Monkey: benchmark results
Provider: HUST. Released 2024-01-05. Access: Open.
Aggregate Rating 1274 ± 41, rank #9024 of 10916 rated models, from 438 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Whoops | 100 | Score (%) | 99.3 |
| OpenVLM MMT-Bench - Gaze Estimation | 35 | Score (%) | 93 |
| OpenVLM COCO Captions | 62.8 | CIDEr | 92.9 |
| OpenVLM OCR-VQA | 67 | Accuracy (%) | 91 |
| OpenVLM MMT-Bench - Micro Expression Recognition | 40 | Score (%) | 89.8 |
| OpenVLM MMT-Bench - Social Relation Recognition | 65 | Score (%) | 87.1 |
| OpenVLM MMT-Bench - Gesture Recognition | 70 | Score (%) | 86.9 |
| OpenVLM MMT-Bench - Color Assimilation | 70 | Score (%) | 85 |
| OpenVLM MMT-Bench - Action Quality Assessment | 30 | Score (%) | 84.7 |
| OpenVLM MMT-Bench - Waste Recognition | 100 | Score (%) | 84.5 |
| OpenVLM MMT-Bench - Deepfake Detection | 60 | Score (%) | 83 |
| OpenVLM MMT-Bench - Other Biological Attributes | 80 | Score (%) | 83 |
Interactive version: theaggregate.ai/model?slug=monkey · How It Works · Data refreshed daily, snapshot 2026-11-08.