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

Hallucination Detection on RAGTruth RT-Summ 1.0 (test)

0.6966F1 Score

SelfcheckGPT

0.4486640.5130320.57740.641768Feb 20, 2026
Updated 5mo ago

Evaluation Results

MethodLinks
2026.02
0.69660.7166
2026.02
0.68490.8075
2026.02
0.67610.8037
2026.02
0.67590.7954
2026.02
0.67230.7978
2026.02
0.66640.6596
2026.02
0.65510.7867
2026.02
0.63490.6674
2026.02
0.60590.608
2026.02
0.59290.7165
2026.02
0.59290.7362
2026.02
0.59240.6346
2026.02
0.58970.576
2026.02
0.58750.7426
2026.02
0.57790.704
2026.02
0.56790.6702
2026.02
0.56510.7042
2026.02
0.55540.5909
2026.02
0.55480.67
2026.02
0.55270.6865
2026.02
0.53790.568
2026.02
0.53280.7156
2026.02
0.51210.5097
2026.02
0.50650.4989
2026.02
0.50310.6722
2026.02
0.5010.5253
2026.02
0.49470.6629
2026.02
0.48860.6492
2026.02
0.4840.5836
2026.02
0.45820.4973