Skip to content
AI HOT (Curated Pool)

Qwen3.7-Max Becomes the World’s No. 2 AI Coding Model

Qwen3.7-Max 成为全球第二AI编程模型

Qwen3.7-Max scored 1541 on Code Arena and ranked behind Claude; the post says it can run 35-hour tasks and perform more than 1,000 tool calls.

Why it matters: Qwen3.7-Max scores 1541 on the Code Arena coding benchmark for second place worldwide behind Claude, with the company also claiming 35 hours of continuous operation and over 1,000 tool calls in a single run.

Read the original ↗Export Markdown