DeepSeek trained its agentic coder as a non reasoner. There is a reason Anthropic evaluated Opus 4.1 without thinking on SweBench, Claude Code has thinking off by default and Qwen released Qwen Coder for Qwen code as a non reasoner. We do not need reasoning for Agentic Coding.

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)

@teortaxestex · Twitter · 2025-08-21 07:27 UTC

And so we know what V3.1 is. Yes, it's an agent. - continued long-context pretrain for 840B tokens - *significant* gains in agentic regimes (I've hopefully accurately aggregated some tables) They responded to GLM&Kimi. …They didn't announce V4.