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 PortugueseMultilingual

Results for 13 models collected from 1 public source.

#ModelScore

1

Qwen3-235B-A22BAlibaba

58.3%

2

Qwen3-32BAlibaba

52.4%

3

Gemini 2.5 ProGoogle

52.2%

4

Qwen3-30B-A3BAlibaba

49.3%

5

QwQ-32BAlibaba

48.7%

6

Qwen3-14BAlibaba

46.7%

7

Qwen3-8BAlibaba

44.8%

8

Qwen3-4BAlibaba

44.2%

9

Qwen3-1.7BAlibaba

28.2%

10

Gemma 3 27BGoogle

20.9%

13 models total