Multimodal Cognition on MME Cognition
525Cognition ScoreCoLLaVO
Evaluation results
| Method | Links | |
|---|---|---|
| CoLLaVONumber of Parameters=7B, Setting=Zero-shot2024.02 | 525 | |
| GPT-4V-1106Size=> 8B2024.02 | 437.5 | |
| MiniCPM-V 2.0Size=Size < 4B2024.02 | 396.8 | |
| Intern-XCNumber of Parameters=7B, Setting=Zero-shot2024.02 | 391.1 | |
| ShareGPT4VNumber of Parameters=7B, Setting=Zero-shot2024.02 | 376.4 | |
| LLaVA-NeXT-Llama-3-8BSize=4B < Size < 8B2024.02 | 367.8 | |
| Bunny-8BSize=4B < Size < 8B2024.02 | 367.5 | |
| Bunny-4BSize=Size < 4B2024.02 | 361.1 | |
| Qwen-VL-ChatNumber of Parameters=7B, Setting=Zero-shot2024.02 | 360.7 | |
| Qwen-VL-ChatLM=Qwen-7B, Res.=4482024.12 | 360.7 | |
| LLaVA-NeXT-7BSize=4B < Size < 8B2024.02 | 332 | |
| MM1-7B-ChatSize=4B < Size < 8B2024.02 | 328.9 | |
| LLaVA-NeXT-13BSize=> 8B2024.02 | 326 | |
| SVIT-v1.5-13BSize=> 8B2024.02 | 323.2 | |
| Mini-Gemini-HD-13BSize=> 8B2024.02 | 320 | |
| LLaVA-1.5LM=Vicuna-7B, Res.=3362024.12 | 316.1 | |
| mPLUG-Owl2Size=4B < Size < 8B2024.02 | 313.2 | |
| mPLUG-Owl2LM=LLaMA-7B, Res.=4482024.12 | 313.2 | |
| ShareGPT4V-13BSize=> 8B2024.02 | 303.2 | |
| LLaVA-v1.5-13B (LORA)Size=> 8B2024.02 | 300.48 | |
| LLaVA1.5Number of Parameters=13B, Setting=Zero-shot2024.02 | 295.4 | |
| Mipha-3BSize=Size < 4B2024.02 | 295 | |
| Mipha-3BLM=Phi-2-2.7B, Res.=3842024.12 | 295 | |
| SPHINX-Intern2Size=4B < Size < 8B2024.02 | 294.6 | |
| LLaVA1.5Number of Parameters=7B, Setting=Zero-shot2024.02 | 293.8 | |
| InstructBLIP-Flan-T5-XXLSize=> 8B2024.02 | 291.8 | |
| BLIP2Number of Parameters=13B, Setting=Zero-shot2024.02 | 290 | |
| BLIP-2-Flan-T5-XXLSize=> 8B2024.02 | 290 | |
| Bunny-3BLM=Phi-2-2.7B, Res.=3842024.12 | 289.3 | |
| LVIS-INSTRUCT4V-13BSize=> 8B2024.02 | 286.8 | |
| OlympusLM=Phi-2-2.7B, Res.=3842024.12 | 283.2 | |
| MM1-3B-ChatSize=Size < 4B2024.02 | 279.3 | |
| LLaVA-v1.5-7B (LORA)Size=4B < Size < 8B2024.02 | 267.98 | |
| LLaVANumber of Parameters=7B, Setting=Zero-shot2024.02 | 247.9 |