Multimodal Understanding on SEED-Bench Image Part
75.9AccuracyInternLM-XComposer2
Evaluation results
| Method | Links | |
|---|---|---|
| InternLM-XComposer2Number of Parameters=7B2024.01 | 75.9 | |
| IXC2-VLLLM=InernLM2-7B2024.04 | 74.9 | |
| SPH-2Number of Parameters=17B2024.01 | 74.8 | |
| IXC2-4KHDLLM=InernLM2-7B2024.04 | 74.7 | |
| Qwen-VL-Plus2024.01 | 72.7 | |
| LLaVA-NextLLM=Vicuna-13B2024.04 | 71.4 | |
| Gemini-Pro2024.01 | 70.7 | |
| LLaVA-XTunerLLM=InernLM2-20B2024.04 | 70.2 | |
| ShareGPT4VLLM=Vicuna-7B2024.04 | 69.7 | |
| GPT-4V2024.01 | 69.1 | |
| MonkeyLLM=Qwen-7B2024.04 | 68.9 | |
| CogVLM-17BLLM=Vicuna-7B2024.04 | 68.8 | |
| LLaVA-1.5LLM=Vicuna-13B2024.04 | 68.2 | |
| InternLM-XCLLM=InernLM-7B2024.04 | 66.1 | |
| Qwen-VL-ChatLLM=Qwen-7B2024.04 | 58.2 |