Claude Opus 4.5 | Humanity's Last Exam Full set — No tools
Anthropic's Claude Opus 4.5 evaluation results on Humanity's Last Exam Full set — No tools
Score: 30.8%
Reasoning level: extended thinking
Anthropic's Claude Opus 4.5 evaluation results on Humanity's Last Exam Full set — No tools
Score: 30.8%
Reasoning level: extended thinking