AI NEWS.ccGLM-4.7-Flash-Coder
We fine-tuned GLM-4.7-Flash to push its agentic coding capabilities further: from 33.15% to 41.65% on SWE-rebench-V2 (+26% relative improvement) at 14% lower inference cost. This 30B Mixture-of-Experts model beats competitors 3.5-4× its size — Qwen3.5-122B-A10B and Devstral-2 — and surpasses Ling-2.6-Flash by a narrow margin. We trained it with Halo, the post-training framework we’re open-sourcing today — the full story of the framework here.
翻訳準備中のため原文を表示しています
We fine-tuned GLM-4.7-Flash to push its agentic coding capabilities further: from 33.15% to 41.65% on SWE-rebench-V2 (+26% relative improvement) at 14% lower inference cost. This 30B Mixture-of-Experts model beats competitors 3.5-4× its size — Qwen3.5-122B-A10B and Devstral-2 — and surpasses Ling-2.6-Flash by a narrow margin. We trained it with Halo, the post-training framework we’re open-sourcing today — the full story of the framework here.