SWE-bench Science launches: best agent (Claude Code + Opus-5) under 50% pass@1

_akhaliq · x · 2026-08-21

A new benchmark, SWE-bench Science, targets scientific software engineering with 119 tasks across 98 repositories and 20 domains. Even the strongest agent—Claude Code with Opus-5—achieves under 50% pass@1, showing scientific computing code remains a clear weak spot for current coding agents.

Related event: SWE-bench Science Launches; Top Agents Pass Under 50%(3 posts)→

Original post →

More from coding & agent

coding & agent channel →