Diagram Understanding on AI2D F
59.7AccuracyGPT-4o
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4oModel Category=Proprietary VLMs2024.06 | 59.7 | |
| InternLM-XComposer2Model Category=Open-Source VLMs2024.06 | 57.5 | |
| InternVL-Chat-v1.5Model Category=Open-Source VLMs2024.06 | 55 | |
| LLaVA-NeXT (Yi-34B)Model Category=Open-Source VLMs2024.06 | 51.6 | |
| GPT-4vModel Category=Proprietary VLMs2024.06 | 45.7 | |
| Prism Captioner-7BModel Category=Prism Models, Reasoning Module=Llama32024.06 | 37.2 | |
| DeepSeek-VL-7BModel Category=Open-Source VLMs2024.06 | 36.9 | |
| LLaVA-NeXT (Vicuna-13B)Model Category=Open-Source VLMs2024.06 | 36.2 | |
| LLaVA-NeXT (Mistral-7B)Model Category=Open-Source VLMs2024.06 | 32.3 | |
| Prism Captioner-7BModel Category=Prism Models, Reasoning Module=ChatGPT2024.06 | 30.6 | |
| Prism Captioner-2BModel Category=Prism Models, Reasoning Module=Llama32024.06 | 30.3 | |
| LLaVA-NeXT (Vicuna-7B)Model Category=Open-Source VLMs2024.06 | 29.3 | |
| LLaVA-InternLM2-20BModel Category=Open-Source VLMs2024.06 | 28.4 | |
| Prism Captioner-2BModel Category=Prism Models, Reasoning Module=ChatGPT2024.06 | 27.4 | |
| MiniCPM-V-2Model Category=Open-Source VLMs2024.06 | 26.9 | |
| LLaVA-InternLM2-7BModel Category=Open-Source VLMs (E2E Baselines)2024.06 | 26.6 | |
| Yi-VL-34BModel Category=Open-Source VLMs2024.06 | 26.4 | |
| LLaVA-InternLM2-1.8BModel Category=Open-Source VLMs (E2E Baselines)2024.06 | 23.5 | |
| LLaVA-v1.5-13BModel Category=Open-Source VLMs2024.06 | 23 | |
| Emu2-ChatModel Category=Open-Source VLMs2024.06 | 22.7 | |
| ShareCaptionerModel Category=Prism Models, Reasoning Module=ChatGPT2024.06 | 22.2 | |
| mPLUG-Owl2Model Category=Open-Source VLMs2024.06 | 20.5 | |
| LLaVA-v1.5-7BModel Category=Open-Source VLMs2024.06 | 17.8 |