Tool Planning on Black-Box Tool Planning (test)
70.58Success RateTOPGUN
Evaluation results
| Method | Links | |
|---|---|---|
| TOPGUNBase Model=GPT-4, Setting=Black-Box2024.02 | 70.58 | |
| DFSDTBase Model=GPT-4, Setting=Black-Box2024.02 | 61.45 | |
| ReActBase Model=GPT-4, Setting=Black-Box2024.02 | 45.45 | |
| ReverseChainBase Model=GPT-4, Setting=Black-Box2024.02 | 43.75 |