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 Feb. 2026Reasoning

Official website

Results for 22 models collected from 9 public sources.

#ModelScore

1

97.7%

2

Qwen3.7-MaxAlibaba

97.1%

3

Claude Opus 4.8Anthropic

96.7%

4

96.7%

5

Claude Opus 4.6Anthropic

96.2%

6

DeepSeek-V4-ProDeepSeek

95.2%

7

Gemini 3.1 ProGoogle

94.7%

8

Qwen3.7-PlusAlibaba

92.9%

9

Kimi-K2.6Moonshot AI

92.7%

10

GLM-5.2Zhipu AI

92.5%

22 models total