Skip to content

Benchmark

AIME 2026

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
40
Scores recorded
40
Sources
3
IQ weight
2.58

Score distribution

90.9%
Mean
94.2%
Median
11.2%
Std dev
82.5%
10th percentile
97.1%
90th percentile
37.5%
Min
37.5%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.58 for chat models, measured over 40 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1DeepSeek V4.1 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim100%
2GLM 5.2· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
99.2%
3Beam 1.0 501B A23B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
97.7%
4Inkling FP4· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
97.1%
5Sakana Namazu· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.7%
6Step 3.5 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
96.7%
7Kimi K2.6· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
96.4%
8GLM 5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
95.8%
9Kimi K2.5· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
95.8%
10Ring 2.6 1T· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim95.8%
11Inkling Small· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
95.5%
12GLM 5.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
95.3%
13Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.3%
14Solar Pro 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.3%
15Muse Glimmer 30B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
94.7%
16Mai Thinking 1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.5%
17Doubao Seed 2.0 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.2%
18MiniMax M2.7· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim94.2%
19DeepSeek V3.2· OpenEvals Leaderboard data· Reported by the model's developer. The source relaying it did not verify it.94.2%
20Qwen3.6 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
94.1%
21Qwen3.5 397B A17B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 3 sources
93.3%
22openPangu 2.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim93.3%
23Qwen3 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.3%
24Ling 3.0 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
93.2%
25Qwen3.6 35B A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim
Values from 2 sources
92.7%
26Qwen3.5 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim90.8%
27Nemotron 3 Super 120B A12B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim90%
28Gemma 4 31B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
29Gemma 4 26B A4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.3%
30Seed 2.0 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.3%
31Qwen3 30B A3B2507, thinking· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim87.5%
32ling-2.6-1t· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim87.4%
33Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.7%
34MiniCPM5-2B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim86.5%
35Qwen3-4B-Thinking-2507· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim82.5%
36Gemma 4 12B It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.5%
37MiniCPM-V 4.7 35B-A3B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim76.5%
38Ling 2.6 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim73.8%
39Gemma 4 E4B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim42.5%
40Gemma 4 E2B-it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim37.5%

Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark · Data by LLM Stats · OpenEvals/leaderboard-data, MIT (licence)