SWE-Bench Multimodal Hits Vals: Every Claude Model Outperforms OpenAI's
dejavucoder · x · 2026-10-15
SWE-Bench Multimodal, created by Ofir Press and colleagues, is now on Vals. The benchmark asks models to fix real JavaScript GitHub issues where the bug report depends on screenshots. Early observation: all Claude models beat OpenAI's on this bench.
Related event: SWE-bench Multimodal Leaderboard Launches; Claude Opus 5.5 Tops at 70.21%(5 posts)→
More from coding & agent
- Epic's Lore vs Anthropic's Scion: two post-Git, centralized VCS architectures compared — ssh4net · 2026-10-15
- Creator uses coding agents + Google Maps 3D Tiles to place billboard art on real buildings — matanSF · 2026-10-15
- banteg: argon Is a Strong Engineer but Sloppy Coder, Needs 3-4 Review Rounds — banteg · 2026-10-15
- 'Writing code is no longer a value add,' dev observes as AI coding spreads — tlakomy · 2026-10-15
- From PM to AI Builder: Treat Your Agent Like Your Engineering Team — brandon_galang · 2026-10-15
- Ex-DeepMind coding agent lead goes solo, betting AI needs humans for the last mile — julianweisser · 2026-10-15