Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

Loading page content

© 2026 Leaderboard.cn. Traceable AI model evaluations and rankings.

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

HMMT 2025Reasoning

Results for 16 models collected from 3 public sources.

#ModelScore

1

GPT-5OpenAI

93.3%

2

GPT-5 miniOpenAI

87.8%

3

85.0%

4

Qwen3-235B-A22B-Thinking-2507Alibaba

83.9%

5

o3OpenAI

81.7%

6

GPT-5 nanoOpenAI

75.6%

7

Qwen3-30B-A3B-Thinking-2507Alibaba

71.4%

8

Qwen3-4B-Thinking-2507Alibaba

55.5%

9

Qwen3-235B-A22B-Instruct-2507Alibaba

55.4%

10

Qwen3-30B-A3B-Instruct-2507Alibaba

43.0%

16 models total