MMBU - Grounded Classification (Masks, Open-Ended): leaderboard
Open-ended grounded classification on MMBU (2026), a biomedical image perception benchmark: the model names the finding in a region marked by a segmentation mask, judged by Qwen3-32B, scored as micro-averaged F1 times 100. Higher is better.
Metric: Open-ended classification of a region marked by a segmentation mask: micro-averaged F1 x100 (0-100) over MMBU's biomedical images from 35 submodalities (95% bootstrap intervals not published); zero-shot, official checkpoints; Qwen3-32B judges strict biomedical equivalence. Source: arxiv.org. Saturation forecast: Around February 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 VL 32B Instruct | 18.2 | #585 |
| 2 | GPT-5.4 Mini | 12.6 | #389 |
| 3 | Qwen 2.5 VL 32B Instruct | 11.5 | #1053 |
| 4 | Qwen 3 VL 8B Instruct | 7.4 | #981 |
| 5 | GPT-4.1 Mini | 6.5 | #779 |
| 6 | Qwen 3 VL 4B Instruct | 6.5 | #1279 |
| 7 | MedGemma-4B-IT | 4.2 | #2716 |
| 8 | Qwen 2.5 VL 7B Instruct | 3 | #1833 |
| 9 | Gemma 3 4B (IT) | 0.9 | #3831 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=mmbu-grounded-classification-masks-open-ended · How It Works · Data refreshed daily, snapshot 2026-11-13.