Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Hallucination Evaluation on MMHE

66.6REG

HarmonicEval

41.53648.04354.5561.057Dec 19, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.12
66.676.473.47773.4
2024.12
62.976.460.973.968.5
2024.12
60.139.760.95253.2
2024.12
60.17571.968.768.9
2024.12
60.17576.57671.9
2024.12
56.420.560.957.848.9
2024.12
4930.85647.945.9
2024.12
46.233.862.153.148.8
2024.12
45.329.457.346.844.7
2024.12
44.429.459.753.646.8
2024.12
42.52562.142.743.1