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

MATH 500Reasoning

Official website

500-problem competition-math benchmark

#ModelScore

1

Gemini 2.5 ProGoogle

98.8%

2

GLM-4.5Zhipu AI

98.2%

3

GLM-4.5-AirZhipu AI

98.1%

4

Qwen3-235B-A22BAlibaba

98.0%

5

QwQ-32BAlibaba

98.0%

6

98.0%

7

Qwen3-30B-A3BAlibaba

98.0%

8

Qwen3-8BAlibaba

97.4%

9

DeepSeek-R1DeepSeek

97.3%

10

Qwen3-32BAlibaba

97.2%

44 models total