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 27 #70 of 373
Knowledge 6
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 26.4% #104 of 339+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 34.6% #49 of 339
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 0.9 #66 of 339
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 75.2% #26 of 271
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 44.1% #36 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 12% #52 of 65
Reasoning 1
Chess Puzzles Models choose the best next move from a novel chess position Epoch 14% #58 of 69
Math 3
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 26.2% #16 of 40
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 8.3% #13 of 33
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 38.2% #52 of 70
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 27.8% #97 of 370
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 2.9% #99 of 342
Coding 5
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,461 #52 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,462 #53 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,461 #52 of 97
DeepSWE1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 2.7% #18 of 20
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 43.9% #22 of 258
Agents 2
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 24.5 #134 of 177
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 20.8% #53 of 137
Multimodal 1
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 78% #37 of 136
Writing 18
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,404 #57 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,407 #59 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,443 #59 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,477 #60 of 198English Human pairwise preferences in the stated text vote pool Arena 1,445 #58 of 205French Human pairwise preferences in the stated text vote pool Arena 1,454 #56 of 164German Human pairwise preferences in the stated text vote pool Arena 1,452 #35 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,424 #60 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,390 #59 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,379 #63 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,424 #58 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,433 #48 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,434 #53 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,432 #67 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,436 #56 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,404 #54 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,436 #58 of 198
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech -2.3 #38 of 45
Health & law 4
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 84.2% #32 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 36.9% #58 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 77% #56 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 14.9% #61 of 73
Documents 1
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 78.3% #64 of 338
Legacy · saturated or no longer reported 6
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 88.2% #50 of 346+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 88.4% #42 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 93.3% #39 of 131
SWE-bench VerifiedEpoch Swe Bench Verified: Agents modify real repositories to resolve the stated Verified issues Epoch 57.9% #21 of 24
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 97.7% #9 of 262
Terminal-Bench2.1 Older, easier version of Terminal-Bench; Still widely reported AA 61.4% #51 of 161
No benchmark matches