News for hackers. Stuff that matters.

SilasYee

Qwen3-Max-Thinking Drops: 36T Tokens

Alibaba has officially launched Qwen3-Max-Thinking, a trillion-parameter MoE flagship LLM pretrained on 36T tokens—double the corpus of Qwen 2.5—and it’s already matching or outperforming top-tier models like GPT-5.2-Thinking, Claude-Opus-4.5, and Gemini 3 Pro across 19 authoritative benchmarks. Its two core technical breakthroughs are what truly set it apart.First, Adaptive Tool Calling: No...

( Read More... | 2 comments | 2 points | on HN )