Visual Reasoning on SEED-Bench
62.8AccuracyEMU-2
Evaluation Results
| Method | Links | |
|---|---|---|
| EMU-2#Param LLM=33B, Task Setting=Multi-image / Video Tasks2024.02 | 62.8 | |
| Brote-IM-XXL (ours)#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.02 | 61.64 | |
| Brote-EX-XXL (ours)#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.02 | 59.31 | |
| Brote-IM-XL (ours)#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.02 | 57.86 | |
| Brote-EX-XL (ours)#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.02 | 57.51 | |
| MMICL-XXL#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.02 | 56.66 | |
| MMICL-XL#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.02 | 54.69 | |
| InstructBLIP-XL#Param LLM=3B, Task Setting=Multi-image / Video Tasks2024.02 | 52.7 | |
| InstructBLIP-XXL#Param LLM=11B, Task Setting=Multi-image / Video Tasks2024.02 | 50.81 | |
| Otter#Param LLM=7B, Task Setting=Multi-image / Video Tasks2024.02 | 39.7 |