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 43.6 #23 of 339
Knowledge 6 Leads on 1
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 47.6% #30 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 53.2% #99 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 19.7 #28 of 323
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 50.6% #27 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 26% #29 of 65
EQ-Bench4 Active emotional and social intelligence in multi-turn conversations with 120 simulated personas EQ-Bench 1,339 #1 of 1
Reasoning 5
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 94.9% #27 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 94.5% #17 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 61.7% #27 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 60.4% #29 of 69
Chess Puzzles Models choose the best next move from a novel chess position Epoch 36% #36 of 69
Math 22
AA Analyst Agent Data-analyst tasks: the model explores data with tools and reports findings AA 38.8% #21 of 43
MathArenaAIME 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.7% #6 of 24+17 versions & slices HMMT February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 97% #3 of 24Apex Answer accuracy on the named mathematics competition under the recorded effort MathArena 65.6% #4 of 34Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 92% #2 of 30ArXivMath · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 54.2% #10 of 17ArXivMath · August 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 38.6% #12 of 14ArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 71.5% #11 of 24ArXivMath · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 61.7% #10 of 19BrokenArXiv · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 59.4% #3 of 15BrokenArXiv · August 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 61.9% #7 of 13BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 51.9% #11 of 24BrokenArXiv · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 42.5% #8 of 18Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 93.8% #3 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 98.3% #2 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 77.1% #3 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 81.7% #5 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.7% #1 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 100% #1 of 16
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 39% #23 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 72.2% #22 of 70
Science 4
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 46.9% #19 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 23.4% #24 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 59.5% #10 of 142
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 8.1% #22 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 12.6% #36 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 85% #11 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 68.5% #12 of 44
FrontierCode1.1 Agents implement changes in real repositories, graded against maintainer-defined requirements AA 43.6% #12 of 38
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 47.7% #9 of 37
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,655 #13 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,655 #14 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,655 #13 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 97.7% #4 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 88.2% #6 of 16
Agents 9
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 58.3% #25 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,499 #20 of 142
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 41.3% #2 of 29
EnterpriseOps-Gym-AA Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 45.3% #10 of 43
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 1,534 #27 of 177
Toolathlon-Verified Toolathlon-Verified as reported in this launch evaluation; the post is the authority for the recorded task and grading scope 76.5% #2 of 6
τ³-benchbanking · 1.0.1 τ-bench official · 3-banking-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 37.1% #10 of 21
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 34.2% #21 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 46% #9 of 134
Multimodal 2
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 80.5% #17 of 128
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 26.6% #18 of 37
Writing 20
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,456 #19 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,461 #17 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,487 #14 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,529 #16 of 198English Human pairwise preferences in the stated text vote pool Arena 1,481 #16 of 205French Human pairwise preferences in the stated text vote pool Arena 1,488 #21 of 164German Human pairwise preferences in the stated text vote pool Arena 1,491 #9 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,485 #12 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,497 #7 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,461 #8 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,465 #19 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,460 #22 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,483 #14 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,475 #15 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,475 #17 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,456 #19 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,475 #17 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 79.6% #17 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 2,084 #5 of 94
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech 2.3 #10 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 5.3% #8 of 23
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 21.7% #17 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 86.2% #12 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 49.4% #19 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 88.1% #14 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 46.2% #13 of 73
Documents 2 Leads on 1
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 88.7% #1 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 22% #21 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 93.5% #9 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 93.1% #17 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 97.2% #29 of 131
No benchmark matches
CheaperGemini 4 Argonhigh×2.7-19%*$1.62Synchronous output stops at 65,536+2
BetterGPT-6 Lunamax+9%-97%$0.068Function calling only with none · Chat Completions+3
OpenQwen3.8 Flashxhigh-35%-96%$0.15 / $0.47Context: 1M → 262K+6
Muse Spark 1.2xhigh+21%-36%$1.29Only auto tool_choice is supported+1
GLM 5.3 FlashmaxOpen-39%-86%$0.28Defaults to max · Self-hosted+4