Content moderation on ProGuard (Score (%))
95.4Score (%)Yuvion VL
Evaluation Results
| Method | Links | |
|---|---|---|
| Yuvion VLModel Scale=32B, Decoding Mode=Reasoning2026.06 | 95.4 | |
| Yuvion VLModel Scale=8B, Decoding Mode=Reasoning2026.06 | 95.1 | |
| Yuvion VLModel Scale=8B, Decoding Mode=Instruct2026.06 | 94.3 | |
| Qwen3-VLModel Scale=32B, Decoding Mode=Instruct2026.06 | 84.7 | |
| GPT-5.4Model Scale=≈1.5T2026.06 | 83.3 | |
| Qwen3-VLModel Scale=8B, Decoding Mode=Instruct2026.06 | 82.8 | |
| Qwen3.5-PlusModel Scale=397B2026.06 | 80.8 | |
| Qwen3-VLModel Scale=32B, Decoding Mode=Thinking2026.06 | 80.6 | |
| Qwen3-VLModel Scale=8B, Decoding Mode=Thinking2026.06 | 80.1 | |
| K2.5Model Scale=≈1T2026.06 | 79.2 | |
| Yuvion VLModel Scale=32B, Decoding Mode=Instruct2026.06 | 67.5 | |
| Opus-4.6Model Scale=≈800B2026.06 | 64 |