Behavior Prediction on GROVE TechCrunch 1.0
85.7Average Performance ScoreCDT (Ours)
Evaluation Results
| Method | Links | |
|---|---|---|
| CDT (Ours)Prediction Model=GPT-4.1, Evaluation Model=GPT-4.12026.04 | 85.7 | |
| RAGPrediction Model=GPT-4.1, Evaluation Model=GPT-4.12026.04 | 84.2 | |
| Human ProfilePrediction Model=GPT-4.1, Evaluation Model=GPT-4.12026.04 | 79.8 | |
| Summarized-basedPrediction Model=GPT-4.1, Evaluation Model=GPT-4.12026.04 | 79 | |
| VanillaPrediction Model=GPT-4.1, Evaluation Model=GPT-4.12026.04 | 78.5 |