DeepSeek ships open-weight V4.1-Flash-1017, Terminal-Bench jumps 31.2 to 42.3
petrusenko_max · x · 2026-10-23
DeepSeek quietly shipped V4.1-Flash-1017, positioned as a minor update to v4.1-flash, with open weights under the MIT license on Hugging Face (51K+ downloads, 2.3K+ likes).
Gains over the previous flash are large: Terminal-Bench 4.0 up from 31.2 to 42.3, ProgramBench from 20.3 to 29.1, HLE from 36.8 to 42.6. On DeepSeek's own table it beats GPT-5.6 Sol on DeepSWE (77.0 vs 73.0) and Terminal-Bench (42.3 vs 39.9), though Opus 5 still leads most rows (51.8 on Terminal-Bench). Third-party providers (together, novita, baseten) already serve it at $1.2 output pricing, with together fastest at 258 tokens/s.
Related event: DeepSeek Open-Sources V4.1-Flash-1017 with Big Terminal-Bench Gains(2 posts)→
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23