List your company

Hallucination detection on SVAMP (test)

53.3ANLLGemma2
51.76462.13272.582.868Dec 4, 2025

Evaluation results

MethodLinks
Gemma2Model=Gemma22025.1253.347.569.175.383.283.884.9—82.882.983.785
Llama3.1Model=Llama3.12025.1257.957.968.984.386.787.892.464.490.490.290.691.4
Llama3.2Model=Llama3.22025.1262.162.157.780.38079.386.260.884.884.484.686.4
Falcon3Model=Falcon32025.1291.791.792.389.290.99394.466.693.49494.795.1