Video Question Answering On Mvbench
Metrics
Avg.
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Avg. |
|---|---|
| st-llm-large-language-models-are-effective-1 | 54.9 |
| tarsier-recipes-for-training-and-evaluating-1 | 67.6 |
| ppllava-varied-video-sequence-understanding | 59.2 |
| minigpt-4-enhancing-vision-language | 18.8 |
| videochat-chat-centric-video-understanding | 35.5 |
| oryx-mllm-on-demand-spatial-temporal | 64.7 |
| instructblip-towards-general-purpose-vision | 32.5 |
| longvu-spatiotemporal-adaptive-compression | 66.9 |
| video-llama-an-instruction-tuned-audio-visual | 34.1 |
| linvt-empower-your-image-level-large-language | 69.3 |
| hawkeye-training-video-text-llms-for | 47.55 |
| video-chatgpt-towards-detailed-video | 32.7 |
| sphinx-x-scaling-data-and-parameters-for-a | 39.7 |
| videollama-2-advancing-spatial-temporal | 62.0 |
| mvbench-a-comprehensive-multi-modal-video | 51.9 |
| mplug-owl3-towards-long-image-sequence | 59.5 |
| pllava-parameter-free-llava-extension-from-1 | 58.1 |
| internvideo2-scaling-video-foundation-models | 67.2 |
| videogpt-integrating-image-and-video-encoders | 58.7 |
| visual-instruction-tuning-1 | 36.0 |
| timechat-a-time-sensitive-multimodal-large | 38.5 |