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 #113 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 39.6% #47 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 89.9% #248 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -14.7 #106 of 321
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 41% #39 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 17% #44 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 47.4% #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 34.2% #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 2.8% #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 5.1% #48 of 66
ARC-AGI-3semi-private ARC-AGI-3 · semi-private: Measures interactive game solving through relative human action efficiency ARC 0.2% #18 of 18
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 17% #56 of 68
Math 2
FrontierMath Tier 4 (v2) 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) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 41.4% #50 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 19.8% #125 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 25.3% #18 of 18
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 46.1% #68 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 3.3% #23 of 33
Coding 4
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+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 43.4% #80 of 156
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 1.5% #39 of 44
ITBench SRE 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 AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 11.7% #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
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications AA 35.8% #6 of 29
EnterpriseOps-Gym-AA 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 GDPval-AA (work tasks) 2.1: Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 24.8 #80 of 175
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 42.5% #15 of 31
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 12.8% #79 of 134
Multimodal 3
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 74% #58 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,257 #41 of 88
Chartography Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 31.4% #12 of 37
Writing 17
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 1,453 #48 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,469 #62 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,441 #62 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,458 #44 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,455 #32 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,437 #45 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,414 #37 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,416 #32 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,417 #65 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,404 #70 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,428 #55 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,446 #47 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,431 #63 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 1,396 #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 MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 6.1% #47 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 84% #38 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 42.4% #43 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 84.4% #31 of 80
Vals Legal Research Bench 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 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 70% #120 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 14.2% #41 of 133
Arena Document Arena Document · overall: Human pairwise preferences in the stated document vote pool Arena 1,457 #17 of 33
Legacy · saturated or no longer reported 9
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 83.5% #92 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 82.3% #63 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 66.7% #79 of 130
SWE-rebenchall · 2026-05-15 to 2026-07-01 SWE-rebench · all · 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 SWE-rebench · 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 SWE-rebench · java · 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 SWE-rebench · python · 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 SWE-rebench · rust · 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 SWE-rebench · typescript · 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
CheaperAgnes 2.5 Pro Beta+89%-67%$0.10 / $0.30Context: 1.05M → 1M
OpenMiMo v2.6 Prothinking×2.5+1,256%$0.13Context: 1.05M → 1M+4
CheaperHy3 previewthinkingOpen+40%-37%$0.18 / $0.60Context: 1.05M → 256K+2
CheaperLing 3.0 FlashthinkingOpen+19%-80%$0.06 / $0.18Context: 1.05M → 262K+1
Gemma 4 31BthinkingOpen+19%-64%$0.10 / $0.34Context: 1.05M → 256K
Claude Haiku 5.5low+36%+149%$0.024Context: 1.05M → 1M+6
Muse Glimmer 30BhighOpen+11%+486%$0.058Context: 1.05M → 131K
Kimi K3maxOpen×2.4+20,253%$2.00Context: 1.05M → 1M+4
Step 5 PreviewthinkingOpen×2.3+10,344%$1.03Context: 1.05M → 1M+3
DeepSeek V4.1 Flash 1017maxOpen×2.2+2,567%$0.26Context: 1.05M → 1M+5