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 38.8 #37 of 339
Knowledge 4
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 51.6% #17 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 54.1% #100 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 25.3 #21 of 323
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 48.3% #29 of 84
Reasoning 6
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 94.8% #28 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 85.7% #36 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 58.2% #31 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 52.6% #36 of 69
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.3% #16 of 19
Chess Puzzles Models choose the best next move from a novel chess position Epoch 35% #39 of 69
Math 5
AA Analyst Agent Data-analyst tasks: the model explores data with tools and reports findings AA 35% #25 of 43
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 24.4% #38 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 57.2% #39 of 70
MathArenaArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.7% #16 of 24+1 versions & slices BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 29.3% #16 of 24
Science 3
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 42.7% #35 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 15.4% #45 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 55% #29 of 142
Coding 6
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 10.6% #41 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 81.6% #19 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 53.8% #23 of 44
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,553 #34 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,553 #35 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,553 #34 of 97
Agents 7
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 57.9% #26 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,278 #40 of 142
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 1,381 #42 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 47.9% #2 of 21
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 22.5% #27 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 42.1% #15 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 80.4% #20 of 128
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,287 #20 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 17% #24 of 37
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,442 #28 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,452 #24 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,466 #34 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,494 #43 of 198English Human pairwise preferences in the stated text vote pool Arena 1,453 #43 of 205French Human pairwise preferences in the stated text vote pool Arena 1,457 #51 of 164German Human pairwise preferences in the stated text vote pool Arena 1,448 #39 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,445 #39 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,431 #29 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,402 #42 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,440 #36 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,431 #50 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,449 #37 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,451 #44 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,448 #38 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,442 #28 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,448 #39 of 198
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,576 #47 of 94
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech -5.1 #45 of 45
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 16.1% #34 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 86% #15 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 43.3% #38 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 86.9% #18 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 38% #33 of 73
Documents 3
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 79.3% #55 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 18.8% #28 of 135
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,452 #20 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 93.1% #12 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 93.4% #13 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 97.8% #27 of 131
SWE-rebenchall · May 15, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 63.8% #2 of 6+5 versions & slices Go · May 15, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 68.6% #4 of 6Java · May 15, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 60% #1 of 6Python · May 15, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 54% #2 of 6Rust · May 15, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 64% #2 of 6TypeScript · May 15, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 70.8% #3 of 6
No benchmark matches
CheaperGLM 5.3 FlashmaxOpen+12%-63%$0.28Defaults to max · Self-hosted+4
CheaperQwen3.8 FlashthinkingOpen+8%-51%$0.37Context: 500K → 262K+6
CheaperDeepSeek V4 Pro 0813maxOpen-6%-11%$0.67No image input+5
CheaperLing 3.0 Flash FinthinkingOpen-8%-97%$0.06 / $0.18Context: 500K → 262K+1
Gemini 3.8 Flashmedium+9%+22%*$0.93Sampling parameters are ignored+1
Kimi K3maxOpen+9%+163%$2.00Sampling parameters are fixed+3