Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 AA Intelligence Index 4.3.2: Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 25.2 #82 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 22.5% #132 of 321+1 versions & slices Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 27.7% #28 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 1.1 #63 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 78% #9 of 248
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 17% #45 of 64
Math 1
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 34.4% #54 of 69
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 35.6% #60 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 9.1% #63 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 46.1% #69 of 140
Coding 3
Terminal-Bench4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 1% #54 of 132+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 61% #52 of 156
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 47% #16 of 242
Agents 6
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 17.4% #65 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 915 #64 of 140
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications AA 22.4% #18 of 29
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 40.6% #22 of 43
GDPval-AA (work tasks)2.1 GDPval-AA (work tasks) 2.1: Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 13.4 #102 of 175
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 17.5% #61 of 134
Multimodal 3
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 80.5% #18 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,278 #26 of 88
Chartography Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 15.8% #30 of 37
Writing 15
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,431 #45 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,456 #43 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,510 #30 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,459 #35 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,472 #29 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,471 #22 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,440 #43 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,412 #38 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,414 #33 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,445 #33 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,450 #27 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,458 #30 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,457 #32 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,455 #35 of 188creative writing · full cohort Arena Text · creative writing · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,439 #34 of 187
Health & law 2
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 9.4% #42 of 64
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 16.4% #50 of 69
Documents 3
AA-LCR (long context)1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 73% #102 of 275
GDP.pdfAA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 12.2% #48 of 133
Arena Document Arena Document · overall: Human pairwise preferences in the stated document vote pool Arena 1,444 #24 of 33
Legacy · saturated or no longer reported 4
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 90% #35 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 87.9% #45 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 93.3% #38 of 130
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 93% #30 of 245
No benchmark matches