Stylized Dialogue on 148-query style-0 persona (test)
4.622Context ScoreSFR
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| SFRTemperature=0.8, Backbone=Qwen3-32B, LLM-judge=Qwen3-235B2026.05 | 4.622 | 4.77 | 4.905 | 4.905 | |
| SFTTemperature=0.8, Backbone=Qwen3-32B, LLM-judge=Qwen3-235B2026.05 | 4.568 | 4.764 | 4.588 | 4.831 | |
| DeepSeek-R1-promptTemperature=0.8, Backbone=DeepSeek-R1 (frozen), LLM-judge=Qwen3-235B2026.05 | 4.5 | 4.662 | 4.654 | 4.838 |