Claude Opus 5.5 | Humanity's Last Exam Full set — With tools
Anthropic's Claude Opus 5.5 evaluation results on Humanity's Last Exam Full set — With tools
Score: 67.7%
Reasoning level: adaptive thinking, max; with tools
Anthropic's Claude Opus 5.5 evaluation results on Humanity's Last Exam Full set — With tools
Score: 67.7%
Reasoning level: adaptive thinking, max; with tools