Qwen3-Max-Thinking | Humanity's Last Exam Full set — With tools

Alibaba (Tongyi)'s Qwen3-Max-Thinking evaluation results on Humanity's Last Exam Full set — With tools

Score: 49.8

Source

Qwen3-Max-Thinking (Registry No. 130002)

Alibaba (Tongyi)

Humanity's Last Exam Full set — With tools