MMR-AD - MVTec 3D-AD Localization: leaderboard

Zero-shot industrial anomaly localization on the MVTec 3D-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 3D-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-527.2#185
2O4 Mini15.7#372
3Qwen 2.5 VL 72B13.3#782
4QVQ-Max11.2#955
5Gemini 2.5 Pro10.9#280
6GPT-4o7#754
7Llama 4 Maverick6.1#1113
8InternVL3-38B2.1#948
9InternVL3.5-38B1.4#1026
10Qwen 2.5 VL 7B1.2#1878
11InternVL3.5-8B1.1#1618
12InternVL3-8B1#1795
13Gemma 3 27B0.7#1672

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mmr-ad-mvtec-3d-ad-localization · How It Works · Data refreshed daily, snapshot 2026-11-22.