Proactive Assistant Evaluation on Synthetic Category (test)
14Response FrequencyLLAMAPIE
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LLAMAPIEevaluation_protocol=GPT-4o (1-5 scale)2025.05 | 14 | 2.08 | 4.32 | 4.52 | 4.67 | 4.77 | 4.73 | 4.74 | 4.77 | 4.35 | 4.89 | 4.21 |
Loading the SOTA2 catalog…