Conversation Evaluation on Robot Domain
88.57Human ScoreGOOD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GOODinference_type=prompt inf2025.08 | 88.57 | 86.9 | |
| GOODinference_type=prob inf2025.08 | 87.22 | 89.1 | |
| Full Context2025.08 | 66.54 | 84.63 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| GOODinference_type=prompt inf2025.08 | 88.57 | 86.9 | |
| GOODinference_type=prob inf2025.08 | 87.22 | 89.1 | |
| Full Context2025.08 | 66.54 | 84.63 |