flash":{"draws":13,"losses":29,"wins":6},"google/gemma-4-31b-it":{"draws":14,"losses":6,"wins":8},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":19,"wins":8},"gpt-5.4":{"draws":17,"losses":26,"wins":3},"gpt-5.4-mini":{"draws":15,"losses":10,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":14,"wins":22},"gpt-5.5":{"draws":13,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":21,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":34,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":20,"wins":8},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":14,"losses":23,"wins":11},"gpt-6-sol":{"draws":5,"losses":38,"wins":5},"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":18,"losses":4,"wins":12},"inception/mercury-3":{"draws":13,"losses":18,"wins":1},"inclusionai/ling-3.0-flash":{"draws":21,"losses":5,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":14,"wins":22},"meta/muse-glimmer-30b":{"draws":18,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":8,"losses":31,"wins":9},"meta/muse-spark-open":{"draws":10,"losses":29,"wins":7},"meta/muse-wonder":{"draws":17,"losses":28,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":12},"minimax/minimax-m3.1-flash":{"draws":11,"losses":20,"wins":11},"mistralai/mistral-large-4-0":{"draws":11,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":5,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":18,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":14,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":18,"losses":29,"wins":19},"openai/gpt-oss-120b":{"draws":19,"losses":13,"wins":10},"poolside/laguna-s-2.1":{"draws":22,"losses":14,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":7,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":21,"wins":7},"qwen/qwen3.8-27b":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":27,"wins":7},"recursive/flint-v1.0":{"draws":1,"losses":5,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":19,"wins":12},"stealth/ox-alpha":{"draws":45,"losses":89,"wins":24},"stealth/space-bunny-alpha":{"draws":12,"losses":14,"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":11,"losses":7,"wins":8},"tencent/hy4-preview":{"draws":17,"losses":20,"wins":9},"thinkingmachines/inkling":{"draws":23,"losses":20,"wins":21},"thinkingmachines/inkling-small":{"draws":18,"losses":11,"wins":19},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":13,"losses":28,"wins":7},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":22,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":19,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":19,"wins":6},"z-ai/glm-5.2":{"draws":36,"losses":37,"wins":23},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":9,"losses":31,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":31,"wins":8}},"gemini-3.1-pro-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":19,"wins":12},"claude-fable-5":{"draws":12,"losses":36,"wins":0},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":25,"wins":7},"claude-opus-4-5":{"draws":22,"losses":48,"wins":8},"claude-opus-4-8":{"draws":11,"losses":28,"wins":5},"claude-opus-5":{"draws":8,"losses":71,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":13,"losses":28,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":33,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":10,"wins":4},"deepseek/deepseek-v4-flash":{"draws":22,"losses":31,"wins":19},"deepseek/deepseek-v4-pro":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":30,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":36,"wins":4},"elorian/glimpse":{"draws":5,"losses":16,"wins":5},"fireworks/ember-1":{"draws":15,"losses":29,"wins":4},"gemini-3.1-pro-preview":{"draws":8,"losses":19,"wins":5},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":11,"wins":12},"google/gemini-3.5-flash":{"draws":14,"losses":36,"wins":10},"google/gemini-3.5-flash-lite":{"draws":29,"losses":30,"wins":25},"google/gemini-3.6-flash":{"draws":32,"losses":54,"wins":6},"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":5,"losses":9,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":16,"losses":18,"wins":8},"gpt-5.4":{"draws":14,"losses":30,"wins":2},"gpt-5.4-mini":{"draws":13,"losses":12,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":19},"gpt-5.5":{"draws":17,"losses":25,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":23,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":39,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":24,"wins":3},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"gpt-6-luna":{"draws":11,"losses":23,"wins":14},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"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":13,"losses":13,"wins":8},"inception/mercury-3":{"draws":12,"losses":16,"wins":4},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":25,"wins":11},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":5},"meta/muse-spark-1.3":{"draws":8,"losses":37,"wins":3},"meta/muse-spark-open":{"draws":12,"losses":33,"wins":1},"meta/muse-wonder":{"draws":8,"losses":38,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":11,"wins":7},"minimax/minimax-m3.1-flash":{"draws":12,"losses":23,"wins":7},"mistralai/mistral-large-4-0":{"draws":9,"losses":15,"wins":6},"mistralai/mistral-medium-3-5":{"draws":14,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":17,"losses":24,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":41,"wins":2},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":15,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":13,"losses":47,"wins":6},"openai/gpt-oss-120b":{"draws":12,"losses":19,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":20,"wins":10},"qwen/qwen3.7-max":{"draws":6,"losses":14,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":30,"wins":2},"qwen/qwen3.8-27b":{"draws":10,"losses":20,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":16,"wins":3},"qwen/qwen3.8-max":{"draws":16,"losses":26,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":33,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":27,"wins":4},"stealth/ox-alpha":{"draws":33,"losses":109,"wins":16},"stealth/space-bunny-alpha":{"draws":9,"losses":20,"wins":9},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":6},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":15,"losses":26,"wins":5},"thinkingmachines/inkling":{"draws":24,"losses":25,"wins":15},"thinkingmachines/inkling-small":{"draws":15,"losses":17,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":33,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":35,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":8,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":33,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":25,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":23,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":41,"wins":20},"z-ai/glm-5.3":{"draws":10,"losses":36,"wins":0},"z-ai/glm-5.3-flash":{"draws":11,"losses":32,"wins":5},"z-ai/glm-5.3-flashx":{"draws":9,"losses":34,"wins":5}},"gemini-4-argon":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":6,"losses":10,"wins":32},"claude-fable-5-1":{"draws":5,"losses":36,"wins":13},"claude-haiku-5-5":{"draws":5,"losses":9,"wins":32},"claude-opus-4-5":{"draws":3,"losses":9,"wins":66},"claude-opus-4-8":{"draws":4,"losses":12,"wins":28},"claude-opus-5":{"draws":10,"losses":40,"wins":32},"claude-opus-5-5":{"draws":3,"losses":38,"wins":11},"claude-sonnet-5":{"draws":4,"losses":2,"wins":42},"claude-sonnet-5-5":{"draws":5,"losses":18,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":66},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":8,"wins":37},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":6,"wins":38},"elorian/glimpse":{"draws":2,"losses":4,"wins":20},"fireworks/ember-1":{"draws":2,"losses":6,"wins":40},"gemini-3.1-pro-preview":{"draws":5,"losses":6,"wins":37},"gemini-4-argon":{"draws":4,"losses":20,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":53},"google/gemini-3.5-flash-lite":{"draws":5,"losses":6,"wins":73},"google/gemini-3.6-flash":{"draws":6,"losses":13,"wins":73},"google/gemini-3.8-flash":{"draws":5,"losses":11,"wins":32},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":27},"gpt-4.1":{"draws":3,"losses":0,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":7,"wins":33},"gpt-5.4":{"draws":4,"losses":5,"wins":37},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":31},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":42},"gpt-5.5":{"draws":2,"losses":10,"wins":32},"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":4,"losses":5,"wins":37},"gpt-6-astra":{"draws":10,"losses":30,"wins":8},"gpt-6-luna":{"draws":4,"losses":2,"wins":42},"gpt-6-sol":{"draws":5,"losses":25,"wins":18},"gpt-6.1-sol":{"draws":5,"losses":32,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":3,"losses":3,"wins":26},"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":2,"wins":48},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":38},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":39},"meta/muse-spark-1.3":{"draws":5,"losses":9,"wins":34},"meta/muse-spark-open":{"draws":6,"losses":9,"wins":31},"meta/muse-wonder":{"draws":5,"losses":10,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":24},"minimax/minimax-m3.1-flash":{"draws":2,"losses":3,"wins":37},"mistralai/mistral-large-4-0":{"draws":4,"losses":5,"wins":21},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":8},"moonshotai/kimi-k3":{"draws":2,"losses":6,"wins":38},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":26,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":39},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":1,"wins":20},"o3":{"draws":1,"losses":5,"wins":60},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":41},"poolside/laguna-s-2.1":{"draws":4,"losses":1,"wins":41},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":23},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":33},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":29},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":27},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":44},"qwen/qwen3.8-max-0902":{"draws":6,"losses":5,"wins":37},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":6,"wins":35},"stealth/ox-alpha":{"draws":17,"losses":17,"wins":124},"stealth/space-bunny-alpha":{"draws":2,"losses":2,"wins":34},"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":4,"losses":10,"wins":32},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":55},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":40},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":4},"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":1,"losses":9,"wins":38},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":36},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":22},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":13},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":10,"losses":6,"wins":80},"z-ai/glm-5.3":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3-flash":{"draws":2,"losses":11,"wins":35},"z-ai/glm-5.3-flashx":{"draws":6,"losses":8,"wins":34}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":16,"wins":4},"claude-fable-5":{"draws":2,"losses":27,"wins":1},"claude-fable-5-1":{"draws":1,"losses":31,"wins":0},"claude-haiku-5-5":{"draws":5,"losses":25,"wins":0},"claude-opus-4-5":{"draws":13,"losses":35,"wins":2},"claude-opus-4-8":{"draws":3,"losses":26,"wins":1},"claude-opus-5":{"draws":4,"losses":41,"wins":1},"claude-opus-5-5":{"draws":1,"losses":29,"wins":0},"claude-sonnet-5":{"draws":6,"losses":21,"wins":3},"claude-sonnet-5-5":{"draws":4,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":29,"wins":6},"deepseek/deepseek-v4-pro":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":19,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":18,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":26,"wins":0},"elorian/glimpse":{"draws":2,"losses":10,"wins":2},"fireworks/ember-1":{"draws":8,"losses":22,"wins":0},"gemini-3.1-pro-preview":{"draws":7,"losses":20,"wins":3},"gemini-4-argon":{"draws":1,"losses":29,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":31,"wins":1},"google/gemini-3.5-flash-lite":{"draws":8,"losses":39,"wins":5},"google/gemini-3.6-flash":{"draws":10,"losses":45,"wins":3},"google/gemini-3.8-flash":{"draws":4,"losses":26,"wins":0},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":4},"gpt-4.1":{"draws":2,"losses":8,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":4,"losses":22,"wins":0},"gpt-5.4":{"draws":4,"losses":24,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":14,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":21,"wins":7},"gpt-5.5":{"draws":6,"losses":19,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":19,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":26,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":21,"wins":1},"gpt-6-astra":{"draws":2,"losses":28,"wins":0},"gpt-6-luna":{"draws":7,"losses":20,"wins":3},"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},"inception/mercury-3":{"draws":8,"losses":12,"wins":0},"inclusionai/ling-3.0-flash":{"draws":3,"losses":12,"wins":5},"meituan/longcat-2.0":{"draws":4,"losses":25,"wins":3},"meta/muse-glimmer-30b":{"draws":8,"losses":12,"wins":4},"meta/muse-spark-1.2":{"draws":8,"losses":18,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":0},"meta/muse-spark-open":{"draws":4,"losses":23,"wins":1},"meta/muse-wonder":{"draws":3,"losses":25,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":10,"wins":4},"minimax/minimax-m3.1-flash":{"draws":4,"losses":22,"wins":2},"mistralai/mistral-large-4-0":{"draws":4,"losses":14,"wins":0},"mistralai/mistral-medium-3-5":{"draws":5,"losses":9,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":20,"wins":0},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":29,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":11,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":20,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":9,"wins":1},"o3":{"draws":2,"losses":44,"wins":2},"openai/gpt-oss-120b":{"draws":6,"losses":16,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":16,"wins":4},"qwen/qwen3.7-max":{"draws":7,"losses":12,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":14,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":3},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":1},"qwen/qwen3.8-max":{"draws":7,"losses":23,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":23,"wins":0},"recursive/flint-v1.0":{"draws":2,"losses":6,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":21,"wins":0},"stealth/ox-alpha":{"draws":12,"losses":64,"wins":8},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":5,"losses":18,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":10,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":26,"wins":0},"thinkingmachines/inkling":{"draws":11,"losses":20,"wins":9},"thinkingmachines/inkling-small":{"draws":9,"losses":16,"wins":5},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"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":5,"losses":24,"wins":1},"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":2,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":15,"losses":27,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":15,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":42,"wins":6},"z-ai/glm-5.3":{"draws":4,"losses":24,"wins":0},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":2},"z-ai/glm-5.3-flashx":{"draws":7,"losses":22,"wins":1}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":33,"wins":26},"claude-fable-5":{"draws":12,"losses":66,"wins":6},"claude-fable-5-1":{"draws":4,"losses":89,"wins":1},"claude-haiku-5-5":{"draws":18,"losses":45,"wins":19},"claude-opus-4-5":{"draws":32,"losses":78,"wins":28},"claude-opus-4-8":{"draws":19,"losses":52,"wins":9},"claude-opus-5":{"draws":14,"losses":118,"wins":8},"claude-opus-5-5":{"draws":4,"losses":88,"wins":0},"claude-sonnet-5":{"draws":26,"losses":36,"wins":22},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":9},"cohere/north-mini-code":{"draws":9,"losses":8,"wins":17},"deepseek/deepseek-v4-flash":{"draws":28,"losses":49,"wins":49},"deepseek/deepseek-v4-pro":{"draws":20,"losses":34,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":37,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":48,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":60,"wins":10},"elorian/glimpse":{"draws":7,"losses":26,"wins":13},"fireworks/ember-1":{"draws":29,"losses":41,"wins":14},"gemini-3.1-pro-preview":{"draws":19,"losses":41,"wins":24},"gemini-4-argon":{"draws":2,"losses":79,"wins":3},"google/gemini-3.1-flash-lite":{"draws":16,"losses":12,"wins":34},"google/gemini-3.5-flash":{"draws":14,"losses":52,"wins":14},"google/gemini-3.5-flash-lite":{"draws":35,"losses":68,"wins":47},"google/gemini-3.6-flash":{"draws":39,"losses":88,"wins":35},"google/gemini-3.8-flash":{"draws":18,"losses":61,"wins":5},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":20},"gpt-4.1":{"draws":8,"losses":14,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":18,"losses":35,"wins":21},"gpt-5.4":{"draws":11,"losses":55,"wins":16},"gpt-5.4-mini":{"draws":16,"losses":19,"wins":21},"gpt-5.4-nano":{"draws":12,"losses":35,"wins":41},"gpt-5.5":{"draws":22,"losses":43,"wins":13},"gpt-5.6-luna":{"draws":20,"losses":37,"wins":27},"gpt-5.6-sol":{"draws":7,"losses":70,"wins":7},"gpt-5.6-terra":{"draws":22,"losses":45,"wins":13},"gpt-6-astra":{"draws":3,"losses":79,"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":20,"losses":16,"wins":24},"inception/mercury-3":{"draws":13,"losses":29,"wins":12},"inclusionai/ling-3.0-flash":{"draws":20,"losses":13,"wins":27},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":28,"wins":46},"meta/muse-glimmer-30b":{"draws":20,"losses":23,"wins":31},"meta/muse-spark-1.2":{"draws":15,"losses":50,"wins":15},"meta/muse-spark-1.3":{"draws":15,"losses":57,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":62,"wins":9},"meta/muse-wonder":{"draws":10,"losses":69,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":19,"wins":19},"minimax/minimax-m3.1-flash":{"draws":14,"losses":38,"wins":22},"mistralai/mistral-large-4-0":{"draws":19,"losses":24,"wins":9},"mistralai/mistral-medium-3-5":{"draws":12,"losses":13,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":5},"moonshotai/kimi-k3":{"draws":26,"losses":37,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":75,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":15,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":27,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":21,"wins":12},"o3":{"draws":19,"losses":61,"wins":46},"openai/gpt-oss-120b":{"draws":20,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":19,"losses":27,"wins":32},"qwen/qwen3.7-max":{"draws":10,"losses":28,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":50,"wins":7},"qwen/qwen3.8-27b":{"draws":9,"losses":36,"wins":15},"qwen/qwen3.8-flash":{"draws":15,"losses":24,"wins":17},"qwen/qwen3.8-max":{"draws":24,"losses":40,"wins":20},"qwen/qwen3.8-max-0902":{"draws":21,"losses":49,"wins":14},"recursive/flint-v1.0":{"draws":5,"losses":6,"wins":15},"reflection/beam-1.0-501b-a23b":{"draws":22,"losses":41,"wins":13},"stealth/ox-alpha":{"draws":44,"losses":171,"wins":45},"stealth/space-bunny-alpha":{"draws":20,"losses":30,"wins":18},"stepfun/step-3.7-flash":{"draws":13,"losses":17,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":15,"losses":20,"wins":11},"tencent/hy4-preview":{"draws":20,"losses":45,"wins":17},"thinkingmachines/inkling":{"draws":22,"losses":37,"wins":53},"thinkingmachines/inkling-small":{"draws":22,"losses":24,"wins":38},"unbiased/pareto-26.10":{"draws":2,"losses":26,"wins":0},"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":16,"losses":55,"wins":13},"x-ai/grok-4.6":{"draws":19,"losses":57,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":62,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":14},"xiaomi/mimo-v2.5":{"draws":40,"losses":42,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":19,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":36,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":34,"wins":13},"z-ai/glm-5.2":{"draws":45,"losses":75,"wins":48},"z-ai/glm-5.3":{"draws":12,"losses":64,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":58,"wins":15},"z-ai/glm-5.3-flashx":{"draws":12,"losses":60,"wins":12}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":27,"wins":30},"claude-fable-5":{"draws":14,"losses":63,"wins":13},"claude-fable-5-1":{"draws":4,"losses":94,"wins":2},"claude-haiku-5-5":{"draws":18,"losses":53,"wins":17},"claude-opus-4-5":{"draws":45,"losses":58,"wins":45},"claude-opus-4-8":{"draws":20,"losses":53,"wins":13},"claude-opus-5":{"draws":20,"losses":120,"wins":12},"claude-opus-5-5":{"draws":4,"losses":93,"wins":1},"claude-sonnet-5":{"draws":25,"losses":44,"wins":21},"claude-sonnet-5-5":{"draws":17,"losses":58,"wins":15},"cohere/north-mini-code":{"draws":11,"losses":9,"wins":14},"deepseek/deepseek-v4-flash":{"draws":36,"losses":46,"wins":54},"deepseek/deepseek-v4-pro":{"draws":23,"losses":32,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":38,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":46,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":62,"wins":15},"elorian/glimpse":{"draws":15,"losses":21,"wins":12},"fireworks/ember-1":{"draws":27,"losses":38,"wins":25},"gemini-3.1-pro-preview":{"draws":33,"losses":31,"wins":26},"gemini-4-argon":{"draws":2,"losses":82,"wins":6},"google/gemini-3.1-flash-lite":{"draws":15,"losses":12,"wins":37},"google/gemini-3.5-flash":{"draws":25,"losses":52,"wins":37},"google/gemini-3.5-flash-lite":{"draws":38,"losses":38,"wins":52},"google/gemini-3.6-flash":{"draws":46,"losses":83,"wins":43},"google/gemini-3.8-flash":{"draws":16,"losses":66,"wins":8},"google/gemma-4-31b-it":{"draws":20,"losses":9,"wins":25},"gpt-4.1":{"draws":7,"losses":7,"wins":16},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":4},"gpt-5":{"draws":19,"losses":34,"wins":25},"gpt-5.4":{"draws":21,"losses":49,"wins":16},"gpt-5.4-mini":{"draws":16,"losses":20,"wins":24},"gpt-5.4-nano":{"draws":16,"losses":35,"wins":43},"gpt-5.5":{"draws":31,"losses":38,"wins":13},"gpt-5.6-luna":{"draws":23,"losses":32,"wins":35},"gpt-5.6-sol":{"draws":9,"losses":68,"wins":13},"gpt-5.6-terra":{"draws":22,"losses":39,"wins":25},"gpt-6-astra":{"draws":4,"losses":86,"wins":0},"gpt-6-luna":{"draws":28,"losses":36,"wins":26},"gpt-6-sol":{"draws":13,"losses":68,"wins":9},"gpt-6.1-sol":{"draws":7,"losses":82,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":29,"losses":8,"wins":29},"inception/mercury-3":{"draws":20,"losses":30,"wins":10},"inclusionai/ling-3.0-flash":{"draws":23,"losses":8,"wins":33},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":25,"wins":50},"meta/muse-glimmer-30b":{"draws":30,"losses":17,"wins":31},"meta/muse-spark-1.2":{"draws":24,"losses":42,"wins":20},"meta/muse-spark-1.3":{"draws":19,"losses":55,"wins":16},"meta/muse-spark-open":{"draws":18,"losses":52,"wins":16},"meta/muse-wonder":{"draws":18,"losses":60,"wins":12},"minimax/minimax-m3":{"draws":13,"losses":17,"wins":20},"minimax/minimax-m3.1-flash":{"draws":19,"losses":32,"wins":27},"mistralai/mistral-large-4-0":{"draws":20,"losses":27,"wins":9},"mistralai/mistral-medium-3-5":{"draws":15,"losses":11,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":11,"wins":7},"moonshotai/kimi-k3":{"draws":27,"losses":38,"wins":21},"moonshotai/kimi-k3.1-pro":{"draws":12,"losses":75,"wins":3},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":5,"losses":3,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":22,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":14,"losses":18,"wins":10},"o3":{"draws":22,"losses":55,"wins":51},"openai/gpt-oss-120b":{"draws":22,"losses":25,"wins":31},"poolside/laguna-s-2.1":{"draws":20,"losses":30,"wins":34},"qwen/qwen3.7-max":{"draws":14,"losses":21,"wins":19},"qwen/qwen3.7-plus":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":43,"wins":20},"qwen/qwen3.8-27b":{"draws":13,"losses":31,"wins":20},"qwen/qwen3.8-flash":{"draws":15,"losses":25,"wins":20},"qwen/qwen3.8-max":{"draws":23,"losses":42,"wins":25},"qwen/qwen3.8-max-0902":{"draws":26,"losses":47,"wins":17},"recursive/flint-v1.0":{"draws":7,"losses":3,"wins":18},"reflection/beam-1.0-501b-a23b":{"draws":26,"losses":37,"wins":19},"stealth/ox-alpha":{"draws":64,"losses":144,"wins":68},"stealth/space-bunny-alpha":{"draws":22,"losses":20,"wins":30},"stepfun/step-3.7-flash":{"draws":19,"losses":11,"wins":34},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":22,"losses":19,"wins":9},"tencent/hy4-preview":{"draws":23,"losses":42,"wins":21},"thinkingmachines/inkling":{"draws":35,"losses":29,"wins":54},"thinkingmachines/inkling-small":{"draws":26,"losses":19,"wins":45},"unbiased/pareto-26.10":{"draws":3,"losses":27,"wins":0},"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":21,"losses":49,"wins":20},"x-ai/grok-4.6":{"draws":17,"losses":57,"wins":16},"x-ai/grok-4.7":{"draws":9,"losses":59,"wins":12},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":13},"xiaomi/mimo-v2.5":{"draws":39,"losses":42,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":16,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":37,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":36,"wins":14},"z-ai/glm-5.2":{"draws":59,"losses":60,"wins":61},"z-ai/glm-5.3":{"draws":12,"losses":68,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":54,"wins":22},"z-ai/glm-5.3-flashx":{"draws":27,"losses":43,"wins":20}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":34,"wins":31},"claude-fable-5":{"draws":17,"losses":68,"wins":11},"claude-fable-5-1":{"draws":7,"losses":99,"wins":2},"claude-haiku-5-5":{"draws":28,"losses":47,"wins":17},"claude-opus-4-5":{"draws":48,"losses":67,"wins":41},"claude-opus-4-8":{"draws":21,"losses":42,"wins":25},"claude-opus-5":{"draws":20,"losses":127,"wins":17},"claude-opus-5-5":{"draws":3,"losses":99,"wins":2},"claude-sonnet-5":{"draws":30,"losses":43,"wins":23},"claude-sonnet-5-5":{"draws":19,"losses":60,"wins":17},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":21},"deepseek/deepseek-v4-flash":{"draws":42,"losses":41,"wins":61},"deepseek/deepseek-v4-pro":{"draws":28,"losses":39,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":42,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":29,"losses":44,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":62,"wins":19},"elorian/glimpse":{"draws":11,"losses":28,"wins":13},"fireworks/ember-1":{"draws":35,"losses":44,"wins":17},"gemini-3.1-pro-preview":{"draws":30,"losses":37,"wins":29},"gemini-4-argon":{"draws":7,"losses":86,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":14,"wins":32},"google/gemini-3.5-flash":{"draws":27,"losses":66,"wins":27},"google/gemini-3.5-flash-lite":{"draws":46,"losses":58,"wins":64},"google/gemini-3.6-flash":{"draws":40,"losses":84,"wins":28},"google/gemini-3.8-flash":{"draws":21,"losses":59,"wins":16},"google/gemma-4-31b-it":{"draws":23,"losses":11,"wins":22},"gpt-4.1":{"draws":12,"losses":10,"wins":10},"gpt-4.1-nano":{"draws":7,"losses":2,"wins":3},"gpt-5":{"draws":25,"losses":44,"wins":15},"gpt-5.4":{"draws":22,"losses":48,"wins":22},"gpt-5.4-mini":{"draws":17,"losses":18,"wins":29},"gpt-5.4-nano":{"draws":19,"losses":37,"wins":40},"gpt-5.5":{"draws":32,"losses":39,"wins":17},"gpt-5.6-luna":{"draws":29,"losses":33,"wins":34},"gpt-5.6-sol":{"draws":12,"losses":75,"wins":9},"gpt-5.6-terra":{"draws":31,"losses":37,"wins":24},"gpt-6-astra":{"draws":7,"losses":89,"wins":0},"gpt-6-luna":{"draws":32,"losses":32,"wins":32},"gpt-6-sol":{"draws":14,"losses":75,"wins":7},"gpt-6.1-sol":{"draws":5,"losses":91,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":27,"losses":8,"wins":33},"inception/mercury-3":{"draws":17,"losses":28,"wins":19},"inclusionai/ling-3.0-flash":{"draws":28,"losses":15,"wins":25},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":26,"losses":31,"wins":47},"meta/muse-glimmer-30b":{"draws":32,"losses":19,"wins":33},"meta/muse-spark-1.2":{"draws":22,"losses":51,"wins":19},"meta/muse-spark-1.3":{"draws":25,"losses":54,"wins":17},"meta/muse-spark-open":{"draws":19,"losses":51,"wins":22},"meta/muse-wonder":{"draws":16,"losses":68,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":14,"wins":24},"minimax/minimax-m3.1-flash":{"draws":24,"losses":33,"wins":27},"mistralai/mistral-large-4-0":{"draws":18,"losses":25,"wins":17},"mistralai/mistral-medium-3-5":{"draws":18,"losses":12,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":11,"wins":6},"moonshotai/kimi-k3":{"draws":27,"losses":45,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":77,"wins":5},"nex-agi/nex-n2-pro":{"draws":12,"losses":11,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":6,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":24,"wins":32},"nvidia/nemotron-3.5-super-vl":{"draws":12,"losses":22,"wins":10},"o3":{"draws":21,"losses":79,"wins":32},"openai/gpt-oss-120b":{"draws":32,"losses":20,"wins":32},"poolside/laguna-s-2.1":{"draws":25,"losses":31,"wins":36},"qwen/qwen3.7-max":{"draws":11,"losses":25,"wins":20},"qwen/qwen3.7-plus":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":46,"wins":22},"qwen/qwen3.8-27b":{"draws":16,"losses":35,"wins":17},"qwen/qwen3.8-flash":{"draws":22,"losses":22,"wins":20},"qwen/qwen3.8-max":{"draws":23,"losses":50,"wins":23},"qwen/qwen3.8-max-0902":{"draws":28,"losses":43,"wins":25},"recursive/flint-v1.0":{"draws":10,"losses":6,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":25,"losses":40,"wins":23},"stealth/ox-alpha":{"draws":77,"losses":166,"wins":73},"stealth/space-bunny-alpha":{"draws":21,"losses":31,"wins":24},"stepfun/step-3.7-flash":{"draws":19,"losses":19,"wins":30},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":20,"losses":14,"wins":18},"tencent/hy4-preview":{"draws":16,"losses":54,"wins":22},"thinkingmachines/inkling":{"draws":40,"losses":24,"wins":64},"thinkingmachines/inkling-small":{"draws":30,"losses":28,"wins":38},"unbiased/pareto-26.10":{"draws":3,"losses":29,"wins":0},"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":23,"losses":53,"wins":20},"x-ai/grok-4.6":{"draws":25,"losses":61,"wins":10},"x-ai/grok-4.7":{"draws":3,"losses":70,"wins":11},"x-ai/grok-build-0.1":{"draws":9,"losses":6,"wins":17},"xiaomi/mimo-v2.5":{"draws":51,"losses":43,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":19,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":38,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":13,"losses":38,"wins":13},"z-ai/glm-5.2":{"draws":57,"losses":87,"wins":48},"z-ai/glm-5.3":{"draws":17,"losses":71,"wins":4},"z-ai/glm-5.3-flash":{"draws":18,"losses":58,"wins":20},"z-ai/glm-5.3-flashx":{"draws":24,"losses":50,"wins":22}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":9,"wins":22},"claude-fable-5":{"draws":7,"losses":31,"wins":10},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":13,"losses":16,"wins":17},"claude-opus-4-5":{"draws":29,"losses":15,"wins":34},"claude-opus-4-8":{"draws":10,"losses":19,"wins":15},"claude-opus-5":{"draws":11,"losses":59,"wins":12},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":13,"losses":13,"wins":22},"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":18,"losses":12,"wins":42},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":17,"wins":18},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":27,"wins":13},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":12,"losses":18,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":16,"wins":22},"gemini-4-argon":{"draws":1,"losses":44,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":25},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":57},"google/gemini-3.6-flash":{"draws":22,"losses":33,"wins":37},"google/gemini-3.8-flash":{"draws":8,"losses":16,"wins":8},"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":11,"losses":9,"wins":22},"gpt-5.4":{"draws":11,"losses":17,"wins":18},"gpt-5.4-mini":{"draws":9,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":32},"gpt-5.5":{"draws":14,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":11,"wins":25},"gpt-5.6-sol":{"draws":6,"losses":29,"wins":13},"gpt-5.6-terra":{"draws":17,"losses":11,"wins":18},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":15,"losses":13,"wins":20},"gpt-6-sol":{"draws":6,"losses":33,"wins":9},"gpt-6.1-sol":{"draws":6,"losses":40,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":21},"inception/mercury-3":{"draws":10,"losses":6,"wins":16},"inclusionai/ling-3.0-flash":{"draws":13,"losses":0,"wins":21},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":9,"losses":8,"wins":35},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":11,"losses":17,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":20},"meta/muse-spark-open":{"draws":13,"losses":19,"wins":14},"meta/muse-wonder":{"draws":12,"losses":24,"wins":12},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":16},"minimax/minimax-m3.1-flash":{"draws":14,"losses":6,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":13,"losses":13,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":38,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":3,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":2,"wins":13},"o3":{"draws":8,"losses":16,"wins":42},"openai/gpt-oss-120b":{"draws":9,"losses":4,"wins":29},"poolside/laguna-s-2.1":{"draws":9,"losses":5,"wins":32},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":16},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-max":{"draws":13,"losses":16,"wins":19},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":37,"losses":67,"wins":54},"stealth/space-bunny-alpha":{"draws":14,"losses":3,"wins":21},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":13},"thinkingmachines/inkling":{"draws":17,"losses":8,"wins":39},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":10,"losses":23,"wins":15},"x-ai/grok-4.6":{"draws":15,"losses":19,"wins":14},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":27,"losses":2,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":8,"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":32,"losses":25,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":8,"losses":23,"wins":17}},"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":10,"losses":23,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":29,"wins":1},"elorian/glimpse":{"draws":6,"losses":10,"wins":2},"fireworks/ember-1":{"draws":12,"losses":20,"wins":4},"gemini-3.1-pro-preview":{"draws":13,"losses":19,"wins":4},"gemini-4-argon":{"draws":0,"losses":36,"wins":0},"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},"inception/mercury-3":{"draws":6,"losses":16,"wins":2},"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-spark-open":{"draws":8,"losses":24,"wins":2},"meta/muse-wonder":{"draws":7,"losses":27,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3.1-flash":{"draws":10,"losses":18,"wins":2},"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},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":33,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":8,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":10,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":3},"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},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":26,"wins":2},"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":{"draws":1,"losses":11,"wins":0},"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":14,"losses":11,"wins":19},"claude-fable-5":{"draws":8,"losses":28,"wins":12},"claude-fable-5-1":{"draws":5,"losses":47,"wins":2},"claude-haiku-5-5":{"draws":14,"losses":24,"wins":8},"claude-opus-4-5":{"draws":26,"losses":35,"wins":17},"claude-opus-4-8":{"draws":10,"losses":27,"wins":7},"claude-opus-5":{"draws":11,"losses":67,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":19,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":30,"wins":8},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":37},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":20,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":25,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":13,"losses":21,"wins":14},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":5,"losses":43,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":12,"losses":31,"wins":17},"google/gemini-3.5-flash-lite":{"draws":25,"losses":28,"wins":31},"google/gemini-3.6-flash":{"draws":25,"losses":48,"wins":19},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":11,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":15,"wins":16},"gpt-5.4":{"draws":11,"losses":24,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":14,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":18,"wins":21},"gpt-5.5":{"draws":10,"losses":25,"wins":9},"gpt-5.6-luna":{"draws":13,"losses":14,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":14,"wins":14},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":9,"losses":20,"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":13,"losses":8,"wins":13},"inception/mercury-3":{"draws":8,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":28},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":15},"meta/muse-spark-1.2":{"draws":16,"losses":22,"wins":8},"meta/muse-spark-1.3":{"draws":16,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":7,"losses":28,"wins":11},"meta/muse-wonder":{"draws":7,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":13},"minimax/minimax-m3.1-flash":{"draws":8,"losses":17,"wins":17},"mistralai/mistral-large-4-0":{"draws":12,"losses":10,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":22,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":43,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":7},"o3":{"draws":13,"losses":26,"wins":27},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":22},"poolside/laguna-s-2.1":{"draws":14,"losses":13,"wins":19},"qwen/qwen3.7-max":{"draws":11,"losses":12,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":23,"wins":8},"qwen/qwen3.8-27b":{"draws":8,"losses":15,"wins":11},"qwen/qwen3.8-flash":{"draws":11,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":14},"qwen/qwen3.8-max-0902":{"draws":14,"losses":24,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":13,"losses":18,"wins":13},"stealth/ox-alpha":{"draws":39,"losses":81,"wins":38},"stealth/space-bunny-alpha":{"draws":11,"losses":13,"wins":14},"stepfun/step-3.7-flash":{"draws":7,"losses":6,"wins":21},"stepfun/step-5-preview":{"draws":3,"losses":1,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":10},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":13,"losses":15,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":11,"losses":28,"wins":9},"x-ai/grok-4.6":{"draws":19,"losses":23,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":34,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":5},"xiaomi/mimo-v2.5":{"draws":26,"losses":16,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":17,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":19,"wins":7},"z-ai/glm-5.2":{"draws":33,"losses":40,"wins":23},"z-ai/glm-5.3":{"draws":6,"losses":32,"wins":8},"z-ai/glm-5.3-flash":{"draws":5,"losses":28,"wins":15},"z-ai/glm-5.3-flashx":{"draws":8,"losses":30,"wins":10}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":10,"wins":0},"elorian/glimpse":{"draws":6,"losses":2,"wins":0},"fireworks/ember-1":{"draws":9,"losses":8,"wins":1},"gemini-3.1-pro-preview":{"draws":11,"losses":4,"wins":3},"gemini-4-argon":{"draws":0,"losses":18,"wins":0},"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},"inception/mercury-3":{"draws":8,"losses":6,"wins":0},"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-spark-open":{"draws":9,"losses":6,"wins":1},"meta/muse-wonder":{"draws":9,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":1},"minimax/minimax-m3.1-flash":{"draws":9,"losses":6,"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},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":2,"wins":0},"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},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":0},"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":{"draws":0,"losses":6,"wins":0},"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":8,"losses":14,"wins":10},"claude-fable-5":{"draws":7,"losses":26,"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":16,"losses":25,"wins":17},"claude-opus-4-8":{"draws":8,"losses":17,"wins":7},"claude-opus-5":{"draws":7,"losses":57,"wins":4},"claude-opus-5-5":{"draws":1,"losses":39,"wins":0},"claude-sonnet-5":{"draws":8,"losses":24,"wins":4},"claude-sonnet-5-5":{"draws":9,"losses":19,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-flash":{"draws":17,"losses":19,"wins":20},"deepseek/deepseek-v4-pro":{"draws":4,"losses":19,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":23,"wins":8},"elorian/glimpse":{"draws":2,"losses":12,"wins":6},"fireworks/ember-1":{"draws":10,"losses":20,"wins":6},"gemini-3.1-pro-preview":{"draws":13,"losses":13,"wins":10},"gemini-4-argon":{"draws":0,"losses":35,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":7,"losses":24,"wins":13},"google/gemini-3.5-flash-lite":{"draws":12,"losses":17,"wins":31},"google/gemini-3.6-flash":{"draws":14,"losses":33,"wins":21},"google/gemini-3.8-flash":{"draws":6,"losses":19,"wins":11},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":3,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":11,"wins":9},"gpt-5.4":{"draws":3,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":18},"gpt-5.5":{"draws":11,"losses":19,"wins":4},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":26,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":19,"wins":9},"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":8,"losses":5,"wins":9},"inception/mercury-3":{"draws":5,"losses":12,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":8,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":11,"wins":19},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":5,"losses":26,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":5,"losses":25,"wins":4},"meta/muse-wonder":{"draws":7,"losses":23,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":12},"minimax/minimax-m3.1-flash":{"draws":4,"losses":11,"wins":15},"mistralai/mistral-large-4-0":{"draws":11,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":19,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":28,"wins":7},"nex-agi/nex-n2-pro":{"draws":1,"losses":8,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":8,"wins":7},"o3":{"draws":6,"losses":21,"wins":23},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":17},"poolside/laguna-s-2.1":{"draws":12,"losses":11,"wins":17},"qwen/qwen3.7-max":{"draws":11,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":10},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":1,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":8,"losses":20,"wins":8},"qwen/qwen3.8-max-0902":{"draws":8,"losses":18,"wins":10},"recursive/flint-v1.0":{"draws":1,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":20,"wins":10},"stealth/ox-alpha":{"draws":22,"losses":70,"wins":32},"stealth/space-bunny-alpha":{"draws":6,"losses":11,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":9},"thinkingmachines/inkling":{"draws":9,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":12,"losses":9,"wins":15},"unbiased/pareto-26.10":{"draws":1,"losses":11,"wins":0},"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":4,"losses":25,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":21,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":25,"wins":7},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":11,"losses":12,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":13,"wins":8},"z-ai/glm-5.2":{"draws":17,"losses":27,"wins":28},"z-ai/glm-5.3":{"draws":4,"losses":25,"wins":5},"z-ai/glm-5.3-flash":{"draws":3,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":7,"losses":20,"wins":9}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":14,"wins":18},"claude-fable-5":{"draws":10,"losses":29,"wins":9},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":21,"wins":13},"claude-opus-4-5":{"draws":27,"losses":28,"wins":23},"claude-opus-4-8":{"draws":13,"losses":16,"wins":15},"claude-opus-5":{"draws":14,"losses":62,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":15,"wins":21},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":23,"losses":15,"wins":34},"deepseek/deepseek-v4-pro":{"draws":9,"losses":19,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":9},"elorian/glimpse":{"draws":8,"losses":9,"wins":9},"fireworks/ember-1":{"draws":18,"losses":16,"wins":14},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":17},"gemini-4-argon":{"draws":3,"losses":42,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":10,"losses":23,"wins":27},"google/gemini-3.5-flash-lite":{"draws":23,"losses":21,"wins":40},"google/gemini-3.6-flash":{"draws":21,"losses":44,"wins":27},"google/gemini-3.8-flash":{"draws":11,"losses":29,"wins":8},"google/gemma-4-31b-it":{"draws":13,"losses":3,"wins":12},"gpt-4.1":{"draws":5,"losses":5,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":17,"wins":17},"gpt-5.4":{"draws":7,"losses":22,"wins":1},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":17},"gpt-5.4-nano":{"draws":7,"losses":16,"wins":25},"gpt-5.5":{"draws":16,"losses":17,"wins":11},"gpt-5.6-luna":{"draws":19,"losses":13,"wins":16},"gpt-5.6-sol":{"draws":9,"losses":27,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":20,"wins":11},"gpt-6-astra":{"draws":1,"losses":43,"wins":4},"gpt-6-luna":{"draws":20,"losses":14,"wins":14},"gpt-6-sol":{"draws":7,"losses":36,"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":15,"losses":2,"wins":17},"inception/mercury-3":{"draws":7,"losses":17,"wins":8},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":26},"meta/muse-glimmer-30b":{"draws":10,"losses":14,"wins":18},"meta/muse-spark-1.2":{"draws":7,"losses":25,"wins":14},"meta/muse-spark-1.3":{"draws":7,"losses":29,"wins":12},"meta/muse-spark-open":{"draws":11,"losses":22,"wins":13},"meta/muse-wonder":{"draws":9,"losses":29,"wins":10},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":7,"losses":14,"wins":21},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":10,"losses":5,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":37,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":4,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":9},"o3":{"draws":9,"losses":29,"wins":28},"openai/gpt-oss-120b":{"draws":10,"losses":12,"wins":20},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":20},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":10},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":18,"wins":7},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":11},"qwen/qwen3.8-max-0902":{"draws":10,"losses":21,"wins":17},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":16,"wins":17},"stealth/ox-alpha":{"draws":38,"losses":80,"wins":40},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":23,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":11,"wins":34},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":11,"losses":22,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":29,"wins":7},"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":21,"losses":13,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":14,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":15,"wins":10},"z-ai/glm-5.2":{"draws":28,"losses":29,"wins":39},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":15},"z-ai/glm-5.3-flashx":{"draws":15,"losses":21,"wins":12}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":22,"wins":5},"claude-fable-5":{"draws":10,"losses":37,"wins":1},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":14,"losses":30,"wins":2},"claude-opus-4-5":{"draws":34,"losses":37,"wins":7},"claude-opus-4-8":{"draws":10,"losses":31,"wins":3},"claude-opus-5":{"draws":20,"losses":58,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":21,"losses":19,"wins":8},"claude-sonnet-5-5":{"draws":10,"losses":33,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":8,"wins":5},"deepseek/deepseek-v4-flash":{"draws":30,"losses":28,"wins":14},"deepseek/deepseek-v4-pro":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":24,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":21,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":32,"wins":2},"elorian/glimpse":{"draws":8,"losses":14,"wins":4},"fireworks/ember-1":{"draws":23,"losses":22,"wins":3},"gemini-3.1-pro-preview":{"draws":18,"losses":24,"wins":6},"gemini-4-argon":{"draws":7,"losses":41,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":17},"google/gemini-3.5-flash":{"draws":16,"losses":39,"wins":5},"google/gemini-3.5-flash-lite":{"draws":27,"losses":39,"wins":18},"google/gemini-3.6-flash":{"draws":30,"losses":56,"wins":6},"google/gemini-3.8-flash":{"draws":13,"losses":34,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":8,"wins":7},"gpt-4.1":{"draws":7,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":23,"wins":4},"gpt-5.4":{"draws":16,"losses":30,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":9,"wins":2},"gpt-5.4-nano":{"draws":14,"losses":27,"wins":7},"gpt-5.5":{"draws":16,"losses":20,"wins":8},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":8},"gpt-5.6-sol":{"draws":10,"losses":37,"wins":1},"gpt-5.6-terra":{"draws":20,"losses":22,"wins":4},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":21,"losses":23,"wins":4},"gpt-6-sol":{"draws":6,"losses":40,"wins":2},"gpt-6.1-sol":{"draws":2,"losses":46,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":10,"wins":8},"inception/mercury-3":{"draws":13,"losses":16,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":20,"losses":23,"wins":9},"meta/muse-glimmer-30b":{"draws":20,"losses":15,"wins":7},"meta/muse-spark-1.2":{"draws":16,"losses":27,"wins":3},"meta/muse-spark-1.3":{"draws":10,"losses":37,"wins":1},"meta/muse-spark-open":{"draws":14,"losses":30,"wins":2},"meta/muse-wonder":{"draws":14,"losses":32,"wins":2},"minimax/minimax-m3":{"draws":7,"losses":15,"wins":4},"minimax/minimax-m3.1-flash":{"draws":19,"losses":20,"wins":3},"mistralai/mistral-large-4-0":{"draws":16,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":12,"losses":9,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":27,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":12,"wins":5},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":20,"wins":4},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":14,"wins":0},"o3":{"draws":14,"losses":45,"wins":7},"openai/gpt-oss-120b":{"draws":21,"losses":15,"wins":6},"poolside/laguna-s-2.1":{"draws":17,"losses":24,"wins":5},"qwen/qwen3.7-max":{"draws":6,"losses":16,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":14,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":28,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":12,"losses":16,"wins":4},"qwen/qwen3.8-max":{"draws":24,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":24,"losses":23,"wins":1},"recursive/flint-v1.0":{"draws":4,"losses":8,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":23,"wins":3},"stealth/ox-alpha":{"draws":52,"losses":92,"wins":14},"stealth/space-bunny-alpha":{"draws":12,"losses":25,"wins":1},"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":11,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":29,"wins":2},"thinkingmachines/inkling":{"draws":24,"losses":26,"wins":14},"thinkingmachines/inkling-small":{"draws":21,"losses":19,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":17,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":19,"losses":27,"wins":2},"x-ai/grok-4.7":{"draws":7,"losses":35,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":28,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":13,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":20,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":21,"wins":1},"z-ai/glm-5.2":{"draws":42,"losses":49,"wins":5},"z-ai/glm-5.3":{"draws":15,"losses":30,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":13,"losses":33,"wins":2}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":30,"wins":22},"claude-fable-5":{"draws":10,"losses":58,"wins":4},"claude-fable-5-1":{"draws":0,"losses":76,"wins":0},"claude-haiku-5-5":{"draws":19,"losses":36,"wins":15},"claude-opus-4-5":{"draws":31,"losses":64,"wins":23},"claude-opus-4-8":{"draws":14,"losses":42,"wins":12},"claude-opus-5":{"draws":11,"losses":106,"wins":3},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":23,"losses":33,"wins":16},"claude-sonnet-5-5":{"draws":12,"losses":53,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":16},"deepseek/deepseek-v4-flash":{"draws":28,"losses":45,"wins":41},"deepseek/deepseek-v4-pro":{"draws":9,"losses":31,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":34,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":22,"losses":36,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":50,"wins":11},"elorian/glimpse":{"draws":8,"losses":21,"wins":7},"fireworks/ember-1":{"draws":17,"losses":45,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":39,"wins":15},"gemini-4-argon":{"draws":0,"losses":68,"wins":4},"google/gemini-3.1-flash-lite":{"draws":11,"losses":13,"wins":26},"google/gemini-3.5-flash":{"draws":12,"losses":62,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":53,"wins":42},"google/gemini-3.6-flash":{"draws":24,"losses":85,"wins":27},"google/gemini-3.8-flash":{"draws":16,"losses":49,"wins":7},"google/gemma-4-31b-it":{"draws":15,"losses":10,"wins":17},"gpt-4.1":{"draws":6,"losses":10,"wins":8},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":38,"wins":17},"gpt-5.4":{"draws":9,"losses":46,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":17,"wins":18},"gpt-5.4-nano":{"draws":12,"losses":26,"wins":22},"gpt-5.5":{"draws":15,"losses":36,"wins":13},"gpt-5.6-luna":{"draws":19,"losses":31,"wins":22},"gpt-5.6-sol":{"draws":6,"losses":59,"wins":7},"gpt-5.6-terra":{"draws":15,"losses":39,"wins":14},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"gpt-6-luna":{"draws":17,"losses":41,"wins":14},"gpt-6-sol":{"draws":8,"losses":56,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":67,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":10,"wins":24},"inception/mercury-3":{"draws":15,"losses":25,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":12,"wins":27},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":16,"losses":29,"wins":33},"meta/muse-glimmer-30b":{"draws":14,"losses":23,"wins":23},"meta/muse-spark-1.2":{"draws":12,"losses":37,"wins":19},"meta/muse-spark-1.3":{"draws":11,"losses":53,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":52,"wins":7},"meta/muse-wonder":{"draws":7,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":14,"wins":20},"minimax/minimax-m3.1-flash":{"draws":8,"losses":30,"wins":22},"mistralai/mistral-large-4-0":{"draws":9,"losses":24,"wins":11},"mistralai/mistral-medium-3-5":{"draws":8,"losses":13,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":10,"wins":5},"moonshotai/kimi-k3":{"draws":17,"losses":38,"wins":13},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":65,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":16,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":26,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":15,"wins":9},"o3":{"draws":9,"losses":61,"wins":38},"openai/gpt-oss-120b":{"draws":24,"losses":24,"wins":16},"poolside/laguna-s-2.1":{"draws":20,"losses":35,"wins":21},"qwen/qwen3.7-max":{"draws":14,"losses":20,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":18,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":44,"wins":11},"qwen/qwen3.8-27b":{"draws":13,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":27,"wins":11},"qwen/qwen3.8-max":{"draws":15,"losses":37,"wins":20},"qwen/qwen3.8-max-0902":{"draws":21,"losses":36,"wins":15},"recursive/flint-v1.0":{"draws":7,"losses":7,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":39,"wins":10},"stealth/ox-alpha":{"draws":41,"losses":129,"wins":52},"stealth/space-bunny-alpha":{"draws":10,"losses":30,"wins":14},"stepfun/step-3.7-flash":{"draws":9,"losses":19,"wins":26},"stepfun/step-5-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":12,"losses":21,"wins":7},"tencent/hy4-preview":{"draws":9,"losses":51,"wins":8},"thinkingmachines/inkling":{"draws":22,"losses":41,"wins":31},"thinkingmachines/inkling-small":{"draws":22,"losses":23,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":17,"losses":46,"wins":9},"x-ai/grok-4.6":{"draws":13,"losses":46,"wins":13},"x-ai/grok-4.7":{"draws":8,"losses":56,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":10,"wins":11},"xiaomi/mimo-v2.5":{"draws":27,"losses":40,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":21,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":14,"losses":27,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":35,"wins":6},"z-ai/glm-5.2":{"draws":35,"losses":71,"wins":38},"z-ai/glm-5.3":{"draws":12,"losses":49,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":46,"wins":15},"z-ai/glm-5.3-flashx":{"draws":18,"losses":39,"wins":15}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":10,"wins":13},"claude-fable-5":{"draws":12,"losses":23,"wins":7},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":17,"losses":17,"wins":6},"claude-opus-4-5":{"draws":35,"losses":23,"wins":10},"claude-opus-4-8":{"draws":15,"losses":17,"wins":6},"claude-opus-5":{"draws":14,"losses":65,"wins":1},"claude-opus-5-5":{"draws":7,"losses":39,"wins":0},"claude-sonnet-5":{"draws":20,"losses":12,"wins":10},"claude-sonnet-5-5":{"draws":11,"losses":21,"wins":10},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":26,"losses":13,"wins":23},"deepseek/deepseek-v4-pro":{"draws":19,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":20,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":20,"wins":8},"elorian/glimpse":{"draws":5,"losses":8,"wins":11},"fireworks/ember-1":{"draws":13,"losses":20,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":15,"wins":13},"gemini-4-argon":{"draws":4,"losses":38,"wins":0},"google/gemini-3.1-flash-lite":{"draws":12,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":16,"losses":21,"wins":15},"google/gemini-3.5-flash-lite":{"draws":34,"losses":14,"wins":24},"google/gemini-3.6-flash":{"draws":28,"losses":37,"wins":15},"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":6,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":19,"losses":12,"wins":7},"gpt-5.4":{"draws":10,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":15},"gpt-5.5":{"draws":15,"losses":9,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":13,"wins":6},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":14,"losses":15,"wins":13},"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":15,"losses":1,"wins":12},"inception/mercury-3":{"draws":12,"losses":10,"wins":6},"inclusionai/ling-3.0-flash":{"draws":19,"losses":2,"wins":7},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":15},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":13,"losses":23,"wins":6},"meta/muse-spark-open":{"draws":10,"losses":25,"wins":5},"meta/muse-wonder":{"draws":17,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":10,"losses":6,"wins":8},"minimax/minimax-m3.1-flash":{"draws":17,"losses":9,"wins":10},"mistralai/mistral-large-4-0":{"draws":14,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":12,"losses":2,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":35,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":4,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":6,"wins":5},"o3":{"draws":16,"losses":18,"wins":20},"openai/gpt-oss-120b":{"draws":18,"losses":6,"wins":14},"poolside/laguna-s-2.1":{"draws":23,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":14,"losses":7,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":17,"wins":8},"qwen/qwen3.8-27b":{"draws":10,"losses":14,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":15,"losses":17,"wins":10},"qwen/qwen3.8-max-0902":{"draws":16,"losses":20,"wins":6},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":43,"losses":70,"wins":29},"stealth/space-bunny-alpha":{"draws":15,"losses":9,"wins":10},"stepfun/step-3.7-flash":{"draws":13,"losses":5,"wins":10},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":3},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":4},"thinkingmachines/inkling":{"draws":26,"losses":7,"wins":25},"thinkingmachines/inkling-small":{"draws":17,"losses":10,"wins":15},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":15,"losses":25,"wins":2},"x-ai/grok-4.6":{"draws":15,"losses":23,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":26,"wins":7},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":30,"losses":9,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":6,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":14,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":24,"wins":25},"z-ai/glm-5.3":{"draws":8,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":20,"wins":9},"z-ai/glm-5.3-flashx":{"draws":14,"losses":21,"wins":7}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":24,"wins":8},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":26,"losses":45,"wins":7},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":10,"losses":68,"wins":4},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":12,"losses":30,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":31,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":8,"wins":7},"deepseek/deepseek-v4-flash":{"draws":26,"losses":34,"wins":12},"deepseek/deepseek-v4-pro":{"draws":13,"losses":26,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":23,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":28,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":36,"wins":3},"elorian/glimpse":{"draws":6,"losses":15,"wins":5},"fireworks/ember-1":{"draws":15,"losses":28,"wins":5},"gemini-3.1-pro-preview":{"draws":11,"losses":29,"wins":8},"gemini-4-argon":{"draws":3,"losses":45,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":17,"wins":8},"google/gemini-3.5-flash":{"draws":13,"losses":41,"wins":6},"google/gemini-3.5-flash-lite":{"draws":23,"losses":44,"wins":17},"google/gemini-3.6-flash":{"draws":23,"losses":65,"wins":4},"google/gemini-3.8-flash":{"draws":6,"losses":39,"wins":3},"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":13,"losses":29,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":16,"wins":4},"gpt-5.4-nano":{"draws":13,"losses":27,"wins":8},"gpt-5.5":{"draws":13,"losses":28,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":18,"wins":4},"gpt-5.6-sol":{"draws":4,"losses":40,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":25,"wins":7},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":16,"losses":25,"wins":7},"gpt-6-sol":{"draws":8,"losses":38,"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":14,"losses":14,"wins":6},"inception/mercury-3":{"draws":13,"losses":16,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":13,"wins":4},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":31,"wins":6},"meta/muse-glimmer-30b":{"draws":17,"losses":22,"wins":3},"meta/muse-spark-1.2":{"draws":16,"losses":24,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":34,"wins":2},"meta/muse-spark-open":{"draws":11,"losses":31,"wins":4},"meta/muse-wonder":{"draws":9,"losses":36,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":13,"wins":5},"minimax/minimax-m3.1-flash":{"draws":11,"losses":22,"wins":9},"mistralai/mistral-large-4-0":{"draws":8,"losses":19,"wins":3},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":26,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":10,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":24,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":14,"wins":2},"o3":{"draws":8,"losses":52,"wins":6},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":8},"poolside/laguna-s-2.1":{"draws":14,"losses":26,"wins":6},"qwen/qwen3.7-max":{"draws":9,"losses":16,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":31,"wins":0},"qwen/qwen3.8-27b":{"draws":11,"losses":20,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":15,"wins":5},"qwen/qwen3.8-max":{"draws":12,"losses":30,"wins":6},"qwen/qwen3.8-max-0902":{"draws":13,"losses":32,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":7,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":22,"wins":7},"stealth/ox-alpha":{"draws":49,"losses":99,"wins":10},"stealth/space-bunny-alpha":{"draws":13,"losses":21,"wins":4},"stepfun/step-3.7-flash":{"draws":9,"losses":16,"wins":9},"stepfun/step-5-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":19,"wins":0},"tencent/hy4-preview":{"draws":13,"losses":31,"wins":2},"thinkingmachines/inkling":{"draws":22,"losses":26,"wins":16},"thinkingmachines/inkling-small":{"draws":18,"losses":23,"wins":7},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":14,"losses":33,"wins":1},"x-ai/grok-4.6":{"draws":9,"losses":36,"wins":3},"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":25,"losses":38,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":17,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":21,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":25,"wins":1},"z-ai/glm-5.2":{"draws":36,"losses":53,"wins":7},"z-ai/glm-5.3":{"draws":8,"losses":37,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":30,"wins":6},"z-ai/glm-5.3-flashx":{"draws":11,"losses":35,"wins":2}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":4,"wins":28},"claude-fable-5":{"draws":7,"losses":30,"wins":11},"claude-fable-5-1":{"draws":3,"losses":46,"wins":5},"claude-haiku-5-5":{"draws":4,"losses":21,"wins":21},"claude-opus-4-5":{"draws":21,"losses":14,"wins":43},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":9,"losses":65,"wins":8},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":14,"losses":9,"wins":25},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":17},"cohere/north-mini-code":{"draws":1,"losses":4,"wins":13},"deepseek/deepseek-v4-flash":{"draws":14,"losses":10,"wins":48},"deepseek/deepseek-v4-pro":{"draws":11,"losses":15,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":16,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":22,"wins":13},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":27,"wins":9},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":11,"losses":19,"wins":18},"gemini-3.1-pro-preview":{"draws":10,"losses":13,"wins":25},"gemini-4-argon":{"draws":4,"losses":40,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":12,"losses":17,"wins":31},"google/gemini-3.5-flash-lite":{"draws":20,"losses":10,"wins":54},"google/gemini-3.6-flash":{"draws":19,"losses":31,"wins":42},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":17},"gpt-4.1":{"draws":4,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":12,"wins":21},"gpt-5.4":{"draws":11,"losses":21,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":33},"gpt-5.5":{"draws":10,"losses":22,"wins":12},"gpt-5.6-luna":{"draws":15,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":2,"losses":19,"wins":11},"gpt-5.6-terra":{"draws":13,"losses":14,"wins":19},"gpt-6-astra":{"draws":3,"losses":42,"wins":3},"gpt-6-luna":{"draws":10,"losses":13,"wins":25},"gpt-6-sol":{"draws":3,"losses":37,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":41,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":21},"inception/mercury-3":{"draws":7,"losses":9,"wins":16},"inclusionai/ling-3.0-flash":{"draws":8,"losses":1,"wins":25},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":11,"losses":4,"wins":37},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":7,"losses":23,"wins":18},"meta/muse-spark-open":{"draws":11,"losses":19,"wins":16},"meta/muse-wonder":{"draws":10,"losses":27,"wins":11},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"minimax/minimax-m3.1-flash":{"draws":9,"losses":13,"wins":20},"mistralai/mistral-large-4-0":{"draws":8,"losses":9,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":16,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":42,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":6,"losses":13,"wins":47},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":31},"qwen/qwen3.7-max":{"draws":5,"losses":7,"wins":16},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":20,"wins":17},"qwen/qwen3.8-27b":{"draws":8,"losses":6,"wins":20},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":15},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":13,"losses":15,"wins":20},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":11,"wins":21},"stealth/ox-alpha":{"draws":33,"losses":62,"wins":63},"stealth/space-bunny-alpha":{"draws":10,"losses":6,"wins":22},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":24},"stepfun/step-5-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":19,"wins":17},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":41},"thinkingmachines/inkling-small":{"draws":14,"losses":4,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":15,"wins":1},"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":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":13,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":6,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"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":9,"losses":19,"wins":20},"z-ai/glm-5.3-flashx":{"draws":10,"losses":17,"wins":21}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":19},"claude-fable-5":{"draws":10,"losses":31,"wins":1},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":20,"wins":5},"claude-opus-4-5":{"draws":25,"losses":32,"wins":11},"claude-opus-4-8":{"draws":15,"losses":18,"wins":5},"claude-opus-5":{"draws":7,"losses":53,"wins":10},"claude-opus-5-5":{"draws":3,"losses":42,"wins":1},"claude-sonnet-5":{"draws":16,"losses":18,"wins":8},"claude-sonnet-5-5":{"draws":12,"losses":23,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":14,"wins":29},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":29,"wins":1},"elorian/glimpse":{"draws":7,"losses":13,"wins":4},"fireworks/ember-1":{"draws":16,"losses":24,"wins":2},"gemini-3.1-pro-preview":{"draws":18,"losses":17,"wins":7},"gemini-4-argon":{"draws":4,"losses":38,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":17,"losses":24,"wins":11},"google/gemini-3.5-flash-lite":{"draws":21,"losses":22,"wins":29},"google/gemini-3.6-flash":{"draws":22,"losses":47,"wins":11},"google/gemini-3.8-flash":{"draws":12,"losses":25,"wins":5},"google/gemma-4-31b-it":{"draws":15,"losses":1,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":19,"wins":8},"gpt-5.4":{"draws":10,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":10,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":15,"wins":16},"gpt-5.5":{"draws":17,"losses":14,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":14,"wins":14},"gpt-5.6-sol":{"draws":10,"losses":29,"wins":3},"gpt-5.6-terra":{"draws":13,"losses":7,"wins":8},"gpt-6-astra":{"draws":5,"losses":37,"wins":0},"gpt-6-luna":{"draws":16,"losses":19,"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":12,"losses":3,"wins":15},"inception/mercury-3":{"draws":13,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":15,"losses":14,"wins":15},"meta/muse-glimmer-30b":{"draws":13,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":15,"losses":18,"wins":7},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":9},"meta/muse-spark-open":{"draws":12,"losses":24,"wins":4},"meta/muse-wonder":{"draws":10,"losses":26,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":15},"mistralai/mistral-large-4-0":{"draws":16,"losses":7,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":13,"losses":18,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":12,"wins":12},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":6,"wins":4},"o3":{"draws":12,"losses":24,"wins":18},"openai/gpt-oss-120b":{"draws":15,"losses":1,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":6,"wins":15},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":18,"wins":7},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":3},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":17,"wins":9},"qwen/qwen3.8-max-0902":{"draws":17,"losses":19,"wins":6},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":18,"wins":6},"stealth/ox-alpha":{"draws":43,"losses":76,"wins":21},"stealth/space-bunny-alpha":{"draws":15,"losses":14,"wins":3},"stepfun/step-3.7-flash":{"draws":11,"losses":8,"wins":11},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":14,"losses":18,"wins":8},"thinkingmachines/inkling":{"draws":17,"losses":17,"wins":20},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":20},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":14,"losses":25,"wins":3},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":10},"xiaomi/mimo-v2.5":{"draws":25,"losses":11,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":8,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":14,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":17,"wins":3},"z-ai/glm-5.2":{"draws":36,"losses":26,"wins":22},"z-ai/glm-5.3":{"draws":11,"losses":26,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":5},"z-ai/glm-5.3-flashx":{"draws":10,"losses":25,"wins":7}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":35},"claude-fable-5":{"draws":6,"losses":9,"wins":33},"claude-fable-5-1":{"draws":4,"losses":29,"wins":21},"claude-haiku-5-5":{"draws":4,"losses":3,"wins":39},"claude-opus-4-5":{"draws":8,"losses":6,"wins":64},"claude-opus-4-8":{"draws":4,"losses":6,"wins":34},"claude-opus-5":{"draws":11,"losses":23,"wins":48},"claude-opus-5-5":{"draws":8,"losses":28,"wins":16},"claude-sonnet-5":{"draws":6,"losses":6,"wins":36},"claude-sonnet-5-5":{"draws":5,"losses":12,"wins":31},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":6,"losses":2,"wins":64},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":2,"wins":36},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":7,"wins":38},"elorian/glimpse":{"draws":5,"losses":4,"wins":17},"fireworks/ember-1":{"draws":9,"losses":2,"wins":37},"gemini-3.1-pro-preview":{"draws":4,"losses":1,"wins":43},"gemini-4-argon":{"draws":8,"losses":17,"wins":23},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":54},"google/gemini-3.5-flash-lite":{"draws":9,"losses":0,"wins":75},"google/gemini-3.6-flash":{"draws":12,"losses":6,"wins":74},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":34},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":24},"gpt-4.1":{"draws":2,"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":5,"losses":7,"wins":34},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":28},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":45},"gpt-5.5":{"draws":4,"losses":2,"wins":38},"gpt-5.6-luna":{"draws":7,"losses":2,"wins":39},"gpt-5.6-sol":{"draws":7,"losses":3,"wins":38},"gpt-5.6-terra":{"draws":10,"losses":1,"wins":35},"gpt-6-astra":{"draws":6,"losses":18,"wins":8},"gpt-6-luna":{"draws":7,"losses":4,"wins":37},"gpt-6-sol":{"draws":4,"losses":15,"wins":29},"gpt-6.1-sol":{"draws":6,"losses":24,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":30},"inception/mercury-3":{"draws":7,"losses":0,"wins":25},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":29},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":4,"losses":3,"wins":45},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":39},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":39},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":35},"meta/muse-spark-open":{"draws":4,"losses":2,"wins":40},"meta/muse-wonder":{"draws":8,"losses":7,"wins":33},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":25},"minimax/minimax-m3.1-flash":{"draws":8,"losses":0,"wins":34},"mistralai/mistral-large-4-0":{"draws":4,"losses":4,"wins":22},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":5,"losses":5,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":19,"wins":24},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":20},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"o3":{"draws":3,"losses":0,"wins":63},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":34},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":40},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":24},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":3,"wins":42},"qwen/qwen3.8-27b":{"draws":3,"losses":0,"wins":31},"qwen/qwen3.8-flash":{"draws":8,"losses":1,"wins":23},"qwen/qwen3.8-max":{"draws":7,"losses":3,"wins":38},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":37},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":3,"wins":33},"stealth/ox-alpha":{"draws":19,"losses":10,"wins":129},"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":8,"losses":3,"wins":35},"thinkingmachines/inkling":{"draws":7,"losses":1,"wins":56},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":43},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"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":4,"losses":5,"wins":39},"x-ai/grok-4.6":{"draws":7,"losses":5,"wins":36},"x-ai/grok-4.7":{"draws":5,"losses":11,"wins":26},"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":24},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":26},"z-ai/glm-5.2":{"draws":15,"losses":5,"wins":76},"z-ai/glm-5.3":{"draws":10,"losses":4,"wins":32},"z-ai/glm-5.3-flash":{"draws":8,"losses":5,"wins":35},"z-ai/glm-5.3-flashx":{"draws":10,"losses":2,"wins":36}},"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":18,"losses":59,"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":14,"losses":14,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":21,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":14,"losses":25,"wins":9},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":16,"losses":22,"wins":10},"gemini-3.1-pro-preview":{"draws":18,"losses":21,"wins":9},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":23,"losses":22,"wins":15},"google/gemini-3.5-flash-lite":{"draws":40,"losses":15,"wins":29},"google/gemini-3.6-flash":{"draws":36,"losses":40,"wins":16},"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":6,"wins":8},"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},"inception/mercury-3":{"draws":10,"losses":12,"wins":10},"inclusionai/ling-3.0-flash":{"draws":19,"losses":4,"wins":11},"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":14,"losses":21,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":32,"wins":5},"meta/muse-spark-open":{"draws":13,"losses":21,"wins":12},"meta/muse-wonder":{"draws":15,"losses":25,"wins":8},"minimax/minimax-m3":{"draws":12,"losses":2,"wins":12},"minimax/minimax-m3.1-flash":{"draws":10,"losses":13,"wins":19},"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},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":42,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":5,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":3,"wins":12},"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},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":17,"wins":15},"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":{"draws":1,"losses":15,"wins":0},"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":5,"wins":33},"claude-fable-5":{"draws":8,"losses":21,"wins":19},"claude-fable-5-1":{"draws":3,"losses":49,"wins":2},"claude-haiku-5-5":{"draws":9,"losses":14,"wins":23},"claude-opus-4-5":{"draws":15,"losses":9,"wins":54},"claude-opus-4-8":{"draws":7,"losses":16,"wins":21},"claude-opus-5":{"draws":12,"losses":58,"wins":12},"claude-opus-5-5":{"draws":2,"losses":43,"wins":7},"claude-sonnet-5":{"draws":12,"losses":6,"wins":30},"claude-sonnet-5-5":{"draws":3,"losses":23,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":54},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":7,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":17,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":21,"wins":19},"elorian/glimpse":{"draws":4,"losses":6,"wins":16},"fireworks/ember-1":{"draws":10,"losses":11,"wins":27},"gemini-3.1-pro-preview":{"draws":8,"losses":12,"wins":28},"gemini-4-argon":{"draws":6,"losses":30,"wins":12},"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":13,"losses":8,"wins":63},"google/gemini-3.6-flash":{"draws":17,"losses":27,"wins":48},"google/gemini-3.8-flash":{"draws":8,"losses":19,"wins":21},"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":6,"losses":7,"wins":29},"gpt-5.4":{"draws":5,"losses":9,"wins":32},"gpt-5.4-mini":{"draws":6,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":38},"gpt-5.5":{"draws":10,"losses":13,"wins":21},"gpt-5.6-luna":{"draws":11,"losses":5,"wins":32},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":20},"gpt-5.6-terra":{"draws":11,"losses":6,"wins":29},"gpt-6-astra":{"draws":4,"losses":39,"wins":5},"gpt-6-luna":{"draws":9,"losses":6,"wins":33},"gpt-6-sol":{"draws":4,"losses":20,"wins":8},"gpt-6.1-sol":{"draws":3,"losses":38,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":23},"inception/mercury-3":{"draws":10,"losses":5,"wins":17},"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":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":10,"losses":10,"wins":28},"meta/muse-spark-open":{"draws":7,"losses":8,"wins":31},"meta/muse-wonder":{"draws":12,"losses":21,"wins":15},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":19},"minimax/minimax-m3.1-flash":{"draws":8,"losses":5,"wins":29},"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":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":27},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":35,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":3,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":36},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":3,"wins":15},"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":11,"losses":11,"wins":26},"qwen/qwen3.8-max-0902":{"draws":13,"losses":10,"wins":25},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":12},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":7,"wins":28},"stealth/ox-alpha":{"draws":24,"losses":33,"wins":101},"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":7,"losses":13,"wins":26},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":48},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":33},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":12,"losses":13,"wins":23},"x-ai/grok-4.6":{"draws":11,"losses":15,"wins":22},"x-ai/grok-4.7":{"draws":4,"losses":26,"wins":12},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":17,"losses":3,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":11,"wins":15},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":60},"z-ai/glm-5.3":{"draws":8,"losses":20,"wins":18},"z-ai/glm-5.3-flash":{"draws":7,"losses":17,"wins":24},"z-ai/glm-5.3-flashx":{"draws":5,"losses":24,"wins":19}},"gpt-6.1-sol":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":4,"wins":31},"claude-fable-5":{"draws":4,"losses":20,"wins":24},"claude-fable-5-1":{"draws":3,"losses":34,"wins":17},"claude-haiku-5-5":{"draws":7,"losses":5,"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":12,"losses":34,"wins":36},"claude-opus-5-5":{"draws":9,"losses":28,"wins":15},"claude-sonnet-5":{"draws":5,"losses":6,"wins":37},"claude-sonnet-5-5":{"draws":1,"losses":16,"wins":31},"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":2,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":5,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":12,"wins":31},"elorian/glimpse":{"draws":3,"losses":3,"wins":20},"fireworks/ember-1":{"draws":10,"losses":7,"wins":31},"gemini-3.1-pro-preview":{"draws":2,"losses":7,"wins":39},"gemini-4-argon":{"draws":10,"losses":19,"wins":19},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":5,"losses":11,"wins":44},"google/gemini-3.5-flash-lite":{"draws":9,"losses":1,"wins":74},"google/gemini-3.6-flash":{"draws":9,"losses":12,"wins":71},"google/gemini-3.8-flash":{"draws":11,"losses":9,"wins":28},"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":3,"wins":34},"gpt-5.4":{"draws":5,"losses":10,"wins":31},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":28},"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":7,"losses":11,"wins":30},"gpt-5.6-terra":{"draws":7,"losses":2,"wins":37},"gpt-6-astra":{"draws":4,"losses":34,"wins":10},"gpt-6-luna":{"draws":10,"losses":4,"wins":34},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"gpt-6.1-sol":{"draws":1,"losses":25,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":7,"losses":2,"wins":23},"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":4,"losses":4,"wins":44},"meta/muse-glimmer-30b":{"draws":7,"losses":1,"wins":34},"meta/muse-spark-1.2":{"draws":9,"losses":7,"wins":30},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":33},"meta/muse-spark-open":{"draws":7,"losses":5,"wins":34},"meta/muse-wonder":{"draws":8,"losses":14,"wins":26},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":21},"minimax/minimax-m3.1-flash":{"draws":11,"losses":2,"wins":29},"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},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":24,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":21},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":30},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":18},"o3":{"draws":2,"losses":6,"wins":58},"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":6,"losses":10,"wins":32},"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":3,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":31},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":5,"losses":2,"wins":37},"stealth/ox-alpha":{"draws":25,"losses":19,"wins":114},"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":4,"losses":8,"wins":34},"thinkingmachines/inkling":{"draws":9,"losses":3,"wins":52},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":44},"unbiased/pareto-26.10":{"draws":3,"losses":10,"wins":3},"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":12,"losses":4,"wins":32},"x-ai/grok-4.7":{"draws":3,"losses":20,"wins":19},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5":{"draws":14,"losses":6,"wins":54},"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":4,"wins":74},"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":11,"losses":9,"wins":28}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":10,"wins":9},"claude-fable-5":{"draws":9,"losses":16,"wins":5},"claude-fable-5-1":{"draws":2,"losses":32,"wins":0},"claude-haiku-5-5":{"draws":9,"losses":16,"wins":3},"claude-opus-4-5":{"draws":23,"losses":20,"wins":5},"claude-opus-4-8":{"draws":11,"losses":9,"wins":6},"claude-opus-5":{"draws":13,"losses":35,"wins":2},"claude-opus-5-5":{"draws":4,"losses":26,"wins":0},"claude-sonnet-5":{"draws":12,"losses":11,"wins":7},"claude-sonnet-5-5":{"draws":8,"losses":15,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":11,"losses":9,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":13,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":13,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":14,"wins":4},"elorian/glimpse":{"draws":7,"losses":7,"wins":0},"fireworks/ember-1":{"draws":13,"losses":12,"wins":5},"gemini-3.1-pro-preview":{"draws":10,"losses":9,"wins":11},"gemini-4-argon":{"draws":3,"losses":27,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":14,"wins":10},"google/gemini-3.5-flash-lite":{"draws":20,"losses":10,"wins":24},"google/gemini-3.6-flash":{"draws":18,"losses":32,"wins":8},"google/gemini-3.8-flash":{"draws":11,"losses":18,"wins":1},"google/gemma-4-31b-it":{"draws":8,"losses":4,"wins":6},"gpt-4.1":{"draws":4,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":10,"losses":9,"wins":5},"gpt-5.4":{"draws":14,"losses":11,"wins":3},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":7},"gpt-5.5":{"draws":11,"losses":10,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":23,"wins":0},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":5},"gpt-6-astra":{"draws":1,"losses":29,"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":8,"losses":2,"wins":4},"inception/mercury-3":{"draws":10,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":11},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":9},"meta/muse-spark-1.2":{"draws":10,"losses":11,"wins":7},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":4},"meta/muse-spark-open":{"draws":9,"losses":15,"wins":4},"meta/muse-wonder":{"draws":10,"losses":17,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":5},"minimax/minimax-m3.1-flash":{"draws":11,"losses":10,"wins":7},"mistralai/mistral-large-4-0":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":14,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":20,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":5,"wins":1},"o3":{"draws":7,"losses":17,"wins":10},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":8,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":18,"wins":1},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":11,"losses":14,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":15,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":14,"wins":3},"stealth/ox-alpha":{"draws":35,"losses":54,"wins":19},"stealth/space-bunny-alpha":{"draws":8,"losses":12,"wins":4},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":17,"losses":5,"wins":18},"thinkingmachines/inkling-small":{"draws":13,"losses":6,"wins":11},"unbiased/pareto-26.10":{"draws":1,"losses":9,"wins":0},"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":11,"losses":16,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":16,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":18,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":15,"wins":9},"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":6,"losses":13,"wins":1},"z-ai/glm-5.2":{"draws":28,"losses":23,"wins":9},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":3},"z-ai/glm-5.3-flash":{"draws":9,"losses":18,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":21,"wins":1}},"inception/mercury-3":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":14},"claude-fable-5":{"draws":10,"losses":37,"wins":1},"claude-fable-5-1":{"draws":2,"losses":52,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":24,"wins":9},"claude-opus-4-5":{"draws":25,"losses":34,"wins":19},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":8,"losses":67,"wins":7},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":21,"wins":12},"claude-sonnet-5-5":{"draws":11,"losses":27,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":21,"losses":30,"wins":21},"deepseek/deepseek-v4-pro":{"draws":12,"losses":24,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":29,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":36,"wins":4},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":15,"losses":19,"wins":14},"gemini-3.1-pro-preview":{"draws":17,"losses":17,"wins":14},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":11,"losses":33,"wins":16},"google/gemini-3.5-flash-lite":{"draws":23,"losses":24,"wins":37},"google/gemini-3.6-flash":{"draws":29,"losses":52,"wins":11},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":4,"losses":6,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":20,"wins":13},"gpt-5.4":{"draws":7,"losses":27,"wins":12},"gpt-5.4-mini":{"draws":11,"losses":8,"wins":13},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":13,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":14,"losses":19,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":39,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":24,"wins":8},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":12,"losses":28,"wins":8},"gpt-6-sol":{"draws":7,"losses":37,"wins":4},"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":14,"losses":8,"wins":12},"inception/mercury-3":{"draws":5,"losses":10,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":13,"wins":12},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":13,"losses":24,"wins":15},"meta/muse-glimmer-30b":{"draws":11,"losses":15,"wins":16},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":8},"meta/muse-spark-1.3":{"draws":8,"losses":33,"wins":7},"meta/muse-spark-open":{"draws":9,"losses":29,"wins":8},"meta/muse-wonder":{"draws":11,"losses":31,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":11},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":18},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":21,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":39,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":12,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":9,"wins":6},"o3":{"draws":11,"losses":26,"wins":29},"openai/gpt-oss-120b":{"draws":10,"losses":17,"wins":15},"poolside/laguna-s-2.1":{"draws":9,"losses":16,"wins":21},"qwen/qwen3.7-max":{"draws":6,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":19,"wins":12},"qwen/qwen3.8-27b":{"draws":9,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":15,"wins":7},"qwen/qwen3.8-max":{"draws":16,"losses":23,"wins":9},"qwen/qwen3.8-max-0902":{"draws":12,"losses":26,"wins":10},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":23,"wins":7},"stealth/ox-alpha":{"draws":40,"losses":80,"wins":38},"stealth/space-bunny-alpha":{"draws":7,"losses":18,"wins":13},"stepfun/step-3.7-flash":{"draws":9,"losses":9,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":12,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":22,"wins":21},"thinkingmachines/inkling-small":{"draws":14,"losses":11,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":16,"losses":23,"wins":9},"x-ai/grok-4.6":{"draws":12,"losses":27,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":35,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":19,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":16,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":30,"losses":38,"wins":28},"z-ai/glm-5.3":{"draws":11,"losses":29,"wins":6},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":30,"wins":8}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":30,"wins":10},"claude-fable-5":{"draws":13,"losses":50,"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":35,"losses":64,"wins":7},"claude-opus-4-8":{"draws":20,"losses":38,"wins":0},"claude-opus-5":{"draws":17,"losses":89,"wins":6},"claude-opus-5-5":{"draws":5,"losses":73,"wins":0},"claude-sonnet-5":{"draws":22,"losses":40,"wins":4},"claude-sonnet-5-5":{"draws":16,"losses":47,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":5},"deepseek/deepseek-v4-flash":{"draws":41,"losses":36,"wins":25},"deepseek/deepseek-v4-pro":{"draws":22,"losses":22,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":29,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":31,"losses":29,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":51,"wins":2},"elorian/glimpse":{"draws":9,"losses":23,"wins":6},"fireworks/ember-1":{"draws":29,"losses":36,"wins":1},"gemini-3.1-pro-preview":{"draws":23,"losses":30,"wins":13},"gemini-4-argon":{"draws":6,"losses":58,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":14,"wins":9},"google/gemini-3.5-flash":{"draws":25,"losses":48,"wins":9},"google/gemini-3.5-flash-lite":{"draws":39,"losses":48,"wins":27},"google/gemini-3.6-flash":{"draws":38,"losses":72,"wins":14},"google/gemini-3.8-flash":{"draws":17,"losses":48,"wins":1},"google/gemma-4-31b-it":{"draws":23,"losses":8,"wins":5},"gpt-4.1":{"draws":9,"losses":13,"wins":0},"gpt-4.1-nano":{"draws":4,"losses":5,"wins":1},"gpt-5":{"draws":19,"losses":23,"wins":16},"gpt-5.4":{"draws":16,"losses":37,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":18,"wins":10},"gpt-5.4-nano":{"draws":16,"losses":36,"wins":16},"gpt-5.5":{"draws":28,"losses":27,"wins":5},"gpt-5.6-luna":{"draws":37,"losses":22,"wins":7},"gpt-5.6-sol":{"draws":8,"losses":56,"wins":2},"gpt-5.6-terra":{"draws":22,"losses":41,"wins":3},"gpt-6-astra":{"draws":3,"losses":62,"wins":1},"gpt-6-luna":{"draws":24,"losses":33,"wins":9},"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":23,"losses":13,"wins":8},"inception/mercury-3":{"draws":10,"losses":29,"wins":11},"inclusionai/ling-3.0-flash":{"draws":14,"losses":10,"wins":12},"inclusionai/ling-3.1-flash":{"draws":6,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":33,"losses":25,"wins":12},"meta/muse-glimmer-30b":{"draws":32,"losses":12,"wins":12},"meta/muse-spark-1.2":{"draws":16,"losses":42,"wins":4},"meta/muse-spark-1.3":{"draws":15,"losses":47,"wins":4},"meta/muse-spark-open":{"draws":11,"losses":48,"wins":5},"meta/muse-wonder":{"draws":9,"losses":52,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":17,"wins":8},"minimax/minimax-m3.1-flash":{"draws":13,"losses":27,"wins":12},"mistralai/mistral-large-4-0":{"draws":21,"losses":14,"wins":5},"mistralai/mistral-medium-3-5":{"draws":12,"losses":14,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":19,"losses":36,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":9,"losses":53,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":14,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":22,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":15,"wins":5},"o3":{"draws":21,"losses":55,"wins":12},"openai/gpt-oss-120b":{"draws":29,"losses":25,"wins":2},"poolside/laguna-s-2.1":{"draws":22,"losses":21,"wins":25},"qwen/qwen3.7-max":{"draws":14,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":43,"wins":1},"qwen/qwen3.8-27b":{"draws":10,"losses":27,"wins":9},"qwen/qwen3.8-flash":{"draws":14,"losses":25,"wins":5},"qwen/qwen3.8-max":{"draws":24,"losses":36,"wins":6},"qwen/qwen3.8-max-0902":{"draws":27,"losses":36,"wins":3},"recursive/flint-v1.0":{"draws":4,"losses":10,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":36,"wins":4},"stealth/ox-alpha":{"draws":62,"losses":147,"wins":17},"stealth/space-bunny-alpha":{"draws":20,"losses":18,"wins":8},"stepfun/step-3.7-flash":{"draws":21,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":6,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":14,"losses":18,"wins":4},"tencent/hy4-preview":{"draws":24,"losses":32,"wins":8},"thinkingmachines/inkling":{"draws":27,"losses":36,"wins":21},"thinkingmachines/inkling-small":{"draws":29,"losses":18,"wins":19},"unbiased/pareto-26.10":{"draws":1,"losses":21,"wins":0},"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":15,"losses":48,"wins":3},"x-ai/grok-4.6":{"draws":22,"losses":41,"wins":3},"x-ai/grok-4.7":{"draws":5,"losses":48,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":12,"wins":2},"xiaomi/mimo-v2.5":{"draws":42,"losses":34,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":14,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":24,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":34,"wins":3},"z-ai/glm-5.2":{"draws":63,"losses":43,"wins":26},"z-ai/glm-5.3":{"draws":16,"losses":43,"wins":3},"z-ai/glm-5.3-flash":{"draws":19,"losses":35,"wins":12},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":4,"losses":2,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":6,"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},"inception/mercury-3":{"draws":0,"losses":6,"wins":0},"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-spark-open":{"draws":0,"losses":6,"wins":0},"meta/muse-wonder":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":2,"wins":2},"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},"recursive/flint-v1.0":{"draws":0,"losses":1,"wins":1},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"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":{"draws":0,"losses":2,"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":18,"losses":37,"wins":23},"claude-fable-5":{"draws":8,"losses":67,"wins":9},"claude-fable-5-1":{"draws":1,"losses":90,"wins":3},"claude-haiku-5-5":{"draws":18,"losses":52,"wins":10},"claude-opus-4-5":{"draws":33,"losses":85,"wins":18},"claude-opus-4-8":{"draws":14,"losses":51,"wins":11},"claude-opus-5":{"draws":13,"losses":118,"wins":9},"claude-opus-5-5":{"draws":5,"losses":85,"wins":2},"claude-sonnet-5":{"draws":23,"losses":43,"wins":18},"claude-sonnet-5-5":{"draws":11,"losses":59,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":8,"wins":20},"deepseek/deepseek-v4-flash":{"draws":28,"losses":56,"wins":44},"deepseek/deepseek-v4-pro":{"draws":14,"losses":46,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":37,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":47,"wins":23},"deepseek/deepseek-v4.1-flash-1017":{"draws":15,"losses":60,"wins":9},"elorian/glimpse":{"draws":6,"losses":30,"wins":10},"fireworks/ember-1":{"draws":23,"losses":49,"wins":12},"gemini-3.1-pro-preview":{"draws":22,"losses":40,"wins":22},"gemini-4-argon":{"draws":3,"losses":77,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":15,"wins":33},"google/gemini-3.5-flash":{"draws":18,"losses":65,"wins":23},"google/gemini-3.5-flash-lite":{"draws":40,"losses":70,"wins":38},"google/gemini-3.6-flash":{"draws":32,"losses":108,"wins":22},"google/gemini-3.8-flash":{"draws":11,"losses":66,"wins":7},"google/gemma-4-31b-it":{"draws":20,"losses":11,"wins":17},"gpt-4.1":{"draws":6,"losses":17,"wins":5},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":3},"gpt-5":{"draws":13,"losses":42,"wins":21},"gpt-5.4":{"draws":19,"losses":53,"wins":10},"gpt-5.4-mini":{"draws":20,"losses":22,"wins":14},"gpt-5.4-nano":{"draws":13,"losses":46,"wins":29},"gpt-5.5":{"draws":29,"losses":36,"wins":13},"gpt-5.6-luna":{"draws":20,"losses":38,"wins":26},"gpt-5.6-sol":{"draws":9,"losses":69,"wins":6},"gpt-5.6-terra":{"draws":21,"losses":41,"wins":18},"gpt-6-astra":{"draws":5,"losses":79,"wins":0},"gpt-6-luna":{"draws":22,"losses":45,"wins":17},"gpt-6-sol":{"draws":7,"losses":69,"wins":8},"gpt-6.1-sol":{"draws":1,"losses":77,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":19,"wins":18},"inception/mercury-3":{"draws":15,"losses":28,"wins":13},"inclusionai/ling-3.0-flash":{"draws":23,"losses":17,"wins":20},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":29,"wins":20},"meta/muse-glimmer-30b":{"draws":26,"losses":27,"wins":21},"meta/muse-spark-1.2":{"draws":14,"losses":55,"wins":11},"meta/muse-spark-1.3":{"draws":15,"losses":57,"wins":12},"meta/muse-spark-open":{"draws":16,"losses":57,"wins":9},"meta/muse-wonder":{"draws":20,"losses":54,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":19,"wins":20},"minimax/minimax-m3.1-flash":{"draws":13,"losses":36,"wins":25},"mistralai/mistral-large-4-0":{"draws":18,"losses":27,"wins":7},"mistralai/mistral-medium-3-5":{"draws":14,"losses":16,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":43,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":70,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":16,"wins":22},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":26,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":23,"wins":5},"o3":{"draws":19,"losses":78,"wins":29},"openai/gpt-oss-120b":{"draws":22,"losses":26,"wins":26},"poolside/laguna-s-2.1":{"draws":28,"losses":36,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":26,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":19,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":51,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":37,"wins":10},"qwen/qwen3.8-flash":{"draws":16,"losses":27,"wins":13},"qwen/qwen3.8-max":{"draws":22,"losses":43,"wins":19},"qwen/qwen3.8-max-0902":{"draws":14,"losses":54,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":9,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":49,"wins":13},"stealth/ox-alpha":{"draws":53,"losses":184,"wins":45},"stealth/space-bunny-alpha":{"draws":17,"losses":39,"wins":10},"stepfun/step-3.7-flash":{"draws":10,"losses":22,"wins":32},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":22,"wins":13},"tencent/hy4-preview":{"draws":19,"losses":51,"wins":12},"thinkingmachines/inkling":{"draws":28,"losses":44,"wins":42},"thinkingmachines/inkling-small":{"draws":26,"losses":28,"wins":30},"unbiased/pareto-26.10":{"draws":0,"losses":28,"wins":0},"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":15,"losses":54,"wins":15},"x-ai/grok-4.6":{"draws":22,"losses":52,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":64,"wins":5},"x-ai/grok-build-0.1":{"draws":6,"losses":11,"wins":11},"xiaomi/mimo-v2.5":{"draws":30,"losses":49,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":29,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":34,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":37,"wins":5},"z-ai/glm-5.2":{"draws":46,"losses":82,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":65,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":52,"wins":19},"z-ai/glm-5.3-flashx":{"draws":11,"losses":63,"wins":10}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":7},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":1,"losses":41,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":24,"wins":3},"claude-opus-4-5":{"draws":15,"losses":38,"wins":5},"claude-opus-4-8":{"draws":5,"losses":23,"wins":4},"claude-opus-5":{"draws":2,"losses":58,"wins":8},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":7,"losses":25,"wins":4},"claude-sonnet-5-5":{"draws":4,"losses":28,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":3},"deepseek/deepseek-v4-flash":{"draws":12,"losses":26,"wins":14},"deepseek/deepseek-v4-pro":{"draws":9,"losses":17,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":20,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":23,"wins":3},"elorian/glimpse":{"draws":7,"losses":11,"wins":4},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":20,"wins":3},"gemini-4-argon":{"draws":3,"losses":31,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":8,"losses":31,"wins":7},"google/gemini-3.5-flash-lite":{"draws":14,"losses":31,"wins":19},"google/gemini-3.6-flash":{"draws":16,"losses":44,"wins":10},"google/gemini-3.8-flash":{"draws":8,"losses":23,"wins":5},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":7},"gpt-4.1":{"draws":3,"losses":8,"wins":1},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":6,"losses":19,"wins":9},"gpt-5.4":{"draws":8,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":12,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":21,"wins":12},"gpt-5.5":{"draws":11,"losses":20,"wins":5},"gpt-5.6-luna":{"draws":9,"losses":16,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":31,"wins":1},"gpt-5.6-terra":{"draws":8,"losses":22,"wins":4},"gpt-6-astra":{"draws":1,"losses":35,"wins":0},"gpt-6-luna":{"draws":10,"losses":19,"wins":7},"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":7,"losses":8,"wins":7},"inception/mercury-3":{"draws":6,"losses":12,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":6,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":8,"losses":21,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":3},"meta/muse-spark-1.2":{"draws":7,"losses":26,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":27,"wins":3},"meta/muse-spark-open":{"draws":8,"losses":25,"wins":3},"meta/muse-wonder":{"draws":6,"losses":26,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":12,"wins":6},"minimax/minimax-m3.1-flash":{"draws":9,"losses":16,"wins":7},"mistralai/mistral-large-4-0":{"draws":8,"losses":10,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":23,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":27,"wins":2},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":12,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":4},"o3":{"draws":6,"losses":32,"wins":14},"openai/gpt-oss-120b":{"draws":6,"losses":15,"wins":11},"poolside/laguna-s-2.1":{"draws":6,"losses":19,"wins":11},"qwen/qwen3.7-max":{"draws":4,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":20,"wins":4},"qwen/qwen3.8-27b":{"draws":4,"losses":15,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.8-max":{"draws":7,"losses":24,"wins":5},"qwen/qwen3.8-max-0902":{"draws":9,"losses":23,"wins":4},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":17,"wins":8},"stealth/ox-alpha":{"draws":21,"losses":88,"wins":17},"stealth/space-bunny-alpha":{"draws":11,"losses":14,"wins":5},"stepfun/step-3.7-flash":{"draws":5,"losses":8,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":14,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":19,"wins":19},"thinkingmachines/inkling-small":{"draws":11,"losses":10,"wins":15},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":8,"losses":24,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":25,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":4},"xiaomi/mimo-v2.5":{"draws":17,"losses":22,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":15,"wins":4},"z-ai/glm-5.2":{"draws":22,"losses":32,"wins":18},"z-ai/glm-5.3":{"draws":3,"losses":29,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":28,"wins":4},"z-ai/glm-5.3-flashx":{"draws":5,"losses":25,"wins":6}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":13,"wins":14},"claude-fable-5":{"draws":5,"losses":37,"wins":6},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":29,"wins":6},"claude-opus-4-5":{"draws":22,"losses":31,"wins":25},"claude-opus-4-8":{"draws":12,"losses":26,"wins":6},"claude-opus-5":{"draws":9,"losses":62,"wins":11},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":15,"losses":19,"wins":14},"claude-sonnet-5-5":{"draws":7,"losses":31,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":12},"deepseek/deepseek-v4-flash":{"draws":21,"losses":20,"wins":31},"deepseek/deepseek-v4-pro":{"draws":9,"losses":21,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":21,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":25,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":6,"losses":9,"wins":11},"fireworks/ember-1":{"draws":14,"losses":25,"wins":9},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":14},"gemini-4-argon":{"draws":3,"losses":41,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":18},"google/gemini-3.5-flash":{"draws":15,"losses":28,"wins":17},"google/gemini-3.5-flash-lite":{"draws":27,"losses":22,"wins":35},"google/gemini-3.6-flash":{"draws":24,"losses":51,"wins":17},"google/gemini-3.8-flash":{"draws":11,"losses":26,"wins":11},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":9,"losses":18,"wins":15},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":10,"losses":23,"wins":11},"gpt-5.6-luna":{"draws":11,"losses":18,"wins":19},"gpt-5.6-sol":{"draws":6,"losses":38,"wins":4},"gpt-5.6-terra":{"draws":13,"losses":18,"wins":15},"gpt-6-astra":{"draws":1,"losses":46,"wins":1},"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":12,"losses":3,"wins":19},"inception/mercury-3":{"draws":10,"losses":15,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":4,"wins":18},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":18,"wins":22},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":17},"meta/muse-spark-1.2":{"draws":7,"losses":17,"wins":6},"meta/muse-spark-1.3":{"draws":12,"losses":26,"wins":10},"meta/muse-spark-open":{"draws":11,"losses":28,"wins":7},"meta/muse-wonder":{"draws":9,"losses":32,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":13},"minimax/minimax-m3.1-flash":{"draws":10,"losses":19,"wins":13},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":21,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":7},"o3":{"draws":8,"losses":34,"wins":24},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":27},"qwen/qwen3.7-max":{"draws":4,"losses":10,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":25,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":20,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":11,"losses":25,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":20,"wins":12},"stealth/ox-alpha":{"draws":38,"losses":85,"wins":35},"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":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":9,"losses":26,"wins":11},"thinkingmachines/inkling":{"draws":23,"losses":15,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":14,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":11,"losses":30,"wins":7},"x-ai/grok-4.6":{"draws":10,"losses":36,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":28,"losses":16,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"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":30,"losses":32,"wins":34},"z-ai/glm-5.3":{"draws":9,"losses":28,"wins":9},"z-ai/glm-5.3-flash":{"draws":8,"losses":28,"wins":12},"z-ai/glm-5.3-flashx":{"draws":9,"losses":24,"wins":15}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":10,"wins":19},"claude-fable-5":{"draws":9,"losses":36,"wins":3},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":29,"wins":4},"claude-opus-4-5":{"draws":27,"losses":31,"wins":20},"claude-opus-4-8":{"draws":11,"losses":27,"wins":6},"claude-opus-5":{"draws":13,"losses":63,"wins":6},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":18,"wins":13},"claude-sonnet-5-5":{"draws":10,"losses":31,"wins":7},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":13},"deepseek/deepseek-v4-flash":{"draws":19,"losses":21,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":26,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":32,"wins":11},"elorian/glimpse":{"draws":6,"losses":13,"wins":7},"fireworks/ember-1":{"draws":14,"losses":23,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":2,"losses":45,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":1,"wins":24},"google/gemini-3.5-flash":{"draws":15,"losses":28,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":24,"wins":40},"google/gemini-3.6-flash":{"draws":20,"losses":50,"wins":22},"google/gemini-3.8-flash":{"draws":12,"losses":31,"wins":5},"google/gemma-4-31b-it":{"draws":11,"losses":4,"wins":13},"gpt-4.1":{"draws":7,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":21,"wins":12},"gpt-5.4":{"draws":10,"losses":26,"wins":10},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":14,"losses":14,"wins":20},"gpt-5.5":{"draws":17,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":17,"losses":17,"wins":14},"gpt-5.6-sol":{"draws":6,"losses":41,"wins":1},"gpt-5.6-terra":{"draws":13,"losses":22,"wins":11},"gpt-6-astra":{"draws":3,"losses":44,"wins":1},"gpt-6-luna":{"draws":14,"losses":20,"wins":14},"gpt-6-sol":{"draws":7,"losses":39,"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":3,"wins":16},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":12,"losses":5,"wins":17},"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":9,"wins":13},"meta/muse-spark-1.2":{"draws":14,"losses":25,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":25,"wins":2},"meta/muse-spark-open":{"draws":10,"losses":31,"wins":5},"meta/muse-wonder":{"draws":10,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":19},"minimax/minimax-m3.1-flash":{"draws":6,"losses":15,"wins":21},"mistralai/mistral-large-4-0":{"draws":12,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":9,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":24,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":41,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":6,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":11,"wins":5},"o3":{"draws":12,"losses":33,"wins":21},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":15,"losses":17,"wins":14},"qwen/qwen3.7-max":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":9},"qwen/qwen3.8-max":{"draws":19,"losses":15,"wins":14},"qwen/qwen3.8-max-0902":{"draws":16,"losses":25,"wins":7},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":21,"wins":12},"stealth/ox-alpha":{"draws":38,"losses":87,"wins":33},"stealth/space-bunny-alpha":{"draws":5,"losses":14,"wins":19},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":21},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":8},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":19,"losses":9,"wins":20},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":10,"losses":33,"wins":5},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":30,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":27,"losses":18,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":18,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":23,"wins":6},"z-ai/glm-5.2":{"draws":28,"losses":39,"wins":29},"z-ai/glm-5.3":{"draws":7,"losses":37,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":34,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":30,"wins":11}},"meta/muse-spark-open":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":28},"claude-fable-5":{"draws":8,"losses":34,"wins":6},"claude-fable-5-1":{"draws":1,"losses":49,"wins":4},"claude-haiku-5-5":{"draws":8,"losses":19,"wins":19},"claude-opus-4-5":{"draws":23,"losses":22,"wins":33},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":12,"losses":51,"wins":19},"claude-opus-5-5":{"draws":4,"losses":44,"wins":4},"claude-sonnet-5":{"draws":11,"losses":13,"wins":24},"claude-sonnet-5-5":{"draws":9,"losses":22,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":16,"losses":13,"wins":43},"deepseek/deepseek-v4-pro":{"draws":10,"losses":10,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":11,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":22,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":30,"wins":7},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":12,"losses":14,"wins":22},"gemini-3.1-pro-preview":{"draws":13,"losses":14,"wins":21},"gemini-4-argon":{"draws":2,"losses":39,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":23},"google/gemini-3.5-flash":{"draws":10,"losses":24,"wins":26},"google/gemini-3.5-flash-lite":{"draws":17,"losses":15,"wins":52},"google/gemini-3.6-flash":{"draws":20,"losses":42,"wins":30},"google/gemini-3.8-flash":{"draws":8,"losses":25,"wins":15},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":21},"gpt-4.1":{"draws":3,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":9,"wins":22},"gpt-5.4":{"draws":8,"losses":21,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":29},"gpt-5.5":{"draws":11,"losses":17,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":10,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":13},"gpt-5.6-terra":{"draws":15,"losses":14,"wins":17},"gpt-6-astra":{"draws":2,"losses":45,"wins":1},"gpt-6-luna":{"draws":9,"losses":16,"wins":23},"gpt-6-sol":{"draws":4,"losses":36,"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":12,"losses":2,"wins":20},"inception/mercury-3":{"draws":9,"losses":7,"wins":16},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":24},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":7,"wins":37},"meta/muse-glimmer-30b":{"draws":10,"losses":5,"wins":27},"meta/muse-spark-1.2":{"draws":10,"losses":16,"wins":20},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":13},"meta/muse-spark-open":{"draws":6,"losses":10,"wins":14},"meta/muse-wonder":{"draws":8,"losses":25,"wins":15},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":21},"mistralai/mistral-large-4-0":{"draws":6,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":8},"moonshotai/kimi-k3":{"draws":12,"losses":14,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":40,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":2,"wins":15},"o3":{"draws":8,"losses":16,"wins":42},"openai/gpt-oss-120b":{"draws":11,"losses":2,"wins":29},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":28},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":15,"wins":17},"qwen/qwen3.8-27b":{"draws":7,"losses":10,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-max-0902":{"draws":13,"losses":22,"wins":13},"recursive/flint-v1.0":{"draws":1,"losses":0,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":13,"wins":23},"stealth/ox-alpha":{"draws":28,"losses":60,"wins":70},"stealth/space-bunny-alpha":{"draws":10,"losses":7,"wins":21},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":26},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":17,"wins":21},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":41},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":32},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":2},"unbiased/pareto-26.10-preview":{"draws":0,"losses":15,"wins":1},"upstage/solar-mini4":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":11,"losses":18,"wins":19},"x-ai/grok-4.6":{"draws":13,"losses":22,"wins":13},"x-ai/grok-4.7":{"draws":3,"losses":32,"wins":7},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":19,"losses":6,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":12,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":16,"wins":12},"z-ai/glm-5.2":{"draws":27,"losses":23,"wins":46},"z-ai/glm-5.3":{"draws":7,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":23},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":17}},"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":15,"losses":12,"wins":19},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":21,"wins":14},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":18,"losses":10,"wins":20},"gemini-3.1-pro-preview":{"draws":11,"losses":11,"wins":26},"gemini-4-argon":{"draws":4,"losses":38,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":26},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":35},"google/gemini-3.5-flash-lite":{"draws":20,"losses":12,"wins":52},"google/gemini-3.6-flash":{"draws":28,"losses":30,"wins":34},"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},"inception/mercury-3":{"draws":11,"losses":11,"wins":10},"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":15,"losses":16,"wins":15},"meta/muse-spark-1.3":{"draws":13,"losses":21,"wins":14},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":16},"meta/muse-wonder":{"draws":7,"losses":19,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":6,"wins":14},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":21},"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},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":32,"wins":10},"nex-agi/nex-n2-pro":{"draws":4,"losses":4,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":1,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":3,"wins":11},"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},"recursive/flint-v1.0":{"draws":3,"losses":0,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":11,"wins":24},"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":{"draws":0,"losses":13,"wins":3},"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":26,"losses":25,"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":20,"wins":8},"claude-fable-5":{"draws":9,"losses":22,"wins":5},"claude-fable-5-1":{"draws":0,"losses":39,"wins":1},"claude-haiku-5-5":{"draws":2,"losses":22,"wins":10},"claude-opus-4-5":{"draws":18,"losses":31,"wins":9},"claude-opus-4-8":{"draws":4,"losses":20,"wins":8},"claude-opus-5":{"draws":8,"losses":57,"wins":3},"claude-opus-5-5":{"draws":2,"losses":37,"wins":1},"claude-sonnet-5":{"draws":8,"losses":17,"wins":11},"claude-sonnet-5-5":{"draws":6,"losses":19,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":11,"losses":17,"wins":28},"deepseek/deepseek-v4-pro":{"draws":4,"losses":20,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":14,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash-1017":{"draws":3,"losses":30,"wins":3},"elorian/glimpse":{"draws":3,"losses":11,"wins":6},"fireworks/ember-1":{"draws":7,"losses":25,"wins":4},"gemini-3.1-pro-preview":{"draws":6,"losses":15,"wins":15},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":17},"google/gemini-3.5-flash":{"draws":6,"losses":22,"wins":16},"google/gemini-3.5-flash-lite":{"draws":15,"losses":16,"wins":29},"google/gemini-3.6-flash":{"draws":10,"losses":41,"wins":17},"google/gemini-3.8-flash":{"draws":4,"losses":28,"wins":4},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":9},"gpt-4.1":{"draws":2,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":7,"losses":17,"wins":10},"gpt-5.4":{"draws":4,"losses":18,"wins":12},"gpt-5.4-mini":{"draws":8,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":19},"gpt-5.5":{"draws":8,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":14,"wins":11},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":18,"wins":10},"gpt-6-astra":{"draws":0,"losses":35,"wins":1},"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":11},"inception/mercury-3":{"draws":9,"losses":8,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":15},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":13,"wins":17},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":19},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":29,"wins":5},"meta/muse-spark-open":{"draws":6,"losses":25,"wins":3},"meta/muse-wonder":{"draws":5,"losses":23,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":6},"minimax/minimax-m3.1-flash":{"draws":4,"losses":13,"wins":13},"mistralai/mistral-large-4-0":{"draws":4,"losses":12,"wins":8},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":24,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":33,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":4,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":9},"o3":{"draws":6,"losses":28,"wins":16},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":15},"poolside/laguna-s-2.1":{"draws":11,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":6,"losses":10,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":23,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":3,"losses":10,"wins":11},"qwen/qwen3.8-max":{"draws":8,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":25,"wins":4},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":21,"wins":7},"stealth/ox-alpha":{"draws":29,"losses":67,"wins":28},"stealth/space-bunny-alpha":{"draws":5,"losses":12,"wins":11},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":6,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":12,"losses":13,"wins":25},"thinkingmachines/inkling-small":{"draws":8,"losses":7,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":11,"wins":1},"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":5,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":29,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":29,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":18,"losses":11,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":10},"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":17,"losses":25,"wins":30},"z-ai/glm-5.3":{"draws":4,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":9},"z-ai/glm-5.3-flashx":{"draws":6,"losses":20,"wins":10}},"minimax/minimax-m3.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":18,"wins":9},"claude-fable-5":{"draws":11,"losses":29,"wins":2},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":11,"losses":22,"wins":7},"claude-opus-4-5":{"draws":22,"losses":32,"wins":14},"claude-opus-4-8":{"draws":9,"losses":25,"wins":4},"claude-opus-5":{"draws":10,"losses":55,"wins":5},"claude-opus-5-5":{"draws":3,"losses":39,"wins":0},"claude-sonnet-5":{"draws":14,"losses":21,"wins":7},"claude-sonnet-5-5":{"draws":13,"losses":25,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":18,"losses":19,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":22,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":26,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":27,"wins":7},"elorian/glimpse":{"draws":8,"losses":10,"wins":4},"fireworks/ember-1":{"draws":12,"losses":21,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":17,"wins":11},"gemini-4-argon":{"draws":5,"losses":36,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":18},"google/gemini-3.5-flash":{"draws":16,"losses":28,"wins":8},"google/gemini-3.5-flash-lite":{"draws":22,"losses":21,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":50,"wins":8},"google/gemini-3.8-flash":{"draws":10,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":11,"losses":21,"wins":4},"gpt-5.4":{"draws":12,"losses":25,"wins":3},"gpt-5.4-mini":{"draws":14,"losses":7,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":15,"wins":18},"gpt-5.5":{"draws":12,"losses":21,"wins":5},"gpt-5.6-luna":{"draws":16,"losses":16,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":4},"gpt-5.6-terra":{"draws":14,"losses":18,"wins":8},"gpt-6-astra":{"draws":5,"losses":37,"wins":0},"gpt-6-luna":{"draws":8,"losses":25,"wins":9},"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":12,"losses":4,"wins":14},"inception/mercury-3":{"draws":7,"losses":14,"wins":5},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":9},"meituan/longcat-2.0":{"draws":11,"losses":18,"wins":15},"meta/muse-glimmer-30b":{"draws":12,"losses":14,"wins":10},"meta/muse-spark-1.2":{"draws":10,"losses":25,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":31,"wins":5},"meta/muse-spark-open":{"draws":12,"losses":23,"wins":5},"meta/muse-wonder":{"draws":9,"losses":27,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":5,"losses":12,"wins":9},"mistralai/mistral-large-4-0":{"draws":8,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":17,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":34,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":7,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":3},"o3":{"draws":7,"losses":32,"wins":17},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":11},"poolside/laguna-s-2.1":{"draws":13,"losses":14,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":11,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":24,"wins":4},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":8},"qwen/qwen3.8-max-0902":{"draws":12,"losses":22,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":4,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":10},"stealth/ox-alpha":{"draws":39,"losses":77,"wins":26},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":7},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":12},"tencent/hy3-preview":{"draws":8,"losses":11,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":12},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":19},"thinkingmachines/inkling-small":{"draws":12,"losses":14,"wins":16},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":19,"wins":8},"x-ai/grok-4.6":{"draws":16,"losses":22,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":28,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":22,"losses":18,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":25,"losses":42,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":30,"wins":5},"z-ai/glm-5.3-flash":{"draws":7,"losses":25,"wins":10},"z-ai/glm-5.3-flashx":{"draws":9,"losses":27,"wins":6}},"mistralai/mistral-large-4-0":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":10},"claude-fable-5":{"draws":9,"losses":25,"wins":8},"claude-fable-5-1":{"draws":3,"losses":43,"wins":2},"claude-haiku-5-5":{"draws":15,"losses":18,"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":12,"losses":61,"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":29,"wins":4},"elorian/glimpse":{"draws":5,"losses":11,"wins":8},"fireworks/ember-1":{"draws":16,"losses":17,"wins":9},"gemini-3.1-pro-preview":{"draws":14,"losses":19,"wins":9},"gemini-4-argon":{"draws":1,"losses":40,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":2,"wins":15},"google/gemini-3.5-flash":{"draws":18,"losses":21,"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":5,"wins":6},"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},"inception/mercury-3":{"draws":11,"losses":11,"wins":6},"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":12,"losses":23,"wins":7},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":5},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":10},"meta/muse-wonder":{"draws":7,"losses":26,"wins":9},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":6},"minimax/minimax-m3.1-flash":{"draws":10,"losses":14,"wins":12},"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},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":4,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":9,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":8,"wins":5},"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},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":20,"wins":6},"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":{"draws":1,"losses":13,"wins":0},"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":15,"losses":17,"wins":8},"claude-fable-5":{"draws":5,"losses":35,"wins":2},"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":22,"losses":45,"wins":1},"claude-opus-4-8":{"draws":11,"losses":23,"wins":4},"claude-opus-5":{"draws":10,"losses":58,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":13,"losses":27,"wins":2},"claude-sonnet-5-5":{"draws":6,"losses":33,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":26,"losses":26,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":24,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":25,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":24,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":33,"wins":3},"elorian/glimpse":{"draws":4,"losses":16,"wins":2},"fireworks/ember-1":{"draws":12,"losses":27,"wins":3},"gemini-3.1-pro-preview":{"draws":14,"losses":25,"wins":3},"gemini-4-argon":{"draws":2,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":7,"wins":10},"google/gemini-3.5-flash":{"draws":12,"losses":35,"wins":5},"google/gemini-3.5-flash-lite":{"draws":17,"losses":37,"wins":20},"google/gemini-3.6-flash":{"draws":23,"losses":48,"wins":9},"google/gemini-3.8-flash":{"draws":6,"losses":34,"wins":2},"google/gemma-4-31b-it":{"draws":11,"losses":11,"wins":2},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":2},"gpt-5":{"draws":9,"losses":20,"wins":7},"gpt-5.4":{"draws":8,"losses":23,"wins":9},"gpt-5.4-mini":{"draws":12,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":28,"wins":6},"gpt-5.5":{"draws":11,"losses":22,"wins":5},"gpt-5.6-luna":{"draws":15,"losses":19,"wins":8},"gpt-5.6-sol":{"draws":4,"losses":35,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":27,"wins":3},"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":15,"losses":10,"wins":5},"inception/mercury-3":{"draws":8,"losses":18,"wins":2},"inclusionai/ling-3.0-flash":{"draws":11,"losses":11,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":19,"wins":11},"meta/muse-glimmer-30b":{"draws":15,"losses":15,"wins":6},"meta/muse-spark-1.2":{"draws":9,"losses":27,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":34,"wins":1},"meta/muse-spark-open":{"draws":7,"losses":31,"wins":2},"meta/muse-wonder":{"draws":8,"losses":31,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":10,"wins":6},"minimax/minimax-m3.1-flash":{"draws":8,"losses":22,"wins":6},"mistralai/mistral-large-4-0":{"draws":11,"losses":11,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":8,"losses":30,"wins":2},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":39,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":9},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":18,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":9,"wins":3},"o3":{"draws":9,"losses":39,"wins":6},"openai/gpt-oss-120b":{"draws":15,"losses":18,"wins":3},"poolside/laguna-s-2.1":{"draws":11,"losses":21,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":12,"wins":2},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":32,"wins":1},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":1},"qwen/qwen3.8-flash":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":9,"losses":29,"wins":4},"qwen/qwen3.8-max-0902":{"draws":13,"losses":27,"wins":2},"recursive/flint-v1.0":{"draws":4,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":27,"wins":3},"stealth/ox-alpha":{"draws":31,"losses":93,"wins":16},"stealth/space-bunny-alpha":{"draws":10,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":12,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":9,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":28,"wins":5},"thinkingmachines/inkling":{"draws":19,"losses":27,"wins":10},"thinkingmachines/inkling-small":{"draws":16,"losses":14,"wins":12},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":9,"losses":30,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":4},"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":26,"losses":27,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":14,"wins":3},"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":29,"losses":44,"wins":11},"z-ai/glm-5.3":{"draws":6,"losses":33,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":24,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":33,"wins":4}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":8,"wins":22},"claude-fable-5":{"draws":5,"losses":30,"wins":13},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":19,"wins":15},"claude-opus-4-5":{"draws":28,"losses":18,"wins":32},"claude-opus-4-8":{"draws":12,"losses":15,"wins":17},"claude-opus-5":{"draws":11,"losses":55,"wins":16},"claude-opus-5-5":{"draws":1,"losses":48,"wins":3},"claude-sonnet-5":{"draws":14,"losses":12,"wins":22},"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":22,"losses":13,"wins":37},"deepseek/deepseek-v4-pro":{"draws":8,"losses":16,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":20,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":29,"wins":15},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":13,"losses":23,"wins":12},"gemini-3.1-pro-preview":{"draws":9,"losses":16,"wins":23},"gemini-4-argon":{"draws":0,"losses":42,"wins":6},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":16,"losses":23,"wins":21},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"wins":41},"google/gemini-3.6-flash":{"draws":28,"losses":33,"wins":31},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":12},"google/gemma-4-31b-it":{"draws":8,"losses":5,"wins":15},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":14,"losses":12,"wins":16},"gpt-5.4":{"draws":5,"losses":26,"wins":15},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":28},"gpt-5.5":{"draws":10,"losses":16,"wins":18},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":11,"losses":27,"wins":10},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":18},"gpt-6-astra":{"draws":4,"losses":40,"wins":4},"gpt-6-luna":{"draws":15,"losses":18,"wins":15},"gpt-6-sol":{"draws":4,"losses":32,"wins":12},"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":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":28},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":20,"wins":16},"meta/muse-spark-1.3":{"draws":8,"losses":24,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":22,"wins":12},"meta/muse-wonder":{"draws":8,"losses":29,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":20},"minimax/minimax-m3.1-flash":{"draws":11,"losses":13,"wins":18},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":38,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":3,"wins":11},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":22},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.7-plus":{"draws":11,"losses":5,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":17,"wins":19},"qwen/qwen3.8-27b":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":12,"losses":18,"wins":18},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":12},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":12,"wins":20},"stealth/ox-alpha":{"draws":40,"losses":66,"wins":52},"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":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":16},"thinkingmachines/inkling":{"draws":21,"losses":14,"wins":29},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":12,"losses":21,"wins":15},"x-ai/grok-4.6":{"draws":7,"losses":27,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":31,"wins":10},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":26,"losses":11,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"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":37,"losses":19,"wins":40},"z-ai/glm-5.3":{"draws":11,"losses":23,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":13,"losses":23,"wins":12}},"moonshotai/kimi-k3.1-pro":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":1,"wins":37},"claude-fable-5":{"draws":4,"losses":12,"wins":32},"claude-fable-5-1":{"draws":6,"losses":38,"wins":10},"claude-haiku-5-5":{"draws":6,"losses":9,"wins":31},"claude-opus-4-5":{"draws":7,"losses":6,"wins":65},"claude-opus-4-8":{"draws":6,"losses":4,"wins":34},"claude-opus-5":{"draws":8,"losses":30,"wins":44},"claude-opus-5-5":{"draws":3,"losses":30,"wins":19},"claude-sonnet-5":{"draws":5,"losses":4,"wins":39},"claude-sonnet-5-5":{"draws":4,"losses":11,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":6,"losses":3,"wins":63},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":35},"deepseek/deepseek-v4.1-flash-1017":{"draws":2,"losses":11,"wins":35},"elorian/glimpse":{"draws":4,"losses":4,"wins":18},"fireworks/ember-1":{"draws":5,"losses":3,"wins":40},"gemini-3.1-pro-preview":{"draws":5,"losses":9,"wins":34},"gemini-4-argon":{"draws":3,"losses":24,"wins":21},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":29},"google/gemini-3.5-flash":{"draws":2,"losses":8,"wins":50},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":67},"google/gemini-3.6-flash":{"draws":11,"losses":11,"wins":70},"google/gemini-3.8-flash":{"draws":4,"losses":8,"wins":36},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":24},"gpt-4.1":{"draws":0,"losses":1,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":5,"wins":37},"gpt-5.4":{"draws":2,"losses":9,"wins":35},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":29},"gpt-5.4-nano":{"draws":5,"losses":1,"wins":42},"gpt-5.5":{"draws":4,"losses":8,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":40},"gpt-5.6-sol":{"draws":0,"losses":13,"wins":35},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":38},"gpt-6-astra":{"draws":1,"losses":34,"wins":13},"gpt-6-luna":{"draws":5,"losses":3,"wins":40},"gpt-6-sol":{"draws":8,"losses":14,"wins":26},"gpt-6.1-sol":{"draws":6,"losses":26,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":27},"inception/mercury-3":{"draws":3,"losses":5,"wins":24},"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":6,"losses":3,"wins":43},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":37},"meta/muse-spark-1.2":{"draws":2,"losses":6,"wins":38},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":34},"meta/muse-spark-open":{"draws":6,"losses":4,"wins":36},"meta/muse-wonder":{"draws":4,"losses":14,"wins":30},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":24},"minimax/minimax-m3.1-flash":{"draws":3,"losses":8,"wins":31},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"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":4,"losses":5,"wins":37},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":10,"wins":18},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":23},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":37},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":2,"wins":19},"o3":{"draws":1,"losses":11,"wins":54},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":36},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":36},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":24},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":6,"wins":34},"qwen/qwen3.8-27b":{"draws":5,"losses":3,"wins":26},"qwen/qwen3.8-flash":{"draws":2,"losses":6,"wins":24},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":40},"qwen/qwen3.8-max-0902":{"draws":1,"losses":9,"wins":38},"recursive/flint-v1.0":{"draws":4,"losses":0,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":2,"wins":41},"stealth/ox-alpha":{"draws":19,"losses":19,"wins":120},"stealth/space-bunny-alpha":{"draws":2,"losses":4,"wins":32},"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":2,"losses":3,"wins":21},"tencent/hy4-preview":{"draws":5,"losses":5,"wins":36},"thinkingmachines/inkling":{"draws":3,"losses":2,"wins":59},"thinkingmachines/inkling-small":{"draws":2,"losses":5,"wins":41},"unbiased/pareto-26.10":{"draws":2,"losses":8,"wins":6},"unbiased/pareto-26.10-preview":{"draws":1,"losses":9,"wins":6},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":10,"wins":32},"x-ai/grok-4.6":{"draws":4,"losses":9,"wins":35},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":24},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":19},"z-ai/glm-5.2":{"draws":14,"losses":7,"wins":75},"z-ai/glm-5.3":{"draws":8,"losses":12,"wins":26},"z-ai/glm-5.3-flash":{"draws":6,"losses":7,"wins":35},"z-ai/glm-5.3-flashx":{"draws":4,"losses":10,"wins":34}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":16,"wins":11},"claude-fable-5":{"draws":8,"losses":32,"wins":2},"claude-fable-5-1":{"draws":3,"losses":44,"wins":1},"claude-haiku-5-5":{"draws":13,"losses":20,"wins":7},"claude-opus-4-5":{"draws":23,"losses":33,"wins":12},"claude-opus-4-8":{"draws":10,"losses":23,"wins":5},"claude-opus-5":{"draws":4,"losses":63,"wins":3},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":15,"losses":21,"wins":6},"claude-sonnet-5-5":{"draws":12,"losses":22,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":11},"deepseek/deepseek-v4-flash":{"draws":16,"losses":28,"wins":18},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":25,"wins":9},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":29,"wins":3},"elorian/glimpse":{"draws":8,"losses":9,"wins":5},"fireworks/ember-1":{"draws":17,"losses":18,"wins":7},"gemini-3.1-pro-preview":{"draws":16,"losses":20,"wins":6},"gemini-4-argon":{"draws":8,"losses":30,"wins":4},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":17},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":17},"google/gemini-3.5-flash-lite":{"draws":20,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":19,"losses":42,"wins":19},"google/gemini-3.8-flash":{"draws":12,"losses":24,"wins":6},"google/gemma-4-31b-it":{"draws":13,"losses":6,"wins":7},"gpt-4.1":{"draws":3,"losses":6,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":11,"wins":16},"gpt-5.4":{"draws":12,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":16,"wins":15},"gpt-5.5":{"draws":13,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":12},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":17,"wins":11},"gpt-6-astra":{"draws":4,"losses":38,"wins":0},"gpt-6-luna":{"draws":11,"losses":22,"wins":9},"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":14,"losses":7,"wins":11},"inception/mercury-3":{"draws":10,"losses":11,"wins":7},"inclusionai/ling-3.0-flash":{"draws":12,"losses":7,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":9,"losses":18,"wins":21},"meta/muse-glimmer-30b":{"draws":14,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":25,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":23,"wins":8},"meta/muse-wonder":{"draws":12,"losses":27,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":14,"losses":12,"wins":10},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":8,"losses":11,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":19,"wins":7},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":33,"wins":2},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":10,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":7},"o3":{"draws":7,"losses":31,"wins":18},"openai/gpt-oss-120b":{"draws":11,"losses":9,"wins":18},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":19},"qwen/qwen3.7-max":{"draws":6,"losses":12,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":11,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":24,"wins":4},"qwen/qwen3.8-max-0902":{"draws":14,"losses":20,"wins":8},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":20,"wins":9},"stealth/ox-alpha":{"draws":39,"losses":79,"wins":24},"stealth/space-bunny-alpha":{"draws":14,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":6,"losses":14,"wins":8},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":2,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":22,"wins":6},"thinkingmachines/inkling":{"draws":17,"losses":18,"wins":19},"thinkingmachines/inkling-small":{"draws":14,"losses":12,"wins":16},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":11,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":12,"losses":26,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":29,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":19,"losses":18,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":32,"losses":30,"wins":22},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":23,"wins":9},"z-ai/glm-5.3-flashx":{"draws":8,"losses":25,"wins":9}},"nex-agi/nex-n2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":9,"wins":6},"claude-fable-5":{"draws":2,"losses":18,"wins":4},"claude-fable-5-1":{"draws":0,"losses":27,"wins":1},"claude-haiku-5-5":{"draws":6,"losses":12,"wins":4},"claude-opus-4-5":{"draws":11,"losses":22,"wins":5},"claude-opus-4-8":{"draws":3,"losses":13,"wins":4},"claude-opus-5":{"draws":4,"losses":39,"wins":1},"claude-opus-5-5":{"draws":3,"losses":25,"wins":0},"claude-sonnet-5":{"draws":8,"losses":11,"wins":5},"claude-sonnet-5-5":{"draws":6,"losses":14,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":12,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":5,"losses":18,"wins":1},"elorian/glimpse":{"draws":3,"losses":9,"wins":2},"fireworks/ember-1":{"draws":5,"losses":16,"wins":3},"gemini-3.1-pro-preview":{"draws":6,"losses":12,"wins":6},"gemini-4-argon":{"draws":0,"losses":24,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":15,"wins":8},"google/gemini-3.5-flash-lite":{"draws":13,"losses":15,"wins":10},"google/gemini-3.6-flash":{"draws":9,"losses":25,"wins":10},"google/gemini-3.8-flash":{"draws":6,"losses":14,"wins":4},"google/gemma-4-31b-it":{"draws":5,"losses":2,"wins":7},"gpt-4.1":{"draws":4,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":7,"losses":10,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":9},"gpt-5.5":{"draws":5,"losses":11,"wins":6},"gpt-5.6-luna":{"draws":11,"losses":4,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":21,"wins":1},"gpt-5.6-terra":{"draws":8,"losses":9,"wins":7},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":7,"losses":11,"wins":6},"gpt-6-sol":{"draws":1,"losses":21,"wins":2},"gpt-6.1-sol":{"draws":1,"losses":23,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":3,"wins":5},"inception/mercury-3":{"draws":6,"losses":9,"wins":5},"inclusionai/ling-3.0-flash":{"draws":5,"losses":10,"wins":3},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":5,"losses":8,"wins":13},"meta/muse-glimmer-30b":{"draws":8,"losses":7,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":14,"wins":3},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":4},"meta/muse-spark-open":{"draws":4,"losses":15,"wins":3},"meta/muse-wonder":{"draws":6,"losses":13,"wins":5},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":3},"minimax/minimax-m3.1-flash":{"draws":6,"losses":7,"wins":5},"mistralai/mistral-large-4-0":{"draws":7,"losses":7,"wins":2},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":12,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":21,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":4,"wins":7},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":5},"o3":{"draws":3,"losses":20,"wins":5},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":13,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":3},"qwen/qwen3.8-flash":{"draws":5,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":3},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":13,"wins":5},"stealth/ox-alpha":{"draws":26,"losses":49,"wins":15},"stealth/space-bunny-alpha":{"draws":4,"losses":11,"wins":3},"stepfun/step-3.7-flash":{"draws":3,"losses":5,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":4},"thinkingmachines/inkling":{"draws":9,"losses":12,"wins":9},"thinkingmachines/inkling-small":{"draws":9,"losses":9,"wins":6},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":0},"upstage/solar-mini4":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":15,"wins":3},"x-ai/grok-4.6":{"draws":5,"losses":17,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":21,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":7,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":10,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":15,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":19,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":15,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":12,"wins":7}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":17,"wins":14},"claude-fable-5":{"draws":6,"losses":30,"wins":6},"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":16,"losses":41,"wins":11},"claude-opus-4-8":{"draws":4,"losses":24,"wins":10},"claude-opus-5":{"draws":9,"losses":59,"wins":2},"claude-opus-5-5":{"draws":2,"losses":43,"wins":1},"claude-sonnet-5":{"draws":10,"losses":19,"wins":13},"claude-sonnet-5-5":{"draws":5,"losses":31,"wins":6},"cohere/north-mini-code":{"draws":7,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":10,"losses":32,"wins":20},"deepseek/deepseek-v4-pro":{"draws":14,"losses":16,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":24,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":33,"wins":3},"elorian/glimpse":{"draws":6,"losses":14,"wins":4},"fireworks/ember-1":{"draws":9,"losses":22,"wins":11},"gemini-3.1-pro-preview":{"draws":11,"losses":21,"wins":10},"gemini-4-argon":{"draws":2,"losses":40,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":13,"wins":13},"google/gemini-3.5-flash":{"draws":10,"losses":30,"wins":14},"google/gemini-3.5-flash-lite":{"draws":22,"losses":27,"wins":27},"google/gemini-3.6-flash":{"draws":16,"losses":50,"wins":16},"google/gemini-3.8-flash":{"draws":8,"losses":29,"wins":5},"google/gemma-4-31b-it":{"draws":9,"losses":7,"wins":8},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":12,"losses":18,"wins":8},"gpt-5.4":{"draws":13,"losses":25,"wins":4},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":2,"losses":22,"wins":18},"gpt-5.5":{"draws":16,"losses":20,"wins":4},"gpt-5.6-luna":{"draws":8,"losses":19,"wins":15},"gpt-5.6-sol":{"draws":3,"losses":35,"wins":4},"gpt-5.6-terra":{"draws":12,"losses":21,"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":7,"losses":14,"wins":7},"inception/mercury-3":{"draws":4,"losses":14,"wins":8},"inclusionai/ling-3.0-flash":{"draws":9,"losses":10,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":13,"losses":24,"wins":11},"meta/muse-glimmer-30b":{"draws":11,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":9,"losses":21,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":33,"wins":4},"meta/muse-spark-open":{"draws":10,"losses":24,"wins":8},"meta/muse-wonder":{"draws":9,"losses":30,"wins":3},"minimax/minimax-m3":{"draws":5,"losses":10,"wins":7},"minimax/minimax-m3.1-flash":{"draws":6,"losses":19,"wins":13},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":8,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":25,"wins":9},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":6,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":9,"wins":6},"o3":{"draws":10,"losses":34,"wins":20},"openai/gpt-oss-120b":{"draws":10,"losses":15,"wins":11},"poolside/laguna-s-2.1":{"draws":11,"losses":13,"wins":16},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":9,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":25,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":16,"wins":7},"qwen/qwen3.8-flash":{"draws":8,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":8,"losses":26,"wins":8},"qwen/qwen3.8-max-0902":{"draws":10,"losses":26,"wins":6},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":7,"losses":23,"wins":8},"stealth/ox-alpha":{"draws":24,"losses":93,"wins":25},"stealth/space-bunny-alpha":{"draws":10,"losses":15,"wins":9},"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":10,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":26,"wins":8},"thinkingmachines/inkling":{"draws":15,"losses":20,"wins":23},"thinkingmachines/inkling-small":{"draws":9,"losses":16,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":10,"losses":29,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":28,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":34,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.5":{"draws":16,"losses":25,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":12,"wins":8},"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":17,"losses":37,"wins":30},"z-ai/glm-5.3":{"draws":5,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":3,"losses":27,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":28,"wins":8}},"nvidia/nemotron-3.5-super-vl":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":1},"claude-fable-5":{"draws":4,"losses":14,"wins":0},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-haiku-5-5":{"draws":3,"losses":11,"wins":4},"claude-opus-4-5":{"draws":9,"losses":18,"wins":3},"claude-opus-4-8":{"draws":5,"losses":12,"wins":1},"claude-opus-5":{"draws":4,"losses":25,"wins":3},"claude-opus-5-5":{"draws":1,"losses":21,"wins":0},"claude-sonnet-5":{"draws":6,"losses":11,"wins":1},"claude-sonnet-5-5":{"draws":4,"losses":13,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-flash":{"draws":4,"losses":16,"wins":6},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":12,"wins":3},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":14,"wins":0},"elorian/glimpse":{"draws":4,"losses":5,"wins":3},"fireworks/ember-1":{"draws":4,"losses":10,"wins":4},"gemini-3.1-pro-preview":{"draws":3,"losses":12,"wins":3},"gemini-4-argon":{"draws":0,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":5,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":6},"google/gemini-3.5-flash-lite":{"draws":12,"losses":14,"wins":6},"google/gemini-3.6-flash":{"draws":10,"losses":20,"wins":4},"google/gemini-3.8-flash":{"draws":2,"losses":12,"wins":4},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":4,"losses":11,"wins":1},"gpt-5.4":{"draws":6,"losses":8,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":11,"wins":4},"gpt-5.5":{"draws":6,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":7},"gpt-5.6-sol":{"draws":1,"losses":16,"wins":1},"gpt-5.6-terra":{"draws":5,"losses":10,"wins":3},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":5,"losses":11,"wins":2},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"gpt-6.1-sol":{"draws":3,"losses":15,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":3},"inception/mercury-3":{"draws":2,"losses":8,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":6,"wins":4},"inclusionai/ling-3.1-flash":{"draws":0,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":6,"losses":11,"wins":5},"meta/muse-glimmer-30b":{"draws":5,"losses":8,"wins":5},"meta/muse-spark-1.2":{"draws":6,"losses":12,"wins":0},"meta/muse-spark-1.3":{"draws":4,"losses":13,"wins":1},"meta/muse-spark-open":{"draws":3,"losses":15,"wins":0},"meta/muse-wonder":{"draws":3,"losses":13,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"minimax/minimax-m3.1-flash":{"draws":6,"losses":5,"wins":3},"mistralai/mistral-large-4-0":{"draws":3,"losses":6,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":2,"losses":16,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":8},"nvidia/nemotron-3.5-super-vl":{"draws":1,"losses":4,"wins":1},"o3":{"draws":3,"losses":20,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":9},"poolside/laguna-s-2.1":{"draws":2,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":12,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.8-max":{"draws":3,"losses":13,"wins":2},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":4},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":3,"losses":12,"wins":3},"stealth/ox-alpha":{"draws":14,"losses":31,"wins":7},"stealth/space-bunny-alpha":{"draws":6,"losses":8,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"stepfun/step-5-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":3,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":8,"losses":7,"wins":7},"thinkingmachines/inkling-small":{"draws":5,"losses":5,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":5,"wins":0},"unbiased/pareto-26.10-preview":{"draws":0,"losses":6,"wins":0},"upstage/solar-mini4":{"draws":2,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":13,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":14,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":12,"losses":11,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":8,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":11,"losses":18,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":16,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":11,"wins":5},"z-ai/glm-5.3-flashx":{"draws":2,"losses":14,"wins":2}},"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":0,"losses":53,"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":12,"losses":24,"wins":8},"claude-opus-5":{"draws":11,"losses":66,"wins":5},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":6,"losses":12,"wins":8},"fireworks/ember-1":{"draws":17,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":14,"losses":18,"wins":16},"gemini-4-argon":{"draws":1,"losses":47,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":20,"losses":24,"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},"inception/mercury-3":{"draws":8,"losses":19,"wins":5},"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":16,"losses":9,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":12,"wins":15},"meta/muse-spark-1.2":{"draws":14,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":13,"losses":29,"wins":6},"meta/muse-spark-open":{"draws":12,"losses":26,"wins":8},"meta/muse-wonder":{"draws":7,"losses":36,"wins":5},"minimax/minimax-m3":{"draws":9,"losses":8,"wins":9},"minimax/minimax-m3.1-flash":{"draws":13,"losses":15,"wins":14},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":46,"wins":2},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":17},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":9,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":7},"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},"recursive/flint-v1.0":{"draws":3,"losses":1,"wins":10},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":22,"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":{"draws":0,"losses":16,"wins":0},"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":24,"losses":21,"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":6,"losses":18,"wins":8},"claude-fable-5":{"draws":6,"losses":27,"wins":3},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-haiku-5-5":{"draws":8,"losses":21,"wins":5},"claude-opus-4-5":{"draws":19,"losses":34,"wins":5},"claude-opus-4-8":{"draws":7,"losses":22,"wins":3},"claude-opus-5":{"draws":4,"losses":60,"wins":4},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":12,"losses":20,"wins":4},"claude-sonnet-5-5":{"draws":6,"losses":26,"wins":4},"cohere/north-mini-code":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4-flash":{"draws":15,"losses":21,"wins":20},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":20,"wins":4},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":23,"wins":6},"elorian/glimpse":{"draws":3,"losses":12,"wins":5},"fireworks/ember-1":{"draws":11,"losses":21,"wins":4},"gemini-3.1-pro-preview":{"draws":9,"losses":22,"wins":5},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":11},"google/gemini-3.5-flash":{"draws":7,"losses":27,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":28,"wins":19},"google/gemini-3.6-flash":{"draws":20,"losses":38,"wins":10},"google/gemini-3.8-flash":{"draws":7,"losses":27,"wins":2},"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":7,"losses":21,"wins":6},"gpt-5.4-mini":{"draws":8,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":11,"wins":13},"gpt-5.5":{"draws":11,"losses":18,"wins":5},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":34,"wins":0},"gpt-5.6-terra":{"draws":8,"losses":23,"wins":3},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":10,"losses":17,"wins":9},"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":6,"losses":8,"wins":8},"inception/mercury-3":{"draws":8,"losses":12,"wins":6},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":10},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":17,"wins":10},"meta/muse-glimmer-30b":{"draws":13,"losses":10,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":28,"wins":1},"meta/muse-spark-1.3":{"draws":11,"losses":21,"wins":4},"meta/muse-spark-open":{"draws":6,"losses":26,"wins":2},"meta/muse-wonder":{"draws":4,"losses":28,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":8},"minimax/minimax-m3.1-flash":{"draws":4,"losses":15,"wins":11},"mistralai/mistral-large-4-0":{"draws":10,"losses":9,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":21,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":29,"wins":1},"nex-agi/nex-n2-pro":{"draws":3,"losses":9,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":6,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":8,"wins":9},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":10,"wins":4},"o3":{"draws":7,"losses":36,"wins":7},"openai/gpt-oss-120b":{"draws":4,"losses":8,"wins":10},"poolside/laguna-s-2.1":{"draws":17,"losses":15,"wins":8},"qwen/qwen3.7-max":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":19,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.8-max":{"draws":10,"losses":23,"wins":3},"qwen/qwen3.8-max-0902":{"draws":10,"losses":22,"wins":4},"recursive/flint-v1.0":{"draws":2,"losses":3,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":20,"wins":4},"stealth/ox-alpha":{"draws":29,"losses":83,"wins":12},"stealth/space-bunny-alpha":{"draws":4,"losses":18,"wins":6},"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":4,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":4},"thinkingmachines/inkling":{"draws":11,"losses":25,"wins":14},"thinkingmachines/inkling-small":{"draws":12,"losses":7,"wins":17},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":10,"losses":21,"wins":5},"x-ai/grok-4.6":{"draws":9,"losses":26,"wins":1},"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":15,"losses":20,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":18,"wins":3},"z-ai/glm-5.2":{"draws":30,"losses":30,"wins":12},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":2},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":5},"z-ai/glm-5.3-flashx":{"draws":7,"losses":25,"wins":4}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":22,"wins":26},"claude-fable-5":{"draws":6,"losses":53,"wins":13},"claude-fable-5-1":{"draws":0,"losses":79,"wins":1},"claude-haiku-5-5":{"draws":15,"losses":30,"wins":23},"claude-opus-4-5":{"draws":30,"losses":61,"wins":25},"claude-opus-4-8":{"draws":10,"losses":41,"wins":13},"claude-opus-5":{"draws":8,"losses":111,"wins":7},"claude-opus-5-5":{"draws":5,"losses":75,"wins":0},"claude-sonnet-5":{"draws":17,"losses":35,"wins":20},"claude-sonnet-5-5":{"draws":10,"losses":47,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":11,"wins":14},"deepseek/deepseek-v4-flash":{"draws":24,"losses":40,"wins":48},"deepseek/deepseek-v4-pro":{"draws":11,"losses":29,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":33,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":26,"losses":32,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":50,"wins":11},"elorian/glimpse":{"draws":7,"losses":22,"wins":11},"fireworks/ember-1":{"draws":17,"losses":38,"wins":17},"gemini-3.1-pro-preview":{"draws":19,"losses":32,"wins":21},"gemini-4-argon":{"draws":2,"losses":69,"wins":1},"google/gemini-3.1-flash-lite":{"draws":9,"losses":12,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":59,"wins":22},"google/gemini-3.5-flash-lite":{"draws":20,"losses":37,"wins":67},"google/gemini-3.6-flash":{"draws":25,"losses":73,"wins":40},"google/gemini-3.8-flash":{"draws":10,"losses":51,"wins":11},"google/gemma-4-31b-it":{"draws":13,"losses":10,"wins":17},"gpt-4.1":{"draws":5,"losses":12,"wins":7},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":13,"losses":27,"wins":28},"gpt-5.4":{"draws":15,"losses":43,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":16,"wins":19},"gpt-5.4-nano":{"draws":9,"losses":32,"wins":37},"gpt-5.5":{"draws":21,"losses":32,"wins":15},"gpt-5.6-luna":{"draws":17,"losses":27,"wins":28},"gpt-5.6-sol":{"draws":8,"losses":57,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":39,"wins":12},"gpt-6-astra":{"draws":2,"losses":70,"wins":0},"gpt-6-luna":{"draws":18,"losses":25,"wins":29},"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":12,"losses":12,"wins":20},"inception/mercury-3":{"draws":11,"losses":27,"wins":12},"inclusionai/ling-3.0-flash":{"draws":10,"losses":16,"wins":24},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":23,"losses":24,"wins":33},"meta/muse-glimmer-30b":{"draws":15,"losses":23,"wins":28},"meta/muse-spark-1.2":{"draws":9,"losses":43,"wins":18},"meta/muse-spark-1.3":{"draws":9,"losses":44,"wins":19},"meta/muse-spark-open":{"draws":8,"losses":47,"wins":15},"meta/muse-wonder":{"draws":10,"losses":57,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":15,"wins":21},"minimax/minimax-m3.1-flash":{"draws":9,"losses":28,"wins":25},"mistralai/mistral-large-4-0":{"draws":13,"losses":17,"wins":16},"mistralai/mistral-medium-3-5":{"draws":7,"losses":11,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":8,"wins":9},"moonshotai/kimi-k3":{"draws":17,"losses":33,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":57,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":11,"wins":19},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":19,"wins":31},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":17,"wins":11},"o3":{"draws":15,"losses":54,"wins":41},"openai/gpt-oss-120b":{"draws":17,"losses":15,"wins":34},"poolside/laguna-s-2.1":{"draws":14,"losses":17,"wins":23},"qwen/qwen3.7-max":{"draws":9,"losses":22,"wins":13},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":46,"wins":10},"qwen/qwen3.8-27b":{"draws":9,"losses":25,"wins":16},"qwen/qwen3.8-flash":{"draws":9,"losses":21,"wins":18},"qwen/qwen3.8-max":{"draws":14,"losses":35,"wins":23},"qwen/qwen3.8-max-0902":{"draws":19,"losses":35,"wins":18},"recursive/flint-v1.0":{"draws":2,"losses":5,"wins":13},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":35,"wins":21},"stealth/ox-alpha":{"draws":44,"losses":140,"wins":64},"stealth/space-bunny-alpha":{"draws":11,"losses":26,"wins":19},"stepfun/step-3.7-flash":{"draws":15,"losses":15,"wins":26},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":13,"wins":15},"tencent/hy4-preview":{"draws":10,"losses":37,"wins":23},"thinkingmachines/inkling":{"draws":18,"losses":28,"wins":54},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":44},"unbiased/pareto-26.10":{"draws":0,"losses":24,"wins":0},"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":14,"losses":45,"wins":13},"x-ai/grok-4.6":{"draws":18,"losses":42,"wins":12},"x-ai/grok-4.7":{"draws":4,"losses":53,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":10,"wins":10},"xiaomi/mimo-v2.5":{"draws":18,"losses":33,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":17,"wins":21},"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":36,"losses":55,"wins":53},"z-ai/glm-5.3":{"draws":6,"losses":54,"wins":8},"z-ai/glm-5.3-flash":{"draws":13,"losses":39,"wins":20},"z-ai/glm-5.3-flashx":{"draws":13,"losses":44,"wins":15}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":20,"wins":10},"claude-fable-5":{"draws":5,"losses":32,"wins":5},"claude-fable-5-1":{"draws":0,"losses":46,"wins":0},"claude-haiku-5-5":{"draws":13,"losses":19,"wins":8},"claude-opus-4-5":{"draws":17,"losses":38,"wins":13},"claude-opus-4-8":{"draws":9,"losses":20,"wins":9},"claude-opus-5":{"draws":9,"losses":58,"wins":3},"claude-opus-5-5":{"draws":5,"losses":41,"wins":0},"claude-sonnet-5":{"draws":13,"losses":21,"wins":8},"claude-sonnet-5-5":{"draws":13,"losses":18,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":7},"deepseek/deepseek-v4-flash":{"draws":14,"losses":26,"wins":26},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":21,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":23,"wins":7},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":29,"wins":6},"elorian/glimpse":{"draws":5,"losses":11,"wins":6},"fireworks/ember-1":{"draws":11,"losses":24,"wins":7},"gemini-3.1-pro-preview":{"draws":10,"losses":20,"wins":12},"gemini-4-argon":{"draws":0,"losses":40,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":7,"wins":17},"google/gemini-3.5-flash":{"draws":10,"losses":25,"wins":17},"google/gemini-3.5-flash-lite":{"draws":13,"losses":24,"wins":35},"google/gemini-3.6-flash":{"draws":17,"losses":47,"wins":16},"google/gemini-3.8-flash":{"draws":14,"losses":19,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":7,"wins":10},"gpt-4.1":{"draws":5,"losses":2,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":15,"wins":10},"gpt-5.4":{"draws":9,"losses":22,"wins":9},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":10,"losses":19,"wins":17},"gpt-5.5":{"draws":11,"losses":20,"wins":7},"gpt-5.6-luna":{"draws":11,"losses":13,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":31,"wins":6},"gpt-5.6-terra":{"draws":11,"losses":24,"wins":5},"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":8,"losses":11,"wins":9},"inception/mercury-3":{"draws":6,"losses":15,"wins":9},"inclusionai/ling-3.0-flash":{"draws":7,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":13,"wins":23},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":15},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":8},"meta/muse-spark-open":{"draws":9,"losses":25,"wins":6},"meta/muse-wonder":{"draws":5,"losses":28,"wins":9},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":13},"minimax/minimax-m3.1-flash":{"draws":3,"losses":19,"wins":14},"mistralai/mistral-large-4-0":{"draws":12,"losses":12,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":31,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":13,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":9,"wins":6},"o3":{"draws":8,"losses":36,"wins":18},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":15},"poolside/laguna-s-2.1":{"draws":14,"losses":15,"wins":15},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":9},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":11},"qwen/qwen3.8-flash":{"draws":4,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":7},"qwen/qwen3.8-max-0902":{"draws":11,"losses":22,"wins":9},"recursive/flint-v1.0":{"draws":2,"losses":4,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":17,"wins":11},"stealth/ox-alpha":{"draws":27,"losses":84,"wins":29},"stealth/space-bunny-alpha":{"draws":8,"losses":13,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":10,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":14,"losses":13,"wins":29},"thinkingmachines/inkling-small":{"draws":8,"losses":13,"wins":21},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":11,"losses":23,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":26,"wins":5},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"losses":17,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":8},"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":23,"losses":34,"wins":27},"z-ai/glm-5.3":{"draws":6,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":10,"losses":25,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":7}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":13,"wins":7},"claude-fable-5":{"draws":7,"losses":26,"wins":3},"claude-fable-5-1":{"draws":3,"losses":37,"wins":0},"claude-haiku-5-5":{"draws":7,"losses":28,"wins":1},"claude-opus-4-5":{"draws":25,"losses":29,"wins":6},"claude-opus-4-8":{"draws":10,"losses":23,"wins":3},"claude-opus-5":{"draws":6,"losses":45,"wins":7},"claude-opus-5-5":{"draws":3,"losses":33,"wins":0},"claude-sonnet-5":{"draws":11,"losses":21,"wins":4},"claude-sonnet-5-5":{"draws":8,"losses":24,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":17,"losses":25,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":19,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":19,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":2},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":26,"wins":3},"elorian/glimpse":{"draws":6,"losses":8,"wins":4},"fireworks/ember-1":{"draws":12,"losses":22,"wins":2},"gemini-3.1-pro-preview":{"draws":13,"losses":21,"wins":2},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":8,"wins":13},"google/gemini-3.5-flash":{"draws":11,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":19,"losses":35,"wins":10},"google/gemini-3.6-flash":{"draws":21,"losses":46,"wins":3},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":3},"google/gemma-4-31b-it":{"draws":7,"losses":9,"wins":6},"gpt-4.1":{"draws":4,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":1},"gpt-5":{"draws":8,"losses":20,"wins":2},"gpt-5.4":{"draws":6,"losses":27,"wins":1},"gpt-5.4-mini":{"draws":8,"losses":11,"wins":5},"gpt-5.4-nano":{"draws":8,"losses":22,"wins":8},"gpt-5.5":{"draws":11,"losses":19,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":15,"wins":6},"gpt-5.6-sol":{"draws":7,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":20,"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":8,"wins":8},"inception/mercury-3":{"draws":8,"losses":13,"wins":1},"inclusionai/ling-3.0-flash":{"draws":9,"losses":12,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":21,"wins":9},"meta/muse-glimmer-30b":{"draws":13,"losses":12,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":17,"wins":7},"meta/muse-spark-1.3":{"draws":5,"losses":27,"wins":4},"meta/muse-spark-open":{"draws":8,"losses":23,"wins":3},"meta/muse-wonder":{"draws":4,"losses":30,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":5},"minimax/minimax-m3.1-flash":{"draws":8,"losses":22,"wins":4},"mistralai/mistral-large-4-0":{"draws":4,"losses":17,"wins":1},"mistralai/mistral-medium-3-5":{"draws":9,"losses":8,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":12,"losses":17,"wins":5},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":31,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":16,"wins":7},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":10,"wins":1},"o3":{"draws":6,"losses":41,"wins":5},"openai/gpt-oss-120b":{"draws":9,"losses":17,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":19,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":12,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":19,"wins":2},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":17,"wins":3},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":2},"recursive/flint-v1.0":{"draws":4,"losses":5,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":17,"wins":6},"stealth/ox-alpha":{"draws":23,"losses":72,"wins":7},"stealth/space-bunny-alpha":{"draws":8,"losses":19,"wins":3},"stepfun/step-3.7-flash":{"draws":5,"losses":15,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":20,"wins":6},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":9},"thinkingmachines/inkling-small":{"draws":15,"losses":18,"wins":3},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":12,"losses":23,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":25,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":26,"wins":3},"x-ai/grok-build-0.1":{"draws":3,"losses":7,"wins":2},"xiaomi/mimo-v2.5":{"draws":23,"losses":29,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":16,"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":22,"losses":42,"wins":8},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":24,"wins":4},"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":12,"losses":13,"wins":19},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":1,"losses":53,"wins":0},"claude-haiku-5-5":{"draws":10,"losses":22,"wins":14},"claude-opus-4-5":{"draws":26,"losses":25,"wins":27},"claude-opus-4-8":{"draws":14,"losses":17,"wins":13},"claude-opus-5":{"draws":8,"losses":62,"wins":12},"claude-opus-5-5":{"draws":5,"losses":43,"wins":4},"claude-sonnet-5":{"draws":15,"losses":10,"wins":23},"claude-sonnet-5-5":{"draws":8,"losses":22,"wins":18},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-flash":{"draws":21,"losses":12,"wins":39},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":15,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":23,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":24,"wins":12},"elorian/glimpse":{"draws":7,"losses":11,"wins":8},"fireworks/ember-1":{"draws":12,"losses":20,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":16,"wins":19},"gemini-4-argon":{"draws":3,"losses":38,"wins":7},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":24},"google/gemini-3.5-flash-lite":{"draws":28,"losses":16,"wins":40},"google/gemini-3.6-flash":{"draws":19,"losses":47,"wins":26},"google/gemini-3.8-flash":{"draws":10,"losses":24,"wins":14},"google/gemma-4-31b-it":{"draws":9,"losses":3,"wins":16},"gpt-4.1":{"draws":4,"losses":5,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":10,"losses":13,"wins":19},"gpt-5.4":{"draws":10,"losses":20,"wins":16},"gpt-5.4-mini":{"draws":13,"losses":3,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":10,"wins":26},"gpt-5.5":{"draws":12,"losses":16,"wins":16},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":32,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":12,"wins":20},"gpt-6-astra":{"draws":2,"losses":46,"wins":0},"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":13,"losses":3,"wins":18},"inception/mercury-3":{"draws":10,"losses":10,"wins":12},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":17},"meta/muse-spark-1.2":{"draws":12,"losses":12,"wins":22},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":17},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":16},"meta/muse-wonder":{"draws":10,"losses":24,"wins":14},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":18},"minimax/minimax-m3.1-flash":{"draws":9,"losses":13,"wins":20},"mistralai/mistral-large-4-0":{"draws":5,"losses":11,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":20},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":10,"losses":20,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":40,"wins":3},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":4,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":4,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":5,"wins":13},"o3":{"draws":12,"losses":18,"wins":36},"openai/gpt-oss-120b":{"draws":14,"losses":5,"wins":23},"poolside/laguna-s-2.1":{"draws":15,"losses":7,"wins":24},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.7-plus":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-27b":{"draws":12,"losses":12,"wins":10},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":26,"wins":11},"qwen/qwen3.8-max-0902":{"draws":13,"losses":19,"wins":16},"recursive/flint-v1.0":{"draws":5,"losses":1,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":13,"wins":19},"stealth/ox-alpha":{"draws":37,"losses":65,"wins":56},"stealth/space-bunny-alpha":{"draws":13,"losses":13,"wins":12},"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":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":29},"unbiased/pareto-26.10":{"draws":3,"losses":13,"wins":0},"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":22,"wins":16},"x-ai/grok-4.6":{"draws":12,"losses":21,"wins":15},"x-ai/grok-4.7":{"draws":5,"losses":29,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":8},"xiaomi/mimo-v2.5":{"draws":27,"losses":5,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":15,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":14,"wins":10},"z-ai/glm-5.2":{"draws":27,"losses":28,"wins":41},"z-ai/glm-5.3":{"draws":8,"losses":30,"wins":8},"z-ai/glm-5.3-flash":{"draws":12,"losses":21,"wins":15},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":15,"wins":2},"elorian/glimpse":{"draws":2,"losses":7,"wins":3},"fireworks/ember-1":{"draws":12,"losses":11,"wins":1},"gemini-3.1-pro-preview":{"draws":8,"losses":8,"wins":8},"gemini-4-argon":{"draws":1,"losses":23,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":19,"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":16,"wins":1},"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},"inception/mercury-3":{"draws":8,"losses":7,"wins":3},"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-spark-open":{"draws":4,"losses":15,"wins":3},"meta/muse-wonder":{"draws":6,"losses":14,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":2},"minimax/minimax-m3.1-flash":{"draws":4,"losses":12,"wins":6},"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},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":18,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":6},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":8,"wins":3},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":4,"wins":1},"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},"recursive/flint-v1.0":{"draws":2,"losses":2,"wins":2},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":11,"wins":1},"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":{"draws":1,"losses":7,"wins":0},"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":14,"losses":15,"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":14,"losses":17,"wins":13},"claude-fable-5":{"draws":8,"losses":38,"wins":2},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":32,"wins":2},"claude-opus-4-5":{"draws":29,"losses":41,"wins":8},"claude-opus-4-8":{"draws":11,"losses":31,"wins":2},"claude-opus-5":{"draws":11,"losses":67,"wins":4},"claude-opus-5-5":{"draws":3,"losses":48,"wins":1},"claude-sonnet-5":{"draws":18,"losses":24,"wins":6},"claude-sonnet-5-5":{"draws":13,"losses":29,"wins":6},"cohere/north-mini-code":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4-flash":{"draws":21,"losses":26,"wins":25},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":24,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":25,"wins":6},"deepseek/deepseek-v4.1-flash-1017":{"draws":8,"losses":32,"wins":8},"elorian/glimpse":{"draws":7,"losses":15,"wins":4},"fireworks/ember-1":{"draws":15,"losses":25,"wins":8},"gemini-3.1-pro-preview":{"draws":17,"losses":20,"wins":11},"gemini-4-argon":{"draws":2,"losses":46,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":10,"wins":13},"google/gemini-3.5-flash":{"draws":11,"losses":41,"wins":8},"google/gemini-3.5-flash-lite":{"draws":25,"losses":33,"wins":26},"google/gemini-3.6-flash":{"draws":29,"losses":57,"wins":6},"google/gemini-3.8-flash":{"draws":8,"losses":39,"wins":1},"google/gemma-4-31b-it":{"draws":13,"losses":5,"wins":10},"gpt-4.1":{"draws":6,"losses":6,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":28,"wins":9},"gpt-5.4":{"draws":8,"losses":28,"wins":10},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":21,"wins":18},"gpt-5.5":{"draws":16,"losses":23,"wins":5},"gpt-5.6-luna":{"draws":17,"losses":22,"wins":9},"gpt-5.6-sol":{"draws":6,"losses":37,"wins":5},"gpt-5.6-terra":{"draws":11,"losses":26,"wins":9},"gpt-6-astra":{"draws":6,"losses":42,"wins":0},"gpt-6-luna":{"draws":14,"losses":25,"wins":9},"gpt-6-sol":{"draws":3,"losses":40,"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":16,"losses":6,"wins":12},"inception/mercury-3":{"draws":8,"losses":17,"wins":7},"inclusionai/ling-3.0-flash":{"draws":10,"losses":8,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":18,"losses":17,"wins":17},"meta/muse-glimmer-30b":{"draws":17,"losses":16,"wins":9},"meta/muse-spark-1.2":{"draws":12,"losses":28,"wins":6},"meta/muse-spark-1.3":{"draws":10,"losses":32,"wins":6},"meta/muse-spark-open":{"draws":9,"losses":32,"wins":5},"meta/muse-wonder":{"draws":11,"losses":35,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":16,"wins":4},"minimax/minimax-m3.1-flash":{"draws":12,"losses":18,"wins":12},"mistralai/mistral-large-4-0":{"draws":11,"losses":18,"wins":1},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":7,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":27,"wins":4},"moonshotai/kimi-k3.1-pro":{"draws":4,"losses":42,"wins":2},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":7,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":18,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":12,"wins":3},"o3":{"draws":11,"losses":39,"wins":16},"openai/gpt-oss-120b":{"draws":12,"losses":17,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":25,"wins":9},"qwen/qwen3.7-max":{"draws":7,"losses":15,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":30,"wins":4},"qwen/qwen3.8-27b":{"draws":6,"losses":17,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":9,"wins":0},"qwen/qwen3.8-max":{"draws":17,"losses":25,"wins":6},"qwen/qwen3.8-max-0902":{"draws":16,"losses":23,"wins":9},"recursive/flint-v1.0":{"draws":5,"losses":3,"wins":6},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":25,"wins":7},"stealth/ox-alpha":{"draws":39,"losses":93,"wins":26},"stealth/space-bunny-alpha":{"draws":13,"losses":16,"wins":9},"stepfun/step-3.7-flash":{"draws":7,"losses":14,"wins":13},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":12,"losses":8,"wins":6},"tencent/hy4-preview":{"draws":9,"losses":32,"wins":5},"thinkingmachines/inkling":{"draws":21,"losses":19,"wins":24},"thinkingmachines/inkling-small":{"draws":16,"losses":14,"wins":18},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":11,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":30,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":37,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":28,"losses":30,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":17,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":23,"wins":3},"z-ai/glm-5.2":{"draws":30,"losses":50,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":32,"wins":3},"z-ai/glm-5.3-flash":{"draws":12,"losses":29,"wins":7},"z-ai/glm-5.3-flashx":{"draws":16,"losses":29,"wins":3}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":14},"claude-fable-5":{"draws":9,"losses":25,"wins":14},"claude-fable-5-1":{"draws":2,"losses":49,"wins":3},"claude-haiku-5-5":{"draws":14,"losses":17,"wins":15},"claude-opus-4-5":{"draws":22,"losses":33,"wins":23},"claude-opus-4-8":{"draws":9,"losses":19,"wins":16},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":5,"losses":41,"wins":6},"claude-sonnet-5":{"draws":17,"losses":15,"wins":16},"claude-sonnet-5-5":{"draws":5,"losses":30,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":13},"deepseek/deepseek-v4-flash":{"draws":29,"losses":11,"wins":32},"deepseek/deepseek-v4-pro":{"draws":14,"losses":12,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":15,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":21,"wins":20},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":24,"wins":15},"elorian/glimpse":{"draws":5,"losses":10,"wins":11},"fireworks/ember-1":{"draws":12,"losses":21,"wins":15},"gemini-3.1-pro-preview":{"draws":13,"losses":18,"wins":17},"gemini-4-argon":{"draws":3,"losses":39,"wins":6},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":23},"google/gemini-3.5-flash":{"draws":21,"losses":18,"wins":21},"google/gemini-3.5-flash-lite":{"draws":29,"losses":21,"wins":34},"google/gemini-3.6-flash":{"draws":20,"losses":38,"wins":34},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":18},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":13,"losses":6,"wins":23},"gpt-5.4":{"draws":14,"losses":16,"wins":16},"gpt-5.4-mini":{"draws":14,"losses":8,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":15,"wins":20},"gpt-5.5":{"draws":13,"losses":17,"wins":14},"gpt-5.6-luna":{"draws":17,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":31,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":13,"wins":20},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":12,"losses":18,"wins":18},"gpt-6-sol":{"draws":5,"losses":31,"wins":12},"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":11,"losses":5,"wins":18},"inception/mercury-3":{"draws":8,"losses":11,"wins":13},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":17},"inclusionai/ling-3.1-flash":{"draws":1,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":19,"losses":7,"wins":26},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":21,"wins":17},"meta/muse-spark-open":{"draws":12,"losses":24,"wins":10},"meta/muse-wonder":{"draws":11,"losses":25,"wins":12},"minimax/minimax-m3":{"draws":8,"losses":7,"wins":11},"minimax/minimax-m3.1-flash":{"draws":12,"losses":10,"wins":20},"mistralai/mistral-large-4-0":{"draws":12,"losses":8,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":13,"losses":16,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":10},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":5,"wins":9},"o3":{"draws":16,"losses":20,"wins":30},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":14,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":8,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":17},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":14,"wins":18},"stealth/ox-alpha":{"draws":46,"losses":68,"wins":44},"stealth/space-bunny-alpha":{"draws":11,"losses":11,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"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":12,"losses":21,"wins":13},"thinkingmachines/inkling":{"draws":20,"losses":12,"wins":32},"thinkingmachines/inkling-small":{"draws":15,"losses":14,"wins":19},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":12,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":12,"losses":23,"wins":13},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":8},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":23,"losses":18,"wins":33},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":16,"wins":8},"z-ai/glm-5.2":{"draws":32,"losses":24,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":10},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":18},"z-ai/glm-5.3-flashx":{"draws":11,"losses":17,"wins":20}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":7,"wins":21},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":22,"wins":10},"claude-opus-4-5":{"draws":28,"losses":26,"wins":24},"claude-opus-4-8":{"draws":14,"losses":13,"wins":17},"claude-opus-5":{"draws":10,"losses":69,"wins":3},"claude-opus-5-5":{"draws":1,"losses":49,"wins":2},"claude-sonnet-5":{"draws":13,"losses":15,"wins":20},"claude-sonnet-5-5":{"draws":13,"losses":23,"wins":12},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":22,"losses":12,"wins":38},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":28,"wins":11},"elorian/glimpse":{"draws":8,"losses":11,"wins":7},"fireworks/ember-1":{"draws":15,"losses":12,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":15,"wins":22},"gemini-4-argon":{"draws":3,"losses":44,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":17,"losses":16,"wins":27},"google/gemini-3.5-flash-lite":{"draws":30,"losses":9,"wins":45},"google/gemini-3.6-flash":{"draws":33,"losses":33,"wins":26},"google/gemini-3.8-flash":{"draws":14,"losses":23,"wins":11},"google/gemma-4-31b-it":{"draws":12,"losses":4,"wins":12},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":10,"losses":23,"wins":13},"gpt-5.4-mini":{"draws":13,"losses":7,"wins":12},"gpt-5.4-nano":{"draws":17,"losses":8,"wins":23},"gpt-5.5":{"draws":20,"losses":14,"wins":10},"gpt-5.6-luna":{"draws":17,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":35,"wins":8},"gpt-5.6-terra":{"draws":15,"losses":15,"wins":16},"gpt-6-astra":{"draws":2,"losses":44,"wins":2},"gpt-6-luna":{"draws":17,"losses":16,"wins":15},"gpt-6-sol":{"draws":8,"losses":34,"wins":6},"gpt-6.1-sol":{"draws":3,"losses":42,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":6,"wins":14},"inception/mercury-3":{"draws":11,"losses":8,"wins":13},"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":10,"losses":8,"wins":34},"meta/muse-glimmer-30b":{"draws":14,"losses":3,"wins":25},"meta/muse-spark-1.2":{"draws":10,"losses":19,"wins":17},"meta/muse-spark-1.3":{"draws":13,"losses":22,"wins":13},"meta/muse-spark-open":{"draws":11,"losses":17,"wins":18},"meta/muse-wonder":{"draws":13,"losses":29,"wins":6},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":17},"minimax/minimax-m3.1-flash":{"draws":11,"losses":9,"wins":22},"mistralai/mistral-large-4-0":{"draws":13,"losses":5,"wins":12},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":23},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":39,"wins":4},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":13},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":3,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":2,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":9},"o3":{"draws":16,"losses":21,"wins":29},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":24},"poolside/laguna-s-2.1":{"draws":17,"losses":8,"wins":21},"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":15,"losses":17,"wins":16},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":13,"losses":17,"wins":18},"qwen/qwen3.8-max-0902":{"draws":7,"losses":15,"wins":10},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":13,"wins":20},"stealth/ox-alpha":{"draws":36,"losses":66,"wins":56},"stealth/space-bunny-alpha":{"draws":9,"losses":7,"wins":22},"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":9,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":32},"thinkingmachines/inkling-small":{"draws":17,"losses":2,"wins":29},"unbiased/pareto-26.10":{"draws":0,"losses":16,"wins":0},"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":13,"losses":28,"wins":7},"x-ai/grok-4.7":{"draws":3,"losses":31,"wins":8},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":27,"losses":8,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":17,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":18,"wins":8},"z-ai/glm-5.2":{"draws":40,"losses":17,"wins":39},"z-ai/glm-5.3":{"draws":11,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":17},"z-ai/glm-5.3-flashx":{"draws":7,"losses":26,"wins":15}},"reflection/beam-1.0-501b-a23b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":11,"wins":13},"claude-fable-5":{"draws":9,"losses":22,"wins":11},"claude-fable-5-1":{"draws":1,"losses":46,"wins":1},"claude-haiku-5-5":{"draws":10,"losses":19,"wins":11},"claude-opus-4-5":{"draws":30,"losses":19,"wins":19},"claude-opus-4-8":{"draws":12,"losses":15,"wins":11},"claude-opus-5":{"draws":11,"losses":58,"wins":11},"claude-opus-5-5":{"draws":5,"losses":37,"wins":4},"claude-sonnet-5":{"draws":18,"losses":13,"wins":11},"claude-sonnet-5-5":{"draws":13,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":10},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":31},"deepseek/deepseek-v4-pro":{"draws":12,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":11,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":26,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":8},"fireworks/ember-1":{"draws":15,"losses":12,"wins":15},"gemini-3.1-pro-preview":{"draws":12,"losses":18,"wins":12},"gemini-4-argon":{"draws":1,"losses":38,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":16},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":17,"wins":26},"google/gemini-3.6-flash":{"draws":24,"losses":34,"wins":22},"google/gemini-3.8-flash":{"draws":7,"losses":22,"wins":13},"google/gemma-4-31b-it":{"draws":10,"losses":4,"wins":10},"gpt-4.1":{"draws":5,"losses":4,"wins":5},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":9,"losses":14,"wins":15},"gpt-5.4":{"draws":9,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":12,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":13,"losses":8,"wins":19},"gpt-5.5":{"draws":11,"losses":22,"wins":7},"gpt-5.6-luna":{"draws":18,"losses":11,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":8},"gpt-5.6-terra":{"draws":14,"losses":13,"wins":13},"gpt-6-astra":{"draws":4,"losses":35,"wins":3},"gpt-6-luna":{"draws":10,"losses":18,"wins":14},"gpt-6-sol":{"draws":8,"losses":26,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":35,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":12},"inception/mercury-3":{"draws":12,"losses":7,"wins":9},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":8},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":18},"meta/muse-glimmer-30b":{"draws":15,"losses":8,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":18,"wins":14},"meta/muse-spark-1.3":{"draws":8,"losses":23,"wins":11},"meta/muse-spark-open":{"draws":9,"losses":16,"wins":15},"meta/muse-wonder":{"draws":8,"losses":24,"wins":10},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":14},"minimax/minimax-m3.1-flash":{"draws":12,"losses":10,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":6,"wins":13},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":4,"wins":5},"moonshotai/kimi-k3":{"draws":13,"losses":17,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":5,"wins":10},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":5,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":6,"wins":17},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":5},"o3":{"draws":14,"losses":18,"wins":22},"openai/gpt-oss-120b":{"draws":15,"losses":9,"wins":14},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":18},"qwen/qwen3.7-max":{"draws":7,"losses":6,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":23,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":9,"losses":18,"wins":15},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":10},"recursive/flint-v1.0":{"draws":5,"losses":0,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":8,"losses":8,"wins":10},"stealth/ox-alpha":{"draws":34,"losses":61,"wins":47},"stealth/space-bunny-alpha":{"draws":14,"losses":7,"wins":13},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":16},"stepfun/step-5-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":12,"losses":21,"wins":7},"thinkingmachines/inkling":{"draws":21,"losses":11,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":10,"wins":17},"unbiased/pareto-26.10":{"draws":1,"losses":13,"wins":0},"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":13,"losses":24,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":4,"losses":30,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":11,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":14,"wins":8},"z-ai/glm-5.2":{"draws":26,"losses":27,"wins":31},"z-ai/glm-5.3":{"draws":8,"losses":24,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":11},"z-ai/glm-5.3-flashx":{"draws":9,"losses":21,"wins":12}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":39,"wins":68},"claude-fable-5":{"draws":32,"losses":111,"wins":25},"claude-fable-5-1":{"draws":6,"losses":189,"wins":1},"claude-haiku-5-5":{"draws":47,"losses":72,"wins":33},"claude-opus-4-5":{"draws":95,"losses":96,"wins":73},"claude-opus-4-8":{"draws":34,"losses":65,"wins":37},"claude-opus-5":{"draws":49,"losses":222,"wins":23},"claude-opus-5-5":{"draws":18,"losses":158,"wins":0},"claude-sonnet-5":{"draws":53,"losses":60,"wins":55},"claude-sonnet-5-5":{"draws":36,"losses":91,"wins":41},"cohere/north-mini-code":{"draws":14,"losses":12,"wins":34},"deepseek/deepseek-v4-flash":{"draws":92,"losses":63,"wins":91},"deepseek/deepseek-v4-pro":{"draws":58,"losses":52,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":48,"losses":68,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":53,"losses":77,"wins":38},"deepseek/deepseek-v4.1-flash-1017":{"draws":37,"losses":92,"wins":39},"elorian/glimpse":{"draws":35,"losses":41,"wins":18},"fireworks/ember-1":{"draws":57,"losses":77,"wins":34},"gemini-3.1-pro-preview":{"draws":43,"losses":62,"wins":63},"gemini-4-argon":{"draws":13,"losses":147,"wins":8},"google/gemini-3.1-flash-lite":{"draws":21,"losses":10,"wins":61},"google/gemini-3.5-flash":{"draws":40,"losses":100,"wins":62},"google/gemini-3.5-flash-lite":{"draws":94,"losses":78,"wins":120},"google/gemini-3.6-flash":{"draws":80,"losses":157,"wins":89},"google/gemini-3.8-flash":{"draws":43,"losses":97,"wins":28},"google/gemma-4-31b-it":{"draws":35,"losses":15,"wins":40},"gpt-4.1":{"draws":21,"losses":19,"wins":16},"gpt-4.1-nano":{"draws":16,"losses":2,"wins":10},"gpt-5":{"draws":51,"losses":58,"wins":41},"gpt-5.4":{"draws":57,"losses":77,"wins":28},"gpt-5.4-mini":{"draws":43,"losses":33,"wins":36},"gpt-5.4-nano":{"draws":37,"losses":52,"wins":57},"gpt-5.5":{"draws":58,"losses":62,"wins":36},"gpt-5.6-luna":{"draws":67,"losses":50,"wins":51},"gpt-5.6-sol":{"draws":30,"losses":115,"wins":23},"gpt-5.6-terra":{"draws":66,"losses":52,"wins":44},"gpt-6-astra":{"draws":12,"losses":156,"wins":0},"gpt-6-luna":{"draws":52,"losses":69,"wins":47},"gpt-6-sol":{"draws":20,"losses":134,"wins":14},"gpt-6.1-sol":{"draws":10,"losses":152,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":46,"losses":13,"wins":49},"inception/mercury-3":{"draws":42,"losses":45,"wins":23},"inclusionai/ling-3.0-flash":{"draws":51,"losses":18,"wins":47},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":60,"losses":38,"wins":80},"meta/muse-glimmer-30b":{"draws":54,"losses":30,"wins":66},"meta/muse-spark-1.2":{"draws":49,"losses":70,"wins":43},"meta/muse-spark-1.3":{"draws":37,"losses":102,"wins":29},"meta/muse-spark-open":{"draws":42,"losses":87,"wins":33},"meta/muse-wonder":{"draws":44,"losses":101,"wins":23},"minimax/minimax-m3":{"draws":23,"losses":20,"wins":41},"minimax/minimax-m3.1-flash":{"draws":47,"losses":43,"wins":64},"mistralai/mistral-large-4-0":{"draws":50,"losses":34,"wins":22},"mistralai/mistral-medium-3-5":{"draws":37,"losses":16,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":12,"wins":11},"moonshotai/kimi-k3":{"draws":49,"losses":68,"wins":45},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":135,"wins":19},"nex-agi/nex-n2-pro":{"draws":31,"losses":12,"wins":45},"nex-agi/nex-n2.5-pro":{"draws":14,"losses":10,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":26,"wins":60},"nvidia/nemotron-3.5-super-vl":{"draws":27,"losses":24,"wins":21},"o3":{"draws":43,"losses":97,"wins":68},"openai/gpt-oss-120b":{"draws":62,"losses":29,"wins":59},"poolside/laguna-s-2.1":{"draws":62,"losses":43,"wins":65},"qwen/qwen3.7-max":{"draws":29,"losses":29,"wins":32},"qwen/qwen3.7-plus":{"draws":20,"losses":13,"wins":37},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":72,"wins":39},"qwen/qwen3.8-27b":{"draws":43,"losses":45,"wins":32},"qwen/qwen3.8-flash":{"draws":44,"losses":44,"wins":24},"qwen/qwen3.8-max":{"draws":54,"losses":75,"wins":39},"qwen/qwen3.8-max-0902":{"draws":54,"losses":75,"wins":39},"recursive/flint-v1.0":{"draws":11,"losses":6,"wins":23},"reflection/beam-1.0-501b-a23b":{"draws":52,"losses":69,"wins":35},"stealth/ox-alpha":{"draws":135,"losses":303,"wins":164},"stealth/space-bunny-alpha":{"draws":50,"losses":39,"wins":41},"stepfun/step-3.7-flash":{"draws":36,"losses":22,"wins":60},"stepfun/step-5-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":33,"losses":22,"wins":29},"tencent/hy4-preview":{"draws":47,"losses":77,"wins":38},"thinkingmachines/inkling":{"draws":85,"losses":53,"wins":98},"thinkingmachines/inkling-small":{"draws":65,"losses":29,"wins":74},"unbiased/pareto-26.10":{"draws":3,"losses":52,"wins":1},"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":48,"losses":74,"wins":46},"x-ai/grok-4.6":{"draws":62,"losses":76,"wins":30},"x-ai/grok-4.7":{"draws":18,"losses":106,"wins":16},"x-ai/grok-build-0.1":{"draws":18,"losses":13,"wins":25},"xiaomi/mimo-v2.5":{"draws":83,"losses":47,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":30,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":26,"losses":54,"wins":26},"xiaomi/mimo-v2.6-pro":{"draws":26,"losses":64,"wins":22},"z-ai/glm-5.2":{"draws":128,"losses":102,"wins":106},"z-ai/glm-5.3":{"draws":32,"losses":109,"wins":21},"z-ai/glm-5.3-flash":{"draws":31,"losses":94,"wins":43},"z-ai/glm-5.3-flashx":{"draws":42,"losses":94,"wins":32}},"stealth/space-bunny-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":12,"wins":9},"claude-fable-5":{"draws":11,"losses":21,"wins":4},"claude-fable-5-1":{"draws":3,"losses":39,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":4},"claude-opus-4-5":{"draws":16,"losses":32,"wins":10},"claude-opus-4-8":{"draws":9,"losses":16,"wins":7},"claude-opus-5":{"draws":10,"losses":54,"wins":4},"claude-opus-5-5":{"draws":4,"losses":36,"wins":0},"claude-sonnet-5":{"draws":9,"losses":20,"wins":7},"claude-sonnet-5-5":{"draws":9,"losses":21,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":20,"losses":17,"wins":15},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":15,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":24,"wins":6},"elorian/glimpse":{"draws":6,"losses":10,"wins":4},"fireworks/ember-1":{"draws":11,"losses":19,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":18,"wins":8},"gemini-4-argon":{"draws":1,"losses":35,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":13},"google/gemini-3.5-flash":{"draws":17,"losses":18,"wins":9},"google/gemini-3.5-flash-lite":{"draws":21,"losses":18,"wins":23},"google/gemini-3.6-flash":{"draws":17,"losses":42,"wins":9},"google/gemini-3.8-flash":{"draws":7,"losses":23,"wins":6},"google/gemma-4-31b-it":{"draws":12,"losses":5,"wins":5},"gpt-4.1":{"draws":3,"losses":5,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":14,"wins":7},"gpt-5.4":{"draws":15,"losses":13,"wins":6},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":10},"gpt-5.4-nano":{"draws":9,"losses":9,"wins":14},"gpt-5.5":{"draws":18,"losses":14,"wins":2},"gpt-5.6-luna":{"draws":14,"losses":9,"wins":13},"gpt-5.6-sol":{"draws":6,"losses":30,"wins":0},"gpt-5.6-terra":{"draws":12,"losses":12,"wins":10},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":12,"losses":17,"wins":7},"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":13,"losses":5,"wins":8},"inception/mercury-3":{"draws":7,"losses":12,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":8,"wins":3},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":11,"wins":17},"meta/muse-glimmer-30b":{"draws":17,"losses":10,"wins":7},"meta/muse-spark-1.2":{"draws":12,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":26,"wins":2},"meta/muse-spark-open":{"draws":9,"losses":21,"wins":4},"meta/muse-wonder":{"draws":9,"losses":23,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":7,"wins":7},"minimax/minimax-m3.1-flash":{"draws":9,"losses":12,"wins":9},"mistralai/mistral-large-4-0":{"draws":11,"losses":10,"wins":3},"mistralai/mistral-medium-3-5":{"draws":8,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"moonshotai/kimi-k3.1-pro":{"draws":1,"losses":32,"wins":3},"nex-agi/nex-n2-pro":{"draws":8,"losses":1,"wins":11},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":0,"wins":16},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":8,"wins":4},"o3":{"draws":10,"losses":26,"wins":8},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":14},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":12,"wins":4},"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":9,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":5},"qwen/qwen3.8-max-0902":{"draws":11,"losses":21,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":18,"wins":7},"stealth/ox-alpha":{"draws":42,"losses":70,"wins":14},"stealth/space-bunny-alpha":{"draws":5,"losses":8,"wins":5},"stepfun/step-3.7-flash":{"draws":7,"losses":8,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":18,"wins":1},"thinkingmachines/inkling":{"draws":18,"losses":14,"wins":16},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":10},"unbiased/pareto-26.10":{"draws":2,"losses":10,"wins":0},"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":12,"losses":20,"wins":4},"x-ai/grok-4.7":{"draws":4,"losses":27,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":21,"losses":13,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":17,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.2":{"draws":28,"losses":26,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":19,"wins":5},"z-ai/glm-5.3-flashx":{"draws":11,"losses":20,"wins":5}},"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":12,"losses":42,"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":14,"losses":13,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":12,"losses":16,"wins":8},"elorian/glimpse":{"draws":5,"losses":9,"wins":6},"fireworks/ember-1":{"draws":14,"losses":15,"wins":7},"gemini-3.1-pro-preview":{"draws":17,"losses":11,"wins":8},"gemini-4-argon":{"draws":0,"losses":34,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":13,"losses":24,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":22,"losses":38,"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},"inception/mercury-3":{"draws":11,"losses":10,"wins":3},"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-spark-open":{"draws":12,"losses":19,"wins":3},"meta/muse-wonder":{"draws":10,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":7,"wins":6},"minimax/minimax-m3.1-flash":{"draws":11,"losses":16,"wins":7},"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},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":32,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":2,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":13},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":7,"wins":1},"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},"recursive/flint-v1.0":{"draws":3,"losses":4,"wins":3},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":9,"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":{"draws":3,"losses":9,"wins":0},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":0,"losses":6,"wins":0},"elorian/glimpse":{"draws":0,"losses":4,"wins":0},"fireworks/ember-1":{"draws":3,"losses":3,"wins":0},"gemini-3.1-pro-preview":{"draws":4,"losses":2,"wins":0},"gemini-4-argon":{"draws":0,"losses":6,"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},"inception/mercury-3":{"draws":0,"losses":5,"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-spark-open":{"draws":0,"losses":6,"wins":0},"meta/muse-wonder":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"minimax/minimax-m3.1-flash":{"draws":0,"losses":1,"wins":1},"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":0},"nvidia/nemotron-3.5-super-vl":{"draws":0,"losses":3,"wins":1},"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},"recursive/flint-v1.0":{"draws":0,"losses":2,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":0,"losses":6,"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":{"draws":0,"losses":2,"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":11,"losses":14,"wins":9},"claude-fable-5":{"draws":11,"losses":19,"wins":6},"claude-fable-5-1":{"draws":4,"losses":33,"wins":3},"claude-haiku-5-5":{"draws":13,"losses":14,"wins":7},"claude-opus-4-5":{"draws":23,"losses":23,"wins":12},"claude-opus-4-8":{"draws":9,"losses":17,"wins":6},"claude-opus-5":{"draws":12,"losses":51,"wins":9},"claude-opus-5-5":{"draws":5,"losses":35,"wins":0},"claude-sonnet-5":{"draws":13,"losses":14,"wins":9},"claude-sonnet-5-5":{"draws":12,"losses":19,"wins":5},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":3},"deepseek/deepseek-v4-flash":{"draws":18,"losses":17,"wins":17},"deepseek/deepseek-v4-pro":{"draws":13,"losses":13,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":10,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":16,"losses":15,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":11,"losses":21,"wins":4},"elorian/glimpse":{"draws":6,"losses":10,"wins":4},"fireworks/ember-1":{"draws":15,"losses":15,"wins":6},"gemini-3.1-pro-preview":{"draws":10,"losses":17,"wins":9},"gemini-4-argon":{"draws":1,"losses":33,"wins":2},"google/gemini-3.1-flash-lite":{"draws":10,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":13,"losses":19,"wins":12},"google/gemini-3.5-flash-lite":{"draws":29,"losses":9,"wins":24},"google/gemini-3.6-flash":{"draws":22,"losses":33,"wins":13},"google/gemini-3.8-flash":{"draws":17,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":11,"losses":10,"wins":11},"gpt-5.4":{"draws":17,"losses":12,"wins":5},"gpt-5.4-mini":{"draws":13,"losses":6,"wins":5},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":16},"gpt-5.5":{"draws":16,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":14,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":28,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":6},"gpt-6-astra":{"draws":6,"losses":30,"wins":0},"gpt-6-luna":{"draws":12,"losses":16,"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":15,"losses":4,"wins":5},"inception/mercury-3":{"draws":9,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":14,"losses":1,"wins":9},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":5},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":6},"meta/muse-spark-open":{"draws":9,"losses":16,"wins":9},"meta/muse-wonder":{"draws":9,"losses":21,"wins":6},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":8},"minimax/minimax-m3.1-flash":{"draws":9,"losses":8,"wins":13},"mistralai/mistral-large-4-0":{"draws":12,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":26,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":7,"wins":3},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":6,"wins":6},"nvidia/nemotron-3.5-super-vl":{"draws":7,"losses":6,"wins":3},"o3":{"draws":12,"losses":18,"wins":12},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":17,"wins":6},"qwen/qwen3.8-27b":{"draws":7,"losses":11,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":6},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":20,"wins":5},"stealth/ox-alpha":{"draws":36,"losses":67,"wins":21},"stealth/space-bunny-alpha":{"draws":14,"losses":10,"wins":4},"stepfun/step-3.7-flash":{"draws":11,"losses":4,"wins":7},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":16,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":5,"wins":12},"unbiased/pareto-26.10":{"draws":0,"losses":12,"wins":0},"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":14,"losses":18,"wins":4},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":2},"x-ai/grok-4.7":{"draws":9,"losses":23,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":28,"losses":11,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":13,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":15,"wins":7},"z-ai/glm-5.2":{"draws":31,"losses":23,"wins":18},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":6},"z-ai/glm-5.3-flashx":{"draws":10,"losses":21,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":7,"losses":39,"wins":2},"claude-fable-5-1":{"draws":3,"losses":51,"wins":0},"claude-haiku-5-5":{"draws":11,"losses":20,"wins":15},"claude-opus-4-5":{"draws":27,"losses":30,"wins":21},"claude-opus-4-8":{"draws":12,"losses":21,"wins":11},"claude-opus-5":{"draws":9,"losses":64,"wins":9},"claude-opus-5-5":{"draws":2,"losses":49,"wins":1},"claude-sonnet-5":{"draws":14,"losses":19,"wins":15},"claude-sonnet-5-5":{"draws":10,"losses":27,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":4,"wins":9},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":32},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":21,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":31,"wins":7},"elorian/glimpse":{"draws":5,"losses":14,"wins":7},"fireworks/ember-1":{"draws":18,"losses":20,"wins":10},"gemini-3.1-pro-preview":{"draws":15,"losses":17,"wins":16},"gemini-4-argon":{"draws":1,"losses":45,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":14,"losses":31,"wins":15},"google/gemini-3.5-flash-lite":{"draws":22,"losses":28,"wins":34},"google/gemini-3.6-flash":{"draws":26,"losses":43,"wins":23},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":9},"google/gemma-4-31b-it":{"draws":11,"losses":7,"wins":10},"gpt-4.1":{"draws":7,"losses":7,"wins":2},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":11,"losses":16,"wins":15},"gpt-5.4":{"draws":12,"losses":27,"wins":7},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":15,"wins":25},"gpt-5.5":{"draws":16,"losses":18,"wins":10},"gpt-5.6-luna":{"draws":20,"losses":11,"wins":17},"gpt-5.6-sol":{"draws":8,"losses":35,"wins":5},"gpt-5.6-terra":{"draws":15,"losses":20,"wins":11},"gpt-6-astra":{"draws":3,"losses":45,"wins":0},"gpt-6-luna":{"draws":19,"losses":19,"wins":10},"gpt-6-sol":{"draws":9,"losses":37,"wins":2},"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":13,"losses":7,"wins":14},"inception/mercury-3":{"draws":10,"losses":15,"wins":7},"inclusionai/ling-3.0-flash":{"draws":11,"losses":7,"wins":16},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":17,"losses":10,"wins":25},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":12,"losses":22,"wins":12},"meta/muse-spark-1.3":{"draws":9,"losses":28,"wins":11},"meta/muse-spark-open":{"draws":9,"losses":28,"wins":9},"meta/muse-wonder":{"draws":12,"losses":31,"wins":5},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":16},"minimax/minimax-m3.1-flash":{"draws":13,"losses":15,"wins":14},"mistralai/mistral-large-4-0":{"draws":9,"losses":11,"wins":10},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":14,"losses":18,"wins":14},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":9,"wins":18},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":8,"losses":38,"wins":20},"openai/gpt-oss-120b":{"draws":16,"losses":10,"wins":16},"poolside/laguna-s-2.1":{"draws":6,"losses":17,"wins":23},"qwen/qwen3.7-max":{"draws":7,"losses":10,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":22,"wins":9},"qwen/qwen3.8-27b":{"draws":9,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":10},"qwen/qwen3.8-max":{"draws":16,"losses":16,"wins":16},"qwen/qwen3.8-max-0902":{"draws":15,"losses":22,"wins":11},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":15,"losses":14,"wins":15},"stealth/ox-alpha":{"draws":33,"losses":85,"wins":40},"stealth/space-bunny-alpha":{"draws":13,"losses":14,"wins":11},"stepfun/step-3.7-flash":{"draws":6,"losses":10,"wins":18},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":11,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":5,"losses":18,"wins":7},"thinkingmachines/inkling":{"draws":16,"losses":13,"wins":35},"thinkingmachines/inkling-small":{"draws":16,"losses":9,"wins":23},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":15,"losses":25,"wins":8},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":32,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.5":{"draws":28,"losses":15,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":15,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":23,"losses":33,"wins":40},"z-ai/glm-5.3":{"draws":8,"losses":31,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":15,"losses":23,"wins":10}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":21},"claude-fable-5":{"draws":16,"losses":49,"wins":7},"claude-fable-5-1":{"draws":6,"losses":75,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":42,"wins":12},"claude-opus-4-5":{"draws":40,"losses":51,"wins":25},"claude-opus-4-8":{"draws":19,"losses":35,"wins":10},"claude-opus-5":{"draws":17,"losses":97,"wins":16},"claude-opus-5-5":{"draws":7,"losses":69,"wins":0},"claude-sonnet-5":{"draws":24,"losses":36,"wins":12},"claude-sonnet-5-5":{"draws":15,"losses":43,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":9,"wins":10},"deepseek/deepseek-v4-flash":{"draws":36,"losses":36,"wins":32},"deepseek/deepseek-v4-pro":{"draws":21,"losses":31,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":23,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":25,"losses":31,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":45,"wins":11},"elorian/glimpse":{"draws":13,"losses":18,"wins":9},"fireworks/ember-1":{"draws":24,"losses":34,"wins":14},"gemini-3.1-pro-preview":{"draws":21,"losses":30,"wins":21},"gemini-4-argon":{"draws":5,"losses":62,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":16,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":52,"wins":19},"google/gemini-3.5-flash-lite":{"draws":31,"losses":52,"wins":45},"google/gemini-3.6-flash":{"draws":46,"losses":77,"wins":17},"google/gemini-3.8-flash":{"draws":13,"losses":49,"wins":10},"google/gemma-4-31b-it":{"draws":18,"losses":12,"wins":10},"gpt-4.1":{"draws":5,"losses":10,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":1,"wins":1},"gpt-5":{"draws":14,"losses":34,"wins":16},"gpt-5.4":{"draws":19,"losses":40,"wins":11},"gpt-5.4-mini":{"draws":16,"losses":17,"wins":15},"gpt-5.4-nano":{"draws":11,"losses":31,"wins":26},"gpt-5.5":{"draws":18,"losses":38,"wins":12},"gpt-5.6-luna":{"draws":23,"losses":30,"wins":19},"gpt-5.6-sol":{"draws":12,"losses":53,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":30,"wins":17},"gpt-6-astra":{"draws":3,"losses":69,"wins":0},"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":67,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":17,"losses":14,"wins":17},"inception/mercury-3":{"draws":16,"losses":20,"wins":8},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":19},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":20,"losses":24,"wins":32},"meta/muse-glimmer-30b":{"draws":25,"losses":17,"wins":24},"meta/muse-spark-1.2":{"draws":21,"losses":31,"wins":18},"meta/muse-spark-1.3":{"draws":16,"losses":47,"wins":9},"meta/muse-spark-open":{"draws":15,"losses":41,"wins":14},"meta/muse-wonder":{"draws":12,"losses":47,"wins":13},"minimax/minimax-m3":{"draws":10,"losses":13,"wins":15},"minimax/minimax-m3.1-flash":{"draws":15,"losses":31,"wins":20},"mistralai/mistral-large-4-0":{"draws":16,"losses":20,"wins":10},"mistralai/mistral-medium-3-5":{"draws":14,"losses":10,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":11,"wins":4},"moonshotai/kimi-k3":{"draws":22,"losses":30,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":7,"losses":61,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":18},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":22,"wins":20},"nvidia/nemotron-3.5-super-vl":{"draws":10,"losses":14,"wins":8},"o3":{"draws":12,"losses":61,"wins":23},"openai/gpt-oss-120b":{"draws":15,"losses":24,"wins":23},"poolside/laguna-s-2.1":{"draws":19,"losses":29,"wins":22},"qwen/qwen3.7-max":{"draws":14,"losses":19,"wins":7},"qwen/qwen3.7-plus":{"draws":11,"losses":14,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":33,"wins":16},"qwen/qwen3.8-27b":{"draws":12,"losses":26,"wins":14},"qwen/qwen3.8-flash":{"draws":13,"losses":24,"wins":11},"qwen/qwen3.8-max":{"draws":24,"losses":35,"wins":13},"qwen/qwen3.8-max-0902":{"draws":19,"losses":41,"wins":12},"recursive/flint-v1.0":{"draws":6,"losses":7,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":36,"wins":12},"stealth/ox-alpha":{"draws":58,"losses":140,"wins":52},"stealth/space-bunny-alpha":{"draws":19,"losses":21,"wins":18},"stepfun/step-3.7-flash":{"draws":12,"losses":28,"wins":10},"stepfun/step-5-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy3-preview":{"draws":13,"losses":17,"wins":10},"tencent/hy4-preview":{"draws":25,"losses":38,"wins":7},"thinkingmachines/inkling":{"draws":30,"losses":20,"wins":28},"thinkingmachines/inkling-small":{"draws":25,"losses":21,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":23,"wins":0},"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":18,"losses":41,"wins":13},"x-ai/grok-4.6":{"draws":27,"losses":35,"wins":10},"x-ai/grok-4.7":{"draws":5,"losses":50,"wins":7},"x-ai/grok-build-0.1":{"draws":7,"losses":11,"wins":6},"xiaomi/mimo-v2.5":{"draws":36,"losses":45,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":22,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":26,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":14,"losses":30,"wins":4},"z-ai/glm-5.2":{"draws":51,"losses":56,"wins":37},"z-ai/glm-5.3":{"draws":15,"losses":43,"wins":10},"z-ai/glm-5.3-flash":{"draws":19,"losses":40,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":43,"wins":13}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":21,"wins":7},"claude-fable-5":{"draws":6,"losses":37,"wins":5},"claude-fable-5-1":{"draws":4,"losses":50,"wins":0},"claude-haiku-5-5":{"draws":12,"losses":29,"wins":5},"claude-opus-4-5":{"draws":24,"losses":47,"wins":7},"claude-opus-4-8":{"draws":12,"losses":30,"wins":2},"claude-opus-5":{"draws":11,"losses":68,"wins":3},"claude-opus-5-5":{"draws":3,"losses":49,"wins":0},"claude-sonnet-5":{"draws":17,"losses":24,"wins":7},"claude-sonnet-5-5":{"draws":10,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":5,"losses":9,"wins":4},"deepseek/deepseek-v4-flash":{"draws":30,"losses":30,"wins":12},"deepseek/deepseek-v4-pro":{"draws":17,"losses":22,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":31,"wins":8},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":35,"wins":3},"elorian/glimpse":{"draws":6,"losses":15,"wins":5},"fireworks/ember-1":{"draws":15,"losses":29,"wins":4},"gemini-3.1-pro-preview":{"draws":16,"losses":27,"wins":5},"gemini-4-argon":{"draws":8,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":11,"losses":14,"wins":7},"google/gemini-3.5-flash":{"draws":16,"losses":36,"wins":8},"google/gemini-3.5-flash-lite":{"draws":24,"losses":37,"wins":23},"google/gemini-3.6-flash":{"draws":24,"losses":51,"wins":17},"google/gemini-3.8-flash":{"draws":11,"losses":33,"wins":4},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":5},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":15,"losses":21,"wins":6},"gpt-5.4":{"draws":13,"losses":27,"wins":6},"gpt-5.4-mini":{"draws":12,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":14,"losses":20,"wins":14},"gpt-5.5":{"draws":12,"losses":27,"wins":5},"gpt-5.6-luna":{"draws":22,"losses":19,"wins":7},"gpt-5.6-sol":{"draws":10,"losses":36,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":28,"wins":2},"gpt-6-astra":{"draws":2,"losses":46,"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":15,"losses":10,"wins":9},"inception/mercury-3":{"draws":11,"losses":18,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":12,"wins":8},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":16,"losses":24,"wins":12},"meta/muse-glimmer-30b":{"draws":16,"losses":18,"wins":8},"meta/muse-spark-1.2":{"draws":13,"losses":26,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":32,"wins":4},"meta/muse-spark-open":{"draws":12,"losses":32,"wins":2},"meta/muse-wonder":{"draws":12,"losses":34,"wins":2},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":8},"minimax/minimax-m3.1-flash":{"draws":15,"losses":23,"wins":4},"mistralai/mistral-large-4-0":{"draws":12,"losses":14,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":15,"losses":25,"wins":6},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":39,"wins":3},"nex-agi/nex-n2-pro":{"draws":7,"losses":9,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":19,"wins":11},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":13,"wins":3},"o3":{"draws":11,"losses":41,"wins":14},"openai/gpt-oss-120b":{"draws":16,"losses":18,"wins":8},"poolside/laguna-s-2.1":{"draws":15,"losses":23,"wins":8},"qwen/qwen3.7-max":{"draws":8,"losses":15,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":6,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":33,"wins":4},"qwen/qwen3.8-27b":{"draws":8,"losses":20,"wins":6},"qwen/qwen3.8-flash":{"draws":10,"losses":17,"wins":5},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":14},"qwen/qwen3.8-max-0902":{"draws":15,"losses":29,"wins":4},"recursive/flint-v1.0":{"draws":4,"losses":6,"wins":4},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":24,"wins":9},"stealth/ox-alpha":{"draws":39,"losses":92,"wins":27},"stealth/space-bunny-alpha":{"draws":13,"losses":17,"wins":8},"stepfun/step-3.7-flash":{"draws":7,"losses":13,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":6},"tencent/hy4-preview":{"draws":12,"losses":28,"wins":6},"thinkingmachines/inkling":{"draws":28,"losses":27,"wins":9},"thinkingmachines/inkling-small":{"draws":12,"losses":12,"wins":8},"unbiased/pareto-26.10":{"draws":1,"losses":15,"wins":0},"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":14,"losses":31,"wins":3},"x-ai/grok-4.6":{"draws":11,"losses":33,"wins":4},"x-ai/grok-4.7":{"draws":6,"losses":36,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":5,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":33,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":21,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":24,"wins":4},"z-ai/glm-5.2":{"draws":33,"losses":47,"wins":16},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":31,"wins":9},"z-ai/glm-5.3-flashx":{"draws":9,"losses":33,"wins":6}},"unbiased/pareto-26.10":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":42},"claude-fable-5":{"draws":1,"losses":4,"wins":43},"claude-fable-5-1":{"draws":7,"losses":21,"wins":26},"claude-haiku-5-5":{"draws":4,"losses":4,"wins":38},"claude-opus-4-5":{"draws":6,"losses":0,"wins":72},"claude-opus-4-8":{"draws":4,"losses":4,"wins":36},"claude-opus-5":{"draws":7,"losses":24,"wins":51},"claude-opus-5-5":{"draws":4,"losses":27,"wins":21},"claude-sonnet-5":{"draws":4,"losses":1,"wins":43},"claude-sonnet-5-5":{"draws":4,"losses":8,"wins":36},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":68},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":44},"deepseek/deepseek-v4.1-flash-1017":{"draws":6,"losses":2,"wins":40},"elorian/glimpse":{"draws":1,"losses":0,"wins":25},"fireworks/ember-1":{"draws":2,"losses":1,"wins":45},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":42},"gemini-4-argon":{"draws":4,"losses":13,"wins":31},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":50},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":79},"google/gemini-3.6-flash":{"draws":8,"losses":3,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":5,"wins":39},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":26},"gpt-4.1":{"draws":1,"losses":1,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":41},"gpt-5.4":{"draws":4,"losses":4,"wins":38},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":30},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":43},"gpt-5.5":{"draws":2,"losses":5,"wins":37},"gpt-5.6-luna":{"draws":3,"losses":1,"wins":44},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":41},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":42},"gpt-6-astra":{"draws":8,"losses":22,"wins":18},"gpt-6-luna":{"draws":3,"losses":1,"wins":44},"gpt-6-sol":{"draws":3,"losses":7,"wins":38},"gpt-6.1-sol":{"draws":6,"losses":17,"wins":25},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":33},"inception/mercury-3":{"draws":2,"losses":1,"wins":29},"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":0,"wins":51},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":40},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":44},"meta/muse-spark-1.3":{"draws":3,"losses":0,"wins":45},"meta/muse-spark-open":{"draws":2,"losses":2,"wins":42},"meta/muse-wonder":{"draws":6,"losses":8,"wins":34},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":25},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"mistralai/mistral-large-4-0":{"draws":3,"losses":1,"wins":26},"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":3,"losses":1,"wins":42},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":15,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":2,"losses":0,"wins":20},"o3":{"draws":0,"losses":0,"wins":66},"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":5,"losses":1,"wins":42},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":32},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":28},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":47},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":44},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":2,"losses":0,"wins":42},"stealth/ox-alpha":{"draws":11,"losses":4,"wins":143},"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":1,"losses":0,"wins":25},"tencent/hy4-preview":{"draws":3,"losses":2,"wins":41},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":63},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":45},"unbiased/pareto-26.10-preview":{"draws":0,"losses":8,"wins":8},"upstage/solar-mini4":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":3,"losses":1,"wins":44},"x-ai/grok-4.6":{"draws":6,"losses":2,"wins":40},"x-ai/grok-4.7":{"draws":5,"losses":10,"wins":27},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":15},"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":2,"losses":1,"wins":27},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":30},"z-ai/glm-5.2":{"draws":4,"losses":1,"wins":91},"z-ai/glm-5.3":{"draws":5,"losses":4,"wins":37},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":39},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":39}},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":1,"losses":10,"wins":37},"elorian/glimpse":{"draws":0,"losses":2,"wins":24},"fireworks/ember-1":{"draws":1,"losses":1,"wins":46},"gemini-3.1-pro-preview":{"draws":1,"losses":1,"wins":46},"gemini-4-argon":{"draws":3,"losses":18,"wins":27},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":31},"google/gemini-3.5-flash":{"draws":2,"losses":5,"wins":53},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":81},"google/gemini-3.6-flash":{"draws":3,"losses":9,"wins":80},"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},"inception/mercury-3":{"draws":0,"losses":2,"wins":30},"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-spark-open":{"draws":0,"losses":3,"wins":43},"meta/muse-wonder":{"draws":4,"losses":9,"wins":35},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":26},"minimax/minimax-m3.1-flash":{"draws":1,"losses":1,"wins":40},"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},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":16,"wins":27},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":24},"nex-agi/nex-n2.5-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":41},"nvidia/nemotron-3.5-super-vl":{"draws":3,"losses":0,"wins":19},"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},"recursive/flint-v1.0":{"draws":0,"losses":0,"wins":14},"reflection/beam-1.0-501b-a23b":{"draws":1,"losses":0,"wins":43},"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},"unbiased/pareto-26.10":{"draws":0,"losses":8,"wins":8},"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},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":2,"wins":0},"elorian/glimpse":{"draws":4,"losses":0,"wins":0},"fireworks/ember-1":{"draws":5,"losses":1,"wins":0},"gemini-3.1-pro-preview":{"draws":3,"losses":3,"wins":0},"gemini-4-argon":{"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},"inception/mercury-3":{"draws":2,"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-spark-open":{"draws":2,"losses":2,"wins":2},"meta/muse-wonder":{"draws":3,"losses":3,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"minimax/minimax-m3.1-flash":{"draws":6,"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},"moonshotai/kimi-k3.1-pro":{"draws":0,"losses":6,"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},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":0,"wins":0},"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},"recursive/flint-v1.0":{"draws":2,"losses":0,"wins":0},"reflection/beam-1.0-501b-a23b":{"draws":4,"losses":2,"wins":0},"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":{"draws":0,"losses":2,"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":12,"losses":10,"wins":22},"claude-fable-5":{"draws":9,"losses":31,"wins":8},"claude-fable-5-1":{"draws":4,"losses":47,"wins":3},"claude-haiku-5-5":{"draws":11,"losses":19,"wins":16},"claude-opus-4-5":{"draws":27,"losses":25,"wins":26},"claude-opus-4-8":{"draws":17,"losses":15,"wins":12},"claude-opus-5":{"draws":15,"losses":53,"wins":14},"claude-opus-5-5":{"draws":4,"losses":41,"wins":7},"claude-sonnet-5":{"draws":18,"losses":12,"wins":18},"claude-sonnet-5-5":{"draws":15,"losses":20,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":17,"losses":16,"wins":39},"deepseek/deepseek-v4-pro":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":17,"wins":19},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":25,"wins":14},"elorian/glimpse":{"draws":5,"losses":11,"wins":10},"fireworks/ember-1":{"draws":16,"losses":13,"wins":19},"gemini-3.1-pro-preview":{"draws":13,"losses":17,"wins":18},"gemini-4-argon":{"draws":5,"losses":33,"wins":10},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":21},"google/gemini-3.5-flash-lite":{"draws":30,"losses":15,"wins":39},"google/gemini-3.6-flash":{"draws":22,"losses":43,"wins":27},"google/gemini-3.8-flash":{"draws":12,"losses":20,"wins":16},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":17},"gpt-4.1":{"draws":4,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":18,"wins":16},"gpt-5.4":{"draws":9,"losses":26,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":7,"wins":13},"gpt-5.4-nano":{"draws":11,"losses":9,"wins":28},"gpt-5.5":{"draws":11,"losses":20,"wins":13},"gpt-5.6-luna":{"draws":15,"losses":14,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":32,"wins":11},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":14},"gpt-6-astra":{"draws":4,"losses":39,"wins":5},"gpt-6-luna":{"draws":17,"losses":15,"wins":16},"gpt-6-sol":{"draws":6,"losses":30,"wins":12},"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":14,"losses":2,"wins":18},"inception/mercury-3":{"draws":12,"losses":9,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":3,"wins":20},"inclusionai/ling-3.1-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":14,"losses":13,"wins":25},"meta/muse-glimmer-30b":{"draws":14,"losses":6,"wins":22},"meta/muse-spark-1.2":{"draws":14,"losses":15,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-spark-open":{"draws":12,"losses":20,"wins":14},"meta/muse-wonder":{"draws":9,"losses":28,"wins":11},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":15},"minimax/minimax-m3.1-flash":{"draws":12,"losses":13,"wins":17},"mistralai/mistral-large-4-0":{"draws":7,"losses":13,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":7},"moonshotai/kimi-k3":{"draws":11,"losses":18,"wins":17},"moonshotai/kimi-k3.1-pro":{"draws":8,"losses":33,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":7,"wins":21},"nvidia/nemotron-3.5-super-vl":{"draws":9,"losses":4,"wins":9},"o3":{"draws":7,"losses":28,"wins":31},"openai/gpt-oss-120b":{"draws":15,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":16,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":16},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":10},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":18,"wins":15},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":14},"recursive/flint-v1.0":{"draws":6,"losses":0,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":14,"losses":18,"wins":12},"stealth/ox-alpha":{"draws":39,"losses":69,"wins":50},"stealth/space-bunny-alpha":{"draws":14,"losses":9,"wins":15},"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":11,"losses":5,"wins":10},"tencent/hy4-preview":{"draws":11,"losses":22,"wins":13},"thinkingmachines/inkling":{"draws":19,"losses":12,"wins":33},"thinkingmachines/inkling-small":{"draws":16,"losses":5,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":10,"losses":16,"wins":6},"x-ai/grok-4.6":{"draws":17,"losses":22,"wins":9},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":7,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":13,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":9},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":29,"wins":13},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":13}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":7,"wins":19},"claude-fable-5":{"draws":13,"losses":30,"wins":5},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":16,"losses":17,"wins":13},"claude-opus-4-5":{"draws":26,"losses":23,"wins":29},"claude-opus-4-8":{"draws":10,"losses":21,"wins":13},"claude-opus-5":{"draws":17,"losses":59,"wins":6},"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":27,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":23,"losses":16,"wins":33},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":22,"wins":11},"deepseek/deepseek-v4.1-flash-1017":{"draws":16,"losses":26,"wins":6},"elorian/glimpse":{"draws":7,"losses":12,"wins":7},"fireworks/ember-1":{"draws":17,"losses":23,"wins":8},"gemini-3.1-pro-preview":{"draws":16,"losses":14,"wins":18},"gemini-4-argon":{"draws":5,"losses":42,"wins":1},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":21},"google/gemini-3.5-flash":{"draws":19,"losses":19,"wins":22},"google/gemini-3.5-flash-lite":{"draws":27,"losses":18,"wins":39},"google/gemini-3.6-flash":{"draws":34,"losses":36,"wins":22},"google/gemini-3.8-flash":{"draws":17,"losses":24,"wins":7},"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":15,"losses":13,"wins":14},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":13,"losses":9,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":17,"wins":21},"gpt-5.5":{"draws":20,"losses":17,"wins":7},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":21},"gpt-5.6-sol":{"draws":10,"losses":29,"wins":9},"gpt-5.6-terra":{"draws":22,"losses":11,"wins":13},"gpt-6-astra":{"draws":5,"losses":43,"wins":0},"gpt-6-luna":{"draws":20,"losses":11,"wins":17},"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":14,"losses":5,"wins":15},"inception/mercury-3":{"draws":12,"losses":10,"wins":10},"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":19,"losses":16,"wins":17},"meta/muse-glimmer-30b":{"draws":20,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":14,"losses":14,"wins":18},"meta/muse-spark-1.3":{"draws":15,"losses":22,"wins":11},"meta/muse-spark-open":{"draws":14,"losses":23,"wins":9},"meta/muse-wonder":{"draws":20,"losses":26,"wins":2},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":16},"minimax/minimax-m3.1-flash":{"draws":14,"losses":15,"wins":13},"mistralai/mistral-large-4-0":{"draws":13,"losses":7,"wins":10},"mistralai/mistral-medium-3-5":{"draws":13,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":10,"wins":20},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":41,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":8,"losses":6,"wins":8},"o3":{"draws":12,"losses":25,"wins":29},"openai/gpt-oss-120b":{"draws":18,"losses":7,"wins":17},"poolside/laguna-s-2.1":{"draws":21,"losses":10,"wins":15},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.7-plus":{"draws":7,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":20,"wins":10},"qwen/qwen3.8-27b":{"draws":13,"losses":13,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":10,"wins":8},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":10},"qwen/qwen3.8-max-0902":{"draws":17,"losses":15,"wins":16},"recursive/flint-v1.0":{"draws":3,"losses":3,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":18,"losses":12,"wins":14},"stealth/ox-alpha":{"draws":59,"losses":74,"wins":25},"stealth/space-bunny-alpha":{"draws":12,"losses":11,"wins":15},"stepfun/step-3.7-flash":{"draws":9,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":18,"losses":18,"wins":10},"thinkingmachines/inkling":{"draws":25,"losses":12,"wins":27},"thinkingmachines/inkling-small":{"draws":16,"losses":10,"wins":22},"unbiased/pareto-26.10":{"draws":4,"losses":12,"wins":0},"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":25,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":17,"wins":1},"x-ai/grok-4.7":{"draws":5,"losses":33,"wins":4},"x-ai/grok-build-0.1":{"draws":9,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":16,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":6,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":19,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":22,"wins":5},"z-ai/glm-5.2":{"draws":35,"losses":28,"wins":33},"z-ai/glm-5.3":{"draws":10,"losses":31,"wins":5},"z-ai/glm-5.3-flash":{"draws":15,"losses":22,"wins":11},"z-ai/glm-5.3-flashx":{"draws":10,"losses":31,"wins":7}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":13,"wins":20},"claude-fable-5":{"draws":6,"losses":25,"wins":11},"claude-fable-5-1":{"draws":3,"losses":40,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":12,"wins":18},"claude-opus-4-5":{"draws":13,"losses":27,"wins":30},"claude-opus-4-8":{"draws":10,"losses":18,"wins":14},"claude-opus-5":{"draws":7,"losses":47,"wins":16},"claude-opus-5-5":{"draws":4,"losses":36,"wins":6},"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":16,"losses":10,"wins":38},"deepseek/deepseek-v4-pro":{"draws":5,"losses":12,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":16,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":24,"wins":11},"elorian/glimpse":{"draws":4,"losses":12,"wins":6},"fireworks/ember-1":{"draws":6,"losses":13,"wins":23},"gemini-3.1-pro-preview":{"draws":7,"losses":15,"wins":20},"gemini-4-argon":{"draws":8,"losses":29,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":28},"google/gemini-3.5-flash":{"draws":11,"losses":16,"wins":27},"google/gemini-3.5-flash-lite":{"draws":14,"losses":20,"wins":40},"google/gemini-3.6-flash":{"draws":10,"losses":39,"wins":31},"google/gemini-3.8-flash":{"draws":8,"losses":14,"wins":20},"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":5,"losses":15,"wins":16},"gpt-5.4":{"draws":8,"losses":14,"wins":18},"gpt-5.4-mini":{"draws":8,"losses":3,"wins":17},"gpt-5.4-nano":{"draws":10,"losses":7,"wins":29},"gpt-5.5":{"draws":7,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":9,"losses":10,"wins":23},"gpt-5.6-sol":{"draws":5,"losses":26,"wins":11},"gpt-5.6-terra":{"draws":7,"losses":15,"wins":18},"gpt-6-astra":{"draws":1,"losses":36,"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":31,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":20},"inception/mercury-3":{"draws":6,"losses":7,"wins":15},"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":7,"losses":20,"wins":13},"meta/muse-spark-1.3":{"draws":7,"losses":19,"wins":16},"meta/muse-spark-open":{"draws":7,"losses":16,"wins":17},"meta/muse-wonder":{"draws":10,"losses":18,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":15},"minimax/minimax-m3.1-flash":{"draws":5,"losses":16,"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":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":18,"wins":15},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":15},"nex-agi/nex-n2.5-pro":{"draws":1,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":7,"wins":28},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":6,"wins":10},"o3":{"draws":8,"losses":24,"wins":30},"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":5,"losses":6,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":15},"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":8,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":11,"losses":16,"wins":15},"recursive/flint-v1.0":{"draws":2,"losses":1,"wins":11},"reflection/beam-1.0-501b-a23b":{"draws":9,"losses":6,"wins":23},"stealth/ox-alpha":{"draws":25,"losses":45,"wins":48},"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":19,"wins":13},"thinkingmachines/inkling":{"draws":11,"losses":9,"wins":34},"thinkingmachines/inkling-small":{"draws":10,"losses":1,"wins":31},"unbiased/pareto-26.10":{"draws":2,"losses":11,"wins":1},"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":9,"losses":19,"wins":14},"x-ai/grok-4.6":{"draws":8,"losses":17,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":18,"wins":5},"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":22,"wins":40},"z-ai/glm-5.3":{"draws":10,"losses":18,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":19,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":17,"wins":16}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":38,"wins":36},"claude-fable-5":{"draws":13,"losses":87,"wins":2},"claude-fable-5-1":{"draws":6,"losses":104,"wins":2},"claude-haiku-5-5":{"draws":17,"losses":63,"wins":20},"claude-opus-4-5":{"draws":42,"losses":92,"wins":34},"claude-opus-4-8":{"draws":13,"losses":65,"wins":20},"claude-opus-5":{"draws":22,"losses":138,"wins":6},"claude-opus-5-5":{"draws":4,"losses":106,"wins":0},"claude-sonnet-5":{"draws":22,"losses":57,"wins":23},"claude-sonnet-5-5":{"draws":13,"losses":74,"wins":15},"cohere/north-mini-code":{"draws":8,"losses":13,"wins":19},"deepseek/deepseek-v4-flash":{"draws":32,"losses":64,"wins":58},"deepseek/deepseek-v4-pro":{"draws":28,"losses":50,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":47,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":60,"wins":22},"deepseek/deepseek-v4.1-flash-1017":{"draws":13,"losses":79,"wins":10},"elorian/glimpse":{"draws":13,"losses":33,"wins":8},"fireworks/ember-1":{"draws":24,"losses":54,"wins":24},"gemini-3.1-pro-preview":{"draws":18,"losses":51,"wins":33},"gemini-4-argon":{"draws":7,"losses":95,"wins":0},"google/gemini-3.1-flash-lite":{"draws":13,"losses":23,"wins":42},"google/gemini-3.5-flash":{"draws":25,"losses":75,"wins":32},"google/gemini-3.5-flash-lite":{"draws":35,"losses":73,"wins":76},"google/gemini-3.6-flash":{"draws":39,"losses":121,"wins":38},"google/gemini-3.8-flash":{"draws":23,"losses":68,"wins":11},"google/gemma-4-31b-it":{"draws":19,"losses":16,"wins":25},"gpt-4.1":{"draws":8,"losses":18,"wins":8},"gpt-4.1-nano":{"draws":3,"losses":1,"wins":6},"gpt-5":{"draws":19,"losses":48,"wins":23},"gpt-5.4":{"draws":20,"losses":71,"wins":9},"gpt-5.4-mini":{"draws":19,"losses":25,"wins":24},"gpt-5.4-nano":{"draws":19,"losses":53,"wins":40},"gpt-5.5":{"draws":35,"losses":47,"wins":12},"gpt-5.6-luna":{"draws":23,"losses":47,"wins":32},"gpt-5.6-sol":{"draws":11,"losses":82,"wins":9},"gpt-5.6-terra":{"draws":23,"losses":63,"wins":10},"gpt-6-astra":{"draws":7,"losses":94,"wins":1},"gpt-6-luna":{"draws":21,"losses":64,"wins":17},"gpt-6-sol":{"draws":15,"losses":77,"wins":10},"gpt-6.1-sol":{"draws":5,"losses":91,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":22,"losses":12,"wins":38},"inception/mercury-3":{"draws":17,"losses":34,"wins":13},"inclusionai/ling-3.0-flash":{"draws":26,"losses":18,"wins":28},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":25,"losses":44,"wins":45},"meta/muse-glimmer-30b":{"draws":25,"losses":30,"wins":33},"meta/muse-spark-1.2":{"draws":23,"losses":57,"wins":16},"meta/muse-spark-1.3":{"draws":17,"losses":72,"wins":13},"meta/muse-spark-open":{"draws":17,"losses":71,"wins":12},"meta/muse-wonder":{"draws":10,"losses":83,"wins":9},"minimax/minimax-m3":{"draws":11,"losses":18,"wins":27},"minimax/minimax-m3.1-flash":{"draws":16,"losses":49,"wins":27},"mistralai/mistral-large-4-0":{"draws":22,"losses":28,"wins":12},"mistralai/mistral-medium-3-5":{"draws":15,"losses":15,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":12,"wins":9},"moonshotai/kimi-k3":{"draws":26,"losses":54,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":11,"losses":86,"wins":5},"nex-agi/nex-n2-pro":{"draws":9,"losses":16,"wins":25},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":9,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":29,"wins":40},"nvidia/nemotron-3.5-super-vl":{"draws":11,"losses":22,"wins":13},"o3":{"draws":22,"losses":99,"wins":39},"openai/gpt-oss-120b":{"draws":17,"losses":35,"wins":34},"poolside/laguna-s-2.1":{"draws":26,"losses":40,"wins":30},"qwen/qwen3.7-max":{"draws":15,"losses":28,"wins":19},"qwen/qwen3.7-plus":{"draws":11,"losses":22,"wins":23},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":56,"wins":15},"qwen/qwen3.8-27b":{"draws":12,"losses":45,"wins":19},"qwen/qwen3.8-flash":{"draws":19,"losses":30,"wins":19},"qwen/qwen3.8-max":{"draws":20,"losses":57,"wins":25},"qwen/qwen3.8-max-0902":{"draws":27,"losses":62,"wins":13},"recursive/flint-v1.0":{"draws":4,"losses":12,"wins":16},"reflection/beam-1.0-501b-a23b":{"draws":21,"losses":51,"wins":18},"stealth/ox-alpha":{"draws":60,"losses":199,"wins":51},"stealth/space-bunny-alpha":{"draws":19,"losses":35,"wins":28},"stepfun/step-3.7-flash":{"draws":18,"losses":29,"wins":31},"stepfun/step-5-preview":{"draws":3,"losses":5,"wins":0},"tencent/hy3-preview":{"draws":16,"losses":23,"wins":17},"tencent/hy4-preview":{"draws":23,"losses":64,"wins":13},"thinkingmachines/inkling":{"draws":27,"losses":41,"wins":70},"thinkingmachines/inkling-small":{"draws":26,"losses":25,"wins":51},"unbiased/pareto-26.10":{"draws":0,"losses":34,"wins":0},"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":18,"losses":72,"wins":12},"x-ai/grok-4.6":{"draws":32,"losses":59,"wins":11},"x-ai/grok-4.7":{"draws":7,"losses":74,"wins":9},"x-ai/grok-build-0.1":{"draws":10,"losses":14,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":47,"wins":56},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":35,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":49,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":11,"losses":51,"wins":6},"z-ai/glm-5.2":{"draws":58,"losses":94,"wins":52},"z-ai/glm-5.3":{"draws":8,"losses":84,"wins":4},"z-ai/glm-5.3-flash":{"draws":17,"losses":62,"wins":23},"z-ai/glm-5.3-flashx":{"draws":12,"losses":76,"wins":14}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":8},"claude-fable-5":{"draws":5,"losses":34,"wins":3},"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":17,"losses":35,"wins":16},"claude-opus-4-8":{"draws":9,"losses":23,"wins":6},"claude-opus-5":{"draws":5,"losses":64,"wins":1},"claude-opus-5-5":{"draws":1,"losses":44,"wins":1},"claude-sonnet-5":{"draws":8,"losses":28,"wins":6},"claude-sonnet-5-5":{"draws":9,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":3,"losses":5,"wins":8},"deepseek/deepseek-v4-flash":{"draws":19,"losses":28,"wins":19},"deepseek/deepseek-v4-pro":{"draws":7,"losses":22,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":23,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":27,"wins":5},"deepseek/deepseek-v4.1-flash-1017":{"draws":7,"losses":31,"wins":4},"elorian/glimpse":{"draws":3,"losses":13,"wins":6},"fireworks/ember-1":{"draws":12,"losses":22,"wins":8},"gemini-3.1-pro-preview":{"draws":10,"losses":21,"wins":11},"gemini-4-argon":{"draws":2,"losses":39,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":9,"losses":29,"wins":14},"google/gemini-3.5-flash-lite":{"draws":20,"losses":33,"wins":19},"google/gemini-3.6-flash":{"draws":15,"losses":50,"wins":15},"google/gemini-3.8-flash":{"draws":9,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":3,"wins":10},"gpt-4.1":{"draws":4,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":4,"losses":1,"wins":1},"gpt-5":{"draws":9,"losses":17,"wins":12},"gpt-5.4":{"draws":6,"losses":28,"wins":6},"gpt-5.4-mini":{"draws":6,"losses":16,"wins":6},"gpt-5.4-nano":{"draws":9,"losses":22,"wins":15},"gpt-5.5":{"draws":12,"losses":18,"wins":8},"gpt-5.6-luna":{"draws":19,"losses":11,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":32,"wins":6},"gpt-5.6-terra":{"draws":7,"losses":29,"wins":4},"gpt-6-astra":{"draws":2,"losses":40,"wins":0},"gpt-6-luna":{"draws":10,"losses":25,"wins":7},"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":10,"losses":8,"wins":10},"inception/mercury-3":{"draws":10,"losses":12,"wins":8},"inclusionai/ling-3.0-flash":{"draws":10,"losses":9,"wins":11},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":11,"losses":17,"wins":18},"meta/muse-glimmer-30b":{"draws":10,"losses":12,"wins":14},"meta/muse-spark-1.2":{"draws":8,"losses":26,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":35,"wins":2},"meta/muse-spark-open":{"draws":7,"losses":29,"wins":4},"meta/muse-wonder":{"draws":4,"losses":31,"wins":7},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":11},"minimax/minimax-m3.1-flash":{"draws":4,"losses":18,"wins":14},"mistralai/mistral-large-4-0":{"draws":8,"losses":13,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":6,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":6,"wins":3},"moonshotai/kimi-k3":{"draws":10,"losses":22,"wins":8},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":35,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":12,"wins":14},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":11,"wins":3},"o3":{"draws":9,"losses":40,"wins":13},"openai/gpt-oss-120b":{"draws":11,"losses":17,"wins":10},"poolside/laguna-s-2.1":{"draws":8,"losses":28,"wins":8},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":27,"wins":6},"qwen/qwen3.8-27b":{"draws":6,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":6,"losses":17,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":24,"wins":10},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":8},"recursive/flint-v1.0":{"draws":1,"losses":6,"wins":5},"reflection/beam-1.0-501b-a23b":{"draws":6,"losses":23,"wins":9},"stealth/ox-alpha":{"draws":29,"losses":87,"wins":24},"stealth/space-bunny-alpha":{"draws":11,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":14},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":8},"tencent/hy4-preview":{"draws":8,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":14,"losses":15,"wins":27},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":18},"unbiased/pareto-26.10":{"draws":0,"losses":14,"wins":0},"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":8,"losses":28,"wins":6},"x-ai/grok-4.6":{"draws":11,"losses":29,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":34,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":19,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":18,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":17,"wins":5},"z-ai/glm-5.2":{"draws":26,"losses":38,"wins":20},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":32,"wins":4},"z-ai/glm-5.3-flashx":{"draws":8,"losses":29,"wins":5}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":11,"wins":17},"claude-fable-5":{"draws":11,"losses":27,"wins":4},"claude-fable-5-1":{"draws":2,"losses":41,"wins":3},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":10},"claude-opus-4-5":{"draws":21,"losses":27,"wins":20},"claude-opus-4-8":{"draws":9,"losses":15,"wins":14},"claude-opus-5":{"draws":8,"losses":56,"wins":6},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":8,"losses":16,"wins":18},"claude-sonnet-5-5":{"draws":8,"losses":23,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":13,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":12},"deepseek/deepseek-v4.1-flash-1017":{"draws":9,"losses":27,"wins":6},"elorian/glimpse":{"draws":3,"losses":8,"wins":11},"fireworks/ember-1":{"draws":9,"losses":18,"wins":15},"gemini-3.1-pro-preview":{"draws":7,"losses":16,"wins":19},"gemini-4-argon":{"draws":2,"losses":38,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":10,"losses":24,"wins":18},"google/gemini-3.5-flash-lite":{"draws":14,"losses":12,"wins":46},"google/gemini-3.6-flash":{"draws":14,"losses":39,"wins":27},"google/gemini-3.8-flash":{"draws":13,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":7,"losses":5,"wins":12},"gpt-4.1":{"draws":4,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":5,"losses":0,"wins":1},"gpt-5":{"draws":7,"losses":17,"wins":14},"gpt-5.4":{"draws":13,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":7,"losses":9,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":10,"wins":22},"gpt-5.5":{"draws":16,"losses":16,"wins":6},"gpt-5.6-luna":{"draws":6,"losses":17,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":30,"wins":5},"gpt-5.6-terra":{"draws":12,"losses":19,"wins":9},"gpt-6-astra":{"draws":1,"losses":39,"wins":2},"gpt-6-luna":{"draws":12,"losses":19,"wins":11},"gpt-6-sol":{"draws":3,"losses":31,"wins":8},"gpt-6.1-sol":{"draws":2,"losses":34,"wins":6},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":18},"inception/mercury-3":{"draws":9,"losses":16,"wins":5},"inclusionai/ling-3.0-flash":{"draws":9,"losses":4,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":25},"meta/muse-glimmer-30b":{"draws":8,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":5,"losses":25,"wins":10},"meta/muse-spark-1.3":{"draws":3,"losses":31,"wins":8},"meta/muse-spark-open":{"draws":6,"losses":23,"wins":11},"meta/muse-wonder":{"draws":4,"losses":32,"wins":6},"minimax/minimax-m3":{"draws":5,"losses":6,"wins":13},"minimax/minimax-m3.1-flash":{"draws":9,"losses":15,"wins":12},"mistralai/mistral-large-4-0":{"draws":8,"losses":12,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":12,"losses":16,"wins":12},"moonshotai/kimi-k3.1-pro":{"draws":3,"losses":36,"wins":3},"nex-agi/nex-n2-pro":{"draws":3,"losses":5,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":19},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":7,"wins":5},"o3":{"draws":9,"losses":23,"wins":30},"openai/gpt-oss-120b":{"draws":9,"losses":5,"wins":24},"poolside/laguna-s-2.1":{"draws":15,"losses":9,"wins":20},"qwen/qwen3.7-max":{"draws":11,"losses":7,"wins":8},"qwen/qwen3.7-plus":{"draws":5,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":17,"wins":12},"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":13,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":8,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":0,"losses":3,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":10},"stealth/ox-alpha":{"draws":32,"losses":72,"wins":36},"stealth/space-bunny-alpha":{"draws":7,"losses":10,"wins":15},"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":8,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":15},"thinkingmachines/inkling":{"draws":16,"losses":13,"wins":27},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":24},"unbiased/pareto-26.10":{"draws":1,"losses":12,"wins":1},"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":26,"wins":6},"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":19,"losses":5,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":8,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":16,"wins":5},"z-ai/glm-5.2":{"draws":20,"losses":33,"wins":31},"z-ai/glm-5.3":{"draws":5,"losses":26,"wins":9},"z-ai/glm-5.3-flash":{"draws":7,"losses":26,"wins":9},"z-ai/glm-5.3-flashx":{"draws":7,"losses":24,"wins":11}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":12,"wins":19},"claude-fable-5":{"draws":6,"losses":33,"wins":9},"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":7,"losses":24,"wins":13},"claude-opus-5":{"draws":10,"losses":58,"wins":14},"claude-opus-5-5":{"draws":5,"losses":42,"wins":5},"claude-sonnet-5":{"draws":15,"losses":16,"wins":17},"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":8,"losses":18,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":16,"wins":17},"deepseek/deepseek-v4.1-flash-1017":{"draws":4,"losses":27,"wins":17},"elorian/glimpse":{"draws":4,"losses":13,"wins":9},"fireworks/ember-1":{"draws":14,"losses":18,"wins":16},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":4,"losses":39,"wins":5},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":20},"google/gemini-3.5-flash":{"draws":12,"losses":26,"wins":22},"google/gemini-3.5-flash-lite":{"draws":21,"losses":18,"wins":45},"google/gemini-3.6-flash":{"draws":29,"losses":41,"wins":22},"google/gemini-3.8-flash":{"draws":13,"losses":22,"wins":13},"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":8,"losses":15,"wins":19},"gpt-5.4":{"draws":10,"losses":24,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":4,"wins":15},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":13,"losses":20,"wins":11},"gpt-5.6-luna":{"draws":14,"losses":12,"wins":22},"gpt-5.6-sol":{"draws":8,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":15,"losses":16,"wins":15},"gpt-6-astra":{"draws":4,"losses":43,"wins":1},"gpt-6-luna":{"draws":11,"losses":16,"wins":21},"gpt-6-sol":{"draws":10,"losses":31,"wins":7},"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":14,"losses":1,"wins":19},"inception/mercury-3":{"draws":8,"losses":13,"wins":11},"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":4,"wins":31},"meta/muse-glimmer-30b":{"draws":15,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":9,"losses":17,"wins":20},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":15},"meta/muse-spark-open":{"draws":10,"losses":22,"wins":14},"meta/muse-wonder":{"draws":8,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":12,"losses":11,"wins":19},"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":15,"wins":19},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":34,"wins":8},"nex-agi/nex-n2-pro":{"draws":5,"losses":3,"wins":16},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":24},"nvidia/nemotron-3.5-super-vl":{"draws":4,"losses":7,"wins":11},"o3":{"draws":10,"losses":17,"wins":39},"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":6,"losses":10,"wins":12},"qwen/qwen3.7-plus":{"draws":7,"losses":3,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":17,"wins":15},"qwen/qwen3.8-27b":{"draws":10,"losses":11,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":16},"qwen/qwen3.8-max-0902":{"draws":11,"losses":18,"wins":19},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":19,"wins":14},"stealth/ox-alpha":{"draws":44,"losses":68,"wins":46},"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":9,"wins":34},"thinkingmachines/inkling-small":{"draws":13,"losses":8,"wins":27},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":24,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":5,"losses":31,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":3,"wins":8},"xiaomi/mimo-v2.5":{"draws":29,"losses":5,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.2":{"draws":39,"losses":22,"wins":35},"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":48,"losses":45,"wins":39},"claude-fable-5":{"draws":24,"losses":101,"wins":19},"claude-fable-5-1":{"draws":6,"losses":155,"wins":1},"claude-haiku-5-5":{"draws":28,"losses":84,"wins":26},"claude-opus-4-5":{"draws":69,"losses":112,"wins":53},"claude-opus-4-8":{"draws":35,"losses":73,"wins":24},"claude-opus-5":{"draws":31,"losses":193,"wins":22},"claude-opus-5-5":{"draws":8,"losses":143,"wins":5},"claude-sonnet-5":{"draws":44,"losses":64,"wins":36},"claude-sonnet-5-5":{"draws":28,"losses":89,"wins":27},"cohere/north-mini-code":{"draws":13,"losses":5,"wins":36},"deepseek/deepseek-v4-flash":{"draws":63,"losses":57,"wins":96},"deepseek/deepseek-v4-pro":{"draws":40,"losses":53,"wins":39},"deepseek/deepseek-v4-pro-0813":{"draws":45,"losses":49,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":48,"losses":67,"wins":29},"deepseek/deepseek-v4.1-flash-1017":{"draws":29,"losses":95,"wins":20},"elorian/glimpse":{"draws":19,"losses":36,"wins":23},"fireworks/ember-1":{"draws":45,"losses":71,"wins":28},"gemini-3.1-pro-preview":{"draws":40,"losses":67,"wins":37},"gemini-4-argon":{"draws":11,"losses":123,"wins":10},"google/gemini-3.1-flash-lite":{"draws":18,"losses":19,"wins":59},"google/gemini-3.5-flash":{"draws":38,"losses":91,"wins":51},"google/gemini-3.5-flash-lite":{"draws":64,"losses":92,"wins":96},"google/gemini-3.6-flash":{"draws":77,"losses":130,"wins":69},"google/gemini-3.8-flash":{"draws":33,"losses":86,"wins":25},"google/gemma-4-31b-it":{"draws":35,"losses":14,"wins":35},"gpt-4.1":{"draws":16,"losses":12,"wins":20},"gpt-4.1-nano":{"draws":10,"losses":0,"wins":8},"gpt-5":{"draws":31,"losses":59,"wins":36},"gpt-5.4":{"draws":35,"losses":75,"wins":28},"gpt-5.4-mini":{"draws":35,"losses":24,"wins":37},"gpt-5.4-nano":{"draws":28,"losses":54,"wins":62},"gpt-5.5":{"draws":45,"losses":62,"wins":25},"gpt-5.6-luna":{"draws":46,"losses":44,"wins":54},"gpt-5.6-sol":{"draws":19,"losses":108,"wins":17},"gpt-5.6-terra":{"draws":45,"losses":56,"wins":37},"gpt-6-astra":{"draws":8,"losses":134,"wins":2},"gpt-6-luna":{"draws":53,"losses":58,"wins":33},"gpt-6-sol":{"draws":25,"losses":106,"wins":13},"gpt-6.1-sol":{"draws":12,"losses":128,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":41,"losses":11,"wins":50},"inception/mercury-3":{"draws":34,"losses":41,"wins":21},"inclusionai/ling-3.0-flash":{"draws":39,"losses":24,"wins":39},"inclusionai/ling-3.1-flash":{"draws":4,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":41,"losses":37,"wins":78},"meta/muse-glimmer-30b":{"draws":51,"losses":26,"wins":49},"meta/muse-spark-1.2":{"draws":33,"losses":67,"wins":38},"meta/muse-spark-1.3":{"draws":27,"losses":87,"wins":30},"meta/muse-spark-open":{"draws":36,"losses":76,"wins":26},"meta/muse-wonder":{"draws":30,"losses":95,"wins":19},"minimax/minimax-m3":{"draws":26,"losses":19,"wins":33},"minimax/minimax-m3.1-flash":{"draws":31,"losses":51,"wins":44},"mistralai/mistral-large-4-0":{"draws":29,"losses":43,"wins":18},"mistralai/mistral-medium-3-5":{"draws":33,"losses":13,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":17,"wins":9},"moonshotai/kimi-k3":{"draws":38,"losses":64,"wins":36},"moonshotai/kimi-k3.1-pro":{"draws":14,"losses":119,"wins":11},"nex-agi/nex-n2-pro":{"draws":23,"losses":15,"wins":34},"nex-agi/nex-n2.5-pro":{"draws":9,"losses":8,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":40,"wins":52},"nvidia/nemotron-3.5-super-vl":{"draws":22,"losses":25,"wins":19},"o3":{"draws":30,"losses":96,"wins":72},"openai/gpt-oss-120b":{"draws":40,"losses":35,"wins":51},"poolside/laguna-s-2.1":{"draws":39,"losses":52,"wins":47},"qwen/qwen3.7-max":{"draws":20,"losses":37,"wins":27},"qwen/qwen3.7-plus":{"draws":16,"losses":17,"wins":39},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":61,"wins":31},"qwen/qwen3.8-27b":{"draws":34,"losses":40,"wins":28},"qwen/qwen3.8-flash":{"draws":33,"losses":32,"wins":31},"qwen/qwen3.8-max":{"draws":42,"losses":63,"wins":39},"qwen/qwen3.8-max-0902":{"draws":48,"losses":66,"wins":30},"recursive/flint-v1.0":{"draws":11,"losses":12,"wins":19},"reflection/beam-1.0-501b-a23b":{"draws":37,"losses":50,"wins":45},"stealth/ox-alpha":{"draws":112,"losses":258,"wins":104},"stealth/space-bunny-alpha":{"draws":34,"losses":43,"wins":37},"stepfun/step-3.7-flash":{"draws":23,"losses":33,"wins":46},"stepfun/step-5-preview":{"draws":4,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":27,"losses":24,"wins":27},"tencent/hy4-preview":{"draws":25,"losses":82,"wins":31},"thinkingmachines/inkling":{"draws":56,"losses":47,"wins":89},"thinkingmachines/inkling-small":{"draws":45,"losses":37,"wins":62},"unbiased/pareto-26.10":{"draws":2,"losses":46,"wins":0},"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":34,"losses":91,"wins":19},"x-ai/grok-4.6":{"draws":34,"losses":87,"wins":23},"x-ai/grok-4.7":{"draws":15,"losses":94,"wins":17},"x-ai/grok-build-0.1":{"draws":18,"losses":15,"wins":15},"xiaomi/mimo-v2.5":{"draws":67,"losses":63,"wins":92},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":33,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":55,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":22,"losses":56,"wins":18},"z-ai/glm-5.2":{"draws":69,"losses":94,"wins":77},"z-ai/glm-5.3":{"draws":31,"losses":96,"wins":11},"z-ai/glm-5.3-flash":{"draws":28,"losses":88,"wins":28},"z-ai/glm-5.3-flashx":{"draws":32,"losses":79,"wins":33}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":9,"wins":23},"claude-fable-5":{"draws":8,"losses":29,"wins":11},"claude-fable-5-1":{"draws":6,"losses":46,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":18,"wins":16},"claude-opus-4-5":{"draws":26,"losses":22,"wins":30},"claude-opus-4-8":{"draws":9,"losses":14,"wins":21},"claude-opus-5":{"draws":11,"losses":63,"wins":8},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":14,"losses":11,"wins":23},"claude-sonnet-5-5":{"draws":10,"losses":25,"wins":13},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":13,"wins":37},"deepseek/deepseek-v4-pro":{"draws":15,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":16,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":22,"wins":14},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":25,"wins":13},"elorian/glimpse":{"draws":7,"losses":9,"wins":10},"fireworks/ember-1":{"draws":15,"losses":13,"wins":20},"gemini-3.1-pro-preview":{"draws":12,"losses":13,"wins":23},"gemini-4-argon":{"draws":2,"losses":43,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":18,"losses":20,"wins":22},"google/gemini-3.5-flash-lite":{"draws":22,"losses":10,"wins":52},"google/gemini-3.6-flash":{"draws":23,"losses":33,"wins":36},"google/gemini-3.8-flash":{"draws":12,"losses":22,"wins":14},"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":9,"wins":20},"gpt-5.4":{"draws":15,"losses":24,"wins":7},"gpt-5.4-mini":{"draws":12,"losses":6,"wins":14},"gpt-5.4-nano":{"draws":11,"losses":13,"wins":24},"gpt-5.5":{"draws":14,"losses":10,"wins":20},"gpt-5.6-luna":{"draws":11,"losses":16,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":20},"gpt-6-astra":{"draws":3,"losses":43,"wins":2},"gpt-6-luna":{"draws":9,"losses":19,"wins":20},"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":12,"losses":6,"wins":16},"inception/mercury-3":{"draws":10,"losses":11,"wins":11},"inclusionai/ling-3.0-flash":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":9,"wins":31},"meta/muse-glimmer-30b":{"draws":7,"losses":7,"wins":28},"meta/muse-spark-1.2":{"draws":11,"losses":26,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":20,"wins":20},"meta/muse-spark-open":{"draws":11,"losses":20,"wins":15},"meta/muse-wonder":{"draws":8,"losses":31,"wins":9},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":15},"minimax/minimax-m3.1-flash":{"draws":11,"losses":12,"wins":19},"mistralai/mistral-large-4-0":{"draws":9,"losses":10,"wins":11},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":16,"wins":11},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":36,"wins":6},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":25},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":3,"wins":13},"o3":{"draws":9,"losses":26,"wins":31},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":13,"losses":9,"wins":24},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":14},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":15},"qwen/qwen3.8-27b":{"draws":13,"losses":4,"wins":17},"qwen/qwen3.8-flash":{"draws":14,"losses":9,"wins":9},"qwen/qwen3.8-max":{"draws":15,"losses":20,"wins":13},"qwen/qwen3.8-max-0902":{"draws":16,"losses":19,"wins":13},"recursive/flint-v1.0":{"draws":4,"losses":2,"wins":8},"reflection/beam-1.0-501b-a23b":{"draws":10,"losses":18,"wins":16},"stealth/ox-alpha":{"draws":43,"losses":69,"wins":46},"stealth/space-bunny-alpha":{"draws":12,"losses":6,"wins":20},"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":7,"losses":6,"wins":13},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":19},"thinkingmachines/inkling":{"draws":15,"losses":15,"wins":34},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":26},"unbiased/pareto-26.10":{"draws":1,"losses":14,"wins":1},"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":15,"losses":15,"wins":18},"x-ai/grok-4.6":{"draws":12,"losses":22,"wins":14},"x-ai/grok-4.7":{"draws":6,"losses":32,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":21,"losses":4,"wins":49},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":4,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":16,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":31,"losses":22,"wins":43},"z-ai/glm-5.3":{"draws":5,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":14,"losses":18,"wins":16},"z-ai/glm-5.3-flashx":{"draws":8,"losses":24,"wins":16}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":8,"wins":21},"claude-fable-5":{"draws":10,"losses":30,"wins":8},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-haiku-5-5":{"draws":12,"losses":24,"wins":10},"claude-opus-4-5":{"draws":23,"losses":25,"wins":30},"claude-opus-4-8":{"draws":6,"losses":22,"wins":16},"claude-opus-5":{"draws":14,"losses":59,"wins":9},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":11,"losses":20,"wins":17},"claude-sonnet-5-5":{"draws":10,"losses":23,"wins":15},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":30,"losses":16,"wins":26},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":15,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":21,"wins":16},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":30,"wins":8},"elorian/glimpse":{"draws":4,"losses":11,"wins":11},"fireworks/ember-1":{"draws":10,"losses":17,"wins":21},"gemini-3.1-pro-preview":{"draws":11,"losses":18,"wins":19},"gemini-4-argon":{"draws":6,"losses":38,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":17},"google/gemini-3.5-flash":{"draws":10,"losses":25,"wins":25},"google/gemini-3.5-flash-lite":{"draws":23,"losses":22,"wins":39},"google/gemini-3.6-flash":{"draws":23,"losses":35,"wins":34},"google/gemini-3.8-flash":{"draws":7,"losses":27,"wins":14},"google/gemma-4-31b-it":{"draws":8,"losses":7,"wins":13},"gpt-4.1":{"draws":1,"losses":8,"wins":7},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":3},"gpt-5":{"draws":9,"losses":14,"wins":19},"gpt-5.4":{"draws":6,"losses":23,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":10},"gpt-5.4-nano":{"draws":12,"losses":15,"wins":21},"gpt-5.5":{"draws":12,"losses":18,"wins":14},"gpt-5.6-luna":{"draws":18,"losses":12,"wins":18},"gpt-5.6-sol":{"draws":12,"losses":27,"wins":9},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":17},"gpt-6-astra":{"draws":5,"losses":41,"wins":2},"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":10,"losses":5,"wins":19},"inception/mercury-3":{"draws":13,"losses":15,"wins":4},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":18},"inclusionai/ling-3.1-flash":{"draws":2,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":12,"losses":13,"wins":27},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":12,"losses":19,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":18},"meta/muse-spark-open":{"draws":8,"losses":27,"wins":11},"meta/muse-wonder":{"draws":16,"losses":24,"wins":8},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"minimax/minimax-m3.1-flash":{"draws":6,"losses":19,"wins":17},"mistralai/mistral-large-4-0":{"draws":11,"losses":8,"wins":11},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":14,"losses":14,"wins":18},"moonshotai/kimi-k3.1-pro":{"draws":6,"losses":38,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":14},"nex-agi/nex-n2.5-pro":{"draws":3,"losses":1,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":16,"wins":15},"nvidia/nemotron-3.5-super-vl":{"draws":5,"losses":8,"wins":9},"o3":{"draws":8,"losses":27,"wins":31},"openai/gpt-oss-120b":{"draws":12,"losses":10,"wins":20},"poolside/laguna-s-2.1":{"draws":17,"losses":12,"wins":17},"qwen/qwen3.7-max":{"draws":11,"losses":8,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":18,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":12,"wins":12},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":13},"qwen/qwen3.8-max-0902":{"draws":12,"losses":24,"wins":12},"recursive/flint-v1.0":{"draws":4,"losses":3,"wins":7},"reflection/beam-1.0-501b-a23b":{"draws":12,"losses":16,"wins":16},"stealth/ox-alpha":{"draws":34,"losses":77,"wins":47},"stealth/space-bunny-alpha":{"draws":12,"losses":10,"wins":16},"stepfun/step-3.7-flash":{"draws":7,"losses":11,"wins":16},"stepfun/step-5-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":11},"tencent/hy4-preview":{"draws":14,"losses":22,"wins":10},"thinkingmachines/inkling":{"draws":19,"losses":17,"wins":28},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":24},"unbiased/pareto-26.10":{"draws":2,"losses":13,"wins":1},"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":8,"losses":22,"wins":18},"x-ai/grok-4.6":{"draws":17,"losses":21,"wins":10},"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":27,"losses":12,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":11,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":19,"wins":5},"z-ai/glm-5.2":{"draws":34,"losses":24,"wins":38},"z-ai/glm-5.3":{"draws":13,"losses":27,"wins":6},"z-ai/glm-5.3-flash":{"draws":4,"losses":20,"wins":8},"z-ai/glm-5.3-flashx":{"draws":12,"losses":26,"wins":10}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":26},"claude-fable-5":{"draws":6,"losses":33,"wins":9},"claude-fable-5-1":{"draws":2,"losses":51,"wins":1},"claude-haiku-5-5":{"draws":14,"losses":21,"wins":11},"claude-opus-4-5":{"draws":21,"losses":26,"wins":31},"claude-opus-4-8":{"draws":10,"losses":20,"wins":14},"claude-opus-5":{"draws":15,"losses":57,"wins":10},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":16,"losses":13,"wins":19},"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":18,"losses":19,"wins":35},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4.1-flash-1017":{"draws":10,"losses":27,"wins":11},"elorian/glimpse":{"draws":8,"losses":10,"wins":8},"fireworks/ember-1":{"draws":14,"losses":20,"wins":14},"gemini-3.1-pro-preview":{"draws":13,"losses":15,"wins":20},"gemini-4-argon":{"draws":6,"losses":37,"wins":5},"google/gemini-3.1-flash-lite":{"draws":11,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":19,"losses":18,"wins":23},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":42},"google/gemini-3.6-flash":{"draws":27,"losses":36,"wins":29},"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":3,"losses":2,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":13,"losses":11,"wins":18},"gpt-5.4":{"draws":14,"losses":20,"wins":12},"gpt-5.4-mini":{"draws":13,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":12,"losses":13,"wins":23},"gpt-5.5":{"draws":18,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":14,"losses":17,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":7},"gpt-5.6-terra":{"draws":11,"losses":20,"wins":15},"gpt-6-astra":{"draws":7,"losses":40,"wins":1},"gpt-6-luna":{"draws":9,"losses":18,"wins":21},"gpt-6-sol":{"draws":8,"losses":29,"wins":11},"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":10,"losses":4,"wins":20},"inception/mercury-3":{"draws":10,"losses":14,"wins":8},"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":12,"losses":10,"wins":30},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":25},"meta/muse-spark-1.2":{"draws":8,"losses":21,"wins":17},"meta/muse-spark-1.3":{"draws":7,"losses":25,"wins":16},"meta/muse-spark-open":{"draws":10,"losses":21,"wins":15},"meta/muse-wonder":{"draws":11,"losses":30,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":3,"wins":17},"minimax/minimax-m3.1-flash":{"draws":8,"losses":8,"wins":26},"mistralai/mistral-large-4-0":{"draws":13,"losses":10,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":16,"losses":14,"wins":16},"moonshotai/kimi-k3.1-pro":{"draws":5,"losses":35,"wins":8},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":12},"nex-agi/nex-n2.5-pro":{"draws":2,"losses":5,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":22},"nvidia/nemotron-3.5-super-vl":{"draws":6,"losses":6,"wins":10},"o3":{"draws":12,"losses":14,"wins":40},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":26},"poolside/laguna-s-2.1":{"draws":18,"losses":8,"wins":20},"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":14,"losses":20,"wins":14},"recursive/flint-v1.0":{"draws":4,"losses":1,"wins":9},"reflection/beam-1.0-501b-a23b":{"draws":11,"losses":15,"wins":18},"stealth/ox-alpha":{"draws":33,"losses":70,"wins":55},"stealth/space-bunny-alpha":{"draws":11,"losses":8,"wins":19},"stepfun/step-3.7-flash":{"draws":7,"losses":3,"wins":24},"stepfun/step-5-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":10},"tencent/hy4-preview":{"draws":14,"losses":20,"wins":12},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":37},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":32},"unbiased/pareto-26.10":{"draws":2,"losses":14,"wins":0},"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":23,"wins":12},"x-ai/grok-4.6":{"draws":10,"losses":24,"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":26,"losses":6,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":14,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":16,"wins":11},"z-ai/glm-5.2":{"draws":32,"losses":28,"wins":36},"z-ai/glm-5.3":{"draws":9,"losses":31,"wins":6},"z-ai/glm-5.3-flash":{"draws":12,"losses":25,"wins":11},"z-ai/glm-5.3-flashx":{"draws":6,"losses":16,"wins":10}}}}}