Web Navigation on Multimodal-Mind2Web Average
54.3Avg. Step Success RateExplorer-7B
Evaluation results
| Method | Links | |
|---|---|---|
| Explorer-7BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. + M2W2025.02 | 54.3 | |
| AgentTrek-7BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. + M2W2025.02 | 53.2 | |
| Explorer-4BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. + M2W2025.02 | 49.8 | |
| Explorer-7BEvaluation Protocol=Supervised Fine-Tuning, Train Data=M2W2025.02 | 49.5 | |
| Explorer-4BEvaluation Protocol=Supervised Fine-Tuning, Train Data=M2W2025.02 | 44.8 | |
| Explorer-7BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. traj.2025.02 | 43 | |
| Explorer-4BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. traj.2025.02 | 37.4 | |
| SeeActEvaluation Protocol=In-Context Learning2025.02 | 36.5 | |
| ScribeAgent-32BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. traj.2025.02 | 35.1 | |
| GPT-4Evaluation Protocol=In-Context Learning2025.02 | 29.7 | |
| EDGE-9.6BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. + M2W2025.02 | 24.5 | |
| SeeClick-9.6BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. + M2W2025.02 | 20.9 | |
| GPT-3.5Evaluation Protocol=In-Context Learning2025.02 | 18.3 | |
| MiniCPM-3.1BEvaluation Protocol=Supervised Fine-Tuning, Train Data=Syn. + M2W2025.02 | 17.6 |