Skip to content

Benchmark

HMMT 2025

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

Models measured
32
Scores recorded
32
Sources
1
IQ weight
2.39

Score distribution

82.9%
Mean
90.7%
Median
19.8%
Std dev
38.8%
10th percentile
97.5%
90th percentile
28.9%
Min
28.9%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.39 for chat models, measured over 32 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-5.2 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim100%
2GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim99.4%
3DeepSeek V3.2 Speciale· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim99.2%
4Kimi K2 Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim97.5%
5Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.7%
6Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.4%
7Qwen3.5 397B A17B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.8%
8Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.7%
9GLM 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.4%
10GLM 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94%
11Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.8%
12GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.3%
13Grok 4 Fast· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.3%
14Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim92%
15Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.4%
16Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.7%
17DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
18DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
19Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89%
20GPT-5 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.8%
21Sarvam 105B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.8%
22MiMo V2 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.4%
23DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.6%
24Qwen3.5 9B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.2%
25DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.4%
26GPT-5 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.6%
27Qwen3.5 4B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74%
28Sarvam-30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
29Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim38.8%
30GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim35%
31DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.5%
32GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim28.9%

Data credits: Data by LLM Stats