Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 AA Intelligence Index 4.3.2: Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 31.9 #52 of 337
Knowledge 7
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 47% #30 of 321+1 versions & slices Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 62.8% #113 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 13.7 #34 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 53.1% #107 of 248
EQ-Bench3 EQ-Bench 3: Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,717 #4 of 50
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 47% #32 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 25% #30 of 64
Reasoning 5
ARC-AGI-1public evaluation ARC-AGI-1 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 96.8% #17 of 61+1 versions & slices semi-private ARC-AGI-1 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 94% #18 of 64
ARC-AGI-2public evaluation ARC-AGI-2 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 79% #17 of 63+1 versions & slices semi-private ARC-AGI-2 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 69.2% #20 of 66
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 21% #49 of 68
Math 22
MathArenaAIME 2026 MathArena · AIME 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.7% #6 of 24+17 versions & slices HMMT February 2026 MathArena · HMMT February 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.2% #5 of 24Apex MathArena · apex · Apex: Answer accuracy on the named mathematics competition under the recorded effort MathArena 34.5% #8 of 34Apex Shortlist MathArena · apex · Apex Shortlist: Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #7 of 30ArXivMath · December 2025 MathArena · arxiv · 12/2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 57.4% #3 of 13ArXivMath · February 2026 MathArena · arxiv · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 40.6% #11 of 20ArXivMath · January 2026 MathArena · arxiv · 01/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 72.8% #4 of 18ArXivMath · March 2026 MathArena · arxiv · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 62.5% #5 of 14BrokenArXiv · February 2026 MathArena · arxiv_false · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 3.2% #14 of 15BrokenArXiv · March 2026 MathArena · arxiv_false · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 5.8% #12 of 13Project Euler MathArena · euler · Project Euler: Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.7% #3 of 11Kangaroo 2025 1-2 MathArena · kangaroo · Kangaroo 2025 1-2: Answer accuracy on the named mathematics competition under the recorded effort MathArena 59.4% #17 of 17Kangaroo 2025 11-12 MathArena · kangaroo · Kangaroo 2025 11-12: Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #14 of 17Kangaroo 2025 3-4 MathArena · kangaroo · Kangaroo 2025 3-4: Answer accuracy on the named mathematics competition under the recorded effort MathArena 50% #16 of 17Kangaroo 2025 5-6 MathArena · kangaroo · Kangaroo 2025 5-6: Answer accuracy on the named mathematics competition under the recorded effort MathArena 58.3% #17 of 17Kangaroo 2025 7-8 MathArena · kangaroo · Kangaroo 2025 7-8: Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #12 of 16Kangaroo 2025 9-10 MathArena · kangaroo · Kangaroo 2025 9-10: Answer accuracy on the named mathematics competition under the recorded effort MathArena 91.7% #13 of 16USAMO 2026 MathArena · usamo · USAMO 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 47% #6 of 8
FrontierMath FrontierMath: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 40.7% #5 of 40
FrontierMath Tier4 FrontierMath Tier 4: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 22.9% #4 of 33
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 26.8% #32 of 54
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 66% #28 of 69
Science 2
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 39.9% #45 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 12.6% #50 of 324
Coding 6
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 31.9% #31 of 44+1 versions & slices 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 27.6% #7 of 20
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,547 #35 of 97+1 versions & slices full cohort WebDev Arena · snapshot 2026-10-19 · native board settings: Human pairwise preferences in the stated webdev vote pool Arena 1,547 #35 of 97
SWE-bench Pro (private) 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 Terminal-Bench Hard (version unstated): 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 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 EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs Epoch 12.7% #19 of 24
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 28.3% #24 of 31
MCP-Atlasfull 1000 MCP-Atlas · full 1000: Tool orchestration across MCP servers on the stated task split Scale 76.8% #4 of 16
Multimodal 2
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 75.4% #44 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,316 #6 of 88
Writing 17
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,500 #4 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,503 #5 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,550 #6 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,512 #3 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,513 #4 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,502 #3 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,522 #3 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,488 #9 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,465 #7 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,488 #7 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,497 #5 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,496 #9 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,510 #4 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,502 #5 of 188creative writing · full cohort Arena Text · creative writing · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,505 #4 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 77.7% #23 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,809 #24 of 91
Health & law 3
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 85.3% #18 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 49.1% #22 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 86.1% #22 of 80
Documents 2
AA-LCR (long context)1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 78% #68 of 275
Arena Document Arena Document · overall: Human pairwise preferences in the stated document vote pool Arena 1,507 #3 of 33
Legacy · saturated or no longer reported 11
GPQA Diamond 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 GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 88.4% #41 of 133
SWE-bench Pro (public) 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 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 91.1% #43 of 130
SWE-rebenchall · 2026-01-01 to 2026-05-15 SWE-rebench · all · 2026-01-01 to 2026-05-15: 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 · 2026-01-01 to 2026-05-15 SWE-rebench · go · 2026-01-01 to 2026-05-15: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Java · 2026-01-01 to 2026-05-15 SWE-rebench · java · 2026-01-01 to 2026-05-15: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Python · 2026-01-01 to 2026-05-15 SWE-rebench · python · 2026-01-01 to 2026-05-15: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 53.3% #1 of 1Rust · 2026-01-01 to 2026-05-15 SWE-rebench · rust · 2026-01-01 to 2026-05-15: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1TypeScript · 2026-01-01 to 2026-05-15 SWE-rebench · typescript · 2026-01-01 to 2026-05-15: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 92.1% #36 of 245
No benchmark matches
BetterGPT-6 Lunaxhigh+8%-98%$0.042Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking+45%-95%$0.13Pass back reasoning_content+3
CheaperGemini 4 Argonhigh+65%-60%*$1.99Synchronous output stops at 65,536+2
Muse Wondermax+64%-20%$4.52Only auto tool_choice is supported+5
DeepSeek V4.1 Flash 1017maxOpen+41%-95%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+40%-79%$2.01No image input+4
Step 5 PreviewthinkingOpen+37%-86%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+36%-40%$2.00Sampling parameters are fixed+3