Creative Writing on Creative Writing (Solved Rate)
51.98Solved RateSelf-Refine
Evaluation Results
| Method | Links | |
|---|---|---|
| Self-RefineModel=Phi-4, Context Window=16k2025.05 | 51.98 | |
| ICRLModel=Qwen3 32B, Context Window=32k2025.05 | 50 | |
| ICRLModel=Qwen3 32B think, Context Window=32k2025.05 | 50 | |
| ICRLModel=Llama 4 Maverick, Context Window=32k2025.05 | 50 | |
| ICRLModel=Phi-4, Context Window=16k2025.05 | 50 | |
| Self-RefineModel=Qwen3 32B, Context Window=32k2025.05 | 46 | |
| Self-RefineModel=Llama 4 Maverick, Context Window=32k2025.05 | 45.52 | |
| ReflexionModel=Qwen3 32B, Context Window=32k2025.05 | 41.17 | |
| ReflexionModel=Qwen3 32B think, Context Window=32k2025.05 | 38.33 | |
| BaseModel=Qwen3 32B, Context Window=32k2025.05 | 34.14 | |
| ReflexionModel=Phi-4, Context Window=16k2025.05 | 33.3 | |
| Self-RefineModel=Qwen3 32B think, Context Window=32k2025.05 | 30.23 | |
| ReflexionModel=Llama 4 Maverick, Context Window=32k2025.05 | 24.96 | |
| BaseModel=Phi-4, Context Window=16k2025.05 | 10.85 | |
| BaseModel=Qwen3 32B think, Context Window=32k2025.05 | 1.24 | |
| BaseModel=Llama 4 Maverick, Context Window=32k2025.05 | 0.98 |