| model,latency | |
| InternVL2-Llama3-76B,10.660117299385437 | |
| InternVL2-26B,4.239272214812449 | |
| dolphin-vision-72b,10.19095800373974 | |
| gpt-4o-2024-05-13,9.488193374830397 | |
| claude-3-5-sonnet-20240620,3.2490840805235996 | |
| idefics-9b-instruct,4.156911970172689 | |
| claude-3-opus-20240229,4.8763568649807185 | |
| gpt-4o-mini-2024-07-18,3.638671743317612 | |
| gpt-4-1106-vision-preview,4.712557435752083 | |
| Phi-3.5-vision-instruct,1.5404880504707106 | |
| InternVL2-40B,6.267102418391499 | |
| gpt-4o-2024-08-06,3.3857084617187416 | |
| idefics-80b-instruct,6.808930391550246 | |
| InternVL2-8B,1.9486003278511734 | |
| gemini-1.5-flash-latest,28.203669643584554 | |
| Idefics3-8B-Llama3,2.7247848158020056 | |
| Phi-3-vision-128k-instruct,1.3368420310828857 | |
| Pixtral-12B-2409,1.4976731684122302 | |
| internlm-xcomposer2d5-7b,8.438096179522184 | |