Qwen-VL: benchmark results
Provider: Alibaba. Released 2023-08-25. Access: Open.
Aggregate Rating 1176 ± 45, rank #9738 of 10916 rated models, from 441 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MMT-Bench - Color Constancy | 100 | Score (%) | 100 |
| OpenVLM MMT-Bench - VI | 80.3 | Score (%) | 100 |
| OpenVLM MMT-Bench - Color Contrast | 85 | Score (%) | 98.8 |
| OpenVLM MMT-Bench - Color Assimilation | 80 | Score (%) | 98.1 |
| OpenVLM OCR-VQA | 67.5 | Accuracy (%) | 92.3 |
| OpenVLM COCO Captions | 41.1 | CIDEr | 89.5 |
| OpenVLM MMT-Bench - Geometrical Relativity | 70 | Score (%) | 87.9 |
| OpenVLM MMT-Bench - Action Quality Assessment | 30 | Score (%) | 84.7 |
| OpenVLM MMT-Bench - Deepfake Detection | 60 | Score (%) | 83 |
| OpenVLM MMT-Bench - One Shot Detection | 75 | Score (%) | 81.1 |
| OpenVLM MMT-Bench - Font Recognition | 30 | Score (%) | 78.6 |
| OpenVLM MMT-Bench - Google Apps | 40 | Score (%) | 74 |
Interactive version: theaggregate.ai/model?slug=qwen-vl · How It Works · Data refreshed daily, snapshot 2026-11-08.