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 37.3 #41 of 337
Knowledge 5
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 42.7% #41 of 321+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 92.6% #278 of 321
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -10.3 #94 of 321
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 41% #39 of 83
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 21% #35 of 64
Reasoning 6
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 90.8% #29 of 61+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 88% #27 of 64
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 60.2% #26 of 63+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 59.5% #29 of 66
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.2% #18 of 18
Chess Puzzles Models choose the best next move from a novel chess position Epoch 43% #24 of 68
Math 2
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 61% #15 of 54
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 82.1% #15 of 69
Science 5
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 39.5% #47 of 337
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 20.6% #28 of 324
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 25.3% #18 of 18
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 53.6% #36 of 140
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 3.3% #23 of 33
Coding 4
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 11.6% #37 of 132+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 80.9% #20 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 67.2% #15 of 44
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 40.3% #16 of 37
Agents 7
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 50.2% #35 of 133
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,342 #32 of 140
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 35.8% #6 of 29
EnterpriseOps-Gym-AA Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 40.8% #20 of 43
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 48 #30 of 175
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 42.5% #15 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 31.1% #34 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 78.6% #29 of 127
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,257 #41 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 31.4% #12 of 37
Writing 17
Arena Textcreative writing Human pairwise preferences in the stated text vote pool Arena 1,410 #56 of 195+14 versions & slices overall Human pairwise preferences in the stated text vote pool Arena 1,453 #48 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,469 #62 of 181English Human pairwise preferences in the stated text vote pool Arena 1,441 #62 of 188French Human pairwise preferences in the stated text vote pool Arena 1,458 #44 of 149German Human pairwise preferences in the stated text vote pool Arena 1,455 #32 of 154instruction following Human pairwise preferences in the stated text vote pool Arena 1,437 #45 of 188Japanese Human pairwise preferences in the stated text vote pool Arena 1,414 #37 of 138Korean Human pairwise preferences in the stated text vote pool Arena 1,416 #32 of 144non-English Human pairwise preferences in the stated text vote pool Arena 1,417 #65 of 188Polish Human pairwise preferences in the stated text vote pool Arena 1,404 #70 of 133Russian Human pairwise preferences in the stated text vote pool Arena 1,428 #55 of 186Spanish Human pairwise preferences in the stated text vote pool Arena 1,446 #47 of 155overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,431 #63 of 188creative writing · full cohort Human pairwise preferences in the stated text vote pool Arena 1,396 #65 of 187
EQ-Bench Longform Creative Writing1.11 Longform Creative Writing 1.11: Models plan, revise and write a story across eight turns, graded with a writing rubric EQ-Bench 75.5% #26 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,829 #22 of 91
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 19.4% #24 of 64
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 84% #38 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 42.4% #43 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 84.4% #31 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 36.5% #35 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 83.7% #10 of 275
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 24% #12 of 133
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,457 #17 of 33
Legacy · saturated or no longer reported 9
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 91.1% #27 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 91.6% #21 of 133
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 98.3% #20 of 130
SWE-rebenchall · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 43.6% #6 of 6+5 versions & slices Go · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 54.3% #6 of 6Java · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 41.9% #6 of 6Python · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 37% #6 of 6Rust · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 32.8% #6 of 6TypeScript · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 52.5% #6 of 6
No benchmark matches
OpenKimi K3max-12%+1,022%$2.00Context: 1.05M → 1M+4
Gemini 4 Argonhigh+5%+1,016%*$1.99Context: 1.05M → 1M+3
GLM 5.3maxOpen-16%+1,025%$2.01Context: 1.05M → 1M+5
DeepSeek V4 Pro 0813maxOpen-21%+278%$0.67Context: 1.05M → 1M+6