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

MathVisionMultimodal

Results for 21 models collected from 6 public sources.

#ModelScore

1

GPT-5.6 SolOpenAI

95.8%

2

Claude Fable 5Anthropic

94.8%

3

Kimi K3Moonshot AI

94.3%

4

92.2%

5

92.0%

6

Qwen3.7-PlusAlibaba

90.3%

7

Gemini 3.1 ProGoogle

89.8%

8

Qwen3.5-397B-A17BAlibaba

88.6%

9

Qwen3.6-PlusAlibaba

88.0%

10

Kimi-K2.6Moonshot AI

87.4%

21 models total