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

MGSMMultilingual

Results for 25 models collected from 1 public source.

#ModelScore

1

Qwen3-235B-A22B-BaseAlibaba

83.5%

2

Qwen3-32B-BaseAlibaba

83.1%

3

DeepSeek-V3 BaseDeepSeek

82.7%

4

Qwen2.5-72BAlibaba

82.4%

5

Qwen2.5-Plus-BaseAlibaba

82.2%

6

Llama 4 Scout BaseMeta

79.9%

7

Llama 4 Maverick BaseMeta

79.7%

8

Qwen3-14B-BaseAlibaba

79.2%

9

Qwen3-30B-A3B-BaseAlibaba

79.1%

10

Qwen2.5-32BAlibaba

78.1%

25 models total