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 16.1 #140 of 336
Knowledge 18
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,458 #36 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,437 #48 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,452 #27 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,461 #28 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,507 #32 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,458 #31 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,445 #57 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,458 #31 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,474 #16 of 168German Human pairwise preferences in the stated text vote pool Arena 1,487 #11 of 167French Human pairwise preferences in the stated text vote pool Arena 1,473 #30 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,434 #22 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,461 #16 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,479 #12 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -16.4 #111 of 320
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 39.1% #51 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 90.9% #259 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 48.7% #121 of 245
Reasoning 4
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 4.9% #52 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 5.1% #50 of 66
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 41% #56 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 56.4% #53 of 64
Math 20
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 24.6% #61 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #54 of 55
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 14.1% #24 of 40
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 0.5% #31 of 34+15 versions & slices AIME 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 88.3% #15 of 30HMMT February 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 82.5% #13 of 30BRUMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #14 of 24SMT 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 84.9% #14 of 24CMIMC 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 58.1% #21 of 22Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 64.6% #14 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.2% #13 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 64.6% #12 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.7% #13 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 82.5% #14 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.8% #9 of 16HMMT November 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 80% #12 of 14Project Euler Answer accuracy on the named mathematics competition under the recorded effort MathArena 27% #11 of 11IMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 31.6% #2 of 4USAMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 24.4% #2 of 3
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.2% #16 of 33
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 22.5% #113 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 2.6% #99 of 323
Health & law 3
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 12.2% #45 of 103
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 73.6% #63 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 50.6% #14 of 78
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 69% #133 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 10.2% #61 of 135
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 84.4% #88 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 85.3% #57 of 134
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 87.7% #26 of 139
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 84.2% #67 of 131
No benchmark matches
CheaperGPT-6.1 Solmedium+56.3-32%$0.21Remove unsupported parameters+5
OpenMuse Spark Openxhigh+41+169%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1
Claude Haiku 5.5low+19.6-92%$0.024Remove sampling parameters+5
MiMo v2.5thinkingOpen+6.5-87%$0.042
Kimi K3maxOpen+36.1+536%$2.00Sampling parameters are fixed+3
Step 5 PreviewthinkingOpen+32.7+227%$1.03No web search+3
GLM 5.3maxOpen+30.7+538%$2.01No image input+4MMotif 3Open+26.5-75%$0.50 / $2Context: 1M → 262K+1