Action Prediction on Mind2Web Cross-Task
87.6Operation F1 ScoreOmniParser
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OmniParserHTML free=true, image=true, variant=LS + ID2024.08 | 87.6 | 42.4 | 39.4 | |
| SeeClickHTML free=true, image=true2024.08 | 87 | 28.3 | 25.5 | |
| OmniParserHTML free=true, image=true, variant=LS + GD2024.08 | 86.7 | 42.3 | 38.7 | |
| Qwen-VLHTML free=true, image=true2024.08 | 84.3 | 14.1 | 12 | |
| DUAL-VCRRanker=DUAL-VCR_VNEI-TXT+VIS, Action Predictor=DUAL-VCRPRED2024.02 | 78.7 | 47 | 46 | |
| DUAL-VCRRanker=DUAL-VCR_VNEI-TXT, Action Predictor=DUAL-VCRPRED2024.02 | 78.4 | 45.3 | 44.5 | |
| MindActRanker=MINDACTRANK, Action Predictor=MINDACTPRED2024.02 | 74.9 | 42 | 41.1 | |
| GPT-4V+textual choiceHTML free=false, image=true2024.08 | 73.4 | 46.4 | 40.2 | |
| MindActHTML free=false, image=false2024.08 | 66.5 | 42.1 | 39.6 | |
| GPT-4HTML free=false, image=false2024.08 | 60.6 | 41.6 | 36.2 | |
| CogAgentHTML free=true, image=true2024.08 | 53 | 22.4 | 17.6 | |
| GPT-3.5-TurboHTML free=false, image=false2024.08 | 52.8 | 21.6 | 18.6 | |
| MindAct (gen)HTML free=false, image=false2024.08 | 44.7 | 14.2 | 11.9 | |
| GPT-4V+somHTML free=false, image=true2024.08 | 32.8 | — | 26.3 |