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

Content Moderation and Data Security on in-house business benchmarks

87.34Overall Accuracy

Yuvion-32B (Agent)

Updated 26d ago

Evaluation Results

Method	Links
Yuvion-32B (Agent) 2026.06		87.34	96.34	83.44	73.51	85.98	97.45
Yuvion-32B 2026.06		86.34	97.21	83.28	74.32	85.83	91.04
Qwen3-Max 2026.06		83	83.09	77.38	78.75	78.64	97.12
Yuvion-8B 2026.06		82.72	95.94	82.43	69.39	83.28	82.57
GPT-5.4 2026.06		80.4	73.85	70.86	80.51	78.95	97.83
KIMI-K2.5 2026.06		79.84	84.91	77.83	69.92	84.98	81.56
Qwen3.6-Plus 2026.06		78.44	73.77	72.04	78.54	82.31	85.56
Qwen3.5-122B-A10B 2026.06		76.61	65.72	74.19	76.45	80.3	86.41
GLM-5 2026.06		73.96	47.28	64.35	77.32	84.42	96.42
Qwen3.5-27B 2026.06		73.92	66.83	71.13	63.39	79.62	88.65
Qwen3.5-Plus 2026.06		73.38	79.17	75.35	31.01	83.89	97.47
Qwen3.5-35B-A3B 2026.06		72.75	69.8	72.17	74.27	81.6	65.89
Qwen3.5-397B-A17B 2026.06		72.62	72.65	72.5	42.51	83.44	91.98
Qwen3.5-9B 2026.06		69.89	55.44	66.13	63.82	80.8	83.28
DeepSeek-V3.2 2026.06		69.88	55.43	62.37	75.01	75	81.6
DeepSeek-R1 2026.06		69.85	54.65	62.72	81.3	80.94	69.62
Qwen3-32B 2026.06		68.1	32.25	56.11	74.83	82.87	94.43
Qwen3-8B 2026.06		67.57	26.38	66.03	78.5	81.96	84.98
Minimax-M2.5 2026.06		56.32	60.84	66.16	47.45	50.27	56.86
Qwen3-30B-A3B-2507 2026.06		56.14	9.27	36.34	72.74	68.66	93.67
Qwen3Guard-8B 2026.06		0.01	0.03	0.03	0	0	0
Llama-Guard4-12B 2026.06		0	0	0.01	0	0	0