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

v0.1.56.100f6e404dfa浙ICP备09076226号-7

Benchmark details loading

Back to benchmarks

SWE-bench MultimodalCodingMultimodal

Official website

SWE-bench Multimodal adds visual context such as screenshots and design mockups to software issues to evaluate visual software engineering tasks.

Ranking Sources

#ModelScore

1

Claude Opus 5.5Anthropic

61.4%

2

Claude Opus 5Anthropic

59.4%

3

Claude Fable 5.1Anthropic

54.7%

3 models total