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

Belebele DravidianMultilingual

Results for 13 models collected from 1 public source.

#ModelScore

1

Qwen3-32BAlibaba

84.5%

2

Gemma 3 27BGoogle

83.5%

3

Qwen3-14BAlibaba

81.0%

4

Gemma 3 12BGoogle

79.0%

5

Qwen3-4BAlibaba

74.3%

6

QwQ-32BAlibaba

69.3%

7

Qwen2.5-32BAlibaba

67.8%

8

Qwen2.5-14BAlibaba

66.2%

9

Gemma 3 4BGoogle

64.8%

10

Qwen3-1.7BAlibaba

52.8%

13 models total