Sales Dialogue Evaluation on Internal Business Sales Dialogues (test)
24.44CVRDuCA
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| DuCAType=Training Method2026.03 | 24.44 | 66.72 | 9.91 | 4.2 | 2.71 | 6.11 | 34.44 | 49.21 | 44.61 | |
| GRPOType=Training Method2026.03 | 22.88 | 65.4 | 12.49 | 5.48 | 15.29 | 9.28 | 47.76 | 61.19 | 43.3 | |
| DeepSeek-R1Type=Foundation Model2026.03 | 22.85 | 65.13 | 9.85 | 35.19 | 1.01 | 2.5 | 7.69 | 59.82 | 42.74 | |
| GDPOType=Training Method2026.03 | 22.51 | 68.53 | 12.19 | 6.48 | 17.22 | 8.41 | 50.03 | 55.96 | 44.11 | |
| SFTType=Training Method, Configuration=Base2026.03 | 22.23 | 59.11 | 11.41 | 9.37 | 35.87 | 10.59 | 52.3 | 51.7 | 43.59 | |
| REINFORCE++Type=Training Method2026.03 | 21.51 | 61.32 | 11.18 | 8.34 | 30.17 | 9.99 | 50.34 | 54.69 | 43.62 | |
| Longcat-Flash-ChatType=Foundation Model2026.03 | 19.99 | 70.17 | 9.27 | 3.02 | 23.13 | 5.92 | 39.1 | 33.35 | 43.65 |