Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 25.2 #82 of 337
Knowledge 5
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 22.5% #132 of 321+1 versions & slices 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 Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 1.1 #63 of 321
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 78% #9 of 248
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) 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 Very hard expert questions across many fields, written to stump today’s models AA 35.6% #60 of 337
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 9.1% #63 of 324
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 46.1% #69 of 140
Coding 3
Terminal-Bench4.0 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 Older, easier version of Terminal-Bench; Still widely reported AA 61% #52 of 156
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 47% #16 of 242
Agents 6
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 Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 915 #64 of 140
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 22.4% #18 of 29
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 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 13.4 #102 of 175
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 17.5% #61 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 80.5% #18 of 127
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,278 #26 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 15.8% #30 of 37
Writing 15
Arena Textcreative writing Human pairwise preferences in the stated text vote pool Arena 1,431 #45 of 195+14 versions & slices overall Human pairwise preferences in the stated text vote pool Arena 1,456 #43 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,510 #30 of 181English Human pairwise preferences in the stated text vote pool Arena 1,459 #35 of 188French Human pairwise preferences in the stated text vote pool Arena 1,472 #29 of 149German Human pairwise preferences in the stated text vote pool Arena 1,471 #22 of 154instruction following Human pairwise preferences in the stated text vote pool Arena 1,440 #43 of 188Japanese Human pairwise preferences in the stated text vote pool Arena 1,412 #38 of 138Korean Human pairwise preferences in the stated text vote pool Arena 1,414 #33 of 144non-English Human pairwise preferences in the stated text vote pool Arena 1,445 #33 of 188Polish Human pairwise preferences in the stated text vote pool Arena 1,450 #27 of 133Russian Human pairwise preferences in the stated text vote pool Arena 1,458 #30 of 186Spanish Human pairwise preferences in the stated text vote pool Arena 1,457 #32 of 155overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,455 #35 of 188creative writing · full cohort Human pairwise preferences in the stated text vote pool Arena 1,439 #34 of 187
Health & law 2
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 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 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 73% #102 of 275
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 12.2% #48 of 133
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,444 #24 of 33
Legacy · saturated or no longer reported 4
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 Models answer graduate-level science multiple-choice questions Epoch 81.8% #65 of 133
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 80% #70 of 130
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 93% #30 of 245
No benchmark matches