Solution Simulation on Human Evaluation Solution Simulation (test)
3.75ScoreGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4oSetting=Prototype Mapping + Refine2025.05 | 3.75 | |
| GPT-4oSetting=Prototype Mapping + CoT2025.05 | 3.7 | |
| GPT-3.5Setting=Prototype Mapping + Refine2025.05 | 3.3 | |
| GPT-3.5Setting=Random + Refine2025.05 | 3.29 | |
| Claude-3.5-SonnetSetting=Prototype Mapping + Refine2025.05 | 3.27 | |
| Claude-3.5-SonnetSetting=Prototype Mapping + IO2025.05 | 3.24 | |
| Llama-3.3-70B-InstructSetting=Prototype Mapping + Refine2025.05 | 3.08 | |
| Llama-3.3-70B-InstructSetting=Prototype Mapping + IO2025.05 | 2.88 |