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

WritingBenchWriting

Results for 47 models collected from 4 public sources.

#ModelScore

1

Qwen3-235B-A22B-Thinking-2507Alibaba

88.3%

2

Qwen3-30B-A3B-Instruct-2507Alibaba

85.5%

3

Claude Opus 4.7Anthropic

85.3%

4

Claude Opus 4.8Anthropic

85.2%

5

Qwen3-235B-A22B-Instruct-2507Alibaba

85.2%

6

Qwen3-30B-A3B-Thinking-2507Alibaba

85.0%

7

84.7%

8

LongCat-2.0Meituan

83.8%

9

Gemini 3.1 ProGoogle

83.7%

10

Qwen3-4B-Instruct-2507Alibaba

83.4%

47 models total