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 #86 of 339
Knowledge 4
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 41.6% #43 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 67.7% #129 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 2 #61 of 323
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 40.3% #43 of 84
Reasoning 5
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 90.6% #33 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 79.5% #39 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 37.8% #36 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 36.5% #39 of 69
Chess Puzzles Models choose the best next move from a novel chess position Epoch 21% #50 of 69
Math 3
AA Analyst Agent Data-analyst tasks: the model explores data with tools and reports findings AA 23.8% #29 of 43
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.9% #52 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 33.3% #56 of 70
Science 4
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 31.9% #76 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 5.4% #79 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 47% #68 of 142
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 0% #36 of 45
Coding 9
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 1% #56 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 55.1% #62 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 5% #38 of 44
FrontierCode1.1 Agents implement changes in real repositories, graded against maintainer-defined requirements AA 15.8% #32 of 38
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,414 #64 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,415 #65 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,414 #64 of 97
SWE-bench Pro (v2 full) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 89.9% #15 of 16
SWE-bench Pro (v2 hard) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 56.9% #14 of 16
Agents 6
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 5% #86 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 833 #75 of 142
EnterpriseOps-Gym-AA Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 38% #26 of 43
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 1,081 #64 of 177
τ³-benchbanking · 1.0.1 τ-bench official · 3-banking-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 25% #17 of 21
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 29.1% #36 of 134
Multimodal 1
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 73.5% #61 of 128
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,390 #73 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,381 #83 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,441 #63 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,493 #47 of 198English Human pairwise preferences in the stated text vote pool Arena 1,441 #63 of 205French Human pairwise preferences in the stated text vote pool Arena 1,460 #46 of 164German Human pairwise preferences in the stated text vote pool Arena 1,445 #41 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,425 #59 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,428 #31 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,406 #40 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,434 #42 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,450 #27 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,431 #56 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,449 #46 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,441 #49 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,387 #70 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,442 #49 of 198
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 72.5% #35 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,609 #42 of 94
Health & law 6
Harvey LAB-AA1.1 Legal agents work from case documents; every rubric criterion must pass and material hallucinations receive no credit AA 0% #18 of 23
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 6.1% #74 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 83% #49 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 41.2% #46 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 85.4% #25 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 28.4% #47 of 73
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 77.3% #78 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 12.8% #47 of 135
Legacy · saturated or no longer reported 3
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 87.2% #57 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 88.3% #44 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 88.9% #50 of 131
No benchmark matches
CheaperGemini 3.8 Flashunstated+85%-13%*$0.75 / $3.75Sampling parameters are ignored+1
BetterDeepSeek V4.1 Flash 1017maxOpen+5%-56%$0.26Pass back reasoning_content · Chat Completions+4
CheaperQwen3.6 Plusunstated+10%-35%$0.50 / $3
GPT-6 Lunamax+3%-89%$0.068Function calling only with none · Chat Completions+3
Grok 4.5high+20%+28%$0.76
GLM 5.3maxOpensame+237%$2.01No image input+4
Kimi K2.7 CodeunstatedOpen-9%same$0.95 / $4Memory (4-bit): 571 GB → 616 GB+1