ModelsSep 2, 2026 · 12:484 sources

Alibaba Qwen3.8-Max-0902 Sets 1,691 Point Record to Lead Code Arena

From huggingnews.com

Image: huggingnews.com
AI;DR

Alibaba's Qwen3.8-Max-0902 model scored 1,691 points on the Code Arena: WebDev leaderboard, placing it above Claude Opus 5 (Max) and Kimi K3 (Max). The model employs 2.4 trillion parameters, supports 1 million context tokens, and is available via API on QwenCloud. Pricing is set at $2 per 1 million input tokens and $6 per 1 million output tokens.

Read the sourceSign in to suggest

Sources

+ 2 more
  1. SUPPORT@arena“scores 3 pts above Claude Opus 5 (Max), 17 pts above Kimi K3 (Max)”x.com
  2. SUPPORT@arena“three models at the top of the overall leaderboard have moved off the Pareto frontier”x.com
#alibaba#qwen#llm#coding#benchmarkMarkdown
Content history (1)
  • 2026-10-04 · Summary · vi · Wording fix
    Mô hình Qwen3.8-Max-0902 của Alibaba sở hữu 2,4 nghìn tỷ tham số và hỗ trợ context window…
    Mô hình Qwen3.8-Max-0902 của Alibaba sở hữu 2,4 nghìn tỷ tham số và hỗ trợ context window…

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today