MUG-U-7B: benchmark results
Provider: Other. Released 2025-02-06.
Aggregate Rating 1523 ± 19, rank #2027 of 10916 rated models, from 527 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMBench V1.1 CN - Social Relation | 93.4 | Accuracy (%) | 99.6 |
| OpenVLM SEEDBench IMG - Visual Reasoning | 84 | Accuracy (%) | 99.6 |
| OpenVLM MMT-Bench - Human Keypoint Detection | 100 | Score (%) | 99.3 |
| OpenVLM AI2D - Food Chains and Webs | 98.8 | Accuracy (%) | 99.1 |
| OpenVLM OCR-VQA | 80.9 | Accuracy (%) | 99.1 |
| OpenVLM MMBench V1.1 CN - Image Emotion | 87.8 | Accuracy (%) | 98.6 |
| OpenVLM MMT-Bench - Raven Progressive Matrices | 65 | Score (%) | 98.3 |
| OpenVLM ChartQA Test - Augmented | 94.8 | Relaxed Accuracy (%) | 98.1 |
| OpenVLM MMT-Bench - DocVQA | 90 | Score (%) | 98.1 |
| OpenVLM MMT-Bench - Sketch-to-Image Retrieval | 95 | Score (%) | 98.1 |
| OpenVLM A-Bench - Attribute Awareness | 96.4 | Accuracy (%) | 97.8 |
| OpenVLM MMT-Bench - Handwritten Mathematical Expression Recognition | 100 | Score (%) | 97.8 |
Interactive version: theaggregate.ai/model?slug=mug-u-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.