← 返回归档

帖子详情

查看 X 原文
L
lmarena.ai@lmarena_ai
Exciting news: DeepSeek-V4.1-Flash-20261017 (Max) by @deepseek_ai is now the #1 open model in Code Arena: WebDev, surpassing Kimi K3 (Max) at 10x lower cost! Highlights: - #1 open model, ahead of Kimi K3 (Max) - #12 overall with 1670 pts, ahead of Claude Opus 5 (High) and within ~10 pts of GPT-6 Sol (Max) - Shifts the Pareto frontier at $0.3/$1.2 per million input/output tokens - +52 pts vs. the previous DeepSeek-V4.1-Flash-20260910 Congrats to the @deepseek_ai team on another strong contribution to the open source ecosystem! DeepSeek @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 🔗 View Quoted Tweet
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：[Errno 104] Connection reset by peer
帖子 ID
2111894091168682086
Markdown
/app/data/archive/2026/10/18/lmarena_ai/2111894091168682086/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111894091168682086"
author: "lmarena_ai"
published_at: "2026-10-18T18:56:03+00:00"
source_url: "https://x.com/arena/status/2111894091168682086"
---

Exciting news: DeepSeek-V4.1-Flash-20261017 (Max) by [@deepseek\_ai](https://x.com/deepseek_ai) is now the #1 open model in Code Arena: WebDev, surpassing Kimi K3 (Max) at 10x lower cost!  
  
Highlights:  
- #1 open model, ahead of Kimi K3 (Max)  
- #12 overall with 1670 pts, ahead of Claude Opus 5 (High) and within ~10 pts of GPT-6 Sol (Max)  
- Shifts the Pareto frontier at $0.3/$1.2 per million input/output tokens  
- +52 pts vs. the previous DeepSeek-V4.1-Flash-20260910  
  
Congrats to the [@deepseek\_ai](https://x.com/deepseek_ai) team on another strong contribution to the open source ecosystem!

![Tweet Image](https://pbs.twimg.com/media/HU7z9aubIAAen5a.jpg)![Tweet Image](https://pbs.twimg.com/media/HU7z9_FbUAA4j2r.jpg)

![DeepSeek](https://pbs.twimg.com/profile_images/1717417613775757312/Uk1zNOj4_normal.jpg)

DeepSeek@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](https://x.com/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

![Tweet Image](https://pbs.twimg.com/media/HU0b65KbsAAypqr.jpg)![Tweet Image](https://pbs.twimg.com/media/HU0b7UfbwAAGXNH.jpg)

[🔗 View Quoted Tweet](https://x.com/deepseek_ai/status/2111375640717033777)