Hallucination Diagnosis on HallusionBench

96LI Score

SmolVLM 500M

Updated 20d ago

Evaluation Results

Method
SmolVLM 500M 2026.05	96	365	278	33.85	-
SmolVLM 500M (Self-Captioning MIT) 2026.05	96	254	342	38.23	-
SmolVLM 500M (Self-Captioning MIT) 2026.05	94	352	281	33.42	-
LLaVa-OneVision 4B (Self-Captioning MIT) 2026.05	92	185	361	43.94	-
LLaVa-OneVision 4B 2026.05	90	317	273	39.45	-
LLaVa-OneVision 8B (Self-Captioning MIT) 2026.05	89	159	351	46.09	-
LLaVa-OneVision 8B 2026.05	86	218	308	45.59	-
LLaVa-OneVision 4B (Self-Captioning MIT) 2026.05	82	200	349	43.99	-
LLaVa-OneVision 8B (Self-Captioning MIT) 2026.05	82	270	252	45.39	-
SmolVLM 256M (Self-Captioning MIT) 2026.05	74	371	278	30.94	-
SmolVLM 2B (Self-Captioning MIT) 2026.05	73	210	355	41.1	-
SmolVLM 2B (Self-Captioning MIT) 2026.05	71	156	404	42.88	-
SmolVLM 256M (Self-Captioning MIT) 2026.05	64	381	281	29.43	-
SmolVLM 2B 2026.05	64	349	275	34.91	-
SmolVLM 256M 2026.05	55	524	175	26.97	-
Visionary-R1 2026.05	-	-	-	-	30
Perception-R1 2026.05	-	-	-	-	65.4
Vision-R1 2026.05	-	-	-	-	32.2
Zero-shot Inference 2026.05	-	-	-	-	45.5
GRPO 2026.05	-	-	-	-	62.6
DAPO 2026.05	-	-	-	-	62.7
PACR 2026.05	-	-	-	-	61.5
PDCR 2026.05	-	-	-	-	61.8
Zero-shot Inference 2026.05	-	-	-	-	52.2
GRPO 2026.05	-	-	-	-	66.6
DAPO 2026.05	-	-	-	-	67
PACR 2026.05	-	-	-	-	67.6
PDCR 2026.05	-	-	-	-	68.4