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 39 #33 of 337
Knowledge 6
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 50.9% #19 of 321+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 91.7% #269 of 321
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 5.8 #48 of 321
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 73.9% #27 of 248
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,563 #11 of 50
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 30.5% #57 of 83
Reasoning 5
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 96.4% #18 of 61+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 93.7% #19 of 64
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 84.2% #16 of 63+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 74% #18 of 66
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.2% #16 of 18
Math 19
MathArenaAIME 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 99.2% #3 of 24+18 versions & slices HMMT February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 97.7% #2 of 24Apex Answer accuracy on the named mathematics competition under the recorded effort MathArena 54.2% #6 of 34Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 81.4% #8 of 30ArXivMath · December 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 60.3% #2 of 13ArXivMath · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 59.4% #5 of 20ArXivMath · January 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 76.1% #1 of 18ArXivMath · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 67.8% #4 of 14BrokenArXiv · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 37.9% #2 of 15BrokenArXiv · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 36.6% #2 of 13ArXivLean · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 17.1% #1 of 5Project Euler Answer accuracy on the named mathematics competition under the recorded effort MathArena 89% #1 of 11Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 94.8% #2 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 98.3% #2 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 83.3% #2 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 83.3% #4 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.8% #3 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 99.2% #6 of 16USAMO 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.2% #2 of 8
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 43.7% #27 of 337
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 23.4% #21 of 324
Coding 6
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 51.8% #26 of 44+1 versions & slices 1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 55.5% #3 of 20
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,401 #68 of 97+1 versions & slices full cohort Human pairwise preferences in the stated webdev vote pool Arena 1,401 #68 of 97
SWE-bench Pro (private) Agents resolve long-horizon professional repository tasks; public and private splits are separate Scale 43.4% #4 of 9
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 57.6% #6 of 242
Agents 6
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 37.3 #48 of 175
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 33.3% #8 of 29
MCP-Atlas Public MCPAtlas Public: MCPAtlas Public as reported in this launch evaluation; the post is the authority for the recorded task and grading scope 75.4% #6 of 16
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 39.4% #9 of 21
MCP-Atlasfull 1000 Tool orchestration across MCP servers on the stated task split Scale 70.6% #6 of 16
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 39.6% #17 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 78.4% #32 of 127
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,303 #11 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 29.6% #14 of 37
Writing 18
Arena Textcreative writing Human pairwise preferences in the stated text vote pool Arena 1,442 #35 of 195+14 versions & slices overall Human pairwise preferences in the stated text vote pool Arena 1,475 #25 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,518 #23 of 181English Human pairwise preferences in the stated text vote pool Arena 1,467 #31 of 188French Human pairwise preferences in the stated text vote pool Arena 1,493 #15 of 149German Human pairwise preferences in the stated text vote pool Arena 1,473 #17 of 154instruction following Human pairwise preferences in the stated text vote pool Arena 1,469 #22 of 188Japanese Human pairwise preferences in the stated text vote pool Arena 1,485 #10 of 138Korean Human pairwise preferences in the stated text vote pool Arena 1,448 #15 of 144non-English Human pairwise preferences in the stated text vote pool Arena 1,465 #18 of 188Polish Human pairwise preferences in the stated text vote pool Arena 1,472 #14 of 133Russian Human pairwise preferences in the stated text vote pool Arena 1,480 #17 of 186Spanish Human pairwise preferences in the stated text vote pool Arena 1,453 #39 of 155overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,469 #24 of 188creative writing · full cohort Human pairwise preferences in the stated text vote pool Arena 1,439 #33 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 78.3% #18 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,840 #21 of 91
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech 2 #10 of 44
Health & law 3
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 86% #13 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 41.3% #45 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 77.6% #54 of 80
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 82% #27 of 275
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,471 #11 of 33
Legacy · saturated or no longer reported 4
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 92% #21 of 315
SWE-bench Pro (public) Agents resolve long-horizon professional repository tasks; public and private splits are separate 59.1% #2 of 19
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 87.1% #54 of 245
Terminal-Bench2.1 Older, easier version of Terminal-Bench; Still widely reported AA 78.3% #25 of 156
No benchmark matches
CheaperClaude Sonnet 5.5max+44%-29%$5.46Context: 1.05M → 1M+6
OpenMiMo v2.6 Prothinking+19%-90%$0.13Context: 1.05M → 1M+4
CheaperGemini 4 Argonhigh+35%-29%*$1.99Context: 1.05M → 1M+3
Muse Spark 1.3max+23%-64%$1.60Context: 1.05M → 1M+6
MiniMax M3.1 Flashthinking+10%-95%$0.22Context: 1.05M → 1M+1
DeepSeek V4.1 Flash 1017maxOpen+16%-91%$0.26Context: 1.05M → 1M+5
GLM 5.3maxOpen+15%-62%$2.01Context: 1.05M → 1M+5
Step 5 PreviewthinkingOpen+12%-75%$1.03Context: 1.05M → 1M+3
Kimi K3maxOpen+12%+7%$2.00Context: 1.05M → 1M+4