Proactive Assistant Evaluation on SODA Category (test)
0.14Response FrequencyLLAMAPIE
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LLAMAPIEevaluation_protocol=GPT-4o (1-5 scale)2025.05 | 0.14 | 2.06 | 4.28 | 4.55 | 4.73 | 4.82 | 4.77 | 4.74 | 4.79 | 4.3 | 4.85 | 4.19 |
Loading the SOTA2 catalog…