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

Video Hallucination Evaluation on ModeVent (Overall)

4.6Fidelity

SelfCheckGPT

Updated 1mo ago

Evaluation Results

Method	Links
SelfCheckGPT 2026.06		4.6	1.28	5.89
MODE-RAG 2026.06		3.76	2.4	6.16
MODE-RAG 2026.06		3.67	3.16	6.83
MODE-RAG 2026.06		3.67	2.57	6.24
SelfCheckGPT 2026.06		3.61	2.26	5.86
Self-RAG 2026.06		3.55	2.48	6.03
Self-RAG 2026.06		3.53	2.83	6.35
MODE-RAG 2026.06		3.34	1.88	5.22
Self-RAG 2026.06		3.28	2.34	5.63
Self-RAG 2026.06		3.26	2.39	5.65
MODE-RAG 2026.06		3.23	2.22	5.45
Woodpecker 2026.06		3.13	2.52	5.64
MODE-RAG 2026.06		3.11	2.34	5.45
Self-RAG 2026.06		3.11	2.11	5.21
Woodpecker 2026.06		3.07	2.58	5.65
Self-RAG 2026.06		2.91	1.91	4.82
Woodpecker 2026.06		2.84	2.44	5.27
Self-RAG 2026.06		2.81	1.27	4.08
Woodpecker 2026.06		2.8	2.44	5.24
Baseline 2026.06		2.8	2.47	5.27
Baseline 2026.06		2.73	2.37	5.1
MODE-RAG 2026.06		2.71	1.81	4.52
Woodpecker 2026.06		2.71	2.22	4.93
Baseline 2026.06		2.62	2.79	5.41
Baseline 2026.06		2.59	2.21	4.8
Woodpecker 2026.06		2.55	2.18	4.73
Self-RAG 2026.06		2.44	1.56	4.01
Woodpecker 2026.06		2.44	1.67	4.12
MODE-RAG 2026.06		2.39	1.44	3.82
Baseline 2026.06		2.34	2.06	4.4
Woodpecker 2026.06		2.2	1.72	3.93
Baseline 2026.06		2.2	1.72	3.93
SelfCheckGPT 2026.06		2.1	0.82	2.92
Baseline 2026.06		1.84	1.86	3.7
SelfCheckGPT 2026.06		1.75	0.32	2.06
Baseline 2026.06		1.66	1.08	2.74
SelfCheckGPT 2026.06		1.41	1.09	2.5
SelfCheckGPT 2026.06		1.19	0.28	1.47
SelfCheckGPT 2026.06		1.04	0.05	1.08
SelfCheckGPT 2026.06		1.03	0.42	1.46