4 Claude agents post-trained Qwen3-4B to instruct level in 104h

Name: 4 Claude agents post-trained Qwen3-4B to instruct level in 104h
Uploaded: 2026-10-16T00:00:00+05:30
Description: ByteDance/Duke Athanor: four Claude Opus 5.5 agents, public data, no teacher models or human research advice, raised Qwen3-4B-Base from 15.9 to 67.3 on a six-task suite in 104 hours (Instruct 66.5) and 48.2 vs 47.9 held-out. Cost ~$11,800. Caveat: one campaign, not yet at Qwen reasoning releases.

Why it matters

ByteDance/Duke Athanor: four Claude Opus 5.5 agents, public data, no teacher models or human research advice, raised Qwen3-4B-Base from 15.9 to 67.3 on a six-task suite in 104 hours (Instruct 66.5) and 48.2 vs 47.9 held-out. Cost ~$11,800. Caveat: one campaign, not yet at Qwen reasoning releases.

Read the source: arXiv (opens in a new tab)

Watch on YouTube Watch on Instagram

All hits from 16 Oct 2026 More Agents Get the daily hits by email