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 52.6 #6 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 49.9% #21 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 15.1% #5 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 42.4 #5 of 321
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 76% #2 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 64% #5 of 64
Reasoning 6 Leads on 1
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 99.5% #1 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 98.5% #1 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 97.1% #4 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 91.3% #5 of 66
ARC-AGI-3semi-private ARC-AGI-3 · semi-private: Measures interactive game solving through relative human action efficiency ARC 49.8% #3 of 18
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 59% #6 of 68
Math 8
AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings AA 48.8% #10 of 43
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 78% #9 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 86% #10 of 69
MathArenaArXivMath · August 2026 MathArena · arxiv · 08/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 82.5% #6 of 12+4 versions & slices ArXivMath · September 2026 MathArena · arxiv · 09/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.7% #2 of 7BrokenArXiv · August 2026 MathArena · arxiv_false · 08/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 54.2% #7 of 12BrokenArXiv · September 2026 MathArena · arxiv_false · 09/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 49.7% #3 of 7ArXivLean · September 2026 MathArena · arxivlean · 09/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 39.6% #2 of 5
Science 5
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 57.1% #3 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 27.1% #15 of 324
Vals Science Index Vals Science Index: Scientific problem solving across the index’s component evaluations Vals 55.4% #5 of 18
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 61.8% #4 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 52.9% #5 of 33
Coding 6
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 57.1% #4 of 132
FrontierCode1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements AA 43.5% #10 of 28
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,678 #9 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 1,678 #9 of 97
SWE-bench Pro (v2 full) SWE-bench Pro (v2 full): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 99.2% #2 of 16
SWE-bench Pro (v2 hard) SWE-bench Pro (v2 hard): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 92.2% #3 of 16
Agents 6 Leads on 2
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 77.5% #1 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,486 #21 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 56.2 #16 of 175
AutomationBenchZapier run AutomationBench · Zapier run: End-to-end completion of business workflows using real SaaS applications Zapier 51.3% #1 of 2
EBR Bench EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs Epoch 64.8% #3 of 24
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 72.5% #5 of 31
Multimodal 1 Leads on 1
Chartography Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 71.6% #1 of 37
Writing 11
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,516 #2 of 195+9 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,524 #1 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,608 #1 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,538 #1 of 188instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,536 #2 of 188non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,522 #1 of 188Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,534 #1 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,504 #5 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,532 #1 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 1,527 #2 of 187
Lech Mazur Short-Story Lech Mazur Short-Story · comparison score: Judges compare stories written to ten required elements; the comparison score can be negative Lech 0.8 #14 of 44
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 3.9% #10 of 23
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 88.3% #3 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 58.8% #3 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 87.4% #16 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 54.8% #4 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 79.7% #48 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 21.8% #21 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 96.4% #1 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 100% #1 of 130
No benchmark matches
CheaperClaude Opus 5.5highwins 46%-8%$1.82No forced tool use+5
OpenGLM 5.3maxwins 39%same$2.01No image input+5
OpenKimi K3maxwins 39%same$2.00Sampling parameters are fixed+3
OpenMiMo v2.6 Prounstatedwins 39%-86%$0.43 / $0.87No PDF input+4