| conversational-web-navigation-on-weblinx | Llama-2-13B | #1 | Overall score: 25.21Intent Match: 81.91Element (IoU): 22.82… |
| conversational-web-navigation-on-weblinx | S-LLaMA-2.7B | #2 | Overall score: 25.02Intent Match: 84.00Element (IoU): 22.60… |
| conversational-web-navigation-on-weblinx | Llama-2-7B | #3 | Overall score: 24.57Intent Match: 82.64Element (IoU): 22.26… |
| conversational-web-navigation-on-weblinx | Flan-T5-3B | #4 | Overall score: 23.77Intent Match: 81.14Element (IoU): 20.31… |
| conversational-web-navigation-on-weblinx | S-LLaMA-1.3B | #5 | Overall score: 23.73Intent Match: 83.32Element (IoU): 20.54… |
| conversational-web-navigation-on-weblinx | GPT-3.5F | #6 | Overall score: 21.22Intent Match: 77.56Element (IoU): 18.64… |
| conversational-web-navigation-on-weblinx | MindAct-3B | #7 | Overall score: 20.94Intent Match: 79.89Element (IoU): 16.50… |
| conversational-web-navigation-on-weblinx | Fuyu-8B | #8 | Overall score: 19.97Intent Match: 80.07Element (IoU): 15.70… |
| conversational-web-navigation-on-weblinx | Flan-T5-780M | #9 | Overall score: 17.27Intent Match: 80.02Element (IoU): 15.36… |
| conversational-web-navigation-on-weblinx | Pix2Act-1.3B | #10 | Overall score: 16.88Intent Match: 81.80Element (IoU): 8.28… |
| conversational-web-navigation-on-weblinx | MindAct-780M | #11 | Overall score: 15.13Intent Match: 75.87Element (IoU): 13.39… |
| conversational-web-navigation-on-weblinx | Flan-T5-250M | #12 | Overall score: 14.99Intent Match: 79.69Element (IoU): 14.86… |
| conversational-web-navigation-on-weblinx | MindAct-250M | #13 | Overall score: 12.63Intent Match: 74.25Element (IoU): 12.05… |
| conversational-web-navigation-on-weblinx | Pix2Act-282M | #14 | Overall score: 12.51Intent Match: 79.71Element (IoU): 6.20… |
| conversational-web-navigation-on-weblinx | GPT-4T (Zero-Shot) | #15 | Overall score: 10.72Intent Match: 41.66Element (IoU): 10.85… |
| conversational-web-navigation-on-weblinx | GPT-4V (Zero-Shot) | #16 | Overall score: 10.45Intent Match: 42.36Element (IoU): 10.91… |
| conversational-web-navigation-on-weblinx | GPT-3.5T (Zero-Shot) | #17 | Overall score: 8.51Intent Match: 42.77Element (IoU): 8.62… |