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

PolyMathMultilingual

Official website

Results for 44 models collected from 4 public sources.

#ModelScore

1

Qwen3-235B-A22B-Thinking-2507Alibaba

60.1%

2

Qwen3-235B-A22BAlibaba

54.7%

3

Qwen3-30B-A3B-Thinking-2507Alibaba

52.6%

4

Gemini 2.5 ProGoogle

52.2%

5

Qwen3-235B-A22B-Instruct-2507Alibaba

50.2%

6

Qwen3-32BAlibaba

47.4%

7

DeepSeek-R1DeepSeek

47.1%

8

Qwen3-4B-Thinking-2507Alibaba

46.2%

9

Qwen3-30B-A3BAlibaba

46.1%

10

QwQ-32BAlibaba

45.9%

44 models total