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 21.5 #108 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 40.8% #45 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 84.3% #197 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -9.2 #90 of 321
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 41.4% #38 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 7% #60 of 64
Reasoning 6
ARC-AGI-1public evaluation ARC-AGI-1 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 46.5% #51 of 61+1 versions & slices semi-private ARC-AGI-1 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 37.7% #53 of 64
ARC-AGI-2public evaluation ARC-AGI-2 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 0.8% #51 of 63+1 versions & slices semi-private ARC-AGI-2 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 4.6% #52 of 66
ARC-AGI-3semi-private ARC-AGI-3 · semi-private: Measures interactive game solving through relative human action efficiency ARC 0% #18 of 18
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 36% #36 of 68
Math 3
AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings AA 43.8% #17 of 43
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 56.1% #17 of 54
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 78.9% #18 of 69
Science 5
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 20.3% #122 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 2.6% #96 of 324
Vals Science Index Vals Science Index: Scientific problem solving across the index’s component evaluations Vals 28.4% #16 of 18
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 46.9% #66 of 140
Terminal-Bench Science0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal AA 8.6% #17 of 33
Coding 5
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 0% #74 of 132
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 67% #17 of 44
FrontierCode1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements AA 41.9% #13 of 28
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,578 #30 of 97+1 versions & slices full cohort WebDev Arena · snapshot 2026-10-19 · native board settings: Human pairwise preferences in the stated webdev vote pool Arena 1,578 #30 of 97
Agents 7
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 12% #73 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 741 #79 of 140
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 26.7 #73 of 175
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 44.2% #13 of 31
SpireClimb SpireClimb: Agents play Slay the Spire under the named game and difficulty setting Epoch 0% #7 of 7
SpireClimb StS1 A20 Heart SpireClimb StS1 A20 Heart: Agents play Slay the Spire under the named game and difficulty setting Epoch 0% #4 of 7
SpireClimb StS2 A10 SpireClimb StS2 A10: Agents play Slay the Spire under the named game and difficulty setting Epoch 0% #7 of 7
Multimodal 3
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 76% #41 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,216 #59 of 88
Chartography Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 29.1% #15 of 37
Writing 15
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,410 #56 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,443 #59 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,428 #92 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,393 #99 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,407 #88 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,387 #77 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,410 #71 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,365 #67 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,368 #66 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,383 #93 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,382 #79 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,393 #87 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,393 #90 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,392 #96 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 1,363 #88 of 187
Health & law 5
Harvey LAB-AA1.1 Harvey LAB-AA 1.1: Legal agents work from case documents; every rubric criterion must pass and material hallucinations receive no credit AA 3.3% #12 of 23
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 16.1% #30 of 64
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 44.7% #33 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 83.7% #37 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 30.3% #40 of 69
Documents 2
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 74% #96 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 9% #62 of 133
Legacy · saturated or no longer reported 2
GPQA DiamondEpoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 90.5% #31 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 98.9% #15 of 130
No benchmark matches
CheaperAgnes 2.5 Pro Beta+85%-25%$0.10 / $0.30Context: 1.05M → 1M
OpenMiMo v2.6 Prothinking×2.4+2,850%$0.13Context: 1.05M → 1M+4
CheaperLing 3.0 FlashthinkingOpen+17%-55%$0.06 / $0.18Context: 1.05M → 262K+1
CheaperGemma 4 31BthinkingOpen+17%-20%$0.10 / $0.34Context: 1.05M → 256K
Claude Haiku 5.5low+33%+442%$0.024Context: 1.05M → 1M+6
Kimi K3maxOpen×2.3+44,184%$2.00Context: 1.05M → 1M+4
Step 5 PreviewthinkingOpen×2.3+22,625%$1.03Context: 1.05M → 1M+4
Muse Spark OpenxhighOpen×2.2+18,576%$0.84Context: 1.05M → 1M+2
DeepSeek V4.1 Flash 1017maxOpen×2.1+5,702%$0.26Context: 1.05M → 1M+5