ainewsblitz.com

Breaking

DeepSeek-V4-Pro (Max) lands near No. 8 on Arena Code WebDev at 1607 AutoEval points

DeepSeek-V4-Pro (Max) lands near No. 8 on Arena Code WebDev at 1607 AutoEval points
  • Foundation Models
  • Software Dev & Coding
  • Open Source

DeepSeek-V4-Pro (Max) has posted an early Code Arena WebDev score of 1607, placing the MIT-licensed open-weights model around eighth overall and second among open models, just behind GPT-5.6 Sol (xHigh) at 1622 and well behind leader Kimi K3 (Max) at 1674. The listing appears as deepseek-v4-pro-max-20260813 and is tagged AutoEval rather than a fully voted human ranking.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,833 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year