Foresight-SWE benchmark: coding agents solve 60.7% of issues but only 14.8% without introducing bugs
OfirPress · x · 2026-11-05
Foresight-SWE tests whether coding agents can avoid introducing bugs that developers later fixed. Across 11 models, agents solve developer-specified issues 60.7% of the time on average—but only 14.8% when they must additionally avoid bugs developers later fixed. They can't catch their own bugs.
More from coding & agent
- Model gets stuck in a loop spamming "it failed!!!" — burning 140K tokens — CtrlAltDwayne · 2026-11-05
- AX to support migrating agentic workloads between local and production clusters — rakyll · 2026-11-05
- OpenAI upgrades Codex: marked-up images now pinpoint edits via API — OpenAIDevs · 2026-11-05
- Baseten Router cuts coding-task costs 72% with only 0.8pt pass-rate drop vs Opus 5.5 — baseten · 2026-11-05
- BrowserForge: open-source MCP server gives agents your real browser with human approval gates — mostafazog · 2026-11-05
- Free course teaches analytics engineers AI skills beyond Snowflake and dbt — Zachly · 2026-11-05