Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

RULER 128KLong context

Results for 10 models collected from 1 public source.

#ModelScore

1

Qwen3-235B-A22BAlibaba · Non-reasoning mode

90.6%

2

Qwen2.5-72BAlibaba

88.4%

3

Qwen3-32BAlibaba · Non-reasoning mode

85.6%

4

Qwen3-14BAlibaba · Non-reasoning mode

85.1%

5

Qwen2.5-32BAlibaba

82.0%

6

Qwen3-30B-A3BAlibaba · Non-reasoning mode

79.2%

7

Qwen2.5-14BAlibaba

78.1%

8

Qwen3-8BAlibaba · Non-reasoning mode

77.4%

9

Qwen3-4BAlibaba

67.2%

10

Qwen2.5-7BAlibaba

55.1%

10 models total