MiniMonkey: benchmark results
Provider: HUST. Released 2024-10-24. Access: Open.
Aggregate Rating 1363 ± 32, rank #7365 of 10916 rated models, from 450 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Animal Keypoint Detection | 55 | Score (%) | 99 |
| OpenVLM MMT-Bench - Gaze Estimation | 40 | Score (%) | 99 |
| OpenVLM SEEDBench IMG - Text Understanding | 83.3 | Accuracy (%) | 98.9 |
| OpenVLM MMT-Bench - Traffic Light Understanding | 100 | Score (%) | 96.4 |
| OpenVLM CCBench - Cultural Relics | 86.6 | Accuracy (%) | 95.6 |
| OpenVLM CCBench - Food and Clothes | 78.3 | Accuracy (%) | 95.6 |
| OpenVLM CCBench - Sketch Reasoning | 93.3 | Accuracy (%) | 95.2 |
| OpenVLM MMT-Bench - Anatomy Identification | 80 | Score (%) | 95.1 |
| OpenVLM MMT-Bench - Pixel Recognition | 75 | Score (%) | 94.7 |
| CCBench | 77.3 | Accuracy (%) | 93.9 |
| OpenVLM MMT-Bench - Crowd Counting | 70 | Score (%) | 92.7 |
| OpenVLM CCBench - Calligraphy and Painting | 84.2 | Accuracy (%) | 91.9 |
Interactive version: theaggregate.ai/model?slug=minimonkey · How It Works · Data refreshed daily, snapshot 2026-11-08.