ToolHop
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-hop tool use | ToolHop | Answer Correctness53.97 | 61 | |
| Tool Use | ToolHop | Answer Correctness54.87 | 18 | |
| Multi-hop Tool-use | ToolHop unseen (test) | Accuracy43.1 | 4 | |
| Multi-hop Tool-use | ToolHop rand (test) | Accuracy31.1 | 4 |
Showing 4 of 4 rows