Skip to content

Benchmark

HMMT25

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

Models measured
23
Scores recorded
25
Sources
1
IQ weight
1.71

Score distribution

75.7%
Mean
78.3%
Median
15.9%
Std dev
54.1%
10th percentile
90.7%
90th percentile
32.5%
Min
32.5%94.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.71 for chat models, measured over 23 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.6%
2Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92.7%
3Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.7%
4Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.3%
5Grok 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
6Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.8%
7Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
8Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.2%
9Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.1%
10Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.8%
11Qwen 3 235B A22B Thinking 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.9%
12Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.9%
13Granite 4.2 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.3%
14Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.77.4%
15Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.8%
16Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.2%
17Qwen3 Next 80B A3Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.9%
18qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.67.6%
19Granite 4.2 3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.7%
20Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.60.6%
21Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.57.4%
22Qwen3 235B A22B Instruct 2507· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.4%
23Qwen3 Next 80B A3B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.1%
24qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.50.6%
25Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.32.5%

Data credits: Data by LLM Stats