Operations Research Problem Solving on Mamo-ComplexLP (test)
72.2Correct RateBPP-Search Variant
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BPP-Search VariantPolicy Model=GPT-4o2024.11 | 72.2 | 21 | |
| Beam Search VariantPolicy Model=GPT-4o2024.11 | 66.6 | 21 | |
| SCPolicy Model=GPT-4o2024.11 | 62.5 | 4 | |
| ToT-RethinkPolicy Model=GPT-4o2024.11 | 58.3 | 40 | |
| Greedy Search VariantPolicy Model=GPT-4o2024.11 | 55.5 | 9 | |
| CoTPolicy Model=GPT-4o2024.11 | 48.6 | 1 | |
| ToT-Randomly-ChosenPolicy Model=GPT-4o2024.11 | 44.4 | 39 |