Kimi K2.5 | Humanity's Last Exam Full set — No tools
Moonshot AI's Kimi K2.5 evaluation results on Humanity's Last Exam Full set — No tools
Score: 30.1
Reasoning level: thinking
Moonshot AI's Kimi K2.5 evaluation results on Humanity's Last Exam Full set — No tools
Score: 30.1
Reasoning level: thinking