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

PolyMATH JapaneseMultilingual

Results for 13 models collected from 1 public source.

#ModelScore

1

Gemini 2.5 ProGoogle

55.4%

2

Qwen3-235B-A22BAlibaba

52.7%

3

Qwen3-32BAlibaba

47.7%

4

Qwen3-30B-A3BAlibaba

47.4%

5

Qwen3-14BAlibaba

45.7%

6

Qwen3-8BAlibaba

44.7%

7

Qwen3-4BAlibaba

40.7%

8

QwQ-32BAlibaba

39.9%

9

Qwen3-1.7BAlibaba

28.5%

10

Qwen2.5-72BAlibaba

17.7%

13 models total