Script-Level Overall Evaluation on Narrative Script Refinement Evaluation Set (test)
84.6Mean ScoreDramaturge
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Dramaturge2025.10 | 84.6 | 0.33 | |
| Gemini-2.5-pro2025.10 | 78.18 | 0.55 | |
| GPT-4.12025.10 | 70.78 | 0.51 | |
| GPT-4.1-mini2025.10 | 68.82 | 0.67 | |
| Deepseek-r12025.10 | 66.38 | 0.76 | |
| GPT-4o2025.10 | 58.58 | 0.65 | |
| Qwen-max2025.10 | 58.18 | 0.57 | |
| Original Scripts2025.10 | 55.24 | 0.78 |