deepseek-v4.1POST

DeepSeek V4.1 Flash 1017 benchmarks: Terminal-Bench 4.0 rises to 42.3

Benchmarks show Terminal-Bench 4.0 up from 31.2 to 42.3, DeepSWE 74.2 to 77.0 and Automation-Bench 54.8 to 60.5, with shorter outputs, lower cost and MIT-licensed weights on Hugging Face.

Neo

@NeoAIForecastArchived 10 days agoOriginally posted 2026.10.17

Neo @NeoAIForecastOriginally posted 2026.10.17

Open original on X

DeepSeek is back baby!!! 🐋 Deepseek-V4.1-Flash-1017 Terminal-Bench 4.0: 31.2 > 42.3 DeepSWE v1.1: 74.2 > 77.0 Automation-Bench: 54.8 > 60.5 Shorter outputs. Faster tasks. Lower cost per task, per DeepSeek. MIT license. Weights on Hugging Face today. https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017

x.com/neoaiforecast/status/2111397629615886468Archived 2026.10.18 16:42