The Information: Kimi K3.1 Pro and DeepSeek V4.1-Flash both distilled from GPT-6 Astra
kimmonismus · x · 2026-11-22
kimmonismus notes that four major Chinese models (Ant Ling 3.1 Flash 1019, Moonshot Kimi K3.1 Pro, MiniMax M3.1 Flash, DeepSeek V4.1 Flash 1017) launched 26–36 days ago, yet none come close to US frontier models.
The attached The Information excerpt cites sources saying Moonshot distilled GPT-6 Astra while building Kimi K3.1 Pro, and DeepSeek's Oct 17 V4.1-Flash 1017 upgrade also benefited from distilling Astra; Claude models were previously the biggest distillation target.
More from Models
- Sakana AI announces its own pretrained LLM series Sakana Sawara, first model due spring 2027 — SakanaAILabs · 2026-11-22
- Open-weight medical MoE LingSante-3.1-flash: 560B params, claims wins over GPT-6 and Claude — DrDatta_AIIMS · 2026-11-22
- Sakana AI announces Sakana Sawara, a from-scratch LLM series built at its RSI Lab — SakanaAILabs · 2026-11-22
- HF's harness adapters lift Qwen3.8-27B from 39% to 55% on Terminal-Bench 2.1 with half the tokens — SergioPaniego · 2026-11-22
- KOL: a month on, none of China's four flagship models comes close to US frontier — kimmonismus · 2026-11-22
- OpenAI and Anthropic week 47: GPT-6.2 Astra/Sol launch, Anthropic's Nasdaq debut, watermarking — btibor91 · 2026-11-22