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

AIME 2024Reasoning

Official website

AIME 2024 problems

#ModelScore

1

Gemini 2.5 ProGoogle

92.0%

2

GLM-4.5Zhipu AI

91.0%

3

GLM-4.5-AirZhipu AI

89.4%

4

87.3%

5

OpenAI o1 pro modeOpenAI

86.0%

6

Qwen3-235B-A22BAlibaba

85.7%

7

Grok-3-Beta ThinkingxAI

83.9%

8

Qwen3-32BAlibaba

81.4%

9

Qwen3-30B-A3BAlibaba

80.4%

10

DeepSeek-R1DeepSeek

79.8%

51 models total