OpenAI Questions Reliability of SWE-Bench Pro
RishiBommasani · x · 2026-07-10
The post discusses OpenAI's audit of SWE-Bench Pro, revealing that the popular AI coding benchmark can no longer reliably measure cutting-edge programming capabilities. OpenAI identified flaws in about 30% of the questions and subsequently withdrew its previous recommendation of the benchmark as a leading coding evaluation.
Related event: OpenAI Says SWE-Bench Pro Is Too Noisy(3 posts)→
More from coding & agent
- Building a Secure AI Agent Gateway: Self-Hosting OAuth for Multiple SaaS Apps — Defiant_Cod_2654 · 2026-07-22
- Rowboat launches as an open-source, local-first AI coworker with memory — ycombinator · 2026-07-22
- Scoble says AI “loops” really means long-running multi-agent workspaces — Scobleizer · 2026-07-22
- Kimi Code opens a waitlist as Moonshot rolls out its coding product — Fabulous_Bonus_8981 · 2026-07-22
- Open-source runtime lets each repo define its own AI code reviewer — ibabufrik · 2026-07-22
- Indie Dev Asks: What's Actually Broken in Your AI Agent's Memory Today? — AcceptableTime7937 · 2026-07-22