List your company

Reasoning on Humanity's Last Exam (HLE) (test)

72.19AccuracyHEART
9.592425.843742.09558.3463Sep 26, 2025

Evaluation results

MethodLinks
HEARTModel=Gemini 3 Pro, Prompt Strategy=HEART, Setting=Human-in-the-Loop Proxy2025.0972.19
Self ReflectionModel=Gemini 3 Pro, Prompt Strategy=Self Reflection, Setting=Human-in-the-Loop Proxy2025.0968.58
CoTModel=Gemini 3 Pro, Prompt Strategy=CoT, Setting=Human-in-the-Loop Proxy2025.0968.14
WaitModel=Gemini 3 Pro, Prompt Strategy=Wait, Setting=Human-in-the-Loop Proxy2025.0966.3
HEARTModel=Gemini 3 Flash, Prompt Strategy=HEART, Setting=Human-in-the-Loop Proxy2025.0958.89
WaitModel=Gemini 3 Flash, Prompt Strategy=Wait, Setting=Human-in-the-Loop Proxy2025.0949.37
Self ReflectionModel=Gemini 3 Flash, Prompt Strategy=Self Reflection, Setting=Human-in-the-Loop Proxy2025.0948.36
CoTModel=Gemini 3 Flash, Prompt Strategy=CoT, Setting=Human-in-the-Loop Proxy2025.0946.83
VanillaModel=Gemini 3 Pro, Prompt Strategy=Vanilla, Setting=Human-in-the-Loop Proxy2025.0940.8
VanillaModel=Gemini 3 Flash, Prompt Strategy=Vanilla, Setting=Human-in-the-Loop Proxy2025.0912