Post by Serena Ge on X
Serena Ge@serenaa_ge
XToday we’re releasing DeepSWE, a new standard for agentic coding benchmarks.
On public leaderboards, top models often look relatively close in capability. DeepSWE shows where they actually diverge, reflecting the realistic experience of developers in their day-to-day work.

6K likes509 repliesPosted May 26, 2026