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

RefCOCO avgMultimodal

Official website

Results for 7 models collected from 4 public sources.

#ModelScore

1

Qwen3.6-PlusAlibaba

93.5%

2

Qwen3.6-27BAlibaba

92.5%

3

Qwen3.5-397B-A17BAlibaba

92.3%

4

Qwen3.6-35B-A3BAlibaba

92.0%

5

Qwen3.5-35B-A3BAlibaba

89.2%

6

Kimi-K2.5Moonshot AI

87.8%

7

Gemini 3 ProGoogle

84.1%

7 models total