List your company

Hallucination Detection on SciQ (test)

59.9ANLLGemma2
59.7260.93562.1563.365Dec 4, 2025

Evaluation results

MethodLinks
Gemma2Model=Gemma22025.1259.959.368.25972.572.474—74.175.175.475.2
Falcon3Model=Falcon32025.126057.562.15770.269.469.162.473.272.973.474.2
Llama3.2Model=Llama3.22025.1264.264.254.565.172.57173.259.173.27575.175.3
Llama3.1Model=Llama3.12025.1264.464.457.663.775.273.876.556.47777.878.478.8