List your company

Hallucination detection on Arithematics (test)

49.6ANLLGemma2
48.73254.59160.4566.309Dec 4, 2025

Evaluation results

MethodLinks
Gemma2Model=Gemma22025.1249.649.656.483.484.784.183.2—82.684.785.186.3
Falcon3Model=Falcon32025.127076.77783.389.989.785.485.783.683.385.386.6
Llama3.2Model=Llama3.22025.1271.271.267.787.987.887.988.858.487.687.287.989
Llama3.1Model=Llama3.12025.1271.371.356.884.787.587.986.364.483.685.488.788.4