MMVIAD - Unseen Categories: leaderboard
Metric: Mean of three accuracies and visible-time mIoU (%; MMVIAD-Unseen test split, 1,062 clips of 12 object categories held out from training, 4,248 questions). Source: arxiv.org. Saturation forecast: Around December 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 63.9 |
| 2 | GPT-5.4 | 53.5 |
| 3 | GPT-5.4 Mini | 53.5 |
| 4 | Qwen 3 VL 8B | 45 |
Interactive version: theaggregate.ai/benchmark?slug=mmviad-unseen-categories · How It Works · Data refreshed daily, snapshot 2026-09-26.