Robot Task Planning On Sheetcopilot
Metrics
Pass@1
Results
Performance results of various models on this benchmark
| Paper Title | ||
|---|---|---|
| SheetAgent (GPT-3.5) | 61.1% | SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models |
| SheetCopilot (NIPS2023) | 44.3% | SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models |
0 of 2 row(s) selected.