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 37.3 #43 of 339
Knowledge 5
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 42.7% #42 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 75% #145 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -10.3 #96 of 323
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 41% #40 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 20% #36 of 65
Reasoning 6
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 90.8% #32 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 88% #30 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 60.2% #28 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 59.5% #31 of 69
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.2% #19 of 19
Chess Puzzles Models choose the best next move from a novel chess position Epoch 3% #66 of 69
Math 2
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 61% #15 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 39.6% #51 of 70
Science 5
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 39.5% #49 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 20.6% #30 of 326
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 25.3% #18 of 19
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 53.6% #38 of 142
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 3.3% #29 of 45
Coding 4
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 11.6% #39 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 80.9% #20 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 67.2% #15 of 44
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 Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 50.2% #37 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,339 #34 of 142
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 35.8% #6 of 29
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 1,460 #34 of 177
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 42.5% #15 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 31.1% #34 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 78.6% #30 of 128
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,257 #41 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 31.4% #12 of 37
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,396 #68 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,410 #56 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,453 #48 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,470 #63 of 198English Human pairwise preferences in the stated text vote pool Arena 1,441 #64 of 205French Human pairwise preferences in the stated text vote pool Arena 1,457 #50 of 164German Human pairwise preferences in the stated text vote pool Arena 1,455 #30 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,438 #46 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,416 #40 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,415 #33 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,417 #65 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,404 #74 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,428 #58 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,445 #51 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,431 #63 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,396 #65 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,431 #66 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 75.5% #27 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,832 #23 of 94
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 20% #22 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 84% #38 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 42.4% #43 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 84.4% #31 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 36.5% #37 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 83.7% #10 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 24% #13 of 135
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,457 #17 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 91.1% #27 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 63.6% #91 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 40% #97 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 43.6% #6 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 54.3% #6 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 41.9% #6 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 37% #6 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 32.8% #6 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 52.5% #6 of 6
No benchmark matches
CheaperClaude Haiku 5.5max+50%-56%$0.21Context: 1.05M → 1M+6
OpenDeepSeek V4.1 Flash 1017max×2.5+17%$0.26Context: 1.05M → 1M+5
CheaperQwen 3.5 Flashunstatedsame-75%$0.065 / $0.26Context: 1.05M → 1M
GLM 5.3maxOpen+65%+378%$2.01Context: 1.05M → 1M+5
Kimi K3maxOpen+30%+1,233%$2.00Context: 1.05M → 1M+4