Visual Question Answering On Mmbench
Metrics
GPT-3.5 score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | GPT-3.5 score |
|---|---|
| video-lavit-unified-video-language-pre | 67.3 |
| dreamllm-synergistic-multimodal-comprehension | 49.9 |
| cumo-scaling-multimodal-llm-with-co-upcycled | 73.0 |
| mixture-of-subspaces-in-low-rank-adaptation | 73.8 |
| mixture-of-subspaces-in-low-rank-adaptation | 73.0 |