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 27 #67 of 337
Knowledge 6
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 26.4% #100 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 34.6% #49 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 0.9 #64 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 75.2% #26 of 248
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 44.1% #36 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 12% #51 of 64
Reasoning 1
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 14% #57 of 68
Math 3
FrontierMath FrontierMath: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 26.2% #16 of 40
FrontierMath Tier4 FrontierMath Tier 4: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 8.3% #13 of 33
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 38.2% #51 of 69
Science 2
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 27.8% #94 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 2.9% #96 of 324
Coding 4
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,461 #52 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 1,461 #52 of 97
DeepSWE1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 2.7% #18 of 20
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 43.9% #22 of 242
Agents 2
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 24.5 #81 of 175
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 20.8% #53 of 134
Multimodal 1
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 78% #35 of 127
Writing 16
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,407 #59 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,443 #59 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,476 #58 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,445 #56 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,454 #50 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,452 #35 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,424 #58 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,390 #55 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,379 #60 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,424 #56 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,433 #44 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,434 #48 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,432 #64 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,436 #56 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 1,404 #54 of 187
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 -2.3 #37 of 44
Health & law 4
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 84.2% #32 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 36.9% #58 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 77% #56 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 14.9% #57 of 69
Documents 1
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 6
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 88.2% #50 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 88.4% #41 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 93.3% #38 of 130
SWE-bench VerifiedEpoch Swe Bench Verified: Agents modify real repositories to resolve the stated Verified issues Epoch 57.9% #21 of 24
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 97.7% #9 of 245
Terminal-Bench2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 61.4% #51 of 156
No benchmark matches
CheaperGLM 4.7 FlashthinkingOpen+1%-87%$0.061 / $0.40Context: 1M → 200K+1
CheaperStep 3.7 FlashhighOpensame-61%$0.20 / $1.15Context: 1M → 256K
CheaperMiniMax M2.5thinkingOpen-2%-53%$0.30 / $1.20Context: 1M → 205K+1