Industrial Anomaly Detection on SDD (Balanced Accuracy)
88.9Balanced AccuracyIndusAgent
Evaluation Results
| Method | Links | |
|---|---|---|
| IndusAgentType=Open Source, Param.=8B, Evaluation Protocol=Zero-shot2026.05 | 88.9 | |
| Anomaly-OVType=Open Source, Param.=7B, Evaluation Protocol=Zero-shot2026.05 | 88.7 | |
| Claude-Sonnet-4Type=Commercial, Param.=/, Evaluation Protocol=Zero-shot2026.05 | 81.7 | |
| GPT-4.1Type=Commercial, Param.=/, Evaluation Protocol=Zero-shot2026.05 | 79.9 | |
| GPT-4.1-miniType=Commercial, Param.=/, Evaluation Protocol=Zero-shot2026.05 | 72.1 | |
| Qwen2.5-VL-InstructType=Open Source, Param.=72B, Evaluation Protocol=Zero-shot2026.05 | 69 | |
| Qwen2.5-VL-InstructType=Open Source, Param.=7B, Evaluation Protocol=Zero-shot2026.05 | 67.4 | |
| GPT-4o-miniType=Commercial, Param.=/, Evaluation Protocol=Zero-shot2026.05 | 66.6 | |
| GPT-4oType=Commercial, Param.=/, Evaluation Protocol=Zero-shot2026.05 | 65.7 | |
| InternVL-2.5Type=Open Source, Param.=4B, Evaluation Protocol=Zero-shot2026.05 | 64.1 | |
| AnomalyR1Type=Open Source, Param.=3B, Evaluation Protocol=Zero-shot2026.05 | 57.6 | |
| Qwen2.5-VL-InstructType=Open Source, Param.=3B, Evaluation Protocol=Zero-shot2026.05 | 50.3 | |
| GPT-4.1-nanoType=Commercial, Param.=/, Evaluation Protocol=Zero-shot2026.05 | 50 | |
| LLaVA-OneVision-SIType=Open Source, Param.=0.5B, Evaluation Protocol=Zero-shot2026.05 | 50 | |
| Anomaly-OVType=Open Source, Param.=0.5B, Evaluation Protocol=Zero-shot2026.05 | 50 | |
| Qwen3-VL-InstructType=Open Source, Param.=8B, Evaluation Protocol=Zero-shot2026.05 | 50 | |
| LLaVA-1.5Type=Open Source, Param.=13B, Evaluation Protocol=Zero-shot2026.05 | 50 | |
| LLaVA-1.6Type=Open Source, Param.=34B, Evaluation Protocol=Zero-shot2026.05 | 50 | |
| AnomalyGPTType=Open Source, Param.=7B, Evaluation Protocol=Zero-shot2026.05 | 49.5 |