SWE-Bench Multimodal

coding

Multilingual: no

SWE-Bench Multimodal extends SWE-Bench to evaluate language models on software engineering tasks that involve visual inputs such as screenshots, UI mockups, and diagrams alongside code understanding.

Methodology

Imported from llm-stats public benchmark metadata. Modality: multimodal. Max score: 1. Categories: agents, code, multimodal, reasoning, vision. Language: en. Verified by llm-stats: no.