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

Belebele Tai-KadaiMultilingual

Results for 13 models collected from 1 public source.

#ModelScore

1

Qwen3-32BAlibaba · Non-reasoning mode

85.0%

2

Qwen3-14BAlibaba

83.5%

3

Gemma 3 27BGoogle

81.0%

4

Gemma 3 12BGoogle

77.5%

5

QwQ-32BAlibaba

77.0%

6

Qwen2.5-32BAlibaba

74.5%

7

Qwen2.5-14BAlibaba

72.2%

8

Qwen3-4BAlibaba

68.5%

9

Gemma 3 4BGoogle

61.5%

10

Qwen3-1.7BAlibaba

53.5%

13 models total