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

SkillsBench Avg5Coding

Official website

Results for 8 models collected from 3 public sources.

#ModelScore

1

Qwen3.6-27BAlibaba

48.2%

2

GLM-5Zhipu AI

47.2%

3

Qwen3.6-PlusAlibaba

45.7%

4

Claude Opus 4.5Anthropic

45.3%

5

Kimi-K2.5Moonshot AI

42.0%

6

Qwen3.5-397B-A17BAlibaba

30.0%

7

Qwen3.6-35B-A3BAlibaba

28.7%

8

Qwen3.5-35B-A3BAlibaba

4.4%

8 models total