SWE-bench Multimodal

SWE-bench Multimodal tests GitHub-issue patching on JavaScript/TypeScript repositories where the issue includes an image, such as a bug screenshot or design mockup.

Also known as: SWE-bench M, SWE-bench MM

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorycoding
SubcategoryGitHub issue resolution / patch generation with visual inputs
Page statusactive
Metric% resolved (FAIL_TO_PASS and PASS_TO_PASS tests both pass)
Directionhigher_is_better
Unit%
Dataset size480
Dataset licenceCC BY 4.0
PublisherOriginally Princeton NLP / Stanford, with the SWE-bench team; maintained today by the SWE-bench Team at swebench.com

What it measures

SWE-bench Multimodal measures the same underlying skill as SWE-bench — resolving a real GitHub issue with a patch a project's own tests accept — but restricted to issues that include a visual element: a screenshot of a bug, a design mockup or wireframe, a diagram of the desired behaviour, or an error message with visual context. Repositories are JavaScript/TypeScript projects for web interface design, diagramming, data visualisation, syntax highlighting and interactive mapping, so a model must read and act on both text and images to succeed, not just text.

Task format

Given an issue description that includes at least one image, plus repository access, the system outputs a patch. The patch is applied inside a container and graded against FAIL_TO_PASS and PASS_TO_PASS tests recovered from the pull request that originally fixed the issue, the same protocol as the rest of the SWE-bench family.

Models reporting this benchmark

These figures come from the model cards, which carry one collection date per card and no per-score attribution. They are shown as reported, not as verified evidence.
ModelProviderScoreCard as of
Claude Mythos PreviewAnthropic59.02026-04
Claude Opus 4.6Anthropic27.12026-04

Data

This page as JSON · Edit on GitHub