Skip to main content

leaderboard.cn

Explore

Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio

Library

Models
Pricing
Organizations
Benchmarks
Data sources

leaderboard.cn

Benchmark details loading

Loading page content

About Ranking methodology Changelog

v0.1.26.a85cb1563d03浙ICP备09076226号-7

Back to benchmarks

MathVista miniMultimodal

Official website

Results for 15 models collected from 4 public sources.

#ModelScore

1

Qwen3.5-397B-A17BAlibaba

90.3%

2

Gemini 3 ProGoogle

87.9%

3

Qwen3.6-27BAlibaba

87.4%

4

Qwen3.6-35B-A3BAlibaba

86.4%

5

Qwen3.5-35B-A3BAlibaba

86.2%

6

GPT-5.2OpenAI

83.1%

7

Claude Opus 4.5Anthropic

80.0%

8

Claude Sonnet 4.5Anthropic

79.8%

9

GPT-4.1 miniOpenAI

73.1%

10

GPT-4.5OpenAI

72.3%

15 models total