Model
Qwen2.5-VL-32B
Alibaba · open weights
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| 4MT-VLM | 75.0 | accuracy | N/A | Independent | medium | arxiv.org |
| DataVista | 54.8 | accuracy | N/A | Independent | medium | arxiv.org |
| ScenePercept-Bench | 0.5 | score | N/A | Independent | medium | arxiv.org |
| SpaceConflict | 54.2 | accuracy | N/A | Independent | medium | arxiv.org |
| ViSiP-Bench | 42.8 | par | N/A | Independent | medium | arxiv.org |
| Visual Sanad | 5.1 | discrimination | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…