WHAT NEW IN X10.29 THU

AI collections from X · 22 collections · 58,925 posts

deepseek-v4.1POST

DeepSeek V4.1 Flash 1017 scores: Terminal-Bench 42.3, DeepSWE 77.0

Official figures show Terminal-Bench 4.0 at 42.3 vs 31.2 and DeepSWE v1.1 at 77.0, beating Opus 5's 74.0; the API now serves deepseek-flash.

Hekate
@iCleanAIArchived 10 days agoOriginally posted 2026.10.17
Hekate @iCleanAIOriginally posted 2026.10.17
Open original on X

42.3 vs 31.2 on Terminal-Bench 4.0: DeepSeek released V4.1-Flash-1017, an open-weight update to its Flash model. DeepSWE v1.1: 77.0 vs Claude Opus 5's 74.0, per DeepSeek. It now serves deepseek-flash in the API. #DeepSeek #LLM https://x.com/deepseek_ai/status/2111375640717033777

This post quotes another post: x.com/deepseek_ai/status/2111375640717033777

x.com/icleanai/status/2111382209399849164Archived 2026.10.18 16:23