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

Zero-shot industrial anomaly detection on the MVTec 3D-AD images of MMR-AD (2026): given a spatially aligned normal reference image and a test image, the model judges whether the test image shows an anomaly. Accuracy in percent, averaged over product classes; higher is better.

Metric: Anomaly detection accuracy (%): share of MVTec 3D-AD test images (from MMR-AD) correctly judged normal or anomalous, 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. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1InternVL3-38B75.9#939
2Gemini 2.5 Pro75.7#276
3InternVL3-8B75.5#1782
4GPT-575#178
5InternVL3.5-38B74.4#1021
6O4 Mini74.1#368
7Qwen 2.5 VL 72B71.6#781
8GPT-4o67.8#751
9Llama 4 Maverick67.1#1110
10InternVL3.5-8B65.8#1604
11Qwen 2.5 VL 7B59.9#1862

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-3d-ad-detection · How It Works · Data refreshed daily, snapshot 2026-11-21.