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 40.9 #30 of 339
Knowledge 5
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 54.6% #11 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 55.2% #101 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 29.6 #14 of 323
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 69.7% #8 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 47% #14 of 65
Reasoning 6
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 98% #11 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 98.5% #1 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 92.5% #9 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 89.2% #9 of 69
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 10.4% #6 of 19
Chess Puzzles Models choose the best next move from a novel chess position Epoch 58% #10 of 69
Math 15
AA Analyst Agent Data-analyst tasks: the model explores data with tools and reports findings AA 46.3% #13 of 43
FrontierMath Erdos Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #6 of 13
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 22% #39 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 68.4% #27 of 70
MathArenaArXivMath · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 64.2% #6 of 17+10 versions & slices ArXivMath · August 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 40.4% #11 of 14ArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 67.4% #15 of 24ArXivMath · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 58.3% #12 of 19ArXivMath · September 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 50% #6 of 9BrokenArXiv · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 33.6% #7 of 15BrokenArXiv · August 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 27.4% #11 of 13BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 20.8% #18 of 24BrokenArXiv · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 19% #13 of 18BrokenArXiv · September 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 26.7% #9 of 9ArXivLean · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 19.6% #5 of 9
Science 5
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 47.8% #17 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 18.3% #35 of 326
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 35.8% #11 of 19
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 56.6% #21 of 142
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 10% #18 of 45
Coding 10
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 19.7% #32 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 87.6% #8 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 73.8% #2 of 44
FrontierCode1.1 Agents implement changes in real repositories, graded against maintainer-defined requirements AA 36.4% #25 of 38
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 52.5% #3 of 37
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,585 #28 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,585 #29 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,585 #28 of 97
SWE-bench Pro (v2 full) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 94.9% #12 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 58.8% #13 of 16
Agents 5
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 59.9% #20 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,202 #45 of 142
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 1,445 #37 of 177
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 31.7% #23 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 44.9% #11 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 85.6% #4 of 128
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,315 #7 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 40.9% #7 of 37
Writing 20
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,489 #8 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,487 #6 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,496 #8 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,553 #5 of 198English Human pairwise preferences in the stated text vote pool Arena 1,498 #8 of 205French Human pairwise preferences in the stated text vote pool Arena 1,495 #12 of 164German Human pairwise preferences in the stated text vote pool Arena 1,509 #3 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,492 #9 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,511 #4 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,471 #5 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,491 #6 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,496 #7 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,516 #5 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,485 #9 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,499 #7 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,492 #7 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,498 #7 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 76.8% #25 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,748 #30 of 94
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech 0.1 #23 of 45
Health & law 6
Harvey LAB-AA1.1 Legal agents work from case documents; every rubric criterion must pass and material hallucinations receive no credit AA 0% #18 of 23
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 10.6% #53 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 87% #5 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 48.1% #26 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 84.5% #30 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 38.9% #28 of 73
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 81.3% #34 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 21% #23 of 135
Legacy · saturated or no longer reported 3
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 95.3% #2 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 95.4% #4 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 98.9% #16 of 131
No benchmark matches
CheaperDeepSeek V4.1 Flash 1017maxOpen+21%-92%$0.26No PDF input+5
BetterMiMo v2.6 FlashthinkingOpen+12%-98%$0.062No PDF input+4
CheaperClaude Sonnet 5.5xhigh+20%-42%$2.01No forced tool use+5
CheaperGrok 4.7xhigh+19%-7%$3.24Context: 1M → 500K+5
GPT-5.6 Lunamax+1%-95%$0.18
GLM 5.3maxOpen+15%-42%$2.01No image input+5
Qwen3.8 FlashthinkingOpen+13%-89%$0.37Context: 1M → 262K+6