List your company

Hallucination Detection on CT

94.33HDRUniHD
47.103659.364371.62583.8857Jun 26, 2026

Evaluation results

MethodLinks
UniHDParam.=-, Backbone=MedGemma2026.0694.3356.84
UniHDParam.=-, Backbone=Grok-42026.0687.8652.56
UniHDParam.=-, Backbone=GPT-5.12026.0682.0158.16
UniHDParam.=-, Backbone=Gemini-32026.0678.8758.95
GPT-5.1-basedParam.=-, Backbone=Gemini-32026.0671.1364.71
GPT-5.1-basedParam.=-, Backbone=GPT-5.12026.0671.0763.43
GPT-5.1-basedParam.=-, Backbone=MedGemma2026.0667.8461.57
CounterVHDParam.=2B, Backbone=MedGemma2026.0663.1264.03
CounterVHDParam.=2B, Backbone=Gemini-32026.0662.6860.14
CounterVHDParam.=2B, Backbone=GPT-5.12026.0661.1568
CounterVHDParam.=2B, Backbone=Grok-42026.066059.57
FaithscoreParam.=13B, Backbone=MedGemma2026.0658.1661.19
GPT-5.1-basedParam.=-, Backbone=Grok-42026.0656.7453.49
FaithscoreParam.=13B, Backbone=Grok-42026.065565.81
FaithscoreParam.=13B, Backbone=Gemini-32026.0652.1164.35
FaithscoreParam.=13B, Backbone=GPT-5.12026.0648.9264.76