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

CharXiv (RQ) (w/ Python)Multimodal

Official website

Results for 20 models collected from 4 public sources.

#ModelScore

1

Claude Fable 5Anthropic

93.5%

2

Kimi K3Moonshot AI

91.3%

3

90.0%

4

Claude Opus 4.8Anthropic

89.9%

5

Gemini 3.1 ProGoogle

89.9%

6

GPT-5.6 SolOpenAI

89.1%

7

89.0%

8

88.7%

9

Kimi-K2.6Moonshot AI

86.7%

10

Claude Opus 4.6Anthropic

84.7%

20 models total