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 30.1 #58 of 339
Knowledge 6
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 44.6% #35 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 89.8% #248 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -5.1 #85 of 323
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 62.2% #80 of 248
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 43.2% #37 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 10% #54 of 65
Reasoning 6
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 84.8% #37 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 77% #39 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 38.9% #34 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 37.5% #38 of 69
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.1% #19 of 19
Chess Puzzles Models choose the best next move from a novel chess position Epoch 47% #19 of 69
Math 2
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 70.7% #13 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 86% #10 of 70
Science 4
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 33.3% #74 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 17.4% #41 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 50.5% #51 of 142
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 13.8% #14 of 45
Coding 7
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 1% #55 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 72.3% #32 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 35.1% #29 of 44
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 51% #5 of 37
SWE-bench Pro (v2 full) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 92.4% #14 of 16
SWE-bench Pro (v2 hard) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 86.3% #8 of 16
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 62.9% #2 of 242
Agents 7
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 33.5% #50 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,038 #53 of 142
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 38.9% #3 of 29
EnterpriseOps-Gym-AA Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 38.5% #25 of 43
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 1,275 #47 of 177
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 54.2% #10 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 25.6% #40 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 76.8% #38 of 128
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,271 #30 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 34% #9 of 37
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,413 #52 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,429 #46 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 1,514 #26 of 198English Human pairwise preferences in the stated text vote pool Arena 1,449 #52 of 205French Human pairwise preferences in the stated text vote pool Arena 1,466 #38 of 164German Human pairwise preferences in the stated text vote pool Arena 1,461 #26 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,455 #32 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,453 #20 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,423 #31 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,441 #34 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,447 #31 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,453 #35 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,448 #47 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,447 #40 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,412 #50 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,448 #38 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 78% #22 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,856 #17 of 94
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 22.8% #14 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 85.1% #21 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 43.4% #37 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 82.9% #43 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 41.4% #23 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 74% #98 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 17% #35 of 135
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,472 #10 of 33
Legacy · saturated or no longer reported 4
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 87.2% #56 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 93.3% #14 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 99.7% #11 of 131
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 72.8% #92 of 245
No benchmark matches
CheaperMuse Spark 1.3max+34%-56%$3.69Context: 1.05M → 1M+6
OpenGLM 5.3unstated+19%-52%$1.40 / $4.40Context: 1.05M → 1M+5
CheaperGemini 4 Argonunstated+33%-11%*$2 / $10Context: 1.05M → 1M+3
CheaperGrok 4.6unstated+16%-33%$2 / $6Context: 1.05M → 500K
CheaperClaude Sonnet 5.5unstated+16%-11%$2 / $10Context: 1.05M → 1M+6
MiMo v2.6 ProunstatedOpen+14%-88%$0.43 / $0.87Context: 1.05M → 1M+4
Kimi K3unstatedOpen+12%+33%$3 / $15Context: 1.05M → 1M+4
DeepSeek V4.1 Flash 1017unstatedOpen+9%-88%$0.30 / $1.20Context: 1.05M → 1M+5
Hy4 previewOpen+9%-72%$0.83 / $2.50Context: 1.05M → 1M+1