RoTBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tool Use | RoTBench Multi-turn | Tool Selection Accuracy72.9 | 35 | |
| Tool Use | RoTBench Single-turn | Tool Selection84.8 | 35 | |
| Robustness of Tool-use | RoTBench | TS78.76 | 27 |
Showing 3 of 3 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Tool Use | RoTBench Multi-turn | Tool Selection Accuracy72.9 | 35 | |
| Tool Use | RoTBench Single-turn | Tool Selection84.8 | 35 | |
| Robustness of Tool-use | RoTBench | TS78.76 | 27 |