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

INCLUDE JapaneseMultilingual

Results for 13 models collected from 1 public source.

#ModelScore

1

Qwen2.5-72BAlibaba

94.1%

2

Qwen3-235B-A22BAlibaba

94.1%

3

GPT-4oOpenAI

92.2%

4

Qwen3-32BAlibaba · Non-reasoning mode

92.2%

5

Qwen3-30B-A3BAlibaba

88.2%

6

Qwen3-14BAlibaba

88.2%

7

Qwen3-8BAlibaba

86.3%

8

QwQ-32BAlibaba

86.3%

9

Gemma 3 27BGoogle

86.3%

10

Qwen3-4BAlibaba

80.4%

13 models total

Benchmark details loading

Back to benchmarks

INCLUDE JapaneseMultilingual

Results for 13 models collected from 1 public source.

#ModelScore

1

Qwen2.5-72BAlibaba

94.1%

2

Qwen3-235B-A22BAlibaba

94.1%

3

GPT-4oOpenAI

92.2%

4

Qwen3-32BAlibaba · Non-reasoning mode

92.2%

5

Qwen3-30B-A3BAlibaba

88.2%

6

Qwen3-14BAlibaba

88.2%

7

Qwen3-8BAlibaba

86.3%

8

QwQ-32BAlibaba

86.3%

9

Gemma 3 27BGoogle

86.3%

10

Qwen3-4BAlibaba

80.4%

13 models total