{"data":[{"id":"aa_agentic_index","display_name":"Artificial Analysis Agentic Index","category":"composite","unit":"index","scale_min":0,"scale_max":100,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"AA sub-index (Agents). Weight 0 by design (brief) — same rationale as aa_coding_index.","models_covered":122,"index_share":null},{"id":"aa_briefcase","display_name":"AA-Briefcase","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_553b3da274594398a3713bcb7b3afa2d","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"aa_briefcase_analytical_quality_elo","display_name":"AA-Briefcase Analytical Quality Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_briefcase_elo","display_name":"AA-Briefcase Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_briefcase_presentation_elo","display_name":"AA-Briefcase Presentation Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_briefcase_rubric_pass_rate","display_name":"AA-Briefcase rubric pass rate","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_coding_agent_index","display_name":"AA Coding Agent Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5a7b2bf97fed4a3cb01efdb8d503d9b4","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"aa_coding_index","display_name":"Artificial Analysis Coding Index","category":"composite","unit":"index","scale_min":0,"scale_max":100,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"AA sub-index (Coding). Weight 0 by design (brief) — aa_intelligence_index alone represents the AA family in the composite; this row exists so the OpenRouter lane has a target to ingest into from day one without dropping the value.","models_covered":136,"index_share":null},{"id":"aa_intelligence_index","display_name":"Artificial Analysis Intelligence Index","category":"composite","unit":"index","scale_min":0,"scale_max":100,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"AA's flagship composite (v4.1.1, 9 evals/4 categories), arrives via OpenRouter's embedded benchmarks.artificial_analysis field (source_type=aggregator, trust 2) per 09-A1 — do not build a direct AA API connector this phase (redistribution licensing gate, R8a §1). 4 of the 9 sub-evals (GDPval-AA, CritPt, SciCode, AA-LCR) are AA-proprietary/closed-methodology (R8a §1.17) — lower independent-reproducibility, still trust 2 as an aggregate.","models_covered":245,"index_share":null},{"id":"aa_lcr","display_name":"AA-LCR","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f7be5cdfc6ed41c99f63660105f869ce","active":true,"notes":null,"models_covered":195,"index_share":null},{"id":"aa_omniscience","display_name":"AA-Omniscience","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a60ebb3a51fe482db14bf1479d4f70ec","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"aa_omniscience_accuracy","display_name":"AA-Omniscience Accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_2e5a562a40d64392a3a803438b1da5c3","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"aa_omniscience_hallucination_rate","display_name":"AA-Omniscience Hallucination Rate","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_553b3da274594398a3713bcb7b3afa2d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_omniscience_index","display_name":"aa_omniscience_index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_94b6620d00e9430381a455dc60e828f0","active":true,"notes":null,"models_covered":46,"index_share":null},{"id":"aa_omniscience_net_score","display_name":"AA-Omniscience Net Score","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_omniscience_non_hallucination","display_name":"AA-Omniscience Non-Hallucination","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_2e5a562a40d64392a3a803438b1da5c3","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aa_omniscience_non_hallucination_rate","display_name":"AA-Omniscience Non-Hallucination Rate","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"aav_capsid_structure","display_name":"AAV capsid structure","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aav_capsid_tropism","display_name":"AAV capsid tropism","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aav_capsid_viability_ood_auroc","display_name":"AAV capsid viability (OOD AUROC)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aav_generative_design","display_name":"AAV generative design","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aegis_2_0","display_name":"Aegis 2.0","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"afumed_drug","display_name":"AFUMED-Drug","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"afumed_drug_internal","display_name":"AFUMED-Drug (internal)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"afusafe_medsce","display_name":"AFUSAFE-MedSCE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"afusafe_medsce_internal","display_name":"AFUSAFE-MedSCE (internal)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"agent_startup_bench","display_name":"Agent Startup Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"agentic_if_index","display_name":"Agentic IF Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_09f703cd057f467692c632c989f68b58","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"agents_last_exam","display_name":"Agents' Last Exam","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_acf3136ad9694471b137d965b747a7f6","active":true,"notes":null,"models_covered":10,"index_share":null},{"id":"agi_eval","display_name":"AGI EVAL","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"agieval","display_name":"AGIEval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d705283605f5404eb26540a36bb3d460","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"ai2_reasoning_challenge","display_name":"AI2 Reasoning Challenge","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_118237c52f154f449b89d1999110b526","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ai2d","display_name":"AI2D","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_eb1342ae95b443ed98b6f405b52f2d37","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"aider","display_name":"Aider","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_42f387694fac489b8a51914a4e11c794","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"aider_polyglot","display_name":"Aider-Polyglot","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97c943d2c5ee4107a9a57d2adea4a5ad","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"aime","display_name":"AIME (annual)","category":"math","unit":"percent","scale_min":20,"scale_max":100,"higher_better":true,"weight_in_composite":0.0735,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Year-parameterized family (aime-2025, aime-2026, ...) — capture edition/year in score_config, not a new benchmark id, per R8a §5b. Small-N (30 problems/year) -> wide CI, single-problem swing ~3.3pts. Near-saturating within ~1yr of each new edition.","models_covered":175,"index_share":0.0793},{"id":"aime_2026_no_tools","display_name":"AIME 2026 no tools","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":false,"notes":"refolded into aime; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"ale_bench","display_name":"ALE-Bench","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":0,"index_share":null},{"id":"alpacaeval_2_0","display_name":"AlpacaEval 2.0","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97c943d2c5ee4107a9a57d2adea4a5ad","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"amc23","display_name":"AMC23","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aab24e5371704d9db079b045e5b11a05","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"analyst_agent","display_name":"analyst_agent","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c1f9150dcede44909ee388a3dc05d2ae","active":true,"notes":null,"models_covered":26,"index_share":null},{"id":"androidbench","display_name":"AndroidBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"androidworld","display_name":"AndroidWorld","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4b491fc5dc374246822a3d46b2e00025","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"anthropic_eci","display_name":"Anthropic ECI","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"apex","display_name":"Apex","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_81a9cdaaecff4d788a0686b15f5261b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"apex_agent","display_name":"APEX-Agent","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_e468d8ceb73f4797b3bd0b95d08879f8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"apex_agents","display_name":"APEX-Agents","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":35,"index_share":null},{"id":"apex_swe","display_name":"APEX-SWE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c666bf86747f4194a293ae4cb54a1df1","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"apexbench","display_name":"ApexBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fc6b593f74ec40498ea09b9410e24246","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"arc","display_name":"ARC","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_572e3239dfa848069a47e0a6d9284200","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"arc_agi_1","display_name":"ARC-AGI-1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d5e2006f4e3e4803b6aa364787492ff0","active":true,"notes":null,"models_covered":60,"index_share":null},{"id":"arc_agi_2","display_name":"ARC-AGI-2","category":"reasoning","unit":"percent","scale_min":5,"scale_max":95,"higher_better":true,"weight_in_composite":0.0735,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Held-out visual/abstract-reasoning grid puzzles. Cost/compute-budget is a load-bearing paired axis (R8a §1.9) — same model can swing 31%/$0.81 to 54%/$31 by inference-time spend; score without cost context is misleading.","models_covered":68,"index_share":0.0793},{"id":"arc_agi_3","display_name":"ARC-AGI-3","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_553b3da274594398a3713bcb7b3afa2d","active":true,"notes":null,"models_covered":13,"index_share":null},{"id":"arc_agi_3_standard_harness","display_name":"ARC-AGI-3 (Standard harness)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_599a92d424b54865bf01fd5d7cbeb036","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"arc_c","display_name":"ARC-c","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f469e4e959734d1cbf42fcdfd1a6f177","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"arc_challenge","display_name":"ARC-Challenge","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"arc_e","display_name":"ARC-E","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_2e6f4a879195426b9e174acc0bc1346a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"arena_elo","display_name":"LMArena / Arena Elo","category":"composite","unit":"elo","scale_min":1279.63,"scale_max":1503.99,"higher_better":true,"weight_in_composite":0.0735,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Human pairwise-preference Elo, live/continuously updated (lmarena.ai rebranded arena.ai Jan 2026). R8a flags this as a preference signal, not a capability signal — top-of-board differences are frequently statistical noise (overlapping CIs); weight kept per spec 07's locked composite table, retained here rather than overridden, but treat rank deltas <~30 Elo as noise.","models_covered":167,"index_share":0.0793},{"id":"arena_elo_document","display_name":"Arena Elo document","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":30,"index_share":null},{"id":"arena_elo_image_to_webdev","display_name":"Arena Elo image_to_webdev","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":29,"index_share":null},{"id":"arena_elo_search","display_name":"Arena Elo search","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"arena_elo_vision","display_name":"Arena Elo vision","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":79,"index_share":null},{"id":"arena_elo_webdev","display_name":"Arena Elo webdev","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":82,"index_share":null},{"id":"arena_hard","display_name":"Arena-Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_129dee01585c4c0b9ef45f159395a156","active":true,"notes":null,"models_covered":18,"index_share":null},{"id":"arena_hard_v2","display_name":"Arena-Hard v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c157934da2b1494e95383b8c151c338e","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"arena_text_elo","display_name":"Arena Text Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"arenahard","display_name":"ArenaHard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97c943d2c5ee4107a9a57d2adea4a5ad","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"artifactsbench","display_name":"ArtifactsBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8a69fb40f715478dbe3668b58472c516","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"artificial_analysis_coding_agent_index","display_name":"Artificial Analysis Coding Agent Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_acf3136ad9694471b137d965b747a7f6","active":false,"notes":"refolded into aa_coding_agent_index; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"artificial_analysis_finance_accounting_index","display_name":"Artificial Analysis Finance & Accounting Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"arxivmath","display_name":"ArXivMath","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5cf46f49f2b545f2a95b2b42f6f2991d","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"arxivmath_june_2026_49_problems","display_name":"ArxivMath (June 2026, 49 problems)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"attaq","display_name":"AttaQ","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"autobench","display_name":"AutoBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a79d8f61dd56498990b7266ec18cfb4b","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"automation_bench","display_name":"Automation-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"automation_bench_partial_score","display_name":"automation_bench_partial_score","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c1f9150dcede44909ee388a3dc05d2ae","active":true,"notes":null,"models_covered":35,"index_share":null},{"id":"automationbench","display_name":"AutomationBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fa44f3cefc824f43ba6c89894e5d3dd1","active":true,"notes":null,"models_covered":13,"index_share":null},{"id":"automationbench_aa","display_name":"AutomationBench-AA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"babyvision","display_name":"BabyVision","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"bbh","display_name":"BBH","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":13,"index_share":null},{"id":"bbq","display_name":"BBQ","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bbq_ambig","display_name":"BBQ Ambig","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_496cde7b49d248459d3e7e1c562450da","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bbq_ambiguous","display_name":"BBQ ambiguous","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7a3458f60e154a0ebff41b4ff6a24883","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bbq_ambiguous_accuracy","display_name":"BBQ ambiguous accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bbq_disambiguated","display_name":"BBQ disambiguated","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7a3458f60e154a0ebff41b4ff6a24883","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bbq_disambiguated_accuracy","display_name":"BBQ disambiguated accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"benchcad","display_name":"BenchCAD","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"beyondaime","display_name":"BeyondAIME","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_28687023448c4de59b92d6744c6737e6","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"bfcl","display_name":"BFCL","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"bfcl_v2","display_name":"BFCL v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_282bf64514de478b9fde1d211282288c","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bfcl_v2_live","display_name":"BFCL V2 Live","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_93aaa1834ee7431193e8e19629a0b424","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"bfcl_v3","display_name":"BFCL v3","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":12,"index_share":null},{"id":"bfcl_v3_tool_calling","display_name":"BFCL v3 (Tool Calling)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bfcl_v4","display_name":"BFCL (v4)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"big_bench_hard","display_name":"BIG-Bench Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f469e4e959734d1cbf42fcdfd1a6f177","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bigbench_extra_hard","display_name":"BigBench Extra Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"bigbench_hard","display_name":"BigBench Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8396420d65094d77a85eb04704426e9d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"bigbenchhard","display_name":"BigBenchHard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6014f4daf7fb44ec934b2ae474f34e8e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bigcodebench","display_name":"BigCodeBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"biomysterybench","display_name":"Biomysterybench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"biomysterybench_human_difficult","display_name":"BioMysteryBench (Human-difficult)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"biomysterybench_human_solvable","display_name":"BioMysteryBench human-solvable","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"biosecbench_function","display_name":"Biosecbench Function","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"biosecbench_surveillance","display_name":"Biosecbench Surveillance","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bird_sql","display_name":"Bird-SQL","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0e010c3d05ae48ea8826c4174c27aed9","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"birdbench","display_name":"BirdBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"bixbench","display_name":"BixBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_131a8a1728b44785bf474e46e254b8be","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"blink","display_name":"BLINK","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"blueprint_bench_2","display_name":"Blueprint-Bench 2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a60ebb3a51fe482db14bf1479d4f70ec","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"boolq","display_name":"BoolQ","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_2e6f4a879195426b9e174acc0bc1346a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"brokenarxiv","display_name":"Brokenarxiv","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"browsecomp","display_name":"BrowseComp","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":27,"index_share":null},{"id":"browsecomp_multi_agent","display_name":"BrowseComp, multi-agent","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"browsecomp_single_agent","display_name":"BrowseComp, single agent","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"browsecomp_zh","display_name":"BrowseComp-ZH","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bf713be07f1c4f6781df4a9b64ce09c5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"business_knowledge_accuracy","display_name":"business knowledge accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"business_knowledge_hallucination","display_name":"business knowledge hallucination","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"c3_bench","display_name":"C3-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8a69fb40f715478dbe3668b58472c516","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"c_eval","display_name":"C-Eval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_047f4152277541e28f06797a7ed31fdc","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"cadgenbench","display_name":"Cadgenbench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"case_law","display_name":"Case Law","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0209f765bc4548f78ed2985f52273135","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"cathedralbench","display_name":"Cathedralbench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"character_editing_elo","display_name":"Character Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"chartography","display_name":"Chartography","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fc6b593f74ec40498ea09b9410e24246","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"chartqa","display_name":"ChartQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4eaa68da41964b1f84786f0dd048a38a","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"charxiv","display_name":"CharXiv","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d96417a9afb74afd8322737c2b9940c9","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"charxiv_reasoning","display_name":"CharXiv Reasoning","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"charxiv_rq","display_name":"CharXiv RQ","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_025dafb136bb47369cd6e8cc4e9d7543","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"chess_puzzles","display_name":"Chess Puzzles","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"claw_eval","display_name":"Claw-Eval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_e468d8ceb73f4797b3bd0b95d08879f8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"claweval_mm","display_name":"ClawEval-MM","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"code_arena","display_name":"Code Arena","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"code_migration","display_name":"Code Migration","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"codeforces_elo","display_name":"Codeforces Elo (LLM, human scale)","category":"code","unit":"elo","scale_min":800,"scale_max":2500,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Keep strictly on the human Codeforces Elo scale (800-3800 human range). Do NOT merge with 0-1-normalized \"Codeforces\" variants seen on some trackers (R8a §1.15) — incompatible units despite the shared name.","models_covered":10,"index_share":null},{"id":"codeforces_rating","display_name":"CodeForces rating","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_31f47c29c79a4a90bd4872872876f9e8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"coding_index","display_name":"Coding Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a469d4cc82b24e61965b5a930a9ba5ff","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"collegemath","display_name":"CollegeMath","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aab24e5371704d9db079b045e5b11a05","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"commonsenseqa","display_name":"CommonsenseQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_572e3239dfa848069a47e0a6d9284200","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"complexfuncbench","display_name":"ComplexFuncBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8a69fb40f715478dbe3668b58472c516","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"corp_fin","display_name":"Corp Fin","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0209f765bc4548f78ed2985f52273135","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"cosmos_reason1","display_name":"Cosmos-Reason1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"countbench","display_name":"CountBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"covost","display_name":"CoVoST","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"coworkbench","display_name":"CoWorkBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"creativework","display_name":"CreativeWork","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"critpt","display_name":"CritPt","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":175,"index_share":null},{"id":"cruxeval_o","display_name":"CRUXEval-O","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"cursorbench","display_name":"CursorBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a927f856add64bd994092110b766a8f2","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"cursorbench_v3_2","display_name":"CursorBench v3.2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c666bf86747f4194a293ae4cb54a1df1","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"cve_bench","display_name":"Cve Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"cwe_bench","display_name":"CWE-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7ac666dcfe3949c691f7cb9da4f69ca1","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"cwe_bench_v1","display_name":"CWE-bench v1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"cyberbench_v1_1","display_name":"CyberBench v1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"cybergym","display_name":"CyberGym","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bf713be07f1c4f6781df4a9b64ce09c5","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"deepmind_math","display_name":"DeepMind Math","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"deepsearch_qa","display_name":"DeepSearch QA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4ce546e34701489ca7c890d1a3a0096c","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"deepsearchqa","display_name":"DeepSearchQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"deepswe","display_name":"DeepSWE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":29,"index_share":null},{"id":"deepswe_1_0","display_name":"DeepSWE 1.0","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_474270a493514b6589ef766381031e54","active":false,"notes":"refolded into deepswe; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"deepswe_1_1","display_name":"DeepSWE 1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":false,"notes":"refolded into deepswe; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"deepswe_v1_1","display_name":"DeepSWE v1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":false,"notes":"refolded into deepswe; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"design_arena_3d","display_name":"design_arena_3d","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":104,"index_share":null},{"id":"design_arena_agenticgamedev","display_name":"design_arena_agenticgamedev","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":25,"index_share":null},{"id":"design_arena_agentichtmlslides","display_name":"design_arena_agentichtmlslides","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":10,"index_share":null},{"id":"design_arena_agenticslides","display_name":"design_arena_agenticslides","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":10,"index_share":null},{"id":"design_arena_androidnative","display_name":"design_arena_androidnative","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":37,"index_share":null},{"id":"design_arena_asciiart","display_name":"design_arena_asciiart","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":65,"index_share":null},{"id":"design_arena_codecategories","display_name":"design_arena_codecategories","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":112,"index_share":null},{"id":"design_arena_dataviz","display_name":"design_arena_dataviz","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":111,"index_share":null},{"id":"design_arena_fullstack","display_name":"design_arena_fullstack","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":43,"index_share":null},{"id":"design_arena_gamedev","display_name":"design_arena_gamedev","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":112,"index_share":null},{"id":"design_arena_godotgamedev","display_name":"design_arena_godotgamedev","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":35,"index_share":null},{"id":"design_arena_graphicdesign","display_name":"design_arena_graphicdesign","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"design_arena_htmlslides","display_name":"design_arena_htmlslides","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":24,"index_share":null},{"id":"design_arena_image","display_name":"design_arena_image","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"design_arena_imageediting","display_name":"design_arena_imageediting","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"design_arena_logo","display_name":"design_arena_logo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"design_arena_mobileapps","display_name":"design_arena_mobileapps","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":43,"index_share":null},{"id":"design_arena_pptxslides","display_name":"design_arena_pptxslides","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":9,"index_share":null},{"id":"design_arena_python_pptxslides","display_name":"design_arena_python-pptxslides","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":27,"index_share":null},{"id":"design_arena_svg","display_name":"design_arena_svg","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":81,"index_share":null},{"id":"design_arena_uicomponent","display_name":"design_arena_uicomponent","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":110,"index_share":null},{"id":"design_arena_webapps","display_name":"design_arena_webapps","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":44,"index_share":null},{"id":"design_arena_website","display_name":"design_arena_website","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68998df3bf3f44729cc6558681a176bf","active":true,"notes":null,"models_covered":119,"index_share":null},{"id":"diagnosisarena_mcq","display_name":"DiagnosisArena-MCQ","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"docvqa","display_name":"DocVQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4eaa68da41964b1f84786f0dd048a38a","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"doodle_editing_elo","display_name":"Doodle Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"drop","display_name":"DROP","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b117e42664ba451c8a56cc67a74071b4","active":true,"notes":null,"models_covered":9,"index_share":null},{"id":"dsbench_hard","display_name":"DSBench-Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fc6b593f74ec40498ea09b9410e24246","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ebr_bench","display_name":"Ebr Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"eci","display_name":"ECI","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"eebench","display_name":"Eebench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"egoschema","display_name":"EgoSchema","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"emb","display_name":"Emb","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"embspatialbench","display_name":"EmbSpatialBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"enterprise_ops_gym","display_name":"enterprise_ops_gym","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c1f9150dcede44909ee388a3dc05d2ae","active":true,"notes":null,"models_covered":30,"index_share":null},{"id":"erqa","display_name":"ERQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4b491fc5dc374246822a3d46b2e00025","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"eval_avg","display_name":"Eval+ Avg","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"expert_swe","display_name":"Expert-SWE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_131a8a1728b44785bf474e46e254b8be","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"exploitbench","display_name":"ExploitBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"exploitbench_v8_bench_autonudge_capability","display_name":"ExploitBench v8-bench AutoNudge capability","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"exploitgym","display_name":"ExploitGym","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"extractbench","display_name":"ExtractBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bb0a1075db914805b47a6006e33f169e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"facts_grounding","display_name":"FACTS Grounding","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0e010c3d05ae48ea8826c4174c27aed9","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"fairpoliticsqa","display_name":"FairPoliticsQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_127804d15e9d458886264b7c2a8554ae","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"finance_accounting_index","display_name":"Finance & Accounting Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"finance_agent","display_name":"Finance Agent","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4c932a77cb624e88b1eb83c143534b88","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"finance_agent_v1_1","display_name":"Finance Agent v1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"finance_agent_v2","display_name":"Finance Agent v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6d1eabd36ecb488885533ee2704804da","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"flenqa","display_name":"FlenQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_33e67aa483c747659f28bbf4ae6d3217","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"fleurs","display_name":"FLEURS","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frames","display_name":"FRAMES","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6923465be3b7424f8e7a207e809d0dc0","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frontier_bench_v0_1","display_name":"Frontier-Bench v0.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_553b3da274594398a3713bcb7b3afa2d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frontiercode_1_1_extended_score","display_name":"FrontierCode 1.1 Extended (score)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frontiercode_1_1_main","display_name":"FrontierCode 1.1 Main","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"frontiercode_1_1_main_score","display_name":"FrontierCode 1.1 Main (score)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frontiercode_v1_1_extended","display_name":"FrontierCode v1.1 (Extended)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c666bf86747f4194a293ae4cb54a1df1","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"frontierfinance","display_name":"FrontierFinance","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"frontiermath","display_name":"FrontierMath","category":"math","unit":"percent","scale_min":0,"scale_max":55,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Epoch AI, 4 tiers (Tier 4 = research-level). v2 (Jun 12 2026) corrected 42% of v1 problems — pre-v2 scores are on a different, partly-erroneous problem set, not directly comparable to post-v2. Also note disclosed Epoch/OpenAI funding relationship as a provenance caveat (R8a §1.14, §2.5).","models_covered":2,"index_share":null},{"id":"frontiermath_tier_4","display_name":"FrontierMath Tier 4 (v2)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"frontiermath_tiers_1_3","display_name":"FrontierMath Tiers 1-3","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_131a8a1728b44785bf474e46e254b8be","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frontiermath_tiers_1_3_v2","display_name":"FrontierMath Tiers 1-3 (v2)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"frontierscience_research","display_name":"FrontierScience-Research","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"frontierswe","display_name":"FrontierSWE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"frontierswe_v2","display_name":"FrontierSWE v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"fullstackbench","display_name":"FullStackBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8a69fb40f715478dbe3668b58472c516","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"furniture_assembly","display_name":"Furniture Assembly","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"gaia2","display_name":"Gaia2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4ce546e34701489ca7c890d1a3a0096c","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gameworld","display_name":"GameWorld","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gaokao2023en","display_name":"GaoKao2023en","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aab24e5371704d9db079b045e5b11a05","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gdm_mrcr_v2","display_name":"GDM-MRCR v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6c3d8d40b1334e50b419a6d5f5788334","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gdm_mrcr_v2_8_needle","display_name":"GDM-MRCR v2 (8-needle)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gdp_pdf","display_name":"Gdp Pdf","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"gdpval","display_name":"GDPval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_f7be5cdfc6ed41c99f63660105f869ce","active":false,"notes":"refolded into gdpval_aa; the edition/lane moved into each score's config","models_covered":1,"index_share":null},{"id":"gdpval_aa","display_name":"GDPval-AA","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":12,"index_share":null},{"id":"gdpval_aa_normalized","display_name":"gdpval_aa_normalized","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_94b6620d00e9430381a455dc60e828f0","active":true,"notes":null,"models_covered":100,"index_share":null},{"id":"gdpval_aa_v2","display_name":"GDPval-AA v2","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_553b3da274594398a3713bcb7b3afa2d","active":true,"notes":null,"models_covered":14,"index_share":null},{"id":"gdpval_aa_v2_elo","display_name":"GDPval-AA v2 Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"genebench_pro","display_name":"GeneBench Pro","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_acf3136ad9694471b137d965b747a7f6","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"general_editing_elo","display_name":"General Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"general_t2i_elo","display_name":"General T2I Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"global_mmlu","display_name":"Global MMLU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_49645f65fcba45d39e5f52ab080c7386","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"global_mmlu_lite","display_name":"Global MMLU-Lite","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_33d010562a42487e9578cf616dfeec53","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"gpqa_diamond","display_name":"GPQA Diamond","category":"reasoning","unit":"percent","scale_min":25,"scale_max":96,"higher_better":true,"weight_in_composite":0.1471,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"PhD-level science MC, hardest curated subset. Near-saturated at frontier (Aug 2026 ~90-95%). Highest cross-source agreement of any benchmark in R8a.","models_covered":288,"index_share":0.1588},{"id":"gpqa_main","display_name":"GPQA Main","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_93559fd129504808ae725d13d08b529b","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"graphwalks","display_name":"GraphWalks","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"gray_swan_ipi_benchmark","display_name":"Gray Swan IPI Benchmark","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6db0fbcfe8ff4848b50db480a1be5711","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gsm8k","display_name":"GSM8K","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":18,"index_share":null},{"id":"gsm_8k","display_name":"GSM-8K","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_118237c52f154f449b89d1999110b526","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gsm_plus","display_name":"GSM-Plus","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_49645f65fcba45d39e5f52ab080c7386","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"gsm_symbolic","display_name":"GSM Symbolic","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"harvey_lab_criteria_pass","display_name":"harvey_lab_criteria_pass","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c1f9150dcede44909ee388a3dc05d2ae","active":true,"notes":null,"models_covered":36,"index_share":null},{"id":"harvey_lab_vals","display_name":"Harvey LAB (Vals)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c666bf86747f4194a293ae4cb54a1df1","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"harveys_legal_agent_benchmark","display_name":"Harvey's Legal Agent Benchmark","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"healthbench","display_name":"HealthBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"healthbench_consensus","display_name":"HealthBench Consensus","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a8319c22a50e4818a64634d19511f43d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"healthbench_hard","display_name":"HealthBench Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a8319c22a50e4818a64634d19511f43d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"healthbench_professional","display_name":"HealthBench Professional","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a8319c22a50e4818a64634d19511f43d","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"hellaswag","display_name":"HellaSwag","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d705283605f5404eb26540a36bb3d460","active":true,"notes":null,"models_covered":11,"index_share":null},{"id":"hiddenmath","display_name":"HiddenMath","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0e010c3d05ae48ea8826c4174c27aed9","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"hle","display_name":"Humanity's Last Exam","category":"reasoning","unit":"percent","scale_min":2,"scale_max":70,"higher_better":true,"weight_in_composite":0.1029,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Confirm tools-on/off + text-only/multimodal variant before comparing scores (R8a §1.8) — AA/PricePerToken (~55%) vs Scale AI official (~35%) diverge sharply, likely different methodology variants, not the same measurement.","models_covered":252,"index_share":0.1111},{"id":"hle_diamond","display_name":"HLE Diamond","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"hle_no_tools","display_name":"HLE no tools","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":false,"notes":"refolded into hle; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"hle_verified","display_name":"HLE-Verified","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"hle_with_search","display_name":"HLE with search","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":false,"notes":"refolded into hle; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"hle_with_tools","display_name":"HLE with tools","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_b81290bb2ab64e88bf29b71d8ba48b7b","active":false,"notes":"refolded into hle; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"hmmt","display_name":"HMMT","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bf713be07f1c4f6781df4a9b64ce09c5","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"hmmt_2026_feb","display_name":"HMMT 2026 Feb","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_652c7c2de97b4b489991fb719fa85b4a","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"hmmt_feb25","display_name":"HMMT Feb25","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"hmmt_feb_2025","display_name":"HMMT Feb 2025","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_195871e76b544cee9e330f942e1e8051","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"hmmt_feb_2026","display_name":"HMMT Feb 2026","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"hmmt_nov_2025","display_name":"HMMT Nov 2025","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"hotpotqa","display_name":"HotpotQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0d2165b50b56406db56047fe17ac199c","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"humaneval","display_name":"HumanEval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":19,"index_share":null},{"id":"humaneval_plus","display_name":"HumanEval Plus","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_eb1342ae95b443ed98b6f405b52f2d37","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"humanevalplus","display_name":"HumanEvalPlus","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_33e67aa483c747659f28bbf4ae6d3217","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"humanitys_last_exam_with_tools","display_name":"Humanity's Last Exam (with tools)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_652c7c2de97b4b489991fb719fa85b4a","active":false,"notes":"refolded into hle; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"if_bench","display_name":"IF-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_1785de774a2b440ea167d1ddd5e1b591","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ifbench","display_name":"IFBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":175,"index_share":null},{"id":"ifbench_prompt","display_name":"IFBench (prompt)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ifeval","display_name":"IFEval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":42,"index_share":null},{"id":"ifeval_avg","display_name":"IFEval Avg","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ifeval_instruction_level_accuracy","display_name":"IFEval (instruction-level accuracy)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ifeval_prompt_level_accuracy","display_name":"IFEval (prompt-level accuracy)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"imo","display_name":"IMO 2025","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"imo_answerbench","display_name":"IMO-AnswerBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_652c7c2de97b4b489991fb719fa85b4a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"imo_proofbench_advanced","display_name":"IMO-ProofBench Advanced","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"imo_proofbench_basic","display_name":"IMO-ProofBench Basic","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"imoanswerbench","display_name":"IMOAnswerBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bf713be07f1c4f6781df4a9b64ce09c5","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"include","display_name":"INCLUDE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"infographicvqa","display_name":"InfographicVQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"ioi","display_name":"Ioi","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"it_bench_sre","display_name":"it_bench_sre","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5c9f9bb0d3484940bdb86d6e7e014bcf","active":true,"notes":null,"models_covered":31,"index_share":null},{"id":"jobbench","display_name":"JobBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"judgebench","display_name":"JudgeBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_93aaa1834ee7431193e8e19629a0b424","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"judgebench_overall_score","display_name":"JudgeBench Overall Score","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a469d4cc82b24e61965b5a930a9ba5ff","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kat_claw_bench","display_name":"KAT Claw Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8daae255e67c4e4c9364b5b22c3ec58e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kat_code_bench","display_name":"KAT Code Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8daae255e67c4e4c9364b5b22c3ec58e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_cuda","display_name":"Kernelbench CUDA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_599a92d424b54865bf01fd5d7cbeb036","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_cuda_canonical_board_rtx_pro_6000","display_name":"KernelBench CUDA (canonical board, RTX PRO 6000)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_cuda_glm_5_2_fused_moe_rtx_pro_6000","display_name":"KernelBench CUDA GLM-5.2 Fused MoE (RTX PRO 6000)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_cuda_grid_mingru_sps_rtx_pro_6000","display_name":"KernelBench CUDA Grid + MinGRU SPS (RTX PRO 6000)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_cuda_megaqwen_decode_rtx_pro_6000","display_name":"KernelBench CUDA MegaQwen Decode (RTX PRO 6000)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_grid_mingru_sps","display_name":"Kernelbench Grid + MinGRU SPS","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_599a92d424b54865bf01fd5d7cbeb036","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_hard","display_name":"KernelBench Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f8e2332c4c034edba09fea1b7882b8b5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_mega","display_name":"Kernelbench Mega","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_599a92d424b54865bf01fd5d7cbeb036","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kernelbench_mega_kimi_linear_decode_rtx_pro_6000","display_name":"KernelBench Mega (Kimi-Linear Decode, RTX PRO 6000)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"kina","display_name":"KINA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fd2f13c110594b94ae58f678edcca06a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"lab_bench_practical","display_name":"Lab Bench Practical","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"labbench_2","display_name":"LABBench 2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"latchbio_capabilities","display_name":"Latchbio Capabilities","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"latchbio_singlecellbench","display_name":"LatchBio SingleCellBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"latchbio_spatialbench_verified","display_name":"LatchBio SpatialBench Verified","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_366215880a6a48db9efc6198ca848c0e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"lcr","display_name":"LCR","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"legal_bench","display_name":"Legal Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"legal_research_bench","display_name":"Legal Research Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"ling_3_0_flash_vl_agentic_index","display_name":"Ling-3.0-flash-VL Agentic Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ling_3_0_flash_vl_coding_index","display_name":"Ling-3.0-flash-VL Coding Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ling_3_0_flash_vl_intelligence_index","display_name":"Ling-3.0-flash-VL Intelligence Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"linguasafe","display_name":"LinguaSafe","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"livebench","display_name":"LiveBench","category":"composite","unit":"index","scale_min":40,"scale_max":85,"higher_better":true,"weight_in_composite":0.1103,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Contamination-resistant (fresh Qs, objective auto-scoring, no LLM-judge). Trust canonical livebench.ai only (trust 3) — third-party mirrors (e.g. BenchLM.ai) diverge meaningfully (R8a §1.5, §2.2).","models_covered":81,"index_share":0.1191},{"id":"livecodebench","display_name":"LiveCodeBench v6","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_15dad7768a114aca88498cbfff0fd7a5","active":true,"notes":null,"models_covered":149,"index_share":null},{"id":"lmarena_text_arena_elo","display_name":"LMArena Text Arena Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bf713be07f1c4f6781df4a9b64ce09c5","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"loft_text_retrieval","display_name":"LOFT Text Retrieval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"logicvista","display_name":"LogicVista","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b9316cd9218541edba4a54b3f349acd3","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"long_context_reasoning","display_name":"Long Context Reasoning","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_3a3bd5282f83458e9783b742cd434d55","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"long_horizon_terminal_bench","display_name":"Long-Horizon-Terminal-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d7b4ee6078684e3a9a7eb5ff12f0c81d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"longbench_v2","display_name":"LongBench v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"longcodebench","display_name":"LongCodeBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_1785de774a2b440ea167d1ddd5e1b591","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"longcodebench_1m","display_name":"LongCodeBench 1M","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d8b288e8a4314a718d62098d4463f8f4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"lvbench","display_name":"LVBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"math","display_name":"MATH","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":24,"index_share":null},{"id":"math500","display_name":"MATH500","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_93aaa1834ee7431193e8e19629a0b424","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"math_500","display_name":"MATH-500","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_15dad7768a114aca88498cbfff0fd7a5","active":true,"notes":null,"models_covered":21,"index_share":null},{"id":"math_hard","display_name":"MATH hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_abc78461c41b4ac8b5d1f69d3ee42e4b","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"math_index","display_name":"Math Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a469d4cc82b24e61965b5a930a9ba5ff","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"math_lvl_5","display_name":"MATH Lvl 5","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d705283605f5404eb26540a36bb3d460","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"math_vision","display_name":"MATH-Vision","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"matharena_apex_2025","display_name":"MathArena Apex 2025","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5cf46f49f2b545f2a95b2b42f6f2991d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mathvision","display_name":"MathVision","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b9316cd9218541edba4a54b3f349acd3","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"mathvista","display_name":"MathVista","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4eaa68da41964b1f84786f0dd048a38a","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"mbpp","display_name":"MBPP","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":10,"index_share":null},{"id":"mbpp_evalplus","display_name":"MBPP EvalPlus","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_282bf64514de478b9fde1d211282288c","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mbpp_plus","display_name":"MBPP Plus","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_eb1342ae95b443ed98b6f405b52f2d37","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mceval","display_name":"McEval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_42f387694fac489b8a51914a4e11c794","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mcp_atlas","display_name":"MCP Atlas","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":12,"index_share":null},{"id":"mdeval","display_name":"MdEval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_42f387694fac489b8a51914a4e11c794","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"medcode","display_name":"Medcode","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"medethicalign","display_name":"MedEthicAlign","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"medmcqa","display_name":"MedMCQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"medqa_usmle","display_name":"MedQA-USMLE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"medscribe","display_name":"Medscribe","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"medxpertqa_mm","display_name":"MedXPertQA MM","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"medxpertqa_text","display_name":"MedXpertQA-Text","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mgsm","display_name":"MGSM","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"milu","display_name":"Milu","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_code_bench","display_name":"MiMo Code Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"mimo_cyber_bench","display_name":"MiMo Cyber Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"mimo_v2_6_pro_aa_lcr","display_name":"MiMo-V2.6-Pro AA-LCR","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_aa_omniscience_accuracy","display_name":"MiMo-V2.6-Pro AA-Omniscience Accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_aa_omniscience_non_hallucination_rate","display_name":"MiMo-V2.6-Pro AA-Omniscience Non-Hallucination Rate","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_critpt","display_name":"MiMo-V2.6-Pro CritPt","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_gdpval_aa","display_name":"MiMo-V2.6-Pro GDPval-AA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_hle","display_name":"MiMo-V2.6-Pro HLE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_intelligence_index","display_name":"MiMo-V2.6-Pro Intelligence Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_v2_6_pro_scicode","display_name":"MiMo-V2.6-Pro SciCode","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mimo_visualcoding","display_name":"MiMo VisualCoding","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"minerva","display_name":"Minerva","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"minerva_math","display_name":"Minerva Math","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"mixeval_hard","display_name":"MixEval Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_49645f65fcba45d39e5f52ab080c7386","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mlcr_overall","display_name":"mlcr_overall","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c1f9150dcede44909ee388a3dc05d2ae","active":true,"notes":null,"models_covered":41,"index_share":null},{"id":"mle_bench","display_name":"MLE-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6c3d8d40b1334e50b419a6d5f5788334","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mle_bench_lite","display_name":"MLE-Bench Lite","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7531f4d597aa43ddb248859c44f27611","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mls_bench_lite","display_name":"MLS-Bench-Lite","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"mlvu","display_name":"MLVU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mm_claw","display_name":"MM Claw","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7531f4d597aa43ddb248859c44f27611","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mm_mtbench","display_name":"MM MTBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_23d9f6edc5c14b038816d74071a4dea8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mm_safetybench","display_name":"MM-SafetyBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mmau","display_name":"MMAU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_025dafb136bb47369cd6e8cc4e9d7543","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mmlongbench_128k","display_name":"MMLongBench-128K","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fd2f13c110594b94ae58f678edcca06a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mmlu","display_name":"MMLU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":29,"index_share":null},{"id":"mmlu_pro","display_name":"MMLU-Pro","category":"knowledge","unit":"percent","scale_min":40,"scale_max":100,"higher_better":true,"weight_in_composite":0.1103,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Near-saturated at frontier (~90%+); low differentiation power at the top in 2026 — retained as a floor/sanity-check signal (contamination/regression detector), not a ranking driver.","models_covered":173,"index_share":0.1191},{"id":"mmlu_prox","display_name":"MMLU-ProX","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_eec8957c31744a3c81cf76968cce1c36","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mmlu_prox_lite_ibm","display_name":"MMLU-ProX lite (IBM)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mmlu_redux","display_name":"MMLU-Redux","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97c943d2c5ee4107a9a57d2adea4a5ad","active":true,"notes":null,"models_covered":15,"index_share":null},{"id":"mmmlu","display_name":"MMMLU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":9,"index_share":null},{"id":"mmmu","display_name":"MMMU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4eaa68da41964b1f84786f0dd048a38a","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"mmmu_pro","display_name":"MMMU-Pro","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":106,"index_share":null},{"id":"mmstar","display_name":"MMStar","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4492b4b1a6fe4d84b6d3770f93bb7b2f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mmvu","display_name":"MMVU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mobile_actions","display_name":"Mobile Actions","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mobileworld","display_name":"MobileWorld","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mortgagetax","display_name":"MortgageTax","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0209f765bc4548f78ed2985f52273135","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mrcr","display_name":"MRCR (multi-needle retrieval)","category":"other","unit":"percent","scale_min":20,"scale_max":97,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"MUST capture needle_count (2/4/8) and context_length bucket per score row — the single largest comparability trap found in R8a (§1.13, §4.6): scores vary 30-60+ points by bucket alone. Weight 0 pending that structured capture.","models_covered":6,"index_share":null},{"id":"mrcr_1m","display_name":"MRCR 1M","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c59159c0343e49c096da469a4161a2e2","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mrcr_256k_512k","display_name":"MRCR 256K-512K","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_09f703cd057f467692c632c989f68b58","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mrcr_v2_8_needle","display_name":"MRCR v2 (8-needle)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"mrcr_v2_8_needle_128k","display_name":"MRCR v2 8 needle 128k","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_21ea043aa0d647e0b594a78b711644f0","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mrcr_v2_8_needle_128k_average","display_name":"MRCR v2 8 needle 128k (average)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"mtbench_avg","display_name":"MTBench Avg","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"mtob_eng_kgv","display_name":"MTOB (eng->kgv)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"mtob_kgv_eng","display_name":"MTOB (kgv->eng)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multi_character_editing_elo","display_name":"Multi Character Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multi_input_editing_elo","display_name":"Multi Input Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multi_policy_accuracy","display_name":"Multi-policy accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7a3458f60e154a0ebff41b4ff6a24883","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multi_product_editing_elo","display_name":"Multi Product Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multi_swe_bench","display_name":"Multi-SWE-bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7531f4d597aa43ddb248859c44f27611","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multichallenge","display_name":"MultiChallenge","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d8b288e8a4314a718d62098d4463f8f4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multiif","display_name":"MultiIF","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68ba010710a0403caedc8b612420d5e3","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"multilingual_mmlu","display_name":"Multilingual MMLU","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4eaa68da41964b1f84786f0dd048a38a","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"multipl_e","display_name":"MultiPL-E","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9cb4e004675749079014377f68f26d29","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"multipl_e_humaneval","display_name":"MultiPL-E HumanEval","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_9c1fc86de31b467badcaeb6b68cb1153","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"multiple","display_name":"MULTIPLE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"musr","display_name":"MuSR","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d705283605f5404eb26540a36bb3d460","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"mvbench","display_name":"MVBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4492b4b1a6fe4d84b6d3770f93bb7b2f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"mysterymechanism","display_name":"Mysterymechanism","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"naturalquestions","display_name":"NaturalQuestions","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_438a8c7ec05149b9904338625ef1bf48","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"next_qa","display_name":"NExT-QA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"nl2repo","display_name":"NL2Repo","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"nl2repo_bench","display_name":"NL2Repo-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"object_environment_editing_elo","display_name":"Object Environment Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ocr_reasoning","display_name":"OCR-Reasoning","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a13211de6c0a4398bf54b5b63e097761","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ocrbench","display_name":"OCRBench","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4492b4b1a6fe4d84b6d3770f93bb7b2f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"ocrbench_v2","display_name":"OCRBench v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_a13211de6c0a4398bf54b5b63e097761","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"officeqa","display_name":"Officeqa","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"officeqa_pro","display_name":"Officeqa Pro","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"official_a","display_name":"Official A","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_599a92d424b54865bf01fd5d7cbeb036","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ojbench","display_name":"OJBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68ba010710a0403caedc8b612420d5e3","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"olympiadbench","display_name":"OlympiadBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8a69fb40f715478dbe3668b58472c516","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"omni_math","display_name":"Omni-MATH","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_76c09e2bfa10439f8a5c27910779ba35","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"omnidoc","display_name":"OmniDoc","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"omnidocbench","display_name":"OmniDocBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4ce546e34701489ca7c890d1a3a0096c","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"omnidocbench_1_5","display_name":"OmniDocBench 1.5","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"omnimath","display_name":"OmniMath","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_33e67aa483c747659f28bbf4ae6d3217","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"online_mind2web","display_name":"Online-Mind2Web","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6d1eabd36ecb488885533ee2704804da","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"openai_internal_multi_policy_moderation_accuracy","display_name":"OpenAI internal multi-policy moderation accuracy","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fabbc8b6d4b74f5095713f8300d109a8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"openai_moderation_2022","display_name":"OpenAI Moderation 2022","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7a3458f60e154a0ebff41b4ff6a24883","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"openai_moderation_2022_f1","display_name":"OpenAI Moderation (2022) F1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fabbc8b6d4b74f5095713f8300d109a8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"openbookqa","display_name":"OpenBookQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_572e3239dfa848069a47e0a6d9284200","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"osworld","display_name":"OSWorld","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5a7b2bf97fed4a3cb01efdb8d503d9b4","active":true,"notes":null,"models_covered":25,"index_share":null},{"id":"osworld_2_0","display_name":"OSWorld-2.0","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_5f55387d72cd481ebb4a7dc5d6f940e5","active":false,"notes":"refolded into osworld; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"osworld_2_0_v2026_08_08_offline_set_partial_score","display_name":"OSWorld 2.0 (v2026.08.08, offline set, partial score)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"osworld_g","display_name":"OSWorld-G","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"osworld_verified","display_name":"OSWorld-Verified","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_f8e2332c4c034edba09fea1b7882b8b5","active":false,"notes":"refolded into osworld; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"otis_mock_aime_2024_2025","display_name":"OTIS Mock AIME 2024-2025","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ovobench","display_name":"OVOBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"paperbench","display_name":"PaperBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"perception_test","display_name":"Perception Test","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"personqa","display_name":"PersonQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7a3458f60e154a0ebff41b4ff6a24883","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"phibench","display_name":"PhiBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b117e42664ba451c8a56cc67a74071b4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"phybench","display_name":"PhyBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fa88a610ad23483087d24af0b402fafa","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"pinchbench","display_name":"PinchBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_407580b701a043a38dfb38f539a26607","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"piqa","display_name":"PIQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f469e4e959734d1cbf42fcdfd1a6f177","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"plawbench","display_name":"PLawBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"polyguard","display_name":"PolyGuard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"polymath","display_name":"PolyMATH","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68ba010710a0403caedc8b612420d5e3","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"posttrainbench","display_name":"PostTrainBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"prbench_finance","display_name":"PRBench-Finance","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"prbench_legal","display_name":"PRBench-Legal","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"profbench","display_name":"ProfBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"programbench","display_name":"ProgramBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"programbench_almost_solved","display_name":"ProgramBench (Almost Solved)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"proofbench","display_name":"ProofBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_45cf67d420f54d08b826c6a784ae397c","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"proofbench_v1_1","display_name":"ProofBench v1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"proteingym_hard","display_name":"ProteinGym Hard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"protocolqa_open_ended","display_name":"Protocolqa Open Ended","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"public_benefits_bench","display_name":"Public Benefits Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"public_benefits_bench_v1_1","display_name":"Public Benefits Bench v1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"qwenqoderbench","display_name":"QwenQoderBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"qwenreactbench","display_name":"QwenReactBench","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"qwensvgbench","display_name":"QwenSVGBench","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"qwenswebench","display_name":"QwenSWEBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"qwenswebench_v2","display_name":"QwenSWEBench V2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"real_world_vulnerability_discovery_20_languages","display_name":"Real world vulnerability discovery (20 languages)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6db0fbcfe8ff4848b50db480a1be5711","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"realworldqa","display_name":"RealWorldQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4b491fc5dc374246822a3d46b2e00025","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"redisqa","display_name":"ReDisQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_8b6e066584eb4d1d93a29fd4f9f67362","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"refcoco","display_name":"RefCOCO","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"refcoco_a","display_name":"RefCOCO-A","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"refcoco_b","display_name":"RefCOCO-B","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"refspatialbench","display_name":"RefSpatialBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"riemannbench","display_name":"RiemannBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"robospatial_pointing","display_name":"RoboSpatial Pointing","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"robospatial_vqa","display_name":"RoboSpatial VQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ruler","display_name":"RULER","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f7be5cdfc6ed41c99f63660105f869ce","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"ruler_128k","display_name":"RULER 128K","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"ruler_64k","display_name":"RULER 64K","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"sage","display_name":"SAGE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4c932a77cb624e88b1eb83c143534b88","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"salad_bench","display_name":"SALAD-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"scicode","display_name":"SciCode","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":true,"notes":null,"models_covered":195,"index_share":null},{"id":"screenspot","display_name":"ScreenSpot","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4492b4b1a6fe4d84b6d3770f93bb7b2f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"screenspot_pro","display_name":"ScreenSpot-Pro","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_2febc58fd4a64b58b24e49b649573bde","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"sec_bench_pro","display_name":"SEC Bench Pro","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"simpleqa","display_name":"SimpleQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d96417a9afb74afd8322737c2b9940c9","active":true,"notes":null,"models_covered":17,"index_share":null},{"id":"skillsbench","display_name":"SkillsBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"social_media_trends_editing_elo","display_name":"Social Media Trends Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"social_media_trends_t2i_elo","display_name":"Social Media Trends T2I Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"spreadsheetbench_2","display_name":"SpreadsheetBench 2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"spreadsheetbench_v1","display_name":"SpreadSheetBench-v1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"sre_bench","display_name":"SRE Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"stylization_elo","display_name":"Stylization Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"superchem","display_name":"SUPERChem","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_5cf46f49f2b545f2a95b2b42f6f2991d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"supergpqa","display_name":"SuperGPQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_c157934da2b1494e95383b8c151c338e","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"swe_atlas","display_name":"SWE Atlas","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_801af9927a3a46269acc9c832171c20e","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"swe_atlas_qna","display_name":"SWE Atlas Qna","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"swe_bench","display_name":"SWE-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4f83241a7eda4f5c9c28b9e12028ed54","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"swe_bench_multilingual","display_name":"SWE-bench Multilingual","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_15dad7768a114aca88498cbfff0fd7a5","active":true,"notes":null,"models_covered":17,"index_share":null},{"id":"swe_bench_multimodal","display_name":"SWE Bench Multimodal","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"swe_bench_pro","display_name":"SWE-bench Pro","category":"code","unit":"percent","scale_min":5,"scale_max":65,"higher_better":true,"weight_in_composite":0,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Scale AI, 1,865 tasks, contamination-resistant. MUST capture dataset_split (public vs private/held-out) per score — public and private numbers are not comparable (R8a §1.3, §4.7). Weight 0 pending split-aware ingestion; do not blend public/private silently.","models_covered":58,"index_share":null},{"id":"swe_bench_verified","display_name":"SWE-bench Verified","category":"code","unit":"percent","scale_min":10,"scale_max":100,"higher_better":true,"weight_in_composite":0.1471,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"OpenAI-created, 500 human-filtered instances. Reliability degrading (Feb 2026 OpenAI audit: 59.4% of hardest unsolved instances have flawed tests) — directional, not precise. OpenAI recommends swe_bench_pro over this going forward.","models_covered":110,"index_share":0.1588},{"id":"swe_fficiency","display_name":"SWE-fficiency","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f8e2332c4c034edba09fea1b7882b8b5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"swe_lancer_ic_swe","display_name":"SWE-Lancer IC SWE","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_777e09aae04a48f3bc63eda13c64f254","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"swe_marathon","display_name":"SWE-Marathon","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"swe_mm","display_name":"SWE-MM","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"swe_multilingual","display_name":"SWE Multilingual","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_28687023448c4de59b92d6744c6737e6","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"swefish","display_name":"SWEFish","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"sysbench","display_name":"SysBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_76c09e2bfa10439f8a5c27910779ba35","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"tau2_airline","display_name":"Tau2 airline","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau2_average_over_3","display_name":"Tau2 (average over 3)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_8af334977ff34304807c6f587f5abffa","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau2_bench_retail","display_name":"tau2-bench (Retail)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau2_bench_telecom","display_name":"tau2-bench (Telecom)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_25639cafaa534a87b7332e203f141975","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau2_retail","display_name":"Tau2 retail","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau2_telecom","display_name":"Tau2 telecom","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_57858c93b69d4f50be7228ce5954a748","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau3_banking","display_name":"tau3-Banking","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_3a3bd5282f83458e9783b742cd434d55","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"tau3_bench","display_name":"tau3-bench","category":"agentic","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"admin","first_seen_run_id":null,"active":true,"notes":"tau3-bench: a later generation than the tau_bench column. Not folded and not weighted - it needs anchors fitted over its OWN population first (2026-09-05).","models_covered":1,"index_share":null},{"id":"tau3_bench_avg","display_name":"τ³-bench (AVG)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cf71e14d26914696a09b7b6f0b29b27e","active":true,"notes":"tau3 / banking: NOT folded into tau_bench - the distribution is not comparable on 20-95 anchors (mean 20.7 vs 62.7; 56 of 103 rows clamped to 0). Reversed 2026-09-05.","models_covered":1,"index_share":null},{"id":"tau3_bench_banking","display_name":"tau3-bench (Banking)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_407580b701a043a38dfb38f539a26607","active":true,"notes":"tau3 / banking: NOT folded into tau_bench - the distribution is not comparable on 20-95 anchors (mean 20.7 vs 62.7; 56 of 103 rows clamped to 0). Reversed 2026-09-05.","models_covered":9,"index_share":null},{"id":"tau3_bench_telecom","display_name":"tau3-bench (Telecom)","category":"agentic","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"admin","first_seen_run_id":null,"active":true,"notes":"tau3-bench telecom domain. Not folded into tau_bench (2026-09-05).","models_covered":2,"index_share":null},{"id":"tau3_telecom","display_name":"tau3-Telecom","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4c932a77cb624e88b1eb83c143534b88","active":true,"notes":"tau3 / banking: NOT folded into tau_bench - the distribution is not comparable on 20-95 anchors (mean 20.7 vs 62.7; 56 of 103 rows clamped to 0). Reversed 2026-09-05.","models_covered":1,"index_share":null},{"id":"tau_bench","display_name":"tau-bench / tau2-bench","category":"agentic","unit":"percent","scale_min":20,"scale_max":95,"higher_better":true,"weight_in_composite":0.0442,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Tool-using conversational agent task success (airline/retail/banking domains). tau-bench and tau2-bench (dynamic-env successor) are DIFFERENT benchmarks despite the name similarity (R8a §3) — do not merge scores across editions; capture edition in score_config.","models_covered":192,"index_share":0.0477},{"id":"tau_bench_banking","display_name":"tau_bench_banking","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_94b6620d00e9430381a455dc60e828f0","active":true,"notes":"tau3 / banking: NOT folded into tau_bench - the distribution is not comparable on 20-95 anchors (mean 20.7 vs 62.7; 56 of 103 rows clamped to 0). Reversed 2026-09-05.","models_covered":96,"index_share":null},{"id":"tau_bench_retail","display_name":"tau-bench Retail","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_6c738b9f3a2d4a97b22b79e5db77ddfa","active":false,"notes":"refolded into tau_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"tau_bench_v3_average","display_name":"tau-bench V3 Average","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f7be5cdfc6ed41c99f63660105f869ce","active":true,"notes":"tau3 / banking: NOT folded into tau_bench - the distribution is not comparable on 20-95 anchors (mean 20.7 vs 62.7; 56 of 103 rows clamped to 0). Reversed 2026-09-05.","models_covered":1,"index_share":null},{"id":"tax_agent_bench","display_name":"Tax Agent Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"tempcompass","display_name":"TempCompass","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"terminal_bench","display_name":"Terminal-Bench (Hard)","category":"agentic","unit":"percent","scale_min":5,"scale_max":90,"higher_better":true,"weight_in_composite":0.0441,"status":"core","origin":"seed","first_seen_run_id":null,"active":true,"notes":"Fractional pass rate across 89 hand-crafted CLI/terminal tasks, ~5 attempts/task averaged. Scaffold/agent-harness-sensitive (101 agents / 23 scaffolds tracked) — capture scaffold as a field, not just model.","models_covered":232,"index_share":0.0476},{"id":"terminal_bench_2_1_vals","display_name":"Terminal-Bench 2.1 (Vals)","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"terminal_bench_4_0","display_name":"Terminal-Bench 4.0","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"deprecated","origin":"auto","first_seen_run_id":"run_b743334c36e74035a3b3c99d2fbb86b8","active":false,"notes":"refolded into terminal_bench; the edition/lane moved into each score's config","models_covered":0,"index_share":null},{"id":"terminal_bench_science","display_name":"Terminal-Bench-Science","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fa44f3cefc824f43ba6c89894e5d3dd1","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"terminal_bench_science_0_1","display_name":"Terminal-Bench-Science 0.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b743334c36e74035a3b3c99d2fbb86b8","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"text_editing_elo","display_name":"Text Editing Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"tomato","display_name":"TOMATO","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"tool_decathlon","display_name":"Tool-Decathlon","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_bf713be07f1c4f6781df4a9b64ce09c5","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"toolathlon","display_name":"Toolathlon","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d5e2006f4e3e4803b6aa364787492ff0","active":true,"notes":null,"models_covered":7,"index_share":null},{"id":"toolathlon_verified","display_name":"Toolathlon Verified","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":11,"index_share":null},{"id":"toxicchat","display_name":"ToxicChat","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7a3458f60e154a0ebff41b4ff6a24883","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"toxicchat_f1","display_name":"ToxicChat F1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fabbc8b6d4b74f5095713f8300d109a8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"toxigen","display_name":"Toxigen","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_496cde7b49d248459d3e7e1c562450da","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"triviaqa","display_name":"TriviaQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_572e3239dfa848069a47e0a6d9284200","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"truthfulqa","display_name":"TruthfulQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d705283605f5404eb26540a36bb3d460","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"tulu3_safety_eval_avg","display_name":"Tulu3 Safety Eval Avg","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_199699ef9abb492e825cd5e67ed4501d","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"usamo_2026","display_name":"USAMO 2026","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_ef9b4984839b4ab5bb4343f87af67480","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vals_finance_agent_v2","display_name":"Vals Finance Agent v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vals_index","display_name":"Vals Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_2e5a562a40d64392a3a803438b1da5c3","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"vals_multimodal_index","display_name":"Vals Multimodal Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_0209f765bc4548f78ed2985f52273135","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vals_rsi_index","display_name":"Vals Rsi Index","category":"other","unit":"index","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"vct","display_name":"Vct","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vibe_code_bench","display_name":"Vibe Code Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_b4dff29e984149d2a2058f09ba55b63e","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"vibe_code_bench_1_100","display_name":"Vibe Code Bench 1 100","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vibe_code_bench_v1_1","display_name":"Vibe Code Bench v1.1","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f075fa67af7b4ec7873cceb3d715f171","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"vibe_pro","display_name":"VIBE-Pro","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7531f4d597aa43ddb248859c44f27611","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"video_mme","display_name":"Video-MME","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_f8e2332c4c034edba09fea1b7882b8b5","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"videohallucer","display_name":"VideoHallucer","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"videomme","display_name":"VideoMME","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fd2f13c110594b94ae58f678edcca06a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"videosimpleqa","display_name":"VideoSimpleQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vision2web","display_name":"Vision2Web","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_4b491fc5dc374246822a3d46b2e00025","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"visual_design_t2i_elo","display_name":"Visual Design T2I Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_074aeec360a54414826536d5c35dc3cc","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vlguard","display_name":"VLGuard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"voicebench","display_name":"VoiceBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_025dafb136bb47369cd6e8cc4e9d7543","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vqa_v2","display_name":"VQA-v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_519e7de29aa54015827d548919d40783","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"vsi_bench","display_name":"VSI-Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_908db40ad08d44228fdcb01f4ee2ad7e","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"wandr","display_name":"Wandr","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_90e29a1a531f4ac58cd684e94d71b97b","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"webarena_verified","display_name":"WebArena-Verified","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"webtest","display_name":"WebTest","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"widesearch","display_name":"WideSearch","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":4,"index_share":null},{"id":"wildbench","display_name":"WildBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_94e056bd14a14c68998308fa2fa0c463","active":true,"notes":null,"models_covered":5,"index_share":null},{"id":"wildbench_v2","display_name":"Wildbench v2","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_eb1342ae95b443ed98b6f405b52f2d37","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"wildclawbench","display_name":"WildClawBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_aff8de7dba644d48940dfb9eb3d32d96","active":true,"notes":null,"models_covered":6,"index_share":null},{"id":"wildguard","display_name":"WildGuard","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"winogrande","display_name":"Winogrande","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_d705283605f5404eb26540a36bb3d460","active":true,"notes":null,"models_covered":8,"index_share":null},{"id":"wmdp_bio","display_name":"Wmdp Bio","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"wmdp_chem","display_name":"Wmdp Chem","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"wmdp_cyber","display_name":"Wmdp Cyber","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_97d9de8e45c846f28b6d5d8b27d512b8","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"workarena_elo","display_name":"WorkArena Elo","category":"other","unit":"elo","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7fc23edf575148a083cb15bfba2b88d7","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"workspace_bench","display_name":"Workspace Bench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fd2f13c110594b94ae58f678edcca06a","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"workspacebench","display_name":"WorkSpaceBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6028ac39c0fb4d9a90025f0eba1e265f","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"worldvqa","display_name":"WorldVQA","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"writingbench","display_name":"WritingBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_68ba010710a0403caedc8b612420d5e3","active":true,"notes":null,"models_covered":3,"index_share":null},{"id":"xdailybench","display_name":"xDailyBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_7d9a7c8edc82492584a1771d1e102ec4","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"xstest","display_name":"XSTest","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_6045fccb592d48c0b7f7c3b41cdd25e5","active":true,"notes":null,"models_covered":1,"index_share":null},{"id":"zebralogic","display_name":"ZebraLogic","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_cc28075b1de84a93a408d60c29c5416f","active":true,"notes":null,"models_covered":2,"index_share":null},{"id":"zerobench","display_name":"ZeroBench","category":"other","unit":"percent","scale_min":null,"scale_max":null,"higher_better":true,"weight_in_composite":0,"status":"provisional","origin":"auto","first_seen_run_id":"run_fc6b593f74ec40498ea09b9410e24246","active":true,"notes":null,"models_covered":2,"index_share":null}]}