Proximal-Labs/frontier-swe

FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research

1 best points · 1 comments · 1 Hacker News post · 238 GitHub stars · View on GitHub

Hacker News discussions

• FrontierSWE – Benchmark for long horizon coding tasks (1 points, 1 comments, by pHequals7, 2026-04-26)