MMR-AD - VisA Localization: leaderboard
Zero-shot industrial anomaly localization on the VisA images of MMR-AD (2026): given a normal reference and a test image, the model draws a box around the anomaly, counted correct at an IoU of at least 0.1 with an annotated region. Accuracy in percent, averaged over product classes; higher is better.
Metric: Anomaly localization accuracy (%) on VisA test images (from MMR-AD): a predicted anomaly box counts as correct at IoU of at least 0.1 with an annotated anomalous region, zero-shot, the model sees a spatially aligned normal reference image and the test image with the MMR-AD instruction template; dataset-level average over the subdataset's product classes; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 13 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 18.5 | #178 |
| 2 | O4 Mini | 12.3 | #368 |
| 3 | Qwen 2.5 VL 72B | 11.1 | #781 |
| 4 | Gemini 2.5 Pro | 10.5 | #276 |
| 5 | Llama 4 Maverick | 6.7 | #1110 |
| 6 | QVQ-Max | 4.8 | #949 |
| 7 | GPT-4o | 3.7 | #751 |
| 8 | InternVL3-8B | 2.9 | #1782 |
| 9 | InternVL3-38B | 2.2 | #939 |
| 10 | Qwen 2.5 VL 7B | 2.2 | #1862 |
| 11 | InternVL3.5-8B | 2.2 | #1604 |
| 12 | InternVL3.5-38B | 1.8 | #1021 |
| 13 | Gemma 3 27B | 0.5 | #1663 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mmr-ad-visa-localization · How It Works · Data refreshed daily, snapshot 2026-11-21.