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 33.7 #47 of 337
Knowledge 7
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 24.3% #120 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 26.3% #24 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 4.4 #54 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 73.3% #30 of 248
EQ-Bench3 EQ-Bench 3: Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,575 #8 of 50
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 34.2% #50 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 19% #38 of 64
Reasoning 5
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 80.4% #35 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 77% #37 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 20.8% #36 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 22.8% #39 of 66
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 22% #47 of 68
Math 17
MathArenaAIME 2026 MathArena · AIME 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #22 of 24+14 versions & slices HMMT February 2026 MathArena · HMMT February 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 92.4% #12 of 24Apex MathArena · apex · Apex: Answer accuracy on the named mathematics competition under the recorded effort MathArena 19.8% #13 of 34Apex Shortlist MathArena · apex · Apex Shortlist: Answer accuracy on the named mathematics competition under the recorded effort MathArena 68.1% #17 of 30ArXivMath · April 2026 MathArena · arxiv · 04/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 47.5% #13 of 17ArXivMath · February 2026 MathArena · arxiv · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 46.1% #7 of 20ArXivMath · June 2026 MathArena · arxiv · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 46.5% #21 of 24ArXivMath · March 2026 MathArena · arxiv · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 61.7% #6 of 14ArXivMath · May 2026 MathArena · arxiv · 05/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 56.7% #13 of 19BrokenArXiv · April 2026 MathArena · arxiv_false · 04/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 18.4% #12 of 15BrokenArXiv · February 2026 MathArena · arxiv_false · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 10.5% #11 of 15BrokenArXiv · June 2026 MathArena · arxiv_false · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 14.2% #22 of 24BrokenArXiv · March 2026 MathArena · arxiv_false · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 12.1% #8 of 13BrokenArXiv · May 2026 MathArena · arxiv_false · 05/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 10.5% #15 of 18ArXivLean · June 2026 MathArena · arxivlean · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 8.7% #8 of 9
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 29.3% #29 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 59.2% #35 of 69
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 41.1% #39 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 20.9% #25 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 51.2% #46 of 140
Coding 8
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 1% #54 of 132+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 77.9% #26 of 156
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 43.8% #29 of 44+1 versions & slices 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 41.5% #5 of 20
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 42.7% #13 of 37
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,604 #24 of 97+1 versions & slices full cohort WebDev Arena · snapshot 2026-10-19 · native board settings: Human pairwise preferences in the stated webdev vote pool Arena 1,604 #24 of 97
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 50.8% #12 of 242
Agents 8
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 28.4% #49 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,229 #42 of 140
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications AA 33.7% #7 of 29
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 42.7% #16 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 43.6 #41 of 175
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
EBR Bench EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs Epoch 9.5% #21 of 24
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 34.6% #26 of 134
Writing 18
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,454 #21 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,476 #24 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,520 #22 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,474 #25 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,479 #24 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,471 #20 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,466 #25 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,451 #19 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,440 #18 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,459 #22 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,453 #24 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,468 #23 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,478 #12 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,470 #23 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 1,463 #14 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 77.9% #22 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,757 #27 of 91
Lech Mazur Short-Story Lech Mazur Short-Story · comparison score: Judges compare stories written to ten required elements; the comparison score can be negative Lech 0.5 #19 of 44
Health & law 5
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 7.2% #45 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 84.1% #35 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 40.8% #49 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 83.5% #40 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 31.3% #39 of 69
Documents 2
GDP.pdfAA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 10.4% #58 of 133
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 78.3% #61 of 275
Legacy · saturated or no longer reported 11
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 89.5% #41 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 91.9% #19 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 86.4% #61 of 130
SWE-bench VerifiedEpoch Swe Bench Verified: Agents modify real repositories to resolve the stated Verified issues Epoch 78.7% #2 of 24
SWE-rebenchall · 2026-03-01 to 2026-07-01 SWE-rebench · all · 2026-03-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 57% #1 of 6+5 versions & slices Go · 2026-03-01 to 2026-07-01 SWE-rebench · go · 2026-03-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 69.5% #1 of 6Java · 2026-03-01 to 2026-07-01 SWE-rebench · java · 2026-03-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 51.4% #1 of 6Python · 2026-03-01 to 2026-07-01 SWE-rebench · python · 2026-03-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 52% #1 of 6Rust · 2026-03-01 to 2026-07-01 SWE-rebench · rust · 2026-03-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 61.6% #1 of 6TypeScript · 2026-03-01 to 2026-07-01 SWE-rebench · typescript · 2026-03-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 73.3% #1 of 6
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 99.1% #1 of 245
No benchmark matches
CheaperGPT-6.1 Solmax+54%-51%$0.72Remove unsupported parameters+5
BetterMiMo v2.6 FlashthinkingOpen+12%-96%$0.062Pass back reasoning_content+3
CheaperClaude Opus 5.5medium+52%-9%$1.34No forced tool use+5
DeepSeek V4.1 Flash 1017maxOpen+34%-82%$0.26Memory (4-bit): 452 GB → 458 GB+5
Step 5 PreviewthinkingOpen+30%-30%$1.03web_search not available · Chat Completions+2