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 31.9 #54 of 339
Knowledge 7
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 47% #31 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 62.8% #115 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 13.7 #35 of 323
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 53.1% #107 of 248
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,712 #4 of 53
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 47% #32 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 25% #31 of 65
Reasoning 5
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 94.8% #27 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 92% #22 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 73.6% #19 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 66.3% #23 of 69
Chess Puzzles Models choose the best next move from a novel chess position Epoch 21% #50 of 69
Math 22
MathArenaAIME 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.7% #6 of 24+17 versions & slices HMMT February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.2% #5 of 24Apex Answer accuracy on the named mathematics competition under the recorded effort MathArena 34.5% #8 of 34Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #7 of 30ArXivMath · December 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 57.4% #3 of 13ArXivMath · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 40.6% #11 of 20ArXivMath · January 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 72.8% #4 of 18ArXivMath · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 62.5% #5 of 14BrokenArXiv · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 3.2% #14 of 15BrokenArXiv · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 5.8% #12 of 13Project Euler Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.7% #3 of 11Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 59.4% #17 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #14 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 50% #16 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 58.3% #17 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #12 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 91.7% #13 of 16USAMO 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 47% #6 of 8
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 40.7% #5 of 40
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 22.9% #4 of 33
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 26.8% #33 of 55
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 66% #29 of 70
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 39.9% #47 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 12.6% #52 of 326
Coding 7
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 31.9% #31 of 44+1 versions & slices 1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 27.6% #7 of 20
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,547 #35 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,546 #36 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,547 #35 of 97
SWE-bench Pro (private) Agents resolve long-horizon professional repository tasks; public and private splits are separate Scale 47.1% #2 of 9
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 48.5% #15 of 242
Agents 6
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 79% #5 of 16
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 33% #9 of 29
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 27.3% #13 of 21
EBR Bench Agents learn to play Earthborne Rangers across repeated playthroughs Epoch 12.7% #19 of 24
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 28.3% #24 of 31
MCP-Atlasfull 1000 Tool orchestration across MCP servers on the stated task split Scale 76.8% #4 of 16
Multimodal 2
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 75.4% #45 of 128
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,316 #6 of 88
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,505 #4 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,500 #4 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,503 #5 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,551 #6 of 198English Human pairwise preferences in the stated text vote pool Arena 1,511 #3 of 205French Human pairwise preferences in the stated text vote pool Arena 1,512 #6 of 164German Human pairwise preferences in the stated text vote pool Arena 1,502 #4 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,521 #3 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,488 #10 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,463 #6 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,488 #7 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,497 #4 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,496 #9 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,509 #4 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,502 #5 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,505 #4 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,501 #5 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 77.7% #24 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,810 #25 of 94
Health & law 3
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 85.3% #18 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 49.1% #22 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 86.1% #22 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 78% #70 of 317
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,507 #3 of 33
Legacy · saturated or no longer reported 11
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 89.6% #39 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 88.4% #42 of 134
SWE-bench Pro (public) Agents resolve long-horizon professional repository tasks; public and private splits are separate 51.9% #4 of 19
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 91.1% #44 of 131
SWE-rebenchall · January 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 53.3% #1 of 1+5 versions & slices Go · January 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Java · January 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Python · January 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 53.3% #1 of 1Rust · January 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1TypeScript · January 1, 2026 to May 15, 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 92.1% #36 of 245
No benchmark matches
CheaperGemini 3.8 Flashhigh+7%-85%*$3.49Sampling parameters are ignored+1
BetterGPT-6.1 Solmedium+4%-60%$0.21Remove unsupported parameters+5
OpenDeepSeek V4.1 Flash 1017high+3%-95%$0.30 / $1.20Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen+3%-40%$2.00Sampling parameters are fixed+3
GLM 5.3 FlashmaxOpen-1%-98%$0.28Defaults to max · Self-hosted+4
Muse Spark OpenxhighOpen-3%-80%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1