As of: 2026-10-18 07:35 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/p/x-suchenzang-2111383170725921142/

# “it took deepseek one month to move the cost/performance pareto on this benchmark (and…”

Susan Zhang (@suchenzang), X, 2026-10-17.
Source: https://x.com/suchenzang/status/2111383170725921142

## Archived text

> it took deepseek one month to move the cost/performance pareto on this benchmark
> 
> (and 5 months to move from v4 to v4.1)
> 
> zero chance of pacing, what a travesty !
> 
> > Quoting @deepseek_ai: 🚀 DeepSeek-V4.1-Flash-1017 is here!
> > 
> > Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
> > 
> > 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
> > 
> > 1/4

Archived 2026-10-18 via fxtwitter (unofficial).
Counts: 111,624 views, 1,508 likes, 52 reposts, 33 replies (at fetch time)
Media: https://pbs.twimg.com/media/HU0jzGIX0AAHIPN.jpg?name=orig

## Cited in

- 2026-10-17: [DeepSeek-V4.1-Flash-1017 update: big agentic-coding gains, same price](https://postcutoff.com/e/2026-10-17-deepseek-v4-1-flash-1017/)