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 11.6 #190 of 339
Knowledge 7
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 21.8% #140 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 90.8% #258 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -49.3 #208 of 323
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 69% #54 of 248
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,073 #39 of 53
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 13.1% #74 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 0% #65 of 65
Math 8
MathArenaAIME 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #11 of 30+7 versions & slices Apex Answer accuracy on the named mathematics competition under the recorded effort MathArena 1% #25 of 34Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 45.2% #24 of 30BRUMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 92.5% #9 of 24CMIMC 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 85% #9 of 22HMMT February 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #8 of 30HMMT November 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #6 of 14SMT 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.7% #10 of 24
Science 4
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 19.6% #128 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 1.1% #122 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 34% #119 of 142
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 0% #36 of 45
Coding 6
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 0% #77 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 26.2% #105 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 0% #41 of 44
FrontierCode1.1 Agents implement changes in real repositories, graded against maintainer-defined requirements AA 1.2% #35 of 38
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 5.6% #36 of 37
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 23.5% #81 of 242
Agents 6
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 0.2% #132 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 0 #131 of 142
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 3.1% #26 of 29
EnterpriseOps-Gym-AA Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 25.5% #41 of 43
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 608 #96 of 177
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 12.8% #80 of 134
Writing 20
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,274 #139 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,279 #144 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,352 #121 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,385 #122 of 198English Human pairwise preferences in the stated text vote pool Arena 1,375 #125 of 205French Human pairwise preferences in the stated text vote pool Arena 1,369 #112 of 164German Human pairwise preferences in the stated text vote pool Arena 1,353 #103 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,318 #132 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,331 #87 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,283 #110 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,350 #117 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,353 #97 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,343 #119 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,389 #99 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,366 #109 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,275 #132 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,366 #113 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 35.8% #82 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 956 #80 of 94
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech -3.2 #42 of 45
Health & law 2
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 1.7% #95 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 75.9% #74 of 89
Documents 2
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 4% #93 of 135
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 52% #178 of 317
Legacy · saturated or no longer reported 20
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 93.4% #10 of 140
LiveCodeBenchAA archived AA evaluates solutions to newly collected competitive-programming problems AA 87.8% #5 of 153
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 78.2% #125 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 75.8% #74 of 134
Aider Polyglottwo attempts Models edit code for 225 Exercism exercises in six languages, with a second attempt after test feedback Aider 41.8% #7 of 15
SWE-bench Pro (public) Agents resolve long-horizon professional repository tasks; public and private splits are separate 16.2% #16 of 19
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 88.9% #50 of 131
SWE-rebenchall · August 1, 2025 to March 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 27.3% #2 of 2+11 versions & slices all · December 1, 2025 to January 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 37% #1 of 1Go · August 1, 2025 to March 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Go · December 1, 2025 to January 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Java · August 1, 2025 to March 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Java · December 1, 2025 to January 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Python · August 1, 2025 to March 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 27.3% #2 of 2Python · December 1, 2025 to January 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 37% #1 of 1Rust · August 1, 2025 to March 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Rust · December 1, 2025 to January 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1TypeScript · August 1, 2025 to March 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2TypeScript · December 1, 2025 to January 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 65.8% #98 of 245
No benchmark matches
CheaperMiMo v2.5thinkingOpen+38%-61%$0.042Memory (4-bit): 70 GB → 186 GB
OpenGLM 4.7 Flashthinking+50%+142%$0.061 / $0.40
CheaperSolar Pro 3high+31%-46%$0.058
CheaperQwen3.5 2Bnon-thinkingOpen+24%-33%$0.02 / $0.10
CheaperMercury 2high+8%-17%$0.089Context: 131K → 128K
MiniMax M2.7thinkingOpen+29%same$0.11Memory (4-bit): 70 GB → 137 GB
Step 3.7 FlashhighOpen+50%+629%$0.20 / $1.15Memory (4-bit): 70 GB → 121 GB
Mistral Medium 3.5highOpen+43%+298%$0.43Memory (4-bit): 70 GB → 77 GB