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

Content Moderation on MMDS (test)

95.76Accuracy

LLaVAShield-7B

Updated 1mo ago

Evaluation Results

Method	Links
LLaVAShield-7B 2025.09		95.76	91.76	100	95.71
LLaVAShield-7B 2025.09		94.24	87.6	97.41	92.24
GPT-5-mini 2025.09		85.76	64.34	98.81	77.93
Gemini-2.5-Pro 2025.09		80	48.84	100	65.62
GPT-5-mini 2025.09		79.7	60.59	100	75.46
GPT-4o 2025.09		76.67	41.09	98.15	57.92
Qwen3-VL-30B-A3B-Instruct 2025.09		75.76	40.31	94.55	56.52
Gemini-2.5-Pro 2025.09		72.73	47.06	100	64
GPT-4o 2025.09		71.21	44.71	98.7	61.54
InternVL3.5-38B 2025.09		69.7	22.48	100	36.71
OpenAI Moderation 2025.09		67.58	23.26	78.95	35.93
Qwen2.5-VL-72B-Instruct 2025.09		67.27	16.28	100	28
Llama Guard-4-12B 2025.09		66.06	17.05	81.48	28.21
Ovis2-34B 2025.09		63.64	7.75	90.91	16.46
InternVL3-78B 2025.09		63.03	5.43	100	10.29
InternVL3-8B 2025.09		62.12	3.88	83.33	7.41
Qwen2.5-VL-7B-Instruct 2025.09		61.21	0.78	100	1.54
LLaVA-OV-7B 2025.09		60.91	0	0	0
InternVL3-78B 2025.09		60.03	22.94	100	37.32
Qwen2.5-VL-72B-Instruct 2025.09		58.79	20	100	33.33
InternVL3.5-38B 2025.09		57.27	17.06	100	29.15
Qwen3-VL-30B-A3B-Instruct 2025.09		54.55	11.76	100	21.05
Ovis2-34B 2025.09		53.33	10	94.44	18.09
Llama Guard-4-12B 2025.09		52.42	7.65	100	14.21
LLaVA-OV-7B 2025.09		48.79	0.59	100	1.17
Qwen2.5-VL-7B-Instruct 2025.09		48.79	0.59	100	1.17
InternVL3-8B 2025.09		48.48	0	0	0