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

MMLUReasoning

Official website

Results for 46 models collected from 5 public sources.

#ModelScore

1

OpenAI o1OpenAI

91.8%

2

90.8%

3

DeepSeek-R1DeepSeek

90.8%

4

90.2%

5

DeepSeek-V4-Pro BaseDeepSeek

90.1%

6

MiMo-V2.5-Pro BaseXiaomi

89.4%

7

DeepSeek-V4-Flash BaseDeepSeek

88.7%

8

Llama 3.1 405B InstructMeta

88.6%

9

DeepSeek-V3DeepSeek

88.5%

10

Claude 3.5 Sonnet 20241022Anthropic

88.3%

46 models total