Scale AI launches SWE-Bench Pro V2, a harder agentic coding benchmark

bigblueboo · x · 2026-09-23

Scale AI announced SWE-Bench Pro V2 is live, with a thread outlining what's new. SWE-Bench Pro is a harder expansion of the mainstream SWE-Bench, and V2 aims to better probe real agentic coding capability.

Original post →

More from Research

Research channel →