MMR-AD - MPDD Localization: leaderboard

Zero-shot industrial anomaly localization on the MPDD 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 MPDD 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

#ModelScoreOverall rank
1Qwen 2.5 VL 72B24.7#782
2O4 Mini23.9#372
3GPT-521.2#185
4QVQ-Max18#955
5Gemini 2.5 Pro16.3#280
6GPT-4o13.6#754
7Llama 4 Maverick10#1113
8Qwen 2.5 VL 7B7.2#1878
9InternVL3-38B5.4#948
10InternVL3.5-38B5.1#1026
11InternVL3.5-8B4.1#1618
12InternVL3-8B3.9#1795
13Gemma 3 27B3.5#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-mpdd-localization · How It Works · Data refreshed daily, snapshot 2026-11-22.