DeepSeek-V4-Pro Ranks #2 Among Open Models in Code Arena

arena · x · 2026-08-13

According to early AutoEval scores from Chatbot Arena, DeepSeek-V4-Pro (Max) ranks around #8 overall and #2 among open models in the WebDev Code Arena.

Scoring 1607 points, it places just behind GPT-5.6 Sol (xHigh) (1622 pts) and Kimi K3 (Max) (1674 pts). These initial results are generated automatically by a Reward Model, and scores will converge as more live human votes are collected.

Related event: DeepSeek-V4-Pro Ranks Second Among Open-Source Models in Coding(3 posts)→

Original post →

More from Models

Models channel →