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 2025Reasoning

Official website

AIME 2025 problems

#ModelScore

1

GPT-5.2 ProOpenAI

100.0%

2

100.0%

3

GLM-4.7Zhipu AI

95.7%

4

Gemini 3 ProGoogle

95.0%

5

GPT-5OpenAI

94.6%

6

Kimi-K2Moonshot AI

94.5%

7

94.0%

8

GLM-4.6Zhipu AI

93.9%

9

DeepSeek-V3.2DeepSeek

93.1%

10

92.7%

60 models total