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 #67 of 337
Knowledge 6
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 26.4% #100 of 321+1 versions & slices 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 Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 0.9 #64 of 321
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 75.2% #26 of 248
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 44.1% #36 of 83
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 12% #51 of 64
Reasoning 1
Chess Puzzles Models choose the best next move from a novel chess position Epoch 14% #57 of 68
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 32.3% #56 of 69
Science 2
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) Research-level physics problems that need many careful reasoning steps AA 2.9% #96 of 324
Coding 4
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,461 #52 of 97+1 versions & slices full cohort 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 242
Agents 2
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 Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 20.8% #53 of 134
Multimodal 1
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 78% #35 of 127
Writing 16
Arena Textcreative writing Human pairwise preferences in the stated text vote pool Arena 1,407 #59 of 195+14 versions & slices overall 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 1,476 #58 of 181English Human pairwise preferences in the stated text vote pool Arena 1,445 #56 of 188French Human pairwise preferences in the stated text vote pool Arena 1,454 #50 of 149German Human pairwise preferences in the stated text vote pool Arena 1,452 #35 of 154instruction following Human pairwise preferences in the stated text vote pool Arena 1,424 #58 of 188Japanese Human pairwise preferences in the stated text vote pool Arena 1,390 #55 of 138Korean Human pairwise preferences in the stated text vote pool Arena 1,379 #60 of 144non-English Human pairwise preferences in the stated text vote pool Arena 1,424 #56 of 188Polish Human pairwise preferences in the stated text vote pool Arena 1,433 #44 of 133Russian Human pairwise preferences in the stated text vote pool Arena 1,434 #48 of 186Spanish Human pairwise preferences in the stated text vote pool Arena 1,432 #64 of 155overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,436 #56 of 188creative writing · full cohort Human pairwise preferences in the stated text vote pool Arena 1,404 #54 of 187
Lech Mazur Short-Story 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 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% #57 of 69
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% #61 of 275
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 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 88.4% #41 of 133
OTIS Mock AIME 20242025 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 Tests service agents that use tools while coordinating with a simulated user AA 97.7% #9 of 245
Terminal-Bench2.1 Older, easier version of Terminal-Bench; Still widely reported AA 61.4% #51 of 156
No benchmark matches