MMR-AD - MVTec AD Localization: leaderboard

Zero-shot industrial anomaly localization on the MVTec AD 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 MVTec AD 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 February 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-541.8#178
2Qwen 2.5 VL 72B36.4#781
3Gemini 2.5 Pro34.4#276
4O4 Mini34.4#368
5QVQ-Max26.6#949
6Llama 4 Maverick19.9#1110
7Qwen 2.5 VL 7B8.9#1862
8GPT-4o8.1#751
9InternVL3.5-38B7.1#1021
10InternVL3-38B6.3#939
11InternVL3-8B5.5#1782
12InternVL3.5-8B5.4#1604
13Gemma 3 27B4#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-mvtec-ad-localization · How It Works · Data refreshed daily, snapshot 2026-11-21.