Probabilistic Program Generation on PosteriorDB Surgical
-38.03ELPD LOOBoxLM
Evaluation results
| Method | Links | |
|---|---|---|
| BoxLMBase Model=GPT-42025.09 | -38.03 | |
| OpenAI-o3Base Model=OpenAI-o32025.09 | -38.73 | |
| ExpertBase Model=Expert stan programs from PosteriorDB2025.09 | -39.73 | |
| REFINESTATBase Model=DQ-7B2025.09 | -46.51 |