ProximalHQ's training setup lifts Qwen3.8-27B to 37.2% Pass@1 on DeepSWE, up 8.4 points
aryaman2020 · x · 2026-10-09
ProximalHQ reports that training Qwen3.8-27B on an internal set of coding tasks with its setup raised Pass@1 on DeepSWE to 37.2%, 8.4 percentage points above the base model, while Pass@8 climbed from 67.7% to 86.6%. The retweeter calls it a cool way to validate your training data.
More from coding & agent
- Agent Buddy: an open-source desk buddy that shows your AI coding agents' status — DanWahlin · 2026-10-09
- Developer's Grok Bot now natively integrates with X, no API or credits needed — daniel_mac8 · 2026-10-09
- AutoScientist's two-agent checklist loop auto-audits every training example — sarahookr · 2026-10-09
- Meta's KernelAgent uses multi-agent orchestration for 2.02x Triton kernel speedups — PyTorch · 2026-10-09
- Claude recovers lost 2019 build paths to recompile MakerDAO's DAI to an exact bytecode match — devanshmehta · 2026-10-09
- 6 models tested on real MCP servers: Opus 5.5 leads, open models cost 87% less per attempt — shensi · 2026-10-09