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

MT-AIME 2024Multilingual

Results for 35 models collected from 1 public source.

#ModelScore

1

Qwen3-235B-A22BAlibaba

80.8%

2

Gemini 2.5 ProGoogle

76.9%

3

Qwen3-32BAlibaba

75.0%

4

73.9%

5

Qwen3-30B-A3BAlibaba

73.9%

6

DeepSeek-R1DeepSeek

73.5%

7

Qwen3-14BAlibaba

73.3%

8

QwQ-32BAlibaba

68.0%

9

OpenAI o1OpenAI

67.4%

10

Qwen3-8BAlibaba

65.4%

35 models total