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

CritPtReasoning

Official website

Results for 16 models collected from 4 public sources.

#ModelScore

1

27.1%

2

Claude Opus 4.8Anthropic

20.9%

3

GLM-5.2Zhipu AI

20.9%

4

Gemini 3.1 ProGoogle

17.7%

5

DeepSeek-V4-ProDeepSeek

14.0%

6

Qwen3.7-MaxAlibaba

13.4%

7

Claude Opus 4.6Anthropic

12.6%

8

DeepSeek-V4-FlashDeepSeek

10.6%

9

Kimi-K2.6Moonshot AI

9.1%

10

Qwen3.7-PlusAlibaba

6.0%

16 models total