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

CRUX-OCoding

Results for 25 models collected from 1 public source.

#ModelScore

1

Qwen3-235B-A22B-BaseAlibaba

79.0%

2

Llama 4 Maverick BaseMeta

77.0%

3

DeepSeek-V3 BaseDeepSeek

76.6%

4

Qwen3-32B-BaseAlibaba

72.5%

5

Qwen3-14B-BaseAlibaba

68.6%

6

Qwen2.5-Plus-BaseAlibaba

68.5%

7

Qwen2.5-32BAlibaba

67.8%

8

Qwen3-30B-A3B-BaseAlibaba

67.2%

9

Qwen2.5-72BAlibaba

66.2%

10

Qwen3-8B-BaseAlibaba

62.0%

25 models total