SWE-bench Multimodal
AI benchmark
A multimodal variant of SWE-bench that adds visual context (screenshots, design mockups) to software engineering issue descriptions, testing whether models can leverage visual information for code generation.
- Domains
- Multimodal
- Data source
- benchlm-benchmarks
- Catalogued
Catalogue entry from the RL Engineering daily scrape of public sources. Data reflects the 2026-08-30 snapshot.