WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 25.21 | 81.91 | 22.82 | 26.60 | Llama-2-13B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 25.02 | 84.00 | 22.60 | 27.17 | S-LLaMA-2.7B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 24.57 | 82.64 | 22.26 | 26.50 | Llama-2-7B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 23.77 | 81.14 | 20.31 | 25.75 | Flan-T5-3B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 23.73 | 83.32 | 20.54 | 25.85 | S-LLaMA-1.3B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 21.22 | 77.56 | 18.64 | 22.39 | GPT-3.5F | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 20.94 | 79.89 | 16.50 | 23.16 | MindAct-3B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 19.97 | 80.07 | 15.70 | 22.30 | Fuyu-8B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 17.27 | 80.02 | 15.36 | 14.05 | Flan-T5-780M | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 16.88 | 81.80 | 8.28 | 25.21 | Pix2Act-1.3B | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 15.13 | 75.87 | 13.39 | 13.58 | MindAct-780M | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 14.99 | 79.69 | 14.86 | 9.21 | Flan-T5-250M | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 12.63 | 74.25 | 12.05 | 7.67 | MindAct-250M | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 12.51 | 79.71 | 6.20 | 16.40 | Pix2Act-282M | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 10.72 | 41.66 | 10.85 | 6.75 | GPT-4T (Zero-Shot) | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 10.45 | 42.36 | 10.91 | 6.21 | GPT-4V (Zero-Shot) | 2024-02-08 |
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue | ✓ Link | 8.51 | 42.77 | 8.62 | 3.45 | GPT-3.5T (Zero-Shot) | 2024-02-08 |