Task-Focused Dialogue on TmallBrand-B
3.761G-Eval ScoreGOPO-Qwen3-14B
Evaluation results
| Method | Links | |
|---|---|---|
| GOPO-Qwen3-14BNumber of parameters=14B2026.01 | 3.761 | |
| Qwen-235BNumber of parameters=235B2026.01 | 3.747 | |
| DeepSeek-R12026.01 | 3.745 | |
| Gemini-2.52026.01 | 3.534 | |
| GPT-5.22026.01 | 3.517 | |
| GLM-4.72026.01 | 3.51 |