Model
Qwen2-VL-7B
Alibaba · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Balrog | 3.7 | average_progress | N/A | Independent | medium | balrogai.com |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ImplicitQA | 44.9 | average_accuracy | N/A | Independent | medium | arxiv.org |
| MM-Vet | 62.0 | gpt-4_score | N/A | Independent | medium | arxiv.org |
| ScreenSpot | 42.1 | accuracy_(%) | N/A | Independent | medium | arxiv.org |
| TVBench | 43.8 | average_accuracy | N/A | Independent | medium | arxiv.org |
| Video-MME | 63.9 | overall_(no_subtitles) | N/A | Independent | medium | video-mme.github.io |
| Vinoground | 40.2 | text_score | N/A | Independent | medium | arxiv.org |
| VLM2-Bench | 27.8 | gc-mat | N/A | Independent | medium | arxiv.org |
| VNBench | 33.9 | accuracy | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…