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)→
More from Models
- Qwen Releases 2.4T-Parameter Open-Weight MoE Model Qwen3.8 — rohanpaul_ai · 2026-08-13
- xAI Ships Grok 4.6: Bets on Post-Training Over Scale-Up, Halves Pricing — eyishazyer · 2026-08-13
- Testing Muse Glimmer 30B: Falls Short in Coding/Writing, Vision May Be Its Strength — Kahvana · 2026-08-13
- Grok 4.6 Costs 5.4x Less Than Claude Opus 5 on Three.js Benchmark, Shattering AI Economics — SucceededMind · 2026-08-13
- Grok 4.6 Tested: Runs Autonomously for Long Periods Without Goals — XFreeze · 2026-08-13
- Shopify CEO Tobi Reports Grok-4.6 Freaking Out Over His Low GitHub ID — johnmccrea · 2026-08-13