Web Interaction on GRAPH2EVAL BENCH
48.89Basic Navigation ScoreGemini 2.5 Flash
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 FlashAgent Configuration=Agent S 2.52025.10 | 48.89 | 100 | 66.67 | 63.4 | 100 | 55 | 62.5 | 69.2 | |
| GPT-4o miniAgent Configuration=Agent S 2.52025.10 | 33.34 | 0 | 20 | 37.63 | 50 | 17.5 | 25 | 33.12 | |
| Qwen2.5-VL-72BAgent Configuration=Agent S 2.52025.10 | 33.34 | 100 | 26.67 | 42.78 | 83.33 | 15 | 56.25 | 38.8 | |
| Gemini 2.5 FlashAgent Configuration=SoM Agent2025.10 | 17.78 | 0 | 20 | 11.34 | 0 | 25 | 18.75 | 14.51 | |
| Qwen2.5-VL-32BAgent Configuration=Agent S 2.52025.10 | 17.78 | 0 | 20 | 15.46 | 33.33 | 7.5 | 12.5 | 15.14 | |
| Qwen2.5-VL-72BAgent Configuration=SoM Agent2025.10 | 13.33 | 100 | 20 | 10.31 | 16.66 | 27.5 | 12.5 | 13.88 | |
| Qwen2.5-VL-7BAgent Configuration=Agent S 2.52025.10 | 11.12 | 0 | 6.66 | 13.92 | 16.67 | 7.5 | 0 | 11.67 | |
| UI-TARS-1.5-7BAgent Configuration=Agent S 2.52025.10 | 8.89 | 0 | 6.67 | 9.79 | 0 | 12.5 | 12.5 | 7.19 | |
| GPT-4o miniAgent Configuration=SoM Agent2025.10 | 6.67 | 0 | 0 | 12.37 | 0 | 7.5 | 0 | 9.46 | |
| UI-TARS-1.5-7BAgent Configuration=SoM Agent2025.10 | 6.67 | 0 | 0 | 7.73 | 0 | 7.5 | 12.5 | 4.91 | |
| Qwen2.5-VL-32BAgent Configuration=SoM Agent2025.10 | 2.22 | 100 | 6.67 | 1.55 | 0 | 7.5 | 0 | 2.83 | |
| Qwen2.5-VL-7BAgent Configuration=SoM Agent2025.10 | 0 | 0 | 0 | 1.03 | 0 | 0 | 0 | 0.63 |