Cinematography language understanding on ShotBench 1.0 (test)
77.9Shot Size Accuracy (SS)ShotVL (3B)
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| ShotVL (3B)Access=Ours2025.06 | 77.9 | 85.6 | 68.8 | 59.3 | 65.7 | 53.1 | 57.4 | 51.7 | 65.1 | |
| Qwen2.5-VL-72B-InstructAccess=Open-Sourced2025.06 | 75.1 | 82.9 | 56.7 | 46.8 | 59 | 49.4 | 54.1 | 48.9 | 59.1 | |
| InternVL3-78BAccess=Open-Sourced2025.06 | 69.7 | 80 | 54.5 | 44 | 65.5 | 47.4 | 51.8 | 44.4 | 57.2 | |
| GPT-4oAccess=Proprietary2025.06 | 69.3 | 83.1 | 58.2 | 48.9 | 63.2 | 48 | 55.2 | 48.3 | 59.3 | |
| Qwen2.5-VL-7B-InstructAccess=Open-Sourced2025.06 | 69.1 | 73.5 | 53.2 | 47 | 60.5 | 47.4 | 49.9 | 30.2 | 53.8 | |
| InternVL3-38BAccess=Open-Sourced2025.06 | 68 | 84 | 51.9 | 43.6 | 64.4 | 46.9 | 54.7 | 44.6 | 57.3 | |
| InternVL2.5-38BAccess=Open-Sourced2025.06 | 67.8 | 85.4 | 55.4 | 41.7 | 61.7 | 48.9 | 52.4 | 44 | 57.2 | |
| Qwen2.5-VL-32B-InstructAccess=Open-Sourced2025.06 | 62.3 | 76.6 | 51 | 48.3 | 61.7 | 44 | 52.2 | 43.8 | 55 | |
| InternVL3-8BAccess=Open-Sourced2025.06 | 62.1 | 65.8 | 46.8 | 42.9 | 58 | 44.3 | 46.8 | 44.2 | 51.4 | |
| InternVL3-14BAccess=Open-Sourced2025.06 | 59.6 | 82.2 | 55.4 | 40.7 | 61.7 | 44.6 | 51.1 | 38.2 | 54.2 | |
| LLaVA-Onevision-Qwen2-7B-Ov-ChatAccess=Open-Sourced2025.06 | 58.4 | 71 | 52.3 | 38.7 | 59.5 | 44.9 | 50.9 | 39.7 | 51.9 | |
| Gemini-2.5-flash-preview-04-17Access=Proprietary2025.06 | 57.7 | 82.9 | 51.4 | 43.8 | 65.2 | 45.7 | 45.9 | 43.5 | 54.5 | |
| LLaVA-Video-7B-Qwen2Access=Open-Sourced2025.06 | 56.9 | 65.4 | 45.1 | 36 | 63.5 | 45.4 | 37.4 | 35.3 | 48.1 | |
| InternVL2.5-8BAccess=Open-Sourced2025.06 | 56.3 | 70.3 | 50.8 | 41.1 | 60.2 | 45.1 | 50.1 | 33.6 | 50.9 | |
| InternVL3-2BAccess=Open-Sourced2025.06 | 56.3 | 56 | 44.4 | 34.6 | 56.8 | 44.6 | 43 | 38.1 | 46.7 | |
| Qwen2.5-VL-3B-InstructAccess=Open-Sourced2025.06 | 54.6 | 56.6 | 43.1 | 36.6 | 59.3 | 45.1 | 41.5 | 31.9 | 46.1 | |
| Internlm-xcomposer2d5-7BAccess=Open-Sourced2025.06 | 51.1 | 71 | 39.8 | 32.7 | 59.3 | 35.7 | 35.7 | 38.8 | 45.5 | |
| Gemini-2.0-flashAccess=Proprietary2025.06 | 48.9 | 75.5 | 44.6 | 31.9 | 62.2 | 48.9 | 52.4 | 47.4 | 51.5 | |
| VILA1.5-8BAccess=Open-Sourced2025.06 | 40.6 | 44.5 | 39.1 | 29.7 | 48.9 | 32.9 | 34.4 | 36.9 | 38.4 | |
| VILA1.5-13BAccess=Open-Sourced2025.06 | 36.7 | 54.6 | 40.7 | 34.8 | 52.8 | 35.4 | 34.2 | 31.3 | 40.1 | |
| LLaVA-NeXT-Video-7BAccess=Open-Sourced2025.06 | 35.9 | 37.1 | 32.5 | 27.8 | 50.9 | 31.7 | 28 | 31.3 | 34.4 | |
| Ovis2-8BAccess=Open-Sourced2025.06 | 35.9 | 37.1 | 32.5 | 27.8 | 50.9 | 31.7 | 28 | 35.3 | 34.9 | |
| VILA1.5-3BAccess=Open-Sourced2025.06 | 33.4 | 44.9 | 32.1 | 28.6 | 50.6 | 35.7 | 28.4 | 21.5 | 34.4 | |
| Instructblip-vicuna-7BAccess=Open-Sourced2025.06 | 27 | 27.9 | 34.5 | 29.4 | 44.4 | 29.7 | 27.1 | 25 | 30.6 | |
| Instructblip-vicuna-13BAccess=Open-Sourced2025.06 | 26.8 | 29.2 | 27.9 | 28 | 39 | 24 | 27.1 | 22 | 28 |