How SWE‑Swiss Enables a 32B Model to Match Larger LLMs on Software Engineering Tasks

Researchers from Peking University, ByteDance Seed, and Hong Kong University present SWE‑Swiss, a 32‑billion‑parameter model that, through a two‑stage training recipe and enhanced self‑consistency, achieves 60.2% accuracy on SWE‑bench Verified, matching larger models while remaining fully open‑source.

LLMSWE‑Swiss

0 likes · 8 min read

How SWE‑Swiss Enables a 32B Model to Match Larger LLMs on Software Engineering Tasks