SWE-bench Multimodal v2.0 Released with 480 Visual Bug-Fixing Tasks
xeophon · x · 2026-09-01
SWE-bench Multimodal v2.0 has been released with 480 new tasks.
This update requires coding agents to interpret visual assets—such as screenshots, diagrams, and recordings—to diagnose and fix bugs within repositories, marking a significant upgrade for evaluating vision-language coding capabilities.
Related event: SWE-bench Multimodal v2.0 Launches with 480 Open-Source Visual Coding Tasks(5 posts)→
More from coding & agent
- Claude-written test harness let 31KB fake archives land on a real backup server — Grimmoner · 2026-10-18
- Matt Pocock's pre-commit hook caps agent-written files at 5,000 tokens — mattpocockuk · 2026-10-18
- Backups silently failed for 10 days: three monitoring blind spots lined up — Grimmoner · 2026-10-18
- Author Laurence Moroney: write your ugly first draft yourself, then let an LLM edit it — lmoroney · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Devs: Opus 5.5 on medium beats Opus on max — eyishazyer · 2026-10-18