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

Harmful Meme Detection on Ex-ToxiCN-MM (test)

96.7Accuracy

InternVL3_5-8B

Updated 8d ago

Evaluation Results

Method	Links
InternVL3_5-8B 2026.05		96.7	96.9	96.8	96.9	-
InternVL3_5-8B 2026.05		96.6	97.4	96.1	96.8	-
Qwen2.5-VL-7B 2026.05		95.7	94.9	97.1	96	-
Qwen2.5-VL-7B 2026.05		95.6	96.2	95.5	95.8	-
Qwen2.5-VL-3B 2026.05		94.8	94	96.4	95.2	-
Qwen2.5-VL-3B 2026.05		94.3	93.7	95.6	94.6	-
LLaVa-1.5-7b 2026.05		91.5	96.9	86.8	91.5	-
LLaVa-1.5-7b 2026.05		89.7	96.9	83.3	89.6	-
Qwen2.5-VL-7B 2026.05		86.9	95.3	79.3	86.6	-
InternVL3_5-8B 2026.05		86.6	96.4	77.6	86	-
Qwen2.5-VL-3B 2026.05		82.6	94.5	71.4	81.3	-
Qwen-VL-max 2026.05		75.7	78.4	74.6	76.5	-
Qwen-VL-max 2026.05		73.1	78	68.6	73	-
LLaVa-1.5-7b 2026.05		72.3	98.6	48.5	65	-
Qwen-VL-max 2026.05		71.9	87.5	54.6	67.3	-
GLM-4v-flash 2026.05		70.5	72.7	67.4	-	70
Qwen2.5-VL-7B 2026.05		70.2	83.4	54.6	66	-
InternVL3_5-8B 2026.05		67.4	84	47.7	60.8	-
GLM-4v-flash 2026.05		64.9	74.7	47	-	57.7
Qwen2.5-VL-7B 2026.05		64.3	80.5	43.1	56.2	-
Qwen2.5-VL-3B 2026.05		61.9	59.5	87.8	71	-
InternVL3_5-8B 2026.05		61.4	81	35.5	49.4	-
GLM-4v-flash 2026.05		60.8	84.3	28.3	-	42.3
InternVL3_5-8B 2026.05		59.6	83.7	29.6	43.7	-
LLaVa-1.5-7b 2026.05		59.2	60.7	65.5	63	-
Qwen2.5-VL-7B 2026.05		58.3	91.2	23.6	37.5	-
Qwen2.5-VL-3B 2026.05		56.9	67.3	36.4	47.2	-
Qwen2.5-VL-3B 2026.05		56.6	56.7	77.2	65.4	-
LLaVa-1.5-7b 2026.05		55.7	58.3	58	58.1	-
LLaVa-1.5-7b 2026.05		50.9	57.2	29.2	38.7	-