deepseek-v4.1IMAGE

V4.1-Flash-1017 beats GPT 5.6 Sol on Terminal-Bench at ~17x lower cost

Claims V4.1-Flash-1017 tops GPT 5.6 Sol on Terminal-Bench while costing ~17x less, a 35% gain over the prior V4.1-Flash from RL on multiple coding agent harnesses rather than algorithmic novelty.

𝕏AID ADIL 👨‍💻

@HOTHEAD01THArchived 12 days agoOriginally posted 2026.10.18

V4.1-Flash-1017 beats GPT 5.6 Sol on Terminal-Bench at ~17x lower cost

𝕏AID ADIL 👨‍💻 @HOTHEAD01THOriginally posted 2026.10.18

Open original on X

DeepSeek V4.1-Flash-1017 has released, beating GPT 5.6 Sol on Terminal-Bench while being ~17x cheaper. It improves the previous DeepSeek V4.1-Flash result by 35%, accomplished with "no algorithmic innovation" but instead by RL training it on multiple coding agent harnesses.

x.com/hothead01th/status/2111723966918271237Archived 2026.10.18 16:33