MMR-AD - VisA Detection: leaderboard
Zero-shot industrial anomaly detection on the VisA 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 VisA 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: Not forecast. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3.5-38B | 74.1 | #1026 |
| 2 | O4 Mini | 73 | #372 |
| 3 | InternVL3-38B | 71.7 | #948 |
| 4 | InternVL3-8B | 71.5 | #1795 |
| 5 | Qwen 2.5 VL 72B | 70 | #782 |
| 6 | InternVL3.5-8B | 67.8 | #1618 |
| 7 | Qwen 2.5 VL 7B | 65.9 | #1878 |
| 8 | GPT-5 | 65.8 | #185 |
| 9 | Gemini 2.5 Pro | 65.7 | #280 |
| 10 | Llama 4 Maverick | 63.8 | #1113 |
| 11 | GPT-4o | 57.6 | #754 |
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-visa-detection · How It Works · Data refreshed daily, snapshot 2026-11-22.