Video Based Generative Performance 5
Metrics
gpt-score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | gpt-score |
|---|---|
| ppllava-varied-video-sequence-understanding | 3.21 |
| videochat-chat-centric-video-understanding | 1.94 |
| mvbench-a-comprehensive-multi-modal-video | 2.66 |
| slowfast-llava-a-strong-training-free | 2.77 |
| llama-adapter-v2-parameter-efficient-visual | 1.98 |
| pllava-parameter-free-llava-extension-from-1 | 2.67 |
| one-for-all-video-conversation-is-feasible | 2.13 |
| video-llama-an-instruction-tuned-audio-visual | 1.82 |
| ts-llava-constructing-visual-tokens-through | 2.77 |
| moviechat-from-dense-token-to-sparse-memory | 2.24 |
| vtimellm-empower-llm-to-grasp-video-moments | 2.49 |
| videogpt-integrating-image-and-video-encoders | 2.83 |
| chat-univi-unified-visual-representation | 2.39 |
| one-for-all-video-conversation-is-feasible | 2.34 |
| st-llm-large-language-models-are-effective-1 | 2.93 |
| minigpt4-video-advancing-multimodal-llms-for | 2.65 |
| video-chatgpt-towards-detailed-video | 1.98 |
| mvbench-a-comprehensive-multi-modal-video | 2.65 |