Qwen-VL-Plus: benchmark results
Provider: Alibaba. Released 2023-12-01. Access: API.
Aggregate Rating 1402 ± 26, rank #5983 of 10916 rated models, from 225 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OpenVLM MME - Landmark | 188.8 | Score | 99.1 |
| OpenVLM MME - Celebrity | 179.1 | Score | 98.3 |
| OpenVLM COCO Captions | 64.2 | CIDEr | 93.8 |
| OpenVLM MMMU - Art | 80 | Accuracy (%) | 92.8 |
| OpenVLM MME - Count | 175 | Score | 91.5 |
| CMMMU | 36.8 | Test Overall (%) | 90.6 |
| OpenVLM MME - Perception | 1692.3 | Score | 87.6 |
| CMMMU (Validation) | 39.5 | Validation Overall (%) | 87.5 |
| OpenVLM CCBench - Scenery and Buildings | 80 | Accuracy (%) | 86.8 |
| OpenVLM MMBench V1.1 CN - Action Recognition | 90.6 | Accuracy (%) | 86.2 |
| OpenVLM AI2D - Atom Structure | 87.5 | Accuracy (%) | 85.2 |
| OpenVLM MMBench V1.1 CN - Celebrity Recognition | 86.4 | Accuracy (%) | 82.2 |
Interactive version: theaggregate.ai/model?slug=qwen-vl-plus · How It Works · Data refreshed daily, snapshot 2026-11-08.