Claude Sonnet 4.6 | Humanity's Last Exam Full set — With tools

Anthropic's Claude Sonnet 4.6 evaluation results on Humanity's Last Exam Full set — With tools

Score: 49.0%

Reasoning level: adaptive thinking, max

Source

Claude Sonnet 4.6 (Registry No. 20009)

Anthropic

Humanity's Last Exam Full set — With tools